| 15 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SCSI_SCSI_CMND_H #define _SCSI_SCSI_CMND_H #include <linux/dma-mapping.h> #include <linux/blkdev.h> #include <linux/t10-pi.h> #include <linux/list.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/scatterlist.h> #include <scsi/scsi_device.h> struct Scsi_Host; /* * MAX_COMMAND_SIZE is: * The longest fixed-length SCSI CDB as per the SCSI standard. * fixed-length means: commands that their size can be determined * by their opcode and the CDB does not carry a length specifier, (unlike * the VARIABLE_LENGTH_CMD(0x7f) command). This is actually not exactly * true and the SCSI standard also defines extended commands and * vendor specific commands that can be bigger than 16 bytes. The kernel * will support these using the same infrastructure used for VARLEN CDB's. * So in effect MAX_COMMAND_SIZE means the maximum size command scsi-ml * supports without specifying a cmd_len by ULD's */ #define MAX_COMMAND_SIZE 16 struct scsi_data_buffer { struct sg_table table; unsigned length; }; /* embedded in scsi_cmnd */ struct scsi_pointer { char *ptr; /* data pointer */ int this_residual; /* left in this buffer */ struct scatterlist *buffer; /* which buffer */ int buffers_residual; /* how many buffers left */ dma_addr_t dma_handle; volatile int Status; volatile int Message; volatile int have_data_in; volatile int sent_command; volatile int phase; }; /* for scmd->flags */ #define SCMD_TAGGED (1 << 0) #define SCMD_INITIALIZED (1 << 1) #define SCMD_LAST (1 << 2) /* * libata uses SCSI EH to fetch sense data for successful commands. * SCSI EH should not overwrite scmd->result when SCMD_FORCE_EH_SUCCESS is set. */ #define SCMD_FORCE_EH_SUCCESS (1 << 3) #define SCMD_FAIL_IF_RECOVERING (1 << 4) /* flags preserved across unprep / reprep */ #define SCMD_PRESERVED_FLAGS (SCMD_INITIALIZED | SCMD_FAIL_IF_RECOVERING) /* for scmd->state */ #define SCMD_STATE_COMPLETE 0 #define SCMD_STATE_INFLIGHT 1 enum scsi_cmnd_submitter { SUBMITTED_BY_BLOCK_LAYER = 0, SUBMITTED_BY_SCSI_ERROR_HANDLER = 1, SUBMITTED_BY_SCSI_RESET_IOCTL = 2, } __packed; struct scsi_cmnd { struct scsi_device *device; struct list_head eh_entry; /* entry for the host eh_abort_list/eh_cmd_q */ struct delayed_work abort_work; struct rcu_head rcu; int eh_eflags; /* Used by error handlr */ int budget_token; /* * This is set to jiffies as it was when the command was first * allocated. It is used to time how long the command has * been outstanding */ unsigned long jiffies_at_alloc; int retries; int allowed; unsigned char prot_op; unsigned char prot_type; unsigned char prot_flags; enum scsi_cmnd_submitter submitter; unsigned short cmd_len; enum dma_data_direction sc_data_direction; unsigned char cmnd[32]; /* SCSI CDB */ /* These elements define the operation we ultimately want to perform */ struct scsi_data_buffer sdb; struct scsi_data_buffer *prot_sdb; unsigned underflow; /* Return error if less than this amount is transferred */ unsigned transfersize; /* How much we are guaranteed to transfer with each SCSI transfer (ie, between disconnect / reconnects. Probably == sector size */ unsigned resid_len; /* residual count */ unsigned sense_len; unsigned char *sense_buffer; /* obtained by REQUEST SENSE when * CHECK CONDITION is received on original * command (auto-sense). Length must be * SCSI_SENSE_BUFFERSIZE bytes. */ int flags; /* Command flags */ unsigned long state; /* Command completion state */ unsigned int extra_len; /* length of alignment and padding */ /* * The fields below can be modified by the LLD but the fields above * must not be modified. */ unsigned char *host_scribble; /* The host adapter is allowed to * call scsi_malloc and get some memory * and hang it here. The host adapter * is also expected to call scsi_free * to release this memory. (The memory * obtained by scsi_malloc is guaranteed * to be at an address < 16Mb). */ int result; /* Status code from lower level driver */ }; /* Variant of blk_mq_rq_from_pdu() that verifies the type of its argument. */ static inline struct request *scsi_cmd_to_rq(struct scsi_cmnd *scmd) { return blk_mq_rq_from_pdu(scmd); } /* * Return the driver private allocation behind the command. * Only works if cmd_size is set in the host template. */ static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd) { return cmd + 1; } void scsi_done(struct scsi_cmnd *cmd); void scsi_done_direct(struct scsi_cmnd *cmd); extern void scsi_finish_command(struct scsi_cmnd *cmd); extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, size_t *offset, size_t *len); extern void scsi_kunmap_atomic_sg(void *virt); blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd); void scsi_free_sgtables(struct scsi_cmnd *cmd); #ifdef CONFIG_SCSI_DMA extern int scsi_dma_map(struct scsi_cmnd *cmd); extern void scsi_dma_unmap(struct scsi_cmnd *cmd); #else /* !CONFIG_SCSI_DMA */ static inline int scsi_dma_map(struct scsi_cmnd *cmd) { return -ENOSYS; } static inline void scsi_dma_unmap(struct scsi_cmnd *cmd) { } #endif /* !CONFIG_SCSI_DMA */ static inline unsigned scsi_sg_count(struct scsi_cmnd *cmd) { return cmd->sdb.table.nents; } static inline struct scatterlist *scsi_sglist(struct scsi_cmnd *cmd) { return cmd->sdb.table.sgl; } static inline unsigned scsi_bufflen(struct scsi_cmnd *cmd) { return cmd->sdb.length; } static inline void scsi_set_resid(struct scsi_cmnd *cmd, unsigned int resid) { cmd->resid_len = resid; } static inline unsigned int scsi_get_resid(struct scsi_cmnd *cmd) { return cmd->resid_len; } #define scsi_for_each_sg(cmd, sg, nseg, __i) \ for_each_sg(scsi_sglist(cmd), sg, nseg, __i) static inline int scsi_sg_copy_from_buffer(struct scsi_cmnd *cmd, const void *buf, int buflen) { return sg_copy_from_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, buflen); } static inline int scsi_sg_copy_to_buffer(struct scsi_cmnd *cmd, void *buf, int buflen) { return sg_copy_to_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, buflen); } static inline sector_t scsi_get_sector(struct scsi_cmnd *scmd) { return blk_rq_pos(scsi_cmd_to_rq(scmd)); } static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd) { unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT; return blk_rq_pos(scsi_cmd_to_rq(scmd)) >> shift; } static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd) { unsigned int shift = ilog2(scmd->device->sector_size); return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift; } /* * The operations below are hints that tell the controller driver how * to handle I/Os with DIF or similar types of protection information. */ enum scsi_prot_operations { /* Normal I/O */ SCSI_PROT_NORMAL = 0, /* OS-HBA: Protected, HBA-Target: Unprotected */ SCSI_PROT_READ_INSERT, SCSI_PROT_WRITE_STRIP, /* OS-HBA: Unprotected, HBA-Target: Protected */ SCSI_PROT_READ_STRIP, SCSI_PROT_WRITE_INSERT, /* OS-HBA: Protected, HBA-Target: Protected */ SCSI_PROT_READ_PASS, SCSI_PROT_WRITE_PASS, }; static inline void scsi_set_prot_op(struct scsi_cmnd *scmd, unsigned char op) { scmd->prot_op = op; } static inline unsigned char scsi_get_prot_op(struct scsi_cmnd *scmd) { return scmd->prot_op; } enum scsi_prot_flags { SCSI_PROT_TRANSFER_PI = 1 << 0, SCSI_PROT_GUARD_CHECK = 1 << 1, SCSI_PROT_REF_CHECK = 1 << 2, SCSI_PROT_REF_INCREMENT = 1 << 3, SCSI_PROT_IP_CHECKSUM = 1 << 4, }; /* * The controller usually does not know anything about the target it * is communicating with. However, when DIX is enabled the controller * must be know target type so it can verify the protection * information passed along with the I/O. */ enum scsi_prot_target_type { SCSI_PROT_DIF_TYPE0 = 0, SCSI_PROT_DIF_TYPE1, SCSI_PROT_DIF_TYPE2, SCSI_PROT_DIF_TYPE3, }; static inline void scsi_set_prot_type(struct scsi_cmnd *scmd, unsigned char type) { scmd->prot_type = type; } static inline unsigned char scsi_get_prot_type(struct scsi_cmnd *scmd) { return scmd->prot_type; } static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd) { struct request *rq = blk_mq_rq_from_pdu(scmd); return t10_pi_ref_tag(rq); } static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd) { return scmd->device->sector_size; } static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd) { return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0; } static inline struct scatterlist *scsi_prot_sglist(struct scsi_cmnd *cmd) { return cmd->prot_sdb ? cmd->prot_sdb->table.sgl : NULL; } static inline struct scsi_data_buffer *scsi_prot(struct scsi_cmnd *cmd) { return cmd->prot_sdb; } #define scsi_for_each_prot_sg(cmd, sg, nseg, __i) \ for_each_sg(scsi_prot_sglist(cmd), sg, nseg, __i) static inline void set_status_byte(struct scsi_cmnd *cmd, char status) { cmd->result = (cmd->result & 0xffffff00) | status; } static inline u8 get_status_byte(struct scsi_cmnd *cmd) { return cmd->result & 0xff; } static inline void set_host_byte(struct scsi_cmnd *cmd, char status) { cmd->result = (cmd->result & 0xff00ffff) | (status << 16); } static inline u8 get_host_byte(struct scsi_cmnd *cmd) { return (cmd->result >> 16) & 0xff; } /** * scsi_msg_to_host_byte() - translate message byte * @cmd: the SCSI command * @msg: the SCSI parallel message byte to translate * * Translate the SCSI parallel message byte to a matching * host byte setting. A message of COMMAND_COMPLETE indicates * a successful command execution, any other message indicate * an error. As the messages themselves only have a meaning * for the SCSI parallel protocol this function translates * them into a matching host byte value for SCSI EH. */ static inline void scsi_msg_to_host_byte(struct scsi_cmnd *cmd, u8 msg) { switch (msg) { case COMMAND_COMPLETE: break; case ABORT_TASK_SET: set_host_byte(cmd, DID_ABORT); break; case TARGET_RESET: set_host_byte(cmd, DID_RESET); break; default: set_host_byte(cmd, DID_ERROR); break; } } static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd) { unsigned int xfer_len = scmd->sdb.length; unsigned int prot_interval = scsi_prot_interval(scmd); if (scmd->prot_flags & SCSI_PROT_TRANSFER_PI) xfer_len += (xfer_len >> ilog2(prot_interval)) * 8; return xfer_len; } extern void scsi_build_sense(struct scsi_cmnd *scmd, int desc, u8 key, u8 asc, u8 ascq); struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); #endif /* _SCSI_SCSI_CMND_H */ |
| 1 1 1 1 1 162 163 163 61 4 2 2 6 6 229 8 6 2 235 229 8 211 208 208 207 2 26 2 24 41 40 26 26 136 136 23 136 4 4 2 4 207 1 209 209 209 209 208 209 2 2 1 9 8 1 105 170 170 10 10 10 10 10 98 99 171 171 155 171 166 158 170 170 167 170 170 169 105 10 99 1 1 55 55 101 101 101 100 1 66 48 101 4 61 88 55 36 78 2 54 36 80 88 88 69 1 2 18 67 69 69 11 11 10 3 7 7 11 11 11 1 10 10 10 10 10 9 5 4 17 4 13 95 95 95 8 8 2 2 10 10 11 11 11 8 3 11 11 11 11 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "btree_key_cache.h" #include "btree_write_buffer.h" #include "bkey_methods.h" #include "btree_update.h" #include "buckets.h" #include "compress.h" #include "dirent.h" #include "disk_accounting.h" #include "error.h" #include "extents.h" #include "extent_update.h" #include "fs.h" #include "inode.h" #include "namei.h" #include "opts.h" #include "str_hash.h" #include "snapshot.h" #include "subvolume.h" #include "varint.h" #include <linux/random.h> #include <linux/unaligned.h> #define x(name, ...) #name, const char * const bch2_inode_opts[] = { BCH_INODE_OPTS() NULL, }; static const char * const bch2_inode_flag_strs[] = { BCH_INODE_FLAGS() NULL }; #undef x static int delete_ancestor_snapshot_inodes(struct btree_trans *, struct bpos); static int may_delete_deleted_inum(struct btree_trans *, subvol_inum); static const u8 byte_table[8] = { 1, 2, 3, 4, 6, 8, 10, 13 }; static int inode_decode_field(const u8 *in, const u8 *end, u64 out[2], unsigned *out_bits) { __be64 be[2] = { 0, 0 }; unsigned bytes, shift; u8 *p; if (in >= end) return -BCH_ERR_inode_unpack_error; if (!*in) return -BCH_ERR_inode_unpack_error; /* * position of highest set bit indicates number of bytes: * shift = number of bits to remove in high byte: */ shift = 8 - __fls(*in); /* 1 <= shift <= 8 */ bytes = byte_table[shift - 1]; if (in + bytes > end) return -BCH_ERR_inode_unpack_error; p = (u8 *) be + 16 - bytes; memcpy(p, in, bytes); *p ^= (1 << 8) >> shift; out[0] = be64_to_cpu(be[0]); out[1] = be64_to_cpu(be[1]); *out_bits = out[0] ? 64 + fls64(out[0]) : fls64(out[1]); return bytes; } static inline void bch2_inode_pack_inlined(struct bkey_inode_buf *packed, const struct bch_inode_unpacked *inode) { struct bkey_i_inode_v3 *k = &packed->inode; u8 *out = k->v.fields; u8 *end = (void *) &packed[1]; u8 *last_nonzero_field = out; unsigned nr_fields = 0, last_nonzero_fieldnr = 0; unsigned bytes; int ret; bkey_inode_v3_init(&packed->inode.k_i); packed->inode.k.p.offset = inode->bi_inum; packed->inode.v.bi_journal_seq = cpu_to_le64(inode->bi_journal_seq); packed->inode.v.bi_hash_seed = inode->bi_hash_seed; packed->inode.v.bi_flags = cpu_to_le64(inode->bi_flags); packed->inode.v.bi_sectors = cpu_to_le64(inode->bi_sectors); packed->inode.v.bi_size = cpu_to_le64(inode->bi_size); packed->inode.v.bi_version = cpu_to_le64(inode->bi_version); SET_INODEv3_MODE(&packed->inode.v, inode->bi_mode); SET_INODEv3_FIELDS_START(&packed->inode.v, INODEv3_FIELDS_START_CUR); #define x(_name, _bits) \ nr_fields++; \ \ if (inode->_name) { \ ret = bch2_varint_encode_fast(out, inode->_name); \ out += ret; \ \ if (_bits > 64) \ *out++ = 0; \ \ last_nonzero_field = out; \ last_nonzero_fieldnr = nr_fields; \ } else { \ *out++ = 0; \ \ if (_bits > 64) \ *out++ = 0; \ } BCH_INODE_FIELDS_v3() #undef x BUG_ON(out > end); out = last_nonzero_field; nr_fields = last_nonzero_fieldnr; bytes = out - (u8 *) &packed->inode.v; set_bkey_val_bytes(&packed->inode.k, bytes); memset_u64s_tail(&packed->inode.v, 0, bytes); SET_INODEv3_NR_FIELDS(&k->v, nr_fields); if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) { struct bch_inode_unpacked unpacked; ret = bch2_inode_unpack(bkey_i_to_s_c(&packed->inode.k_i), &unpacked); BUG_ON(ret); BUG_ON(unpacked.bi_inum != inode->bi_inum); BUG_ON(unpacked.bi_hash_seed != inode->bi_hash_seed); BUG_ON(unpacked.bi_sectors != inode->bi_sectors); BUG_ON(unpacked.bi_size != inode->bi_size); BUG_ON(unpacked.bi_version != inode->bi_version); BUG_ON(unpacked.bi_mode != inode->bi_mode); #define x(_name, _bits) if (unpacked._name != inode->_name) \ panic("unpacked %llu should be %llu", \ (u64) unpacked._name, (u64) inode->_name); BCH_INODE_FIELDS_v3() #undef x } } void bch2_inode_pack(struct bkey_inode_buf *packed, const struct bch_inode_unpacked *inode) { bch2_inode_pack_inlined(packed, inode); } static noinline int bch2_inode_unpack_v1(struct bkey_s_c_inode inode, struct bch_inode_unpacked *unpacked) { const u8 *in = inode.v->fields; const u8 *end = bkey_val_end(inode); u64 field[2]; unsigned fieldnr = 0, field_bits; int ret; #define x(_name, _bits) \ if (fieldnr++ == INODEv1_NR_FIELDS(inode.v)) { \ unsigned offset = offsetof(struct bch_inode_unpacked, _name);\ memset((void *) unpacked + offset, 0, \ sizeof(*unpacked) - offset); \ return 0; \ } \ \ ret = inode_decode_field(in, end, field, &field_bits); \ if (ret < 0) \ return ret; \ \ if (field_bits > sizeof(unpacked->_name) * 8) \ return -BCH_ERR_inode_unpack_error; \ \ unpacked->_name = field[1]; \ in += ret; BCH_INODE_FIELDS_v2() #undef x /* XXX: signal if there were more fields than expected? */ return 0; } static int bch2_inode_unpack_v2(struct bch_inode_unpacked *unpacked, const u8 *in, const u8 *end, unsigned nr_fields) { unsigned fieldnr = 0; int ret; u64 v[2]; #define x(_name, _bits) \ if (fieldnr < nr_fields) { \ ret = bch2_varint_decode_fast(in, end, &v[0]); \ if (ret < 0) \ return ret; \ in += ret; \ \ if (_bits > 64) { \ ret = bch2_varint_decode_fast(in, end, &v[1]); \ if (ret < 0) \ return ret; \ in += ret; \ } else { \ v[1] = 0; \ } \ } else { \ v[0] = v[1] = 0; \ } \ \ unpacked->_name = v[0]; \ if (v[1] || v[0] != unpacked->_name) \ return -BCH_ERR_inode_unpack_error; \ fieldnr++; BCH_INODE_FIELDS_v2() #undef x /* XXX: signal if there were more fields than expected? */ return 0; } static int bch2_inode_unpack_v3(struct bkey_s_c k, struct bch_inode_unpacked *unpacked) { struct bkey_s_c_inode_v3 inode = bkey_s_c_to_inode_v3(k); const u8 *in = inode.v->fields; const u8 *end = bkey_val_end(inode); unsigned nr_fields = INODEv3_NR_FIELDS(inode.v); unsigned fieldnr = 0; int ret; u64 v[2]; unpacked->bi_inum = inode.k->p.offset; unpacked->bi_snapshot = inode.k->p.snapshot; unpacked->bi_journal_seq= le64_to_cpu(inode.v->bi_journal_seq); unpacked->bi_hash_seed = inode.v->bi_hash_seed; unpacked->bi_flags = le64_to_cpu(inode.v->bi_flags); unpacked->bi_sectors = le64_to_cpu(inode.v->bi_sectors); unpacked->bi_size = le64_to_cpu(inode.v->bi_size); unpacked->bi_version = le64_to_cpu(inode.v->bi_version); unpacked->bi_mode = INODEv3_MODE(inode.v); #define x(_name, _bits) \ if (fieldnr < nr_fields) { \ ret = bch2_varint_decode_fast(in, end, &v[0]); \ if (ret < 0) \ return ret; \ in += ret; \ \ if (_bits > 64) { \ ret = bch2_varint_decode_fast(in, end, &v[1]); \ if (ret < 0) \ return ret; \ in += ret; \ } else { \ v[1] = 0; \ } \ } else { \ v[0] = v[1] = 0; \ } \ \ unpacked->_name = v[0]; \ if (v[1] || v[0] != unpacked->_name) \ return -BCH_ERR_inode_unpack_error; \ fieldnr++; BCH_INODE_FIELDS_v3() #undef x /* XXX: signal if there were more fields than expected? */ return 0; } static noinline int bch2_inode_unpack_slowpath(struct bkey_s_c k, struct bch_inode_unpacked *unpacked) { memset(unpacked, 0, sizeof(*unpacked)); switch (k.k->type) { case KEY_TYPE_inode: { struct bkey_s_c_inode inode = bkey_s_c_to_inode(k); unpacked->bi_inum = inode.k->p.offset; unpacked->bi_snapshot = inode.k->p.snapshot; unpacked->bi_journal_seq= 0; unpacked->bi_hash_seed = inode.v->bi_hash_seed; unpacked->bi_flags = le32_to_cpu(inode.v->bi_flags); unpacked->bi_mode = le16_to_cpu(inode.v->bi_mode); if (INODEv1_NEW_VARINT(inode.v)) { return bch2_inode_unpack_v2(unpacked, inode.v->fields, bkey_val_end(inode), INODEv1_NR_FIELDS(inode.v)); } else { return bch2_inode_unpack_v1(inode, unpacked); } break; } case KEY_TYPE_inode_v2: { struct bkey_s_c_inode_v2 inode = bkey_s_c_to_inode_v2(k); unpacked->bi_inum = inode.k->p.offset; unpacked->bi_snapshot = inode.k->p.snapshot; unpacked->bi_journal_seq= le64_to_cpu(inode.v->bi_journal_seq); unpacked->bi_hash_seed = inode.v->bi_hash_seed; unpacked->bi_flags = le64_to_cpu(inode.v->bi_flags); unpacked->bi_mode = le16_to_cpu(inode.v->bi_mode); return bch2_inode_unpack_v2(unpacked, inode.v->fields, bkey_val_end(inode), INODEv2_NR_FIELDS(inode.v)); } default: BUG(); } } int bch2_inode_unpack(struct bkey_s_c k, struct bch_inode_unpacked *unpacked) { return likely(k.k->type == KEY_TYPE_inode_v3) ? bch2_inode_unpack_v3(k, unpacked) : bch2_inode_unpack_slowpath(k, unpacked); } int __bch2_inode_peek(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, subvol_inum inum, unsigned flags, bool warn) { u32 snapshot; int ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn); if (ret) return ret; struct bkey_s_c k = bch2_bkey_get_iter(trans, iter, BTREE_ID_inodes, SPOS(0, inum.inum, snapshot), flags|BTREE_ITER_cached); ret = bkey_err(k); if (ret) return ret; ret = bkey_is_inode(k.k) ? 0 : -BCH_ERR_ENOENT_inode; if (ret) goto err; ret = bch2_inode_unpack(k, inode); if (ret) goto err; return 0; err: if (warn) bch_err_msg(trans->c, ret, "looking up inum %llu:%llu:", inum.subvol, inum.inum); bch2_trans_iter_exit(trans, iter); return ret; } int bch2_inode_find_by_inum_snapshot(struct btree_trans *trans, u64 inode_nr, u32 snapshot, struct bch_inode_unpacked *inode, unsigned flags) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, SPOS(0, inode_nr, snapshot), flags); int ret = bkey_err(k); if (ret) goto err; ret = bkey_is_inode(k.k) ? bch2_inode_unpack(k, inode) : -BCH_ERR_ENOENT_inode; err: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_inode_find_by_inum_nowarn_trans(struct btree_trans *trans, subvol_inum inum, struct bch_inode_unpacked *inode) { struct btree_iter iter; int ret; ret = bch2_inode_peek_nowarn(trans, &iter, inode, inum, 0); if (!ret) bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_inode_find_by_inum_trans(struct btree_trans *trans, subvol_inum inum, struct bch_inode_unpacked *inode) { struct btree_iter iter; int ret; ret = bch2_inode_peek(trans, &iter, inode, inum, 0); if (!ret) bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_inode_find_by_inum(struct bch_fs *c, subvol_inum inum, struct bch_inode_unpacked *inode) { return bch2_trans_do(c, bch2_inode_find_by_inum_trans(trans, inum, inode)); } int bch2_inode_find_snapshot_root(struct btree_trans *trans, u64 inum, struct bch_inode_unpacked *root) { struct btree_iter iter; struct bkey_s_c k; int ret = 0; for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, U32_MAX), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inum) break; if (bkey_is_inode(k.k)) { ret = bch2_inode_unpack(k, root); goto out; } } /* We're only called when we know we have an inode for @inum */ BUG_ON(!ret); out: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_inode_write_flags(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, enum btree_iter_update_trigger_flags flags) { struct bkey_inode_buf *inode_p; inode_p = bch2_trans_kmalloc(trans, sizeof(*inode_p)); if (IS_ERR(inode_p)) return PTR_ERR(inode_p); bch2_inode_pack_inlined(inode_p, inode); inode_p->inode.k.p.snapshot = iter->snapshot; return bch2_trans_update(trans, iter, &inode_p->inode.k_i, flags); } int __bch2_fsck_write_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bkey_inode_buf *inode_p = bch2_trans_kmalloc(trans, sizeof(*inode_p)); if (IS_ERR(inode_p)) return PTR_ERR(inode_p); bch2_inode_pack(inode_p, inode); inode_p->inode.k.p.snapshot = inode->bi_snapshot; return bch2_btree_insert_nonextent(trans, BTREE_ID_inodes, &inode_p->inode.k_i, BTREE_UPDATE_internal_snapshot_node); } int bch2_fsck_write_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, __bch2_fsck_write_inode(trans, inode)); bch_err_fn(trans->c, ret); return ret; } struct bkey_i *bch2_inode_to_v3(struct btree_trans *trans, struct bkey_i *k) { struct bch_inode_unpacked u; struct bkey_inode_buf *inode_p; int ret; if (!bkey_is_inode(&k->k)) return ERR_PTR(-ENOENT); inode_p = bch2_trans_kmalloc(trans, sizeof(*inode_p)); if (IS_ERR(inode_p)) return ERR_CAST(inode_p); ret = bch2_inode_unpack(bkey_i_to_s_c(k), &u); if (ret) return ERR_PTR(ret); bch2_inode_pack(inode_p, &u); return &inode_p->inode.k_i; } static int __bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { struct bch_inode_unpacked unpacked; int ret = 0; bkey_fsck_err_on(k.k->p.inode, c, inode_pos_inode_nonzero, "nonzero k.p.inode"); bkey_fsck_err_on(k.k->p.offset < BLOCKDEV_INODE_MAX, c, inode_pos_blockdev_range, "fs inode in blockdev range"); bkey_fsck_err_on(bch2_inode_unpack(k, &unpacked), c, inode_unpack_error, "invalid variable length fields"); bkey_fsck_err_on(unpacked.bi_data_checksum >= BCH_CSUM_OPT_NR + 1, c, inode_checksum_type_invalid, "invalid data checksum type (%u >= %u", unpacked.bi_data_checksum, BCH_CSUM_OPT_NR + 1); bkey_fsck_err_on(unpacked.bi_compression && !bch2_compression_opt_valid(unpacked.bi_compression - 1), c, inode_compression_type_invalid, "invalid compression opt %u", unpacked.bi_compression - 1); bkey_fsck_err_on((unpacked.bi_flags & BCH_INODE_unlinked) && unpacked.bi_nlink != 0, c, inode_unlinked_but_nlink_nonzero, "flagged as unlinked but bi_nlink != 0"); bkey_fsck_err_on(unpacked.bi_subvol && !S_ISDIR(unpacked.bi_mode), c, inode_subvol_root_but_not_dir, "subvolume root but not a directory"); fsck_err: return ret; } int bch2_inode_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { struct bkey_s_c_inode inode = bkey_s_c_to_inode(k); int ret = 0; bkey_fsck_err_on(INODEv1_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, inode_str_hash_invalid, "invalid str hash type (%llu >= %u)", INODEv1_STR_HASH(inode.v), BCH_STR_HASH_NR); ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } int bch2_inode_v2_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { struct bkey_s_c_inode_v2 inode = bkey_s_c_to_inode_v2(k); int ret = 0; bkey_fsck_err_on(INODEv2_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, inode_str_hash_invalid, "invalid str hash type (%llu >= %u)", INODEv2_STR_HASH(inode.v), BCH_STR_HASH_NR); ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } int bch2_inode_v3_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { struct bkey_s_c_inode_v3 inode = bkey_s_c_to_inode_v3(k); int ret = 0; bkey_fsck_err_on(INODEv3_FIELDS_START(inode.v) < INODEv3_FIELDS_START_INITIAL || INODEv3_FIELDS_START(inode.v) > bkey_val_u64s(inode.k), c, inode_v3_fields_start_bad, "invalid fields_start (got %llu, min %u max %zu)", INODEv3_FIELDS_START(inode.v), INODEv3_FIELDS_START_INITIAL, bkey_val_u64s(inode.k)); bkey_fsck_err_on(INODEv3_STR_HASH(inode.v) >= BCH_STR_HASH_NR, c, inode_str_hash_invalid, "invalid str hash type (%llu >= %u)", INODEv3_STR_HASH(inode.v), BCH_STR_HASH_NR); ret = __bch2_inode_validate(c, k, from); fsck_err: return ret; } static void __bch2_inode_unpacked_to_text(struct printbuf *out, struct bch_inode_unpacked *inode) { prt_printf(out, "\n"); printbuf_indent_add(out, 2); prt_printf(out, "mode=%o\n", inode->bi_mode); prt_str(out, "flags="); prt_bitflags(out, bch2_inode_flag_strs, inode->bi_flags & ((1U << 20) - 1)); prt_printf(out, "(%x)\n", inode->bi_flags); prt_printf(out, "journal_seq=%llu\n", inode->bi_journal_seq); prt_printf(out, "hash_seed=%llx\n", inode->bi_hash_seed); prt_printf(out, "hash_type="); bch2_prt_str_hash_type(out, INODE_STR_HASH(inode)); prt_newline(out); prt_printf(out, "bi_size=%llu\n", inode->bi_size); prt_printf(out, "bi_sectors=%llu\n", inode->bi_sectors); prt_printf(out, "bi_version=%llu\n", inode->bi_version); #define x(_name, _bits) \ prt_printf(out, #_name "=%llu\n", (u64) inode->_name); BCH_INODE_FIELDS_v3() #undef x bch2_printbuf_strip_trailing_newline(out); printbuf_indent_sub(out, 2); } void bch2_inode_unpacked_to_text(struct printbuf *out, struct bch_inode_unpacked *inode) { prt_printf(out, "inum: %llu:%u ", inode->bi_inum, inode->bi_snapshot); __bch2_inode_unpacked_to_text(out, inode); } void bch2_inode_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { struct bch_inode_unpacked inode; if (bch2_inode_unpack(k, &inode)) { prt_printf(out, "(unpack error)"); return; } __bch2_inode_unpacked_to_text(out, &inode); } static inline u64 bkey_inode_flags(struct bkey_s_c k) { switch (k.k->type) { case KEY_TYPE_inode: return le32_to_cpu(bkey_s_c_to_inode(k).v->bi_flags); case KEY_TYPE_inode_v2: return le64_to_cpu(bkey_s_c_to_inode_v2(k).v->bi_flags); case KEY_TYPE_inode_v3: return le64_to_cpu(bkey_s_c_to_inode_v3(k).v->bi_flags); default: return 0; } } static inline void bkey_inode_flags_set(struct bkey_s k, u64 f) { switch (k.k->type) { case KEY_TYPE_inode: bkey_s_to_inode(k).v->bi_flags = cpu_to_le32(f); return; case KEY_TYPE_inode_v2: bkey_s_to_inode_v2(k).v->bi_flags = cpu_to_le64(f); return; case KEY_TYPE_inode_v3: bkey_s_to_inode_v3(k).v->bi_flags = cpu_to_le64(f); return; default: BUG(); } } static inline bool bkey_is_unlinked_inode(struct bkey_s_c k) { unsigned f = bkey_inode_flags(k) & BCH_INODE_unlinked; return (f & BCH_INODE_unlinked) && !(f & BCH_INODE_has_child_snapshot); } static struct bkey_s_c bch2_bkey_get_iter_snapshot_parent(struct btree_trans *trans, struct btree_iter *iter, enum btree_id btree, struct bpos pos, unsigned flags) { struct bch_fs *c = trans->c; struct bkey_s_c k; int ret = 0; for_each_btree_key_max_norestart(trans, *iter, btree, bpos_successor(pos), SPOS(pos.inode, pos.offset, U32_MAX), flags|BTREE_ITER_all_snapshots, k, ret) if (bch2_snapshot_is_ancestor(c, pos.snapshot, k.k->p.snapshot)) return k; bch2_trans_iter_exit(trans, iter); return ret ? bkey_s_c_err(ret) : bkey_s_c_null; } static struct bkey_s_c bch2_inode_get_iter_snapshot_parent(struct btree_trans *trans, struct btree_iter *iter, struct bpos pos, unsigned flags) { struct bkey_s_c k; again: k = bch2_bkey_get_iter_snapshot_parent(trans, iter, BTREE_ID_inodes, pos, flags); if (!k.k || bkey_err(k) || bkey_is_inode(k.k)) return k; bch2_trans_iter_exit(trans, iter); pos = k.k->p; goto again; } int __bch2_inode_has_child_snapshots(struct btree_trans *trans, struct bpos pos) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret = 0; for_each_btree_key_max_norestart(trans, iter, BTREE_ID_inodes, POS(0, pos.offset), bpos_predecessor(pos), BTREE_ITER_all_snapshots| BTREE_ITER_with_updates, k, ret) if (bch2_snapshot_is_ancestor(c, k.k->p.snapshot, pos.snapshot) && bkey_is_inode(k.k)) { ret = 1; break; } bch2_trans_iter_exit(trans, &iter); return ret; } static int update_inode_has_children(struct btree_trans *trans, struct bkey_s k, bool have_child) { if (!have_child) { int ret = bch2_inode_has_child_snapshots(trans, k.k->p); if (ret) return ret < 0 ? ret : 0; } u64 f = bkey_inode_flags(k.s_c); if (have_child != !!(f & BCH_INODE_has_child_snapshot)) bkey_inode_flags_set(k, f ^ BCH_INODE_has_child_snapshot); return 0; } static int update_parent_inode_has_children(struct btree_trans *trans, struct bpos pos, bool have_child) { struct btree_iter iter; struct bkey_s_c k = bch2_inode_get_iter_snapshot_parent(trans, &iter, pos, BTREE_ITER_with_updates); int ret = bkey_err(k); if (ret) return ret; if (!k.k) return 0; if (!have_child) { ret = bch2_inode_has_child_snapshots(trans, k.k->p); if (ret) { ret = ret < 0 ? ret : 0; goto err; } } u64 f = bkey_inode_flags(k); if (have_child != !!(f & BCH_INODE_has_child_snapshot)) { struct bkey_i *update = bch2_bkey_make_mut(trans, &iter, &k, BTREE_UPDATE_internal_snapshot_node); ret = PTR_ERR_OR_ZERO(update); if (ret) goto err; bkey_inode_flags_set(bkey_i_to_s(update), f ^ BCH_INODE_has_child_snapshot); } err: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_trigger_inode(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; if ((flags & BTREE_TRIGGER_atomic) && (flags & BTREE_TRIGGER_insert)) { BUG_ON(!trans->journal_res.seq); bkey_s_to_inode_v3(new).v->bi_journal_seq = cpu_to_le64(trans->journal_res.seq); } s64 nr[1] = { bkey_is_inode(new.k) - bkey_is_inode(old.k) }; if ((flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc)) && nr[0]) { int ret = bch2_disk_accounting_mod2(trans, flags & BTREE_TRIGGER_gc, nr, nr_inodes); if (ret) return ret; } if (flags & BTREE_TRIGGER_transactional) { int unlinked_delta = (int) bkey_is_unlinked_inode(new.s_c) - (int) bkey_is_unlinked_inode(old); if (unlinked_delta) { int ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_deleted_inodes, new.k->p, unlinked_delta > 0); if (ret) return ret; } /* * If we're creating or deleting an inode at this snapshot ID, * and there might be an inode in a parent snapshot ID, we might * need to set or clear the has_child_snapshot flag on the * parent. */ int deleted_delta = (int) bkey_is_inode(new.k) - (int) bkey_is_inode(old.k); if (deleted_delta && bch2_snapshot_parent(c, new.k->p.snapshot)) { int ret = update_parent_inode_has_children(trans, new.k->p, deleted_delta > 0); if (ret) return ret; } /* * When an inode is first updated in a new snapshot, we may need * to clear has_child_snapshot */ if (deleted_delta > 0) { int ret = update_inode_has_children(trans, new, false); if (ret) return ret; } } return 0; } int bch2_inode_generation_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { int ret = 0; bkey_fsck_err_on(k.k->p.inode, c, inode_pos_inode_nonzero, "nonzero k.p.inode"); fsck_err: return ret; } void bch2_inode_generation_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { struct bkey_s_c_inode_generation gen = bkey_s_c_to_inode_generation(k); prt_printf(out, "generation: %u", le32_to_cpu(gen.v->bi_generation)); } int bch2_inode_alloc_cursor_validate(struct bch_fs *c, struct bkey_s_c k, struct bkey_validate_context from) { int ret = 0; bkey_fsck_err_on(k.k->p.inode != LOGGED_OPS_INUM_inode_cursors, c, inode_alloc_cursor_inode_bad, "k.p.inode bad"); fsck_err: return ret; } void bch2_inode_alloc_cursor_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { struct bkey_s_c_inode_alloc_cursor i = bkey_s_c_to_inode_alloc_cursor(k); prt_printf(out, "idx %llu generation %llu", le64_to_cpu(i.v->idx), le64_to_cpu(i.v->gen)); } void bch2_inode_init_early(struct bch_fs *c, struct bch_inode_unpacked *inode_u) { enum bch_str_hash_type str_hash = bch2_str_hash_opt_to_type(c, c->opts.str_hash); memset(inode_u, 0, sizeof(*inode_u)); SET_INODE_STR_HASH(inode_u, str_hash); get_random_bytes(&inode_u->bi_hash_seed, sizeof(inode_u->bi_hash_seed)); } void bch2_inode_init_late(struct bch_fs *c, struct bch_inode_unpacked *inode_u, u64 now, uid_t uid, gid_t gid, umode_t mode, dev_t rdev, struct bch_inode_unpacked *parent) { inode_u->bi_mode = mode; inode_u->bi_uid = uid; inode_u->bi_gid = gid; inode_u->bi_dev = rdev; inode_u->bi_atime = now; inode_u->bi_mtime = now; inode_u->bi_ctime = now; inode_u->bi_otime = now; if (parent && parent->bi_mode & S_ISGID) { inode_u->bi_gid = parent->bi_gid; if (S_ISDIR(mode)) inode_u->bi_mode |= S_ISGID; } if (parent) { #define x(_name, ...) inode_u->bi_##_name = parent->bi_##_name; BCH_INODE_OPTS() #undef x } if (!S_ISDIR(mode)) inode_u->bi_casefold = 0; if (bch2_inode_casefold(c, inode_u)) inode_u->bi_flags |= BCH_INODE_has_case_insensitive; } void bch2_inode_init(struct bch_fs *c, struct bch_inode_unpacked *inode_u, uid_t uid, gid_t gid, umode_t mode, dev_t rdev, struct bch_inode_unpacked *parent) { bch2_inode_init_early(c, inode_u); bch2_inode_init_late(c, inode_u, bch2_current_time(c), uid, gid, mode, rdev, parent); } static struct bkey_i_inode_alloc_cursor * bch2_inode_alloc_cursor_get(struct btree_trans *trans, u64 cpu, u64 *min, u64 *max) { struct bch_fs *c = trans->c; u64 cursor_idx = c->opts.inodes_32bit ? 0 : cpu + 1; cursor_idx &= ~(~0ULL << c->opts.shard_inode_numbers_bits); struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_logged_ops, POS(LOGGED_OPS_INUM_inode_cursors, cursor_idx), BTREE_ITER_cached); int ret = bkey_err(k); if (ret) return ERR_PTR(ret); struct bkey_i_inode_alloc_cursor *cursor = k.k->type == KEY_TYPE_inode_alloc_cursor ? bch2_bkey_make_mut_typed(trans, &iter, &k, 0, inode_alloc_cursor) : bch2_bkey_alloc(trans, &iter, 0, inode_alloc_cursor); ret = PTR_ERR_OR_ZERO(cursor); if (ret) goto err; if (c->opts.inodes_32bit) { *min = BLOCKDEV_INODE_MAX; *max = INT_MAX; } else { cursor->v.bits = c->opts.shard_inode_numbers_bits; unsigned bits = 63 - c->opts.shard_inode_numbers_bits; *min = max(cpu << bits, (u64) INT_MAX + 1); *max = (cpu << bits) | ~(ULLONG_MAX << bits); } if (le64_to_cpu(cursor->v.idx) < *min) cursor->v.idx = cpu_to_le64(*min); if (le64_to_cpu(cursor->v.idx) >= *max) { cursor->v.idx = cpu_to_le64(*min); le32_add_cpu(&cursor->v.gen, 1); } err: bch2_trans_iter_exit(trans, &iter); return ret ? ERR_PTR(ret) : cursor; } /* * This just finds an empty slot: */ int bch2_inode_create(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode_u, u32 snapshot, u64 cpu) { u64 min, max; struct bkey_i_inode_alloc_cursor *cursor = bch2_inode_alloc_cursor_get(trans, cpu, &min, &max); int ret = PTR_ERR_OR_ZERO(cursor); if (ret) return ret; u64 start = le64_to_cpu(cursor->v.idx); u64 pos = start; bch2_trans_iter_init(trans, iter, BTREE_ID_inodes, POS(0, pos), BTREE_ITER_all_snapshots| BTREE_ITER_intent); struct bkey_s_c k; again: while ((k = bch2_btree_iter_peek(trans, iter)).k && !(ret = bkey_err(k)) && bkey_lt(k.k->p, POS(0, max))) { if (pos < iter->pos.offset) goto found_slot; /* * We don't need to iterate over keys in every snapshot once * we've found just one: */ pos = iter->pos.offset + 1; bch2_btree_iter_set_pos(trans, iter, POS(0, pos)); } if (!ret && pos < max) goto found_slot; if (!ret && start == min) ret = bch_err_throw(trans->c, ENOSPC_inode_create); if (ret) { bch2_trans_iter_exit(trans, iter); return ret; } /* Retry from start */ pos = start = min; bch2_btree_iter_set_pos(trans, iter, POS(0, pos)); le32_add_cpu(&cursor->v.gen, 1); goto again; found_slot: bch2_btree_iter_set_pos(trans, iter, SPOS(0, pos, snapshot)); k = bch2_btree_iter_peek_slot(trans, iter); ret = bkey_err(k); if (ret) { bch2_trans_iter_exit(trans, iter); return ret; } inode_u->bi_inum = k.k->p.offset; inode_u->bi_generation = le64_to_cpu(cursor->v.gen); cursor->v.idx = cpu_to_le64(k.k->p.offset + 1); return 0; } static int bch2_inode_delete_keys(struct btree_trans *trans, subvol_inum inum, enum btree_id id) { struct btree_iter iter; struct bkey_s_c k; struct bkey_i delete; struct bpos end = POS(inum.inum, U64_MAX); u32 snapshot; int ret = 0; /* * We're never going to be deleting partial extents, no need to use an * extent iterator: */ bch2_trans_iter_init(trans, &iter, id, POS(inum.inum, 0), BTREE_ITER_intent); while (1) { bch2_trans_begin(trans); ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); if (ret) goto err; bch2_btree_iter_set_snapshot(trans, &iter, snapshot); k = bch2_btree_iter_peek_max(trans, &iter, end); ret = bkey_err(k); if (ret) goto err; if (!k.k) break; bkey_init(&delete.k); delete.k.p = iter.pos; if (iter.flags & BTREE_ITER_is_extents) bch2_key_resize(&delete.k, bpos_min(end, k.k->p).offset - iter.pos.offset); ret = bch2_trans_update(trans, &iter, &delete, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); err: if (ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart)) break; } bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_inode_rm(struct bch_fs *c, subvol_inum inum) { struct btree_trans *trans = bch2_trans_get(c); struct btree_iter iter = {}; struct bkey_s_c k; u32 snapshot; int ret; ret = lockrestart_do(trans, may_delete_deleted_inum(trans, inum)); if (ret) goto err2; /* * If this was a directory, there shouldn't be any real dirents left - * but there could be whiteouts (from hash collisions) that we should * delete: * * XXX: the dirent code ideally would delete whiteouts when they're no * longer needed */ ret = bch2_inode_delete_keys(trans, inum, BTREE_ID_extents) ?: bch2_inode_delete_keys(trans, inum, BTREE_ID_xattrs) ?: bch2_inode_delete_keys(trans, inum, BTREE_ID_dirents); if (ret) goto err2; retry: bch2_trans_begin(trans); ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); if (ret) goto err; k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, SPOS(0, inum.inum, snapshot), BTREE_ITER_intent|BTREE_ITER_cached); ret = bkey_err(k); if (ret) goto err; if (!bkey_is_inode(k.k)) { bch2_fs_inconsistent(c, "inode %llu:%u not found when deleting", inum.inum, snapshot); ret = bch_err_throw(c, ENOENT_inode); goto err; } ret = bch2_btree_delete_at(trans, &iter, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); err: bch2_trans_iter_exit(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) goto retry; if (ret) goto err2; ret = delete_ancestor_snapshot_inodes(trans, SPOS(0, inum.inum, snapshot)); err2: bch2_trans_put(trans); return ret; } int bch2_inode_nlink_inc(struct bch_inode_unpacked *bi) { if (bi->bi_flags & BCH_INODE_unlinked) bi->bi_flags &= ~BCH_INODE_unlinked; else { if (bi->bi_nlink == U32_MAX) return -EINVAL; bi->bi_nlink++; } return 0; } void bch2_inode_nlink_dec(struct btree_trans *trans, struct bch_inode_unpacked *bi) { if (bi->bi_nlink && (bi->bi_flags & BCH_INODE_unlinked)) { bch2_trans_inconsistent(trans, "inode %llu unlinked but link count nonzero", bi->bi_inum); return; } if (bi->bi_flags & BCH_INODE_unlinked) { bch2_trans_inconsistent(trans, "inode %llu link count underflow", bi->bi_inum); return; } if (bi->bi_nlink) bi->bi_nlink--; else bi->bi_flags |= BCH_INODE_unlinked; } struct bch_opts bch2_inode_opts_to_opts(struct bch_inode_unpacked *inode) { struct bch_opts ret = { 0 }; #define x(_name, _bits) \ if (inode->bi_##_name) \ opt_set(ret, _name, inode->bi_##_name - 1); BCH_INODE_OPTS() #undef x return ret; } void bch2_inode_opts_get(struct bch_io_opts *opts, struct bch_fs *c, struct bch_inode_unpacked *inode) { #define x(_name, _bits) \ if ((inode)->bi_##_name) { \ opts->_name = inode->bi_##_name - 1; \ opts->_name##_from_inode = true; \ } else { \ opts->_name = c->opts._name; \ opts->_name##_from_inode = false; \ } BCH_INODE_OPTS() #undef x bch2_io_opts_fixups(opts); } int bch2_inum_opts_get(struct btree_trans *trans, subvol_inum inum, struct bch_io_opts *opts) { struct bch_inode_unpacked inode; int ret = lockrestart_do(trans, bch2_inode_find_by_inum_trans(trans, inum, &inode)); if (ret) return ret; bch2_inode_opts_get(opts, trans->c, &inode); return 0; } int bch2_inode_set_casefold(struct btree_trans *trans, subvol_inum inum, struct bch_inode_unpacked *bi, unsigned v) { struct bch_fs *c = trans->c; #ifndef CONFIG_UNICODE bch_err(c, "Cannot use casefolding on a kernel without CONFIG_UNICODE"); return -EOPNOTSUPP; #endif if (c->opts.casefold_disabled) return -EOPNOTSUPP; int ret = 0; /* Not supported on individual files. */ if (!S_ISDIR(bi->bi_mode)) return -EOPNOTSUPP; /* * Make sure the dir is empty, as otherwise we'd need to * rehash everything and update the dirent keys. */ ret = bch2_empty_dir_trans(trans, inum); if (ret < 0) return ret; ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding); if (ret) return ret; bch2_check_set_feature(c, BCH_FEATURE_casefolding); bi->bi_casefold = v + 1; bi->bi_fields_set |= BIT(Inode_opt_casefold); return bch2_maybe_propagate_has_case_insensitive(trans, inum, bi); } static noinline int __bch2_inode_rm_snapshot(struct btree_trans *trans, u64 inum, u32 snapshot) { struct bch_fs *c = trans->c; struct btree_iter iter = {}; struct bkey_i_inode_generation delete; struct bch_inode_unpacked inode_u; struct bkey_s_c k; int ret; do { ret = bch2_btree_delete_range_trans(trans, BTREE_ID_extents, SPOS(inum, 0, snapshot), SPOS(inum, U64_MAX, snapshot), 0, NULL) ?: bch2_btree_delete_range_trans(trans, BTREE_ID_dirents, SPOS(inum, 0, snapshot), SPOS(inum, U64_MAX, snapshot), 0, NULL) ?: bch2_btree_delete_range_trans(trans, BTREE_ID_xattrs, SPOS(inum, 0, snapshot), SPOS(inum, U64_MAX, snapshot), 0, NULL); } while (ret == -BCH_ERR_transaction_restart_nested); if (ret) goto err; retry: bch2_trans_begin(trans); k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, SPOS(0, inum, snapshot), BTREE_ITER_intent); ret = bkey_err(k); if (ret) goto err; if (!bkey_is_inode(k.k)) { bch2_fs_inconsistent(c, "inode %llu:%u not found when deleting", inum, snapshot); ret = bch_err_throw(c, ENOENT_inode); goto err; } bch2_inode_unpack(k, &inode_u); /* Subvolume root? */ if (inode_u.bi_subvol) bch_warn(c, "deleting inode %llu marked as unlinked, but also a subvolume root!?", inode_u.bi_inum); bkey_inode_generation_init(&delete.k_i); delete.k.p = iter.pos; delete.v.bi_generation = cpu_to_le32(inode_u.bi_generation + 1); ret = bch2_trans_update(trans, &iter, &delete.k_i, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); err: bch2_trans_iter_exit(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) goto retry; return ret ?: -BCH_ERR_transaction_restart_nested; } /* * After deleting an inode, there may be versions in older snapshots that should * also be deleted - if they're not referenced by sibling snapshots and not open * in other subvolumes: */ static int delete_ancestor_snapshot_inodes(struct btree_trans *trans, struct bpos pos) { struct btree_iter iter; struct bkey_s_c k; int ret; next_parent: ret = lockrestart_do(trans, bkey_err(k = bch2_inode_get_iter_snapshot_parent(trans, &iter, pos, 0))); if (ret || !k.k) return ret; bool unlinked = bkey_is_unlinked_inode(k); pos = k.k->p; bch2_trans_iter_exit(trans, &iter); if (!unlinked) return 0; ret = lockrestart_do(trans, bch2_inode_or_descendents_is_open(trans, pos)); if (ret) return ret < 0 ? ret : 0; ret = __bch2_inode_rm_snapshot(trans, pos.offset, pos.snapshot); if (ret) return ret; goto next_parent; } int bch2_inode_rm_snapshot(struct btree_trans *trans, u64 inum, u32 snapshot) { return __bch2_inode_rm_snapshot(trans, inum, snapshot) ?: delete_ancestor_snapshot_inodes(trans, SPOS(0, inum, snapshot)); } static int may_delete_deleted_inode(struct btree_trans *trans, struct bpos pos, bool from_deleted_inodes) { struct bch_fs *c = trans->c; struct btree_iter inode_iter; struct bkey_s_c k; struct bch_inode_unpacked inode; struct printbuf buf = PRINTBUF; int ret; k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, pos, BTREE_ITER_cached); ret = bkey_err(k); if (ret) return ret; ret = bkey_is_inode(k.k) ? 0 : bch_err_throw(c, ENOENT_inode); if (fsck_err_on(from_deleted_inodes && ret, trans, deleted_inode_missing, "nonexistent inode %llu:%u in deleted_inodes btree", pos.offset, pos.snapshot)) goto delete; if (ret) goto out; ret = bch2_inode_unpack(k, &inode); if (ret) goto out; if (S_ISDIR(inode.bi_mode)) { ret = bch2_empty_dir_snapshot(trans, pos.offset, 0, pos.snapshot); if (fsck_err_on(from_deleted_inodes && bch2_err_matches(ret, ENOTEMPTY), trans, deleted_inode_is_dir, "non empty directory %llu:%u in deleted_inodes btree", pos.offset, pos.snapshot)) goto delete; if (ret) goto out; } ret = inode.bi_flags & BCH_INODE_unlinked ? 0 : bch_err_throw(c, inode_not_unlinked); if (fsck_err_on(from_deleted_inodes && ret, trans, deleted_inode_not_unlinked, "non-deleted inode %llu:%u in deleted_inodes btree", pos.offset, pos.snapshot)) goto delete; if (ret) goto out; ret = !(inode.bi_flags & BCH_INODE_has_child_snapshot) ? 0 : bch_err_throw(c, inode_has_child_snapshot); if (fsck_err_on(from_deleted_inodes && ret, trans, deleted_inode_has_child_snapshots, "inode with child snapshots %llu:%u in deleted_inodes btree", pos.offset, pos.snapshot)) goto delete; if (ret) goto out; ret = bch2_inode_has_child_snapshots(trans, k.k->p); if (ret < 0) goto out; if (ret) { if (fsck_err(trans, inode_has_child_snapshots_wrong, "inode has_child_snapshots flag wrong (should be set)\n%s", (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &inode), buf.buf))) { inode.bi_flags |= BCH_INODE_has_child_snapshot; ret = __bch2_fsck_write_inode(trans, &inode); if (ret) goto out; } if (!from_deleted_inodes) { ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?: bch_err_throw(c, inode_has_child_snapshot); goto out; } goto delete; } if (from_deleted_inodes) { if (test_bit(BCH_FS_clean_recovery, &c->flags) && !fsck_err(trans, deleted_inode_but_clean, "filesystem marked as clean but have deleted inode %llu:%u", pos.offset, pos.snapshot)) { ret = 0; goto out; } ret = 1; } out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); printbuf_exit(&buf); return ret; delete: ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_deleted_inodes, pos, false); goto out; } static int may_delete_deleted_inum(struct btree_trans *trans, subvol_inum inum) { u32 snapshot; return bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot) ?: may_delete_deleted_inode(trans, SPOS(0, inum.inum, snapshot), false); } int bch2_delete_dead_inodes(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); int ret; /* * if we ran check_inodes() unlinked inodes will have already been * cleaned up but the write buffer will be out of sync; therefore we * alway need a write buffer flush */ ret = bch2_btree_write_buffer_flush_sync(trans); if (ret) goto err; /* * Weird transaction restart handling here because on successful delete, * bch2_inode_rm_snapshot() will return a nested transaction restart, * but we can't retry because the btree write buffer won't have been * flushed and we'd spin: */ ret = for_each_btree_key_commit(trans, iter, BTREE_ID_deleted_inodes, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ ret = may_delete_deleted_inode(trans, k.k->p, true); if (ret > 0) { bch_verbose_ratelimited(c, "deleting unlinked inode %llu:%u", k.k->p.offset, k.k->p.snapshot); ret = bch2_inode_rm_snapshot(trans, k.k->p.offset, k.k->p.snapshot); /* * We don't want to loop here: a transaction restart * error here means we handled a transaction restart and * we're actually done, but if we loop we'll retry the * same key because the write buffer hasn't been flushed * yet */ if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { ret = 0; continue; } } ret; })); err: bch2_trans_put(trans); bch_err_fn(c, ret); return ret; } |
| 60 76 36 17 23 23 60 48 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_FS_IO_PAGECACHE_H #define _BCACHEFS_FS_IO_PAGECACHE_H #include <linux/pagemap.h> typedef DARRAY(struct folio *) folios; int bch2_filemap_get_contig_folios_d(struct address_space *, loff_t, u64, fgf_t, gfp_t, folios *); int bch2_write_invalidate_inode_pages_range(struct address_space *, loff_t, loff_t); /* * Use u64 for the end pos and sector helpers because if the folio covers the * max supported range of the mapping, the start offset of the next folio * overflows loff_t. This breaks much of the range based processing in the * buffered write path. */ static inline u64 folio_end_pos(struct folio *folio) { return folio_pos(folio) + folio_size(folio); } static inline size_t folio_sectors(struct folio *folio) { return PAGE_SECTORS << folio_order(folio); } static inline loff_t folio_sector(struct folio *folio) { return folio_pos(folio) >> 9; } static inline u64 folio_end_sector(struct folio *folio) { return folio_end_pos(folio) >> 9; } #define BCH_FOLIO_SECTOR_STATE() \ x(unallocated) \ x(reserved) \ x(dirty) \ x(dirty_reserved) \ x(allocated) enum bch_folio_sector_state { #define x(n) SECTOR_##n, BCH_FOLIO_SECTOR_STATE() #undef x }; struct bch_folio_sector { /* Uncompressed, fully allocated replicas (or on disk reservation): */ u8 nr_replicas:4, /* Owns PAGE_SECTORS * replicas_reserved sized in memory reservation: */ replicas_reserved:4; u8 state; }; struct bch_folio { spinlock_t lock; atomic_t write_count; /* * Is the sector state up to date with the btree? * (Not the data itself) */ bool uptodate; struct bch_folio_sector s[]; }; /* Helper for when we need to add debug instrumentation: */ static inline void bch2_folio_sector_set(struct folio *folio, struct bch_folio *s, unsigned i, unsigned n) { s->s[i].state = n; } /* file offset (to folio offset) to bch_folio_sector index */ static inline int folio_pos_to_s(struct folio *folio, loff_t pos) { u64 f_offset = pos - folio_pos(folio); BUG_ON(pos < folio_pos(folio) || pos >= folio_end_pos(folio)); return f_offset >> SECTOR_SHIFT; } /* for newly allocated folios: */ static inline void __bch2_folio_release(struct folio *folio) { kfree(folio_detach_private(folio)); } static inline void bch2_folio_release(struct folio *folio) { EBUG_ON(!folio_test_locked(folio)); __bch2_folio_release(folio); } static inline struct bch_folio *__bch2_folio(struct folio *folio) { return folio_get_private(folio); } static inline struct bch_folio *bch2_folio(struct folio *folio) { EBUG_ON(!folio_test_locked(folio)); return __bch2_folio(folio); } struct bch_folio *__bch2_folio_create(struct folio *, gfp_t); struct bch_folio *bch2_folio_create(struct folio *, gfp_t); struct bch2_folio_reservation { struct disk_reservation disk; struct quota_res quota; }; static inline unsigned inode_nr_replicas(struct bch_fs *c, struct bch_inode_info *inode) { /* XXX: this should not be open coded */ return inode->ei_inode.bi_data_replicas ? inode->ei_inode.bi_data_replicas - 1 : c->opts.data_replicas; } static inline void bch2_folio_reservation_init(struct bch_fs *c, struct bch_inode_info *inode, struct bch2_folio_reservation *res) { memset(res, 0, sizeof(*res)); res->disk.nr_replicas = inode_nr_replicas(c, inode); } int bch2_folio_set(struct bch_fs *, subvol_inum, struct folio **, unsigned); void bch2_bio_page_state_set(struct bio *, struct bkey_s_c); void bch2_mark_pagecache_unallocated(struct bch_inode_info *, u64, u64); int bch2_mark_pagecache_reserved(struct bch_inode_info *, u64 *, u64, bool); int bch2_get_folio_disk_reservation(struct bch_fs *, struct bch_inode_info *, struct folio *, bool); void bch2_folio_reservation_put(struct bch_fs *, struct bch_inode_info *, struct bch2_folio_reservation *); int bch2_folio_reservation_get(struct bch_fs *, struct bch_inode_info *, struct folio *, struct bch2_folio_reservation *, size_t, size_t); ssize_t bch2_folio_reservation_get_partial(struct bch_fs *, struct bch_inode_info *, struct folio *, struct bch2_folio_reservation *, size_t, size_t); void bch2_set_folio_dirty(struct bch_fs *, struct bch_inode_info *, struct folio *, struct bch2_folio_reservation *, unsigned, unsigned); vm_fault_t bch2_page_fault(struct vm_fault *); vm_fault_t bch2_page_mkwrite(struct vm_fault *); void bch2_invalidate_folio(struct folio *, size_t, size_t); bool bch2_release_folio(struct folio *, gfp_t); loff_t bch2_seek_pagecache_data(struct inode *, loff_t, loff_t, unsigned, bool); loff_t bch2_seek_pagecache_hole(struct inode *, loff_t, loff_t, unsigned, bool); int bch2_clamp_data_hole(struct inode *, u64 *, u64 *, unsigned, bool); #endif /* _BCACHEFS_FS_IO_PAGECACHE_H */ |
| 3 3 71 67 3 74 214 74 74 74 70 70 70 214 2 70 70 2 73 74 74 74 74 73 73 74 74 74 74 73 72 72 73 73 3 72 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_shared.h" #include "xfs_mount.h" #include "xfs_ag.h" #include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_extfree_item.h" #include "xfs_log.h" #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_log_priv.h" #include "xfs_log_recover.h" #include "xfs_rtalloc.h" #include "xfs_inode.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" #include "xfs_zone_alloc.h" struct kmem_cache *xfs_efi_cache; struct kmem_cache *xfs_efd_cache; static const struct xfs_item_ops xfs_efi_item_ops; static inline struct xfs_efi_log_item *EFI_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_efi_log_item, efi_item); } STATIC void xfs_efi_item_free( struct xfs_efi_log_item *efip) { kvfree(efip->efi_item.li_lv_shadow); if (efip->efi_format.efi_nextents > XFS_EFI_MAX_FAST_EXTENTS) kfree(efip); else kmem_cache_free(xfs_efi_cache, efip); } /* * Freeing the efi requires that we remove it from the AIL if it has already * been placed there. However, the EFI may not yet have been placed in the AIL * when called by xfs_efi_release() from EFD processing due to the ordering of * committed vs unpin operations in bulk insert operations. Hence the reference * count to ensure only the last caller frees the EFI. */ STATIC void xfs_efi_release( struct xfs_efi_log_item *efip) { ASSERT(atomic_read(&efip->efi_refcount) > 0); if (!atomic_dec_and_test(&efip->efi_refcount)) return; xfs_trans_ail_delete(&efip->efi_item, 0); xfs_efi_item_free(efip); } STATIC void xfs_efi_item_size( struct xfs_log_item *lip, int *nvecs, int *nbytes) { struct xfs_efi_log_item *efip = EFI_ITEM(lip); *nvecs += 1; *nbytes += xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents); } unsigned int xfs_efi_log_space(unsigned int nr) { return xlog_item_space(1, xfs_efi_log_format_sizeof(nr)); } /* * This is called to fill in the vector of log iovecs for the * given efi log item. We use only 1 iovec, and we point that * at the efi_log_format structure embedded in the efi item. * It is at this point that we assert that all of the extent * slots in the efi item have been filled. */ STATIC void xfs_efi_item_format( struct xfs_log_item *lip, struct xfs_log_vec *lv) { struct xfs_efi_log_item *efip = EFI_ITEM(lip); struct xfs_log_iovec *vecp = NULL; ASSERT(atomic_read(&efip->efi_next_extent) == efip->efi_format.efi_nextents); ASSERT(lip->li_type == XFS_LI_EFI || lip->li_type == XFS_LI_EFI_RT); efip->efi_format.efi_type = lip->li_type; efip->efi_format.efi_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT, &efip->efi_format, xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents)); } /* * The unpin operation is the last place an EFI is manipulated in the log. It is * either inserted in the AIL or aborted in the event of a log I/O error. In * either case, the EFI transaction has been successfully committed to make it * this far. Therefore, we expect whoever committed the EFI to either construct * and commit the EFD or drop the EFD's reference in the event of error. Simply * drop the log's EFI reference now that the log is done with it. */ STATIC void xfs_efi_item_unpin( struct xfs_log_item *lip, int remove) { struct xfs_efi_log_item *efip = EFI_ITEM(lip); xfs_efi_release(efip); } /* * The EFI has been either committed or aborted if the transaction has been * cancelled. If the transaction was cancelled, an EFD isn't going to be * constructed and thus we free the EFI here directly. */ STATIC void xfs_efi_item_release( struct xfs_log_item *lip) { xfs_efi_release(EFI_ITEM(lip)); } /* * Allocate and initialize an efi item with the given number of extents. */ STATIC struct xfs_efi_log_item * xfs_efi_init( struct xfs_mount *mp, unsigned short item_type, uint nextents) { struct xfs_efi_log_item *efip; ASSERT(item_type == XFS_LI_EFI || item_type == XFS_LI_EFI_RT); ASSERT(nextents > 0); if (nextents > XFS_EFI_MAX_FAST_EXTENTS) { efip = kzalloc(xfs_efi_log_item_sizeof(nextents), GFP_KERNEL | __GFP_NOFAIL); } else { efip = kmem_cache_zalloc(xfs_efi_cache, GFP_KERNEL | __GFP_NOFAIL); } xfs_log_item_init(mp, &efip->efi_item, item_type, &xfs_efi_item_ops); efip->efi_format.efi_nextents = nextents; efip->efi_format.efi_id = (uintptr_t)(void *)efip; atomic_set(&efip->efi_next_extent, 0); atomic_set(&efip->efi_refcount, 2); return efip; } /* * Copy an EFI format buffer from the given buf, and into the destination * EFI format structure. * The given buffer can be in 32 bit or 64 bit form (which has different padding), * one of which will be the native format for this kernel. * It will handle the conversion of formats if necessary. */ STATIC int xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) { xfs_efi_log_format_t *src_efi_fmt = buf->i_addr; uint i; uint len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents); uint len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents); uint len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents); if (buf->i_len == len) { memcpy(dst_efi_fmt, src_efi_fmt, offsetof(struct xfs_efi_log_format, efi_extents)); for (i = 0; i < src_efi_fmt->efi_nextents; i++) memcpy(&dst_efi_fmt->efi_extents[i], &src_efi_fmt->efi_extents[i], sizeof(struct xfs_extent)); return 0; } else if (buf->i_len == len32) { xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr; dst_efi_fmt->efi_type = src_efi_fmt_32->efi_type; dst_efi_fmt->efi_size = src_efi_fmt_32->efi_size; dst_efi_fmt->efi_nextents = src_efi_fmt_32->efi_nextents; dst_efi_fmt->efi_id = src_efi_fmt_32->efi_id; for (i = 0; i < dst_efi_fmt->efi_nextents; i++) { dst_efi_fmt->efi_extents[i].ext_start = src_efi_fmt_32->efi_extents[i].ext_start; dst_efi_fmt->efi_extents[i].ext_len = src_efi_fmt_32->efi_extents[i].ext_len; } return 0; } else if (buf->i_len == len64) { xfs_efi_log_format_64_t *src_efi_fmt_64 = buf->i_addr; dst_efi_fmt->efi_type = src_efi_fmt_64->efi_type; dst_efi_fmt->efi_size = src_efi_fmt_64->efi_size; dst_efi_fmt->efi_nextents = src_efi_fmt_64->efi_nextents; dst_efi_fmt->efi_id = src_efi_fmt_64->efi_id; for (i = 0; i < dst_efi_fmt->efi_nextents; i++) { dst_efi_fmt->efi_extents[i].ext_start = src_efi_fmt_64->efi_extents[i].ext_start; dst_efi_fmt->efi_extents[i].ext_len = src_efi_fmt_64->efi_extents[i].ext_len; } return 0; } XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->i_addr, buf->i_len); return -EFSCORRUPTED; } static inline struct xfs_efd_log_item *EFD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_efd_log_item, efd_item); } STATIC void xfs_efd_item_free(struct xfs_efd_log_item *efdp) { kvfree(efdp->efd_item.li_lv_shadow); if (efdp->efd_format.efd_nextents > XFS_EFD_MAX_FAST_EXTENTS) kfree(efdp); else kmem_cache_free(xfs_efd_cache, efdp); } STATIC void xfs_efd_item_size( struct xfs_log_item *lip, int *nvecs, int *nbytes) { struct xfs_efd_log_item *efdp = EFD_ITEM(lip); *nvecs += 1; *nbytes += xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents); } unsigned int xfs_efd_log_space(unsigned int nr) { return xlog_item_space(1, xfs_efd_log_format_sizeof(nr)); } /* * This is called to fill in the vector of log iovecs for the * given efd log item. We use only 1 iovec, and we point that * at the efd_log_format structure embedded in the efd item. * It is at this point that we assert that all of the extent * slots in the efd item have been filled. */ STATIC void xfs_efd_item_format( struct xfs_log_item *lip, struct xfs_log_vec *lv) { struct xfs_efd_log_item *efdp = EFD_ITEM(lip); struct xfs_log_iovec *vecp = NULL; ASSERT(efdp->efd_next_extent == efdp->efd_format.efd_nextents); ASSERT(lip->li_type == XFS_LI_EFD || lip->li_type == XFS_LI_EFD_RT); efdp->efd_format.efd_type = lip->li_type; efdp->efd_format.efd_size = 1; xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT, &efdp->efd_format, xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents)); } /* * The EFD is either committed or aborted if the transaction is cancelled. If * the transaction is cancelled, drop our reference to the EFI and free the EFD. */ STATIC void xfs_efd_item_release( struct xfs_log_item *lip) { struct xfs_efd_log_item *efdp = EFD_ITEM(lip); xfs_efi_release(efdp->efd_efip); xfs_efd_item_free(efdp); } static struct xfs_log_item * xfs_efd_item_intent( struct xfs_log_item *lip) { return &EFD_ITEM(lip)->efd_efip->efi_item; } static const struct xfs_item_ops xfs_efd_item_ops = { .flags = XFS_ITEM_RELEASE_WHEN_COMMITTED | XFS_ITEM_INTENT_DONE, .iop_size = xfs_efd_item_size, .iop_format = xfs_efd_item_format, .iop_release = xfs_efd_item_release, .iop_intent = xfs_efd_item_intent, }; static inline struct xfs_extent_free_item *xefi_entry(const struct list_head *e) { return list_entry(e, struct xfs_extent_free_item, xefi_list); } static inline bool xfs_efi_item_isrt(const struct xfs_log_item *lip) { ASSERT(lip->li_type == XFS_LI_EFI || lip->li_type == XFS_LI_EFI_RT); return lip->li_type == XFS_LI_EFI_RT; } /* * Fill the EFD with all extents from the EFI when we need to roll the * transaction and continue with a new EFI. * * This simply copies all the extents in the EFI to the EFD rather than make * assumptions about which extents in the EFI have already been processed. We * currently keep the xefi list in the same order as the EFI extent list, but * that may not always be the case. Copying everything avoids leaving a landmine * were we fail to cancel all the extents in an EFI if the xefi list is * processed in a different order to the extents in the EFI. */ static void xfs_efd_from_efi( struct xfs_efd_log_item *efdp) { struct xfs_efi_log_item *efip = efdp->efd_efip; uint i; ASSERT(efip->efi_format.efi_nextents > 0); ASSERT(efdp->efd_next_extent < efip->efi_format.efi_nextents); for (i = 0; i < efip->efi_format.efi_nextents; i++) { efdp->efd_format.efd_extents[i] = efip->efi_format.efi_extents[i]; } efdp->efd_next_extent = efip->efi_format.efi_nextents; } static void xfs_efd_add_extent( struct xfs_efd_log_item *efdp, struct xfs_extent_free_item *xefi) { struct xfs_extent *extp; ASSERT(efdp->efd_next_extent < efdp->efd_format.efd_nextents); extp = &efdp->efd_format.efd_extents[efdp->efd_next_extent]; extp->ext_start = xefi->xefi_startblock; extp->ext_len = xefi->xefi_blockcount; efdp->efd_next_extent++; } /* Sort bmap items by AG. */ static int xfs_extent_free_diff_items( void *priv, const struct list_head *a, const struct list_head *b) { struct xfs_extent_free_item *ra = xefi_entry(a); struct xfs_extent_free_item *rb = xefi_entry(b); return ra->xefi_group->xg_gno - rb->xefi_group->xg_gno; } /* Log a free extent to the intent item. */ STATIC void xfs_extent_free_log_item( struct xfs_trans *tp, struct xfs_efi_log_item *efip, struct xfs_extent_free_item *xefi) { uint next_extent; struct xfs_extent *extp; /* * atomic_inc_return gives us the value after the increment; * we want to use it as an array index so we need to subtract 1 from * it. */ next_extent = atomic_inc_return(&efip->efi_next_extent) - 1; ASSERT(next_extent < efip->efi_format.efi_nextents); extp = &efip->efi_format.efi_extents[next_extent]; extp->ext_start = xefi->xefi_startblock; extp->ext_len = xefi->xefi_blockcount; } static struct xfs_log_item * __xfs_extent_free_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, bool sort, unsigned short item_type) { struct xfs_mount *mp = tp->t_mountp; struct xfs_efi_log_item *efip; struct xfs_extent_free_item *xefi; ASSERT(count > 0); efip = xfs_efi_init(mp, item_type, count); if (sort) list_sort(mp, items, xfs_extent_free_diff_items); list_for_each_entry(xefi, items, xefi_list) xfs_extent_free_log_item(tp, efip, xefi); return &efip->efi_item; } static struct xfs_log_item * xfs_extent_free_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, bool sort) { return __xfs_extent_free_create_intent(tp, items, count, sort, XFS_LI_EFI); } static inline unsigned short xfs_efd_type_from_efi(const struct xfs_efi_log_item *efip) { return xfs_efi_item_isrt(&efip->efi_item) ? XFS_LI_EFD_RT : XFS_LI_EFD; } /* Get an EFD so we can process all the free extents. */ static struct xfs_log_item * xfs_extent_free_create_done( struct xfs_trans *tp, struct xfs_log_item *intent, unsigned int count) { struct xfs_efi_log_item *efip = EFI_ITEM(intent); struct xfs_efd_log_item *efdp; ASSERT(count > 0); if (count > XFS_EFD_MAX_FAST_EXTENTS) { efdp = kzalloc(xfs_efd_log_item_sizeof(count), GFP_KERNEL | __GFP_NOFAIL); } else { efdp = kmem_cache_zalloc(xfs_efd_cache, GFP_KERNEL | __GFP_NOFAIL); } xfs_log_item_init(tp->t_mountp, &efdp->efd_item, xfs_efd_type_from_efi(efip), &xfs_efd_item_ops); efdp->efd_efip = efip; efdp->efd_format.efd_nextents = count; efdp->efd_format.efd_efi_id = efip->efi_format.efi_id; return &efdp->efd_item; } static inline const struct xfs_defer_op_type * xefi_ops( struct xfs_extent_free_item *xefi) { if (xfs_efi_is_realtime(xefi)) return &xfs_rtextent_free_defer_type; if (xefi->xefi_agresv == XFS_AG_RESV_AGFL) return &xfs_agfl_free_defer_type; return &xfs_extent_free_defer_type; } /* Add this deferred EFI to the transaction. */ void xfs_extent_free_defer_add( struct xfs_trans *tp, struct xfs_extent_free_item *xefi, struct xfs_defer_pending **dfpp) { struct xfs_mount *mp = tp->t_mountp; xefi->xefi_group = xfs_group_intent_get(mp, xefi->xefi_startblock, xfs_efi_is_realtime(xefi) ? XG_TYPE_RTG : XG_TYPE_AG); trace_xfs_extent_free_defer(mp, xefi); *dfpp = xfs_defer_add(tp, &xefi->xefi_list, xefi_ops(xefi)); } /* Cancel a free extent. */ STATIC void xfs_extent_free_cancel_item( struct list_head *item) { struct xfs_extent_free_item *xefi = xefi_entry(item); xfs_group_intent_put(xefi->xefi_group); kmem_cache_free(xfs_extfree_item_cache, xefi); } /* Process a free extent. */ STATIC int xfs_extent_free_finish_item( struct xfs_trans *tp, struct xfs_log_item *done, struct list_head *item, struct xfs_btree_cur **state) { struct xfs_owner_info oinfo = { }; struct xfs_extent_free_item *xefi = xefi_entry(item); struct xfs_efd_log_item *efdp = EFD_ITEM(done); struct xfs_mount *mp = tp->t_mountp; xfs_agblock_t agbno; int error = 0; agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock); oinfo.oi_owner = xefi->xefi_owner; if (xefi->xefi_flags & XFS_EFI_ATTR_FORK) oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK) oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; trace_xfs_extent_free_deferred(mp, xefi); /* * If we need a new transaction to make progress, the caller will log a * new EFI with the current contents. It will also log an EFD to cancel * the existing EFI, and so we need to copy all the unprocessed extents * in this EFI to the EFD so this works correctly. */ if (!(xefi->xefi_flags & XFS_EFI_CANCELLED)) error = __xfs_free_extent(tp, to_perag(xefi->xefi_group), agbno, xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv, xefi->xefi_flags & XFS_EFI_SKIP_DISCARD); if (error == -EAGAIN) { xfs_efd_from_efi(efdp); return error; } xfs_efd_add_extent(efdp, xefi); xfs_extent_free_cancel_item(item); return error; } /* Abort all pending EFIs. */ STATIC void xfs_extent_free_abort_intent( struct xfs_log_item *intent) { xfs_efi_release(EFI_ITEM(intent)); } /* * AGFL blocks are accounted differently in the reserve pools and are not * inserted into the busy extent list. */ STATIC int xfs_agfl_free_finish_item( struct xfs_trans *tp, struct xfs_log_item *done, struct list_head *item, struct xfs_btree_cur **state) { struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_efd_log_item *efdp = EFD_ITEM(done); struct xfs_extent_free_item *xefi = xefi_entry(item); struct xfs_buf *agbp; int error; xfs_agblock_t agbno; ASSERT(xefi->xefi_blockcount == 1); agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock); oinfo.oi_owner = xefi->xefi_owner; trace_xfs_agfl_free_deferred(mp, xefi); error = xfs_alloc_read_agf(to_perag(xefi->xefi_group), tp, 0, &agbp); if (!error) error = xfs_free_ag_extent(tp, agbp, agbno, 1, &oinfo, XFS_AG_RESV_AGFL); xfs_efd_add_extent(efdp, xefi); xfs_extent_free_cancel_item(&xefi->xefi_list); return error; } /* Is this recovered EFI ok? */ static inline bool xfs_efi_validate_ext( struct xfs_mount *mp, bool isrt, struct xfs_extent *extp) { if (isrt) return xfs_verify_rtbext(mp, extp->ext_start, extp->ext_len); return xfs_verify_fsbext(mp, extp->ext_start, extp->ext_len); } static inline void xfs_efi_recover_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp, bool isrt, struct xfs_extent *extp) { struct xfs_extent_free_item *xefi; xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); xefi->xefi_startblock = extp->ext_start; xefi->xefi_blockcount = extp->ext_len; xefi->xefi_agresv = XFS_AG_RESV_NONE; xefi->xefi_owner = XFS_RMAP_OWN_UNKNOWN; xefi->xefi_group = xfs_group_intent_get(mp, extp->ext_start, isrt ? XG_TYPE_RTG : XG_TYPE_AG); if (isrt) xefi->xefi_flags |= XFS_EFI_REALTIME; xfs_defer_add_item(dfp, &xefi->xefi_list); } /* * Process an extent free intent item that was recovered from * the log. We need to free the extents that it describes. */ STATIC int xfs_extent_free_recover_work( struct xfs_defer_pending *dfp, struct list_head *capture_list) { struct xfs_trans_res resv; struct xfs_log_item *lip = dfp->dfp_intent; struct xfs_efi_log_item *efip = EFI_ITEM(lip); struct xfs_mount *mp = lip->li_log->l_mp; struct xfs_trans *tp; int i; int error = 0; bool isrt = xfs_efi_item_isrt(lip); /* * First check the validity of the extents described by the EFI. If * any are bad, then assume that all are bad and just toss the EFI. * Mixing RT and non-RT extents in the same EFI item is not allowed. */ for (i = 0; i < efip->efi_format.efi_nextents; i++) { if (!xfs_efi_validate_ext(mp, isrt, &efip->efi_format.efi_extents[i])) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &efip->efi_format, sizeof(efip->efi_format)); return -EFSCORRUPTED; } xfs_efi_recover_work(mp, dfp, isrt, &efip->efi_format.efi_extents[i]); } resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp); if (error) return error; error = xlog_recover_finish_intent(tp, dfp); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &efip->efi_format, sizeof(efip->efi_format)); if (error) goto abort_error; return xfs_defer_ops_capture_and_commit(tp, capture_list); abort_error: xfs_trans_cancel(tp); return error; } /* Relog an intent item to push the log tail forward. */ static struct xfs_log_item * xfs_extent_free_relog_intent( struct xfs_trans *tp, struct xfs_log_item *intent, struct xfs_log_item *done_item) { struct xfs_efd_log_item *efdp = EFD_ITEM(done_item); struct xfs_efi_log_item *efip; struct xfs_extent *extp; unsigned int count; count = EFI_ITEM(intent)->efi_format.efi_nextents; extp = EFI_ITEM(intent)->efi_format.efi_extents; ASSERT(intent->li_type == XFS_LI_EFI || intent->li_type == XFS_LI_EFI_RT); efdp->efd_next_extent = count; memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp)); efip = xfs_efi_init(tp->t_mountp, intent->li_type, count); memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp)); atomic_set(&efip->efi_next_extent, count); return &efip->efi_item; } const struct xfs_defer_op_type xfs_extent_free_defer_type = { .name = "extent_free", .max_items = XFS_EFI_MAX_FAST_EXTENTS, .create_intent = xfs_extent_free_create_intent, .abort_intent = xfs_extent_free_abort_intent, .create_done = xfs_extent_free_create_done, .finish_item = xfs_extent_free_finish_item, .cancel_item = xfs_extent_free_cancel_item, .recover_work = xfs_extent_free_recover_work, .relog_intent = xfs_extent_free_relog_intent, }; /* sub-type with special handling for AGFL deferred frees */ const struct xfs_defer_op_type xfs_agfl_free_defer_type = { .name = "agfl_free", .max_items = XFS_EFI_MAX_FAST_EXTENTS, .create_intent = xfs_extent_free_create_intent, .abort_intent = xfs_extent_free_abort_intent, .create_done = xfs_extent_free_create_done, .finish_item = xfs_agfl_free_finish_item, .cancel_item = xfs_extent_free_cancel_item, .recover_work = xfs_extent_free_recover_work, .relog_intent = xfs_extent_free_relog_intent, }; #ifdef CONFIG_XFS_RT /* Create a realtime extent freeing */ static struct xfs_log_item * xfs_rtextent_free_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, bool sort) { return __xfs_extent_free_create_intent(tp, items, count, sort, XFS_LI_EFI_RT); } /* Process a free realtime extent. */ STATIC int xfs_rtextent_free_finish_item( struct xfs_trans *tp, struct xfs_log_item *done, struct list_head *item, struct xfs_btree_cur **state) { struct xfs_mount *mp = tp->t_mountp; struct xfs_extent_free_item *xefi = xefi_entry(item); struct xfs_efd_log_item *efdp = EFD_ITEM(done); struct xfs_rtgroup **rtgp = (struct xfs_rtgroup **)state; int error = 0; trace_xfs_extent_free_deferred(mp, xefi); if (xefi->xefi_flags & XFS_EFI_CANCELLED) goto done; if (*rtgp != to_rtg(xefi->xefi_group)) { unsigned int lock_flags; if (xfs_has_zoned(mp)) lock_flags = XFS_RTGLOCK_RMAP; else lock_flags = XFS_RTGLOCK_BITMAP; *rtgp = to_rtg(xefi->xefi_group); xfs_rtgroup_lock(*rtgp, lock_flags); xfs_rtgroup_trans_join(tp, *rtgp, lock_flags); } if (xfs_has_zoned(mp)) { error = xfs_zone_free_blocks(tp, *rtgp, xefi->xefi_startblock, xefi->xefi_blockcount); } else { error = xfs_rtfree_blocks(tp, *rtgp, xefi->xefi_startblock, xefi->xefi_blockcount); } if (error == -EAGAIN) { xfs_efd_from_efi(efdp); return error; } done: xfs_efd_add_extent(efdp, xefi); xfs_extent_free_cancel_item(item); return error; } const struct xfs_defer_op_type xfs_rtextent_free_defer_type = { .name = "rtextent_free", .max_items = XFS_EFI_MAX_FAST_EXTENTS, .create_intent = xfs_rtextent_free_create_intent, .abort_intent = xfs_extent_free_abort_intent, .create_done = xfs_extent_free_create_done, .finish_item = xfs_rtextent_free_finish_item, .cancel_item = xfs_extent_free_cancel_item, .recover_work = xfs_extent_free_recover_work, .relog_intent = xfs_extent_free_relog_intent, }; #else const struct xfs_defer_op_type xfs_rtextent_free_defer_type = { .name = "rtextent_free", }; #endif /* CONFIG_XFS_RT */ STATIC bool xfs_efi_item_match( struct xfs_log_item *lip, uint64_t intent_id) { return EFI_ITEM(lip)->efi_format.efi_id == intent_id; } static const struct xfs_item_ops xfs_efi_item_ops = { .flags = XFS_ITEM_INTENT, .iop_size = xfs_efi_item_size, .iop_format = xfs_efi_item_format, .iop_unpin = xfs_efi_item_unpin, .iop_release = xfs_efi_item_release, .iop_match = xfs_efi_item_match, }; /* * This routine is called to create an in-core extent free intent * item from the efi format structure which was logged on disk. * It allocates an in-core efi, copies the extents from the format * structure into it, and adds the efi to the AIL with the given * LSN. */ STATIC int xlog_recover_efi_commit_pass2( struct xlog *log, struct list_head *buffer_list, struct xlog_recover_item *item, xfs_lsn_t lsn) { struct xfs_mount *mp = log->l_mp; struct xfs_efi_log_item *efip; struct xfs_efi_log_format *efi_formatp; int error; efi_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } efip = xfs_efi_init(mp, ITEM_TYPE(item), efi_formatp->efi_nextents); error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format); if (error) { xfs_efi_item_free(efip); return error; } atomic_set(&efip->efi_next_extent, efi_formatp->efi_nextents); xlog_recover_intent_item(log, &efip->efi_item, lsn, &xfs_extent_free_defer_type); return 0; } const struct xlog_recover_item_ops xlog_efi_item_ops = { .item_type = XFS_LI_EFI, .commit_pass2 = xlog_recover_efi_commit_pass2, }; #ifdef CONFIG_XFS_RT STATIC int xlog_recover_rtefi_commit_pass2( struct xlog *log, struct list_head *buffer_list, struct xlog_recover_item *item, xfs_lsn_t lsn) { struct xfs_mount *mp = log->l_mp; struct xfs_efi_log_item *efip; struct xfs_efi_log_format *efi_formatp; int error; efi_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } efip = xfs_efi_init(mp, ITEM_TYPE(item), efi_formatp->efi_nextents); error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format); if (error) { xfs_efi_item_free(efip); return error; } atomic_set(&efip->efi_next_extent, efi_formatp->efi_nextents); xlog_recover_intent_item(log, &efip->efi_item, lsn, &xfs_rtextent_free_defer_type); return 0; } #else STATIC int xlog_recover_rtefi_commit_pass2( struct xlog *log, struct list_head *buffer_list, struct xlog_recover_item *item, xfs_lsn_t lsn) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } #endif const struct xlog_recover_item_ops xlog_rtefi_item_ops = { .item_type = XFS_LI_EFI_RT, .commit_pass2 = xlog_recover_rtefi_commit_pass2, }; /* * This routine is called when an EFD format structure is found in a committed * transaction in the log. Its purpose is to cancel the corresponding EFI if it * was still in the log. To do this it searches the AIL for the EFI with an id * equal to that in the EFD format structure. If we find it we drop the EFD * reference, which removes the EFI from the AIL and frees it. */ STATIC int xlog_recover_efd_commit_pass2( struct xlog *log, struct list_head *buffer_list, struct xlog_recover_item *item, xfs_lsn_t lsn) { struct xfs_efd_log_format *efd_formatp; int buflen = item->ri_buf[0].i_len; efd_formatp = item->ri_buf[0].i_addr; if (buflen < sizeof(struct xfs_efd_log_format)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, efd_formatp, buflen); return -EFSCORRUPTED; } if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof( efd_formatp->efd_nextents) && item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof( efd_formatp->efd_nextents)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, efd_formatp, buflen); return -EFSCORRUPTED; } xlog_recover_release_intent(log, XFS_LI_EFI, efd_formatp->efd_efi_id); return 0; } const struct xlog_recover_item_ops xlog_efd_item_ops = { .item_type = XFS_LI_EFD, .commit_pass2 = xlog_recover_efd_commit_pass2, }; #ifdef CONFIG_XFS_RT STATIC int xlog_recover_rtefd_commit_pass2( struct xlog *log, struct list_head *buffer_list, struct xlog_recover_item *item, xfs_lsn_t lsn) { struct xfs_efd_log_format *efd_formatp; int buflen = item->ri_buf[0].i_len; efd_formatp = item->ri_buf[0].i_addr; if (buflen < sizeof(struct xfs_efd_log_format)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, efd_formatp, buflen); return -EFSCORRUPTED; } if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof( efd_formatp->efd_nextents) && item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof( efd_formatp->efd_nextents)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, efd_formatp, buflen); return -EFSCORRUPTED; } xlog_recover_release_intent(log, XFS_LI_EFI_RT, efd_formatp->efd_efi_id); return 0; } #else # define xlog_recover_rtefd_commit_pass2 xlog_recover_rtefi_commit_pass2 #endif const struct xlog_recover_item_ops xlog_rtefd_item_ops = { .item_type = XFS_LI_EFD_RT, .commit_pass2 = xlog_recover_rtefd_commit_pass2, }; |
| 259 44 5646 5646 19 4655 142 4670 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { refcount_t usage; int ngroups; kgid_t gid[]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { refcount_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (refcount_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } static inline const struct cred *override_creds(const struct cred *override_cred) { return rcu_replace_pointer(current->cred, override_cred, 1); } static inline const struct cred *revert_creds(const struct cred *revert_cred) { return rcu_replace_pointer(current->cred, revert_cred, 1); } /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of credentials. The caller must release * all acquired reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; nonconst_cred->non_rcu = 0; atomic_long_add(nr, &nonconst_cred->usage); return cred; } /* * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. */ static inline const struct cred *get_cred(const struct cred *cred) { return get_cred_many(cred, 1); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * @nr: Number of references to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred_many(const struct cred *_cred, int nr) { struct cred *cred = (struct cred *) _cred; if (cred) { if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } /* * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. */ static inline void put_cred(const struct cred *cred) { put_cred_many(cred, 1); } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) #define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 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 | /* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ /* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 * as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: * Copyright (c) 2008, Swedish Institute of Computer Science. * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. 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. * 3. Neither the name of the Institute nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> #include <linux/if_arp.h> #include <net/ipv6.h> #include <net/netdev_lock.h> #include "6lowpan_i.h" static int open_count; static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; static int lowpan_dev_init(struct net_device *ldev) { netdev_lockdep_set_classes(ldev); return 0; } static int lowpan_open(struct net_device *dev) { if (!open_count) lowpan_rx_init(); open_count++; return 0; } static int lowpan_stop(struct net_device *dev) { open_count--; if (!open_count) lowpan_rx_exit(); return 0; } static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) { struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n)); /* default no short_addr is available for a neighbour */ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); return 0; } static int lowpan_get_iflink(const struct net_device *dev) { return READ_ONCE(lowpan_802154_dev(dev)->wdev->ifindex); } static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) { memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; ldev->netns_immutable = true; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) return -EINVAL; } return 0; } static int lowpan_newlink(struct net_device *ldev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **tb = params->tb; struct net_device *wdev; int ret; ASSERT_RTNL(); pr_debug("adding new link\n"); if (!tb[IFLA_LINK]) return -EINVAL; if (params->link_net && !net_eq(params->link_net, dev_net(ldev))) return -EINVAL; /* find and hold wpan device */ wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; if (wdev->type != ARPHRD_IEEE802154) { dev_put(wdev); return -EINVAL; } if (wdev->ieee802154_ptr->lowpan_dev) { dev_put(wdev); return -EBUSY; } lowpan_802154_dev(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ __dev_addr_set(ldev, wdev->dev_addr, IEEE802154_ADDR_LEN); /* We need headroom for possible wpan_dev_hard_header call and tailroom * for encryption/fcs handling. The lowpan interface will replace * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6 * header. */ ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN + wdev->needed_headroom; ldev->needed_tailroom = wdev->needed_tailroom; ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh); ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154); if (ret < 0) { dev_put(wdev); return ret; } wdev->ieee802154_ptr->lowpan_dev = ldev; return 0; } static void lowpan_dellink(struct net_device *ldev, struct list_head *head) { struct net_device *wdev = lowpan_802154_dev(ldev)->wdev; ASSERT_RTNL(); wdev->ieee802154_ptr->lowpan_dev = NULL; lowpan_unregister_netdevice(ldev); dev_put(wdev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { .kind = "lowpan", .priv_size = LOWPAN_PRIV_SIZE(sizeof(struct lowpan_802154_dev)), .setup = lowpan_setup, .newlink = lowpan_newlink, .dellink = lowpan_dellink, .validate = lowpan_validate, }; static inline int __init lowpan_netlink_init(void) { return rtnl_link_register(&lowpan_link_ops); } static inline void lowpan_netlink_fini(void) { rtnl_link_unregister(&lowpan_link_ops); } static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev; if (ndev->type != ARPHRD_IEEE802154) return NOTIFY_DONE; wpan_dev = ndev->ieee802154_ptr; if (!wpan_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: /* Check if wpan interface is unregistered that we * also delete possible lowpan interfaces which belongs * to the wpan interface. */ if (wpan_dev->lowpan_dev) lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_dev_notifier = { .notifier_call = lowpan_device_event, }; static int __init lowpan_init_module(void) { int err = 0; err = lowpan_net_frag_init(); if (err < 0) goto out; err = lowpan_netlink_init(); if (err < 0) goto out_frag; err = register_netdevice_notifier(&lowpan_dev_notifier); if (err < 0) goto out_pack; return 0; out_pack: lowpan_netlink_fini(); out_frag: lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { lowpan_netlink_fini(); lowpan_net_frag_exit(); unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); module_exit(lowpan_cleanup_module); MODULE_DESCRIPTION("IPv6 over Low power Wireless Personal Area Network IEEE 802.15.4 core"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("lowpan"); |
| 139 138 139 | 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 | // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/string.h> #include <linux/zstd.h> #include "common/zstd_deps.h" #include "common/zstd_internal.h" #include "compress/zstd_compress_internal.h" #define ZSTD_FORWARD_IF_ERR(ret) \ do { \ size_t const __ret = (ret); \ if (ZSTD_isError(__ret)) \ return __ret; \ } while (0) static size_t zstd_cctx_init(zstd_cctx *cctx, const zstd_parameters *parameters, unsigned long long pledged_src_size) { ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_reset( cctx, ZSTD_reset_session_and_parameters)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setPledgedSrcSize( cctx, pledged_src_size)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_windowLog, parameters->cParams.windowLog)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_hashLog, parameters->cParams.hashLog)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_chainLog, parameters->cParams.chainLog)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_searchLog, parameters->cParams.searchLog)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_minMatch, parameters->cParams.minMatch)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_targetLength, parameters->cParams.targetLength)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_strategy, parameters->cParams.strategy)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_contentSizeFlag, parameters->fParams.contentSizeFlag)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_checksumFlag, parameters->fParams.checksumFlag)); ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( cctx, ZSTD_c_dictIDFlag, !parameters->fParams.noDictIDFlag)); return 0; } int zstd_min_clevel(void) { return ZSTD_minCLevel(); } EXPORT_SYMBOL(zstd_min_clevel); int zstd_max_clevel(void) { return ZSTD_maxCLevel(); } EXPORT_SYMBOL(zstd_max_clevel); int zstd_default_clevel(void) { return ZSTD_defaultCLevel(); } EXPORT_SYMBOL(zstd_default_clevel); size_t zstd_compress_bound(size_t src_size) { return ZSTD_compressBound(src_size); } EXPORT_SYMBOL(zstd_compress_bound); zstd_parameters zstd_get_params(int level, unsigned long long estimated_src_size) { return ZSTD_getParams(level, estimated_src_size, 0); } EXPORT_SYMBOL(zstd_get_params); zstd_compression_parameters zstd_get_cparams(int level, unsigned long long estimated_src_size, size_t dict_size) { return ZSTD_getCParams(level, estimated_src_size, dict_size); } EXPORT_SYMBOL(zstd_get_cparams); size_t zstd_cctx_set_param(zstd_cctx *cctx, ZSTD_cParameter param, int value) { return ZSTD_CCtx_setParameter(cctx, param, value); } EXPORT_SYMBOL(zstd_cctx_set_param); size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams) { return ZSTD_estimateCCtxSize_usingCParams(*cparams); } EXPORT_SYMBOL(zstd_cctx_workspace_bound); // Used by zstd_cctx_workspace_bound_with_ext_seq_prod() static size_t dummy_external_sequence_producer( void *sequenceProducerState, ZSTD_Sequence *outSeqs, size_t outSeqsCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize, int compressionLevel, size_t windowSize) { (void)sequenceProducerState; (void)outSeqs; (void)outSeqsCapacity; (void)src; (void)srcSize; (void)dict; (void)dictSize; (void)compressionLevel; (void)windowSize; return ZSTD_SEQUENCE_PRODUCER_ERROR; } static void init_cctx_params_from_compress_params( ZSTD_CCtx_params *cctx_params, const zstd_compression_parameters *compress_params) { ZSTD_parameters zstd_params; memset(&zstd_params, 0, sizeof(zstd_params)); zstd_params.cParams = *compress_params; ZSTD_CCtxParams_init_advanced(cctx_params, zstd_params); } size_t zstd_cctx_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *compress_params) { ZSTD_CCtx_params cctx_params; init_cctx_params_from_compress_params(&cctx_params, compress_params); ZSTD_CCtxParams_registerSequenceProducer(&cctx_params, NULL, dummy_external_sequence_producer); return ZSTD_estimateCCtxSize_usingCCtxParams(&cctx_params); } EXPORT_SYMBOL(zstd_cctx_workspace_bound_with_ext_seq_prod); size_t zstd_cstream_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *compress_params) { ZSTD_CCtx_params cctx_params; init_cctx_params_from_compress_params(&cctx_params, compress_params); ZSTD_CCtxParams_registerSequenceProducer(&cctx_params, NULL, dummy_external_sequence_producer); return ZSTD_estimateCStreamSize_usingCCtxParams(&cctx_params); } EXPORT_SYMBOL(zstd_cstream_workspace_bound_with_ext_seq_prod); zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size) { if (workspace == NULL) return NULL; return ZSTD_initStaticCCtx(workspace, workspace_size); } EXPORT_SYMBOL(zstd_init_cctx); zstd_cctx *zstd_create_cctx_advanced(zstd_custom_mem custom_mem) { return ZSTD_createCCtx_advanced(custom_mem); } EXPORT_SYMBOL(zstd_create_cctx_advanced); size_t zstd_free_cctx(zstd_cctx *cctx) { return ZSTD_freeCCtx(cctx); } EXPORT_SYMBOL(zstd_free_cctx); zstd_cdict *zstd_create_cdict_byreference(const void *dict, size_t dict_size, zstd_compression_parameters cparams, zstd_custom_mem custom_mem) { return ZSTD_createCDict_advanced(dict, dict_size, ZSTD_dlm_byRef, ZSTD_dct_auto, cparams, custom_mem); } EXPORT_SYMBOL(zstd_create_cdict_byreference); size_t zstd_free_cdict(zstd_cdict *cdict) { return ZSTD_freeCDict(cdict); } EXPORT_SYMBOL(zstd_free_cdict); size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, const void *src, size_t src_size, const zstd_parameters *parameters) { ZSTD_FORWARD_IF_ERR(zstd_cctx_init(cctx, parameters, src_size)); return ZSTD_compress2(cctx, dst, dst_capacity, src, src_size); } EXPORT_SYMBOL(zstd_compress_cctx); size_t zstd_compress_using_cdict(zstd_cctx *cctx, void *dst, size_t dst_capacity, const void *src, size_t src_size, const ZSTD_CDict *cdict) { return ZSTD_compress_usingCDict(cctx, dst, dst_capacity, src, src_size, cdict); } EXPORT_SYMBOL(zstd_compress_using_cdict); size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams) { return ZSTD_estimateCStreamSize_usingCParams(*cparams); } EXPORT_SYMBOL(zstd_cstream_workspace_bound); zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters, unsigned long long pledged_src_size, void *workspace, size_t workspace_size) { zstd_cstream *cstream; if (workspace == NULL) return NULL; cstream = ZSTD_initStaticCStream(workspace, workspace_size); if (cstream == NULL) return NULL; /* 0 means unknown in linux zstd API but means 0 in new zstd API */ if (pledged_src_size == 0) pledged_src_size = ZSTD_CONTENTSIZE_UNKNOWN; if (ZSTD_isError(zstd_cctx_init(cstream, parameters, pledged_src_size))) return NULL; return cstream; } EXPORT_SYMBOL(zstd_init_cstream); size_t zstd_reset_cstream(zstd_cstream *cstream, unsigned long long pledged_src_size) { if (pledged_src_size == 0) pledged_src_size = ZSTD_CONTENTSIZE_UNKNOWN; ZSTD_FORWARD_IF_ERR( ZSTD_CCtx_reset(cstream, ZSTD_reset_session_only) ); ZSTD_FORWARD_IF_ERR( ZSTD_CCtx_setPledgedSrcSize(cstream, pledged_src_size) ); return 0; } EXPORT_SYMBOL(zstd_reset_cstream); size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output, zstd_in_buffer *input) { return ZSTD_compressStream(cstream, output, input); } EXPORT_SYMBOL(zstd_compress_stream); size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output) { return ZSTD_flushStream(cstream, output); } EXPORT_SYMBOL(zstd_flush_stream); size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output) { return ZSTD_endStream(cstream, output); } EXPORT_SYMBOL(zstd_end_stream); void zstd_register_sequence_producer( zstd_cctx *cctx, void* sequence_producer_state, zstd_sequence_producer_f sequence_producer ) { ZSTD_registerSequenceProducer(cctx, sequence_producer_state, sequence_producer); } EXPORT_SYMBOL(zstd_register_sequence_producer); size_t zstd_compress_sequences_and_literals(zstd_cctx *cctx, void* dst, size_t dst_capacity, const zstd_sequence *in_seqs, size_t in_seqs_size, const void* literals, size_t lit_size, size_t lit_capacity, size_t decompressed_size) { return ZSTD_compressSequencesAndLiterals(cctx, dst, dst_capacity, in_seqs, in_seqs_size, literals, lit_size, lit_capacity, decompressed_size); } EXPORT_SYMBOL(zstd_compress_sequences_and_literals); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("Zstd Compressor"); |
| 85 85 67 80 80 10 4 135 134 86 85 81 1 3 1 135 2 1 127 25 138 1 3 135 135 21 114 127 17 135 135 124 25 133 4 44 103 63 85 135 135 134 1 88 89 1 3 14 76 12 1 12 12 12 3 10 1 1 156 156 1 151 5 8 8 152 26 26 1 1 1 23 23 25 2 2 13 1 12 1 1 1 9 9 10 27 1 1 1 3 22 7 1 6 12 1 12 1 1 3 8 26 2 9 23 9 12 10 12 19 1 14 14 14 10 1 31 31 10 22 21 1 24 6 1 1 23 4 6 2 3 5 5 17 6 21 5 16 9 21 4 18 7 15 6 4 25 1 1 7 6 1 6 3 1 3 1 3 2 2 4 3 4 3 4 3 5 2 4 3 5 2 3 4 7 39 39 39 8 31 39 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/namei.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/pagemap.h> #include <linux/sched.h> #include <linux/ctype.h> #include <linux/random.h> #include <linux/dcache.h> #include <linux/namei.h> #include <linux/quotaops.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" #include "acl.h" #include <trace/events/f2fs.h> static inline bool is_extension_exist(const unsigned char *s, const char *sub, bool tmp_ext, bool tmp_dot) { size_t slen = strlen(s); size_t sublen = strlen(sub); int i; if (sublen == 1 && *sub == '*') return true; /* * filename format of multimedia file should be defined as: * "filename + '.' + extension + (optional: '.' + temp extension)". */ if (slen < sublen + 2) return false; if (!tmp_ext) { /* file has no temp extension */ if (s[slen - sublen - 1] != '.') return false; return !strncasecmp(s + slen - sublen, sub, sublen); } for (i = 1; i < slen - sublen; i++) { if (s[i] != '.') continue; if (!strncasecmp(s + i + 1, sub, sublen)) { if (!tmp_dot) return true; if (i == slen - sublen - 1 || s[i + 1 + sublen] == '.') return true; } } return false; } static inline bool is_temperature_extension(const unsigned char *s, const char *sub) { return is_extension_exist(s, sub, true, false); } static inline bool is_compress_extension(const unsigned char *s, const char *sub) { return is_extension_exist(s, sub, true, true); } int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set) { __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; int cold_count = le32_to_cpu(sbi->raw_super->extension_count); int hot_count = sbi->raw_super->hot_ext_count; int total_count = cold_count + hot_count; int start, count; int i; if (set) { if (total_count == F2FS_MAX_EXTENSION) return -EINVAL; } else { if (!hot && !cold_count) return -EINVAL; if (hot && !hot_count) return -EINVAL; } if (hot) { start = cold_count; count = total_count; } else { start = 0; count = cold_count; } for (i = start; i < count; i++) { if (strcmp(name, extlist[i])) continue; if (set) return -EINVAL; memcpy(extlist[i], extlist[i + 1], F2FS_EXTENSION_LEN * (total_count - i - 1)); memset(extlist[total_count - 1], 0, F2FS_EXTENSION_LEN); if (hot) sbi->raw_super->hot_ext_count = hot_count - 1; else sbi->raw_super->extension_count = cpu_to_le32(cold_count - 1); return 0; } if (!set) return -EINVAL; if (hot) { memcpy(extlist[count], name, strlen(name)); sbi->raw_super->hot_ext_count = hot_count + 1; } else { char buf[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN]; memcpy(buf, &extlist[cold_count], F2FS_EXTENSION_LEN * hot_count); memset(extlist[cold_count], 0, F2FS_EXTENSION_LEN); memcpy(extlist[cold_count], name, strlen(name)); memcpy(&extlist[cold_count + 1], buf, F2FS_EXTENSION_LEN * hot_count); sbi->raw_super->extension_count = cpu_to_le32(cold_count + 1); } return 0; } static void set_compress_new_inode(struct f2fs_sb_info *sbi, struct inode *dir, struct inode *inode, const unsigned char *name) { __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; unsigned char (*noext)[F2FS_EXTENSION_LEN] = F2FS_OPTION(sbi).noextensions; unsigned char (*ext)[F2FS_EXTENSION_LEN] = F2FS_OPTION(sbi).extensions; unsigned char ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt; unsigned char noext_cnt = F2FS_OPTION(sbi).nocompress_ext_cnt; int i, cold_count, hot_count; if (!f2fs_sb_has_compression(sbi)) return; if (S_ISDIR(inode->i_mode)) goto inherit_comp; /* This name comes only from normal files. */ if (!name) return; /* Don't compress hot files. */ f2fs_down_read(&sbi->sb_lock); cold_count = le32_to_cpu(sbi->raw_super->extension_count); hot_count = sbi->raw_super->hot_ext_count; for (i = cold_count; i < cold_count + hot_count; i++) if (is_temperature_extension(name, extlist[i])) break; f2fs_up_read(&sbi->sb_lock); if (i < (cold_count + hot_count)) return; /* Don't compress unallowed extension. */ for (i = 0; i < noext_cnt; i++) if (is_compress_extension(name, noext[i])) return; /* Compress wanting extension. */ for (i = 0; i < ext_cnt; i++) { if (is_compress_extension(name, ext[i])) { set_compress_context(inode); return; } } inherit_comp: /* Inherit the {no-}compression flag in directory */ if (F2FS_I(dir)->i_flags & F2FS_NOCOMP_FL) { F2FS_I(inode)->i_flags |= F2FS_NOCOMP_FL; f2fs_mark_inode_dirty_sync(inode, true); } else if (F2FS_I(dir)->i_flags & F2FS_COMPR_FL) { set_compress_context(inode); } } /* * Set file's temperature for hot/cold data separation */ static void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode, const unsigned char *name) { __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; int i, cold_count, hot_count; f2fs_down_read(&sbi->sb_lock); cold_count = le32_to_cpu(sbi->raw_super->extension_count); hot_count = sbi->raw_super->hot_ext_count; for (i = 0; i < cold_count + hot_count; i++) if (is_temperature_extension(name, extlist[i])) break; f2fs_up_read(&sbi->sb_lock); if (i == cold_count + hot_count) return; if (i < cold_count) file_set_cold(inode); else file_set_hot(inode); } static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, struct inode *dir, umode_t mode, const char *name) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct f2fs_inode_info *fi; nid_t ino; struct inode *inode; bool nid_free = false; bool encrypt = false; int xattr_size = 0; int err; inode = new_inode(dir->i_sb); if (!inode) return ERR_PTR(-ENOMEM); if (!f2fs_alloc_nid(sbi, &ino)) { err = -ENOSPC; goto fail; } nid_free = true; inode_init_owner(idmap, inode, dir, mode); fi = F2FS_I(inode); inode->i_ino = ino; inode->i_blocks = 0; simple_inode_init_ts(inode); fi->i_crtime = inode_get_mtime(inode); inode->i_generation = get_random_u32(); if (S_ISDIR(inode->i_mode)) fi->i_current_depth = 1; err = insert_inode_locked(inode); if (err) { err = -EINVAL; goto fail; } if (f2fs_sb_has_project_quota(sbi) && (F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL)) fi->i_projid = F2FS_I(dir)->i_projid; else fi->i_projid = make_kprojid(&init_user_ns, F2FS_DEF_PROJID); err = fscrypt_prepare_new_inode(dir, inode, &encrypt); if (err) goto fail_drop; err = f2fs_dquot_initialize(inode); if (err) goto fail_drop; set_inode_flag(inode, FI_NEW_INODE); if (encrypt) f2fs_set_encrypted_inode(inode); if (f2fs_sb_has_extra_attr(sbi)) { set_inode_flag(inode, FI_EXTRA_ATTR); fi->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE; } if (test_opt(sbi, INLINE_XATTR)) set_inode_flag(inode, FI_INLINE_XATTR); if (f2fs_may_inline_dentry(inode)) set_inode_flag(inode, FI_INLINE_DENTRY); if (f2fs_sb_has_flexible_inline_xattr(sbi)) { f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode)); if (f2fs_has_inline_xattr(inode)) xattr_size = F2FS_OPTION(sbi).inline_xattr_size; /* Otherwise, will be 0 */ } else if (f2fs_has_inline_xattr(inode) || f2fs_has_inline_dentry(inode)) { xattr_size = DEFAULT_INLINE_XATTR_ADDRS; } fi->i_inline_xattr_size = xattr_size; fi->i_flags = f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED); if (S_ISDIR(inode->i_mode)) fi->i_flags |= F2FS_INDEX_FL; if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); /* Check compression first. */ set_compress_new_inode(sbi, dir, inode, name); /* Should enable inline_data after compression set */ if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode)) set_inode_flag(inode, FI_INLINE_DATA); if (name && !test_opt(sbi, DISABLE_EXT_IDENTIFY)) set_file_temperature(sbi, inode, name); stat_inc_inline_xattr(inode); stat_inc_inline_inode(inode); stat_inc_inline_dir(inode); f2fs_set_inode_flags(inode); f2fs_init_extent_tree(inode); trace_f2fs_new_inode(inode, 0); return inode; fail: trace_f2fs_new_inode(inode, err); make_bad_inode(inode); if (nid_free) set_inode_flag(inode, FI_FREE_NID); iput(inode); return ERR_PTR(err); fail_drop: trace_f2fs_new_inode(inode, err); dquot_drop(inode); inode->i_flags |= S_NOQUOTA; make_bad_inode(inode); if (nid_free) set_inode_flag(inode, FI_FREE_NID); clear_nlink(inode); unlock_new_inode(inode); iput(inode); return ERR_PTR(err); } static int f2fs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; nid_t ino = 0; int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; err = f2fs_dquot_initialize(dir); if (err) return err; inode = f2fs_new_inode(idmap, dir, mode, dentry->d_name.name); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &f2fs_file_inode_operations; inode->i_fop = &f2fs_file_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; ino = inode->i_ino; f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) goto out; f2fs_unlock_op(sbi); f2fs_alloc_nid_done(sbi, ino); d_instantiate_new(dentry, inode); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); f2fs_balance_fs(sbi, true); return 0; out: f2fs_handle_failed_inode(inode); return err; } static int f2fs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); struct f2fs_sb_info *sbi = F2FS_I_SB(dir); int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; err = fscrypt_prepare_link(old_dentry, dir, dentry); if (err) return err; if (is_inode_flag_set(dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(dir)->i_projid, F2FS_I(inode)->i_projid))) return -EXDEV; err = f2fs_dquot_initialize(dir); if (err) return err; f2fs_balance_fs(sbi, true); inode_set_ctime_current(inode); ihold(inode); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) goto out; f2fs_unlock_op(sbi); d_instantiate(dentry, inode); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); return 0; out: clear_inode_flag(inode, FI_INC_LINK); iput(inode); f2fs_unlock_op(sbi); return err; } struct dentry *f2fs_get_parent(struct dentry *child) { struct folio *folio; unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot_name, &folio); if (!ino) { if (IS_ERR(folio)) return ERR_CAST(folio); return ERR_PTR(-ENOENT); } return d_obtain_alias(f2fs_iget(child->d_sb, ino)); } static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct f2fs_dir_entry *de; struct folio *folio; struct dentry *new; nid_t ino = -1; int err = 0; struct f2fs_filename fname; trace_f2fs_lookup_start(dir, dentry, flags); if (dentry->d_name.len > F2FS_NAME_LEN) { err = -ENAMETOOLONG; goto out; } err = f2fs_prepare_lookup(dir, dentry, &fname); if (err == -ENOENT) goto out_splice; if (err) goto out; de = __f2fs_find_entry(dir, &fname, &folio); f2fs_free_filename(&fname); if (!de) { if (IS_ERR(folio)) { err = PTR_ERR(folio); goto out; } err = -ENOENT; goto out_splice; } ino = le32_to_cpu(de->ino); f2fs_folio_put(folio, false); inode = f2fs_iget(dir->i_sb, ino); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out; } if (inode->i_nlink == 0) { f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink", __func__, inode->i_ino); err = -EFSCORRUPTED; set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); goto out_iput; } if (IS_ENCRYPTED(dir) && (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && !fscrypt_has_permitted_context(dir, inode)) { f2fs_warn(F2FS_I_SB(inode), "Inconsistent encryption contexts: %lu/%lu", dir->i_ino, inode->i_ino); err = -EPERM; goto out_iput; } out_splice: if (IS_ENABLED(CONFIG_UNICODE) && !inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as * well. For now, prevent the negative dentry * from being cached. */ trace_f2fs_lookup_end(dir, dentry, ino, err); return NULL; } new = d_splice_alias(inode, dentry); trace_f2fs_lookup_end(dir, !IS_ERR_OR_NULL(new) ? new : dentry, ino, IS_ERR(new) ? PTR_ERR(new) : err); return new; out_iput: iput(inode); out: trace_f2fs_lookup_end(dir, dentry, ino, err); return ERR_PTR(err); } static int f2fs_unlink(struct inode *dir, struct dentry *dentry) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode = d_inode(dentry); struct f2fs_dir_entry *de; struct folio *folio; int err; trace_f2fs_unlink_enter(dir, dentry); if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; goto fail; } err = f2fs_dquot_initialize(dir); if (err) goto fail; err = f2fs_dquot_initialize(inode); if (err) goto fail; de = f2fs_find_entry(dir, &dentry->d_name, &folio); if (!de) { if (IS_ERR(folio)) err = PTR_ERR(folio); goto fail; } if (unlikely(inode->i_nlink == 0)) { f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink", __func__, inode->i_ino); err = -EFSCORRUPTED; set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); f2fs_folio_put(folio, false); goto fail; } f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); err = f2fs_acquire_orphan_inode(sbi); if (err) { f2fs_unlock_op(sbi); f2fs_folio_put(folio, false); goto fail; } f2fs_delete_entry(de, folio, dir, inode); f2fs_unlock_op(sbi); /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the * negative dentries at f2fs_lookup(), when it is better * supported by the VFS for the CI case. */ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) d_invalidate(dentry); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); fail: trace_f2fs_unlink_exit(inode, err); return err; } static const char *f2fs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { const char *link = page_get_link(dentry, inode, done); if (!IS_ERR(link) && !*link) { /* this is broken symlink case */ do_delayed_call(done); clear_delayed_call(done); link = ERR_PTR(-ENOENT); } return link; } static int f2fs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; size_t len = strlen(symname); struct fscrypt_str disk_link; int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, &disk_link); if (err) return err; err = f2fs_dquot_initialize(dir); if (err) return err; inode = f2fs_new_inode(idmap, dir, S_IFLNK | S_IRWXUGO, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); if (IS_ENCRYPTED(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) goto out_f2fs_handle_failed_inode; f2fs_unlock_op(sbi); f2fs_alloc_nid_done(sbi, inode->i_ino); err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link); if (err) goto err_out; err = page_symlink(inode, disk_link.name, disk_link.len); err_out: d_instantiate_new(dentry, inode); /* * Let's flush symlink data in order to avoid broken symlink as much as * possible. Nevertheless, fsyncing is the best way, but there is no * way to get a file descriptor in order to flush that. * * Note that, it needs to do dir->fsync to make this recoverable. * If the symlink path is stored into inline_data, there is no * performance regression. */ if (!err) { filemap_write_and_wait_range(inode->i_mapping, 0, disk_link.len - 1); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); } else { f2fs_unlink(dir, dentry); } f2fs_balance_fs(sbi, true); goto out_free_encrypted_link; out_f2fs_handle_failed_inode: f2fs_handle_failed_inode(inode); out_free_encrypted_link: if (disk_link.name != (unsigned char *)symname) kfree(disk_link.name); return err; } static struct dentry *f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; int err; if (unlikely(f2fs_cp_error(sbi))) return ERR_PTR(-EIO); err = f2fs_dquot_initialize(dir); if (err) return ERR_PTR(err); inode = f2fs_new_inode(idmap, dir, S_IFDIR | mode, NULL); if (IS_ERR(inode)) return ERR_CAST(inode); inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) goto out_fail; f2fs_unlock_op(sbi); f2fs_alloc_nid_done(sbi, inode->i_ino); d_instantiate_new(dentry, inode); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); f2fs_balance_fs(sbi, true); return NULL; out_fail: clear_inode_flag(inode, FI_INC_LINK); f2fs_handle_failed_inode(inode); return ERR_PTR(err); } static int f2fs_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (f2fs_empty_dir(inode)) return f2fs_unlink(dir, dentry); return -ENOTEMPTY; } static int f2fs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; int err = 0; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; err = f2fs_dquot_initialize(dir); if (err) return err; inode = f2fs_new_inode(idmap, dir, mode, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &f2fs_special_inode_operations; f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) goto out; f2fs_unlock_op(sbi); f2fs_alloc_nid_done(sbi, inode->i_ino); d_instantiate_new(dentry, inode); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); f2fs_balance_fs(sbi, true); return 0; out: f2fs_handle_failed_inode(inode); return err; } static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode, bool is_whiteout, struct inode **new_inode, struct f2fs_filename *fname) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; int err; err = f2fs_dquot_initialize(dir); if (err) return err; inode = f2fs_new_inode(idmap, dir, mode, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); if (is_whiteout) { init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); inode->i_op = &f2fs_special_inode_operations; } else { inode->i_op = &f2fs_file_inode_operations; inode->i_fop = &f2fs_file_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; } f2fs_lock_op(sbi); err = f2fs_acquire_orphan_inode(sbi); if (err) goto out; err = f2fs_do_tmpfile(inode, dir, fname); if (err) goto release_out; /* * add this non-linked tmpfile to orphan list, in this way we could * remove all unused data of tmpfile after abnormal power-off. */ f2fs_add_orphan_inode(inode); f2fs_alloc_nid_done(sbi, inode->i_ino); if (is_whiteout) { f2fs_i_links_write(inode, false); spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } else { if (file) d_tmpfile(file, inode); else f2fs_i_links_write(inode, false); } /* link_count was changed by d_tmpfile as well. */ f2fs_unlock_op(sbi); unlock_new_inode(inode); if (new_inode) *new_inode = inode; f2fs_balance_fs(sbi, true); return 0; release_out: f2fs_release_orphan_inode(sbi); out: f2fs_handle_failed_inode(inode); return err; } static int f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL, NULL); return finish_open_simple(file, err); } static int f2fs_create_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct inode **whiteout, struct f2fs_filename *fname) { return __f2fs_tmpfile(idmap, dir, NULL, S_IFCHR | WHITEOUT_MODE, true, whiteout, fname); } int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct inode **new_inode) { return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, false, new_inode, NULL); } static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir); struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct inode *whiteout = NULL; struct folio *old_dir_folio = NULL; struct folio *old_folio, *new_folio = NULL; struct f2fs_dir_entry *old_dir_entry = NULL; struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; bool old_is_dir = S_ISDIR(old_inode->i_mode); int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, F2FS_I(old_inode)->i_projid))) return -EXDEV; /* * If new_inode is null, the below renaming flow will * add a link in old_dir which can convert inline_dir. * After then, if we failed to get the entry due to other * reasons like ENOMEM, we had to remove the new entry. * Instead of adding such the error handling routine, let's * simply convert first here. */ if (old_dir == new_dir && !new_inode) { err = f2fs_try_convert_inline_dir(old_dir, new_dentry); if (err) return err; } if (flags & RENAME_WHITEOUT) { struct f2fs_filename fname; err = f2fs_setup_filename(old_dir, &old_dentry->d_name, 0, &fname); if (err) return err; err = f2fs_create_whiteout(idmap, old_dir, &whiteout, &fname); if (err) return err; } err = f2fs_dquot_initialize(old_dir); if (err) goto out; err = f2fs_dquot_initialize(new_dir); if (err) goto out; if (new_inode) { err = f2fs_dquot_initialize(new_inode); if (err) goto out; } err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_folio); if (!old_entry) { if (IS_ERR(old_folio)) err = PTR_ERR(old_folio); goto out; } if (old_is_dir && old_dir != new_dir) { old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_folio); if (!old_dir_entry) { if (IS_ERR(old_dir_folio)) err = PTR_ERR(old_dir_folio); goto out_old; } } if (new_inode) { err = -ENOTEMPTY; if (old_is_dir && !f2fs_empty_dir(new_inode)) goto out_dir; err = -ENOENT; new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_folio); if (!new_entry) { if (IS_ERR(new_folio)) err = PTR_ERR(new_folio); goto out_dir; } f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); err = f2fs_acquire_orphan_inode(sbi); if (err) goto put_out_dir; f2fs_set_link(new_dir, new_entry, new_folio, old_inode); new_folio = NULL; inode_set_ctime_current(new_inode); f2fs_down_write(&F2FS_I(new_inode)->i_sem); if (old_is_dir) f2fs_i_links_write(new_inode, false); f2fs_i_links_write(new_inode, false); f2fs_up_write(&F2FS_I(new_inode)->i_sem); if (!new_inode->i_nlink) f2fs_add_orphan_inode(new_inode); else f2fs_release_orphan_inode(sbi); } else { f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); err = f2fs_add_link(new_dentry, old_inode); if (err) { f2fs_unlock_op(sbi); goto out_dir; } if (old_is_dir) f2fs_i_links_write(new_dir, true); } f2fs_down_write(&F2FS_I(old_inode)->i_sem); if (!old_is_dir || whiteout) file_lost_pino(old_inode); else /* adjust dir's i_pino to pass fsck check */ f2fs_i_pino_write(old_inode, new_dir->i_ino); f2fs_up_write(&F2FS_I(old_inode)->i_sem); inode_set_ctime_current(old_inode); f2fs_mark_inode_dirty_sync(old_inode, false); f2fs_delete_entry(old_entry, old_folio, old_dir, NULL); old_folio = NULL; if (whiteout) { set_inode_flag(whiteout, FI_INC_LINK); err = f2fs_add_link(old_dentry, whiteout); if (err) goto put_out_dir; spin_lock(&whiteout->i_lock); whiteout->i_state &= ~I_LINKABLE; spin_unlock(&whiteout->i_lock); iput(whiteout); } if (old_dir_entry) f2fs_set_link(old_inode, old_dir_entry, old_dir_folio, new_dir); if (old_is_dir) f2fs_i_links_write(old_dir, false); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); if (S_ISDIR(old_inode->i_mode)) f2fs_add_ino_entry(sbi, old_inode->i_ino, TRANS_DIR_INO); } f2fs_unlock_op(sbi); if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); f2fs_update_time(sbi, REQ_TIME); return 0; put_out_dir: f2fs_unlock_op(sbi); f2fs_folio_put(new_folio, false); out_dir: if (old_dir_entry) f2fs_folio_put(old_dir_folio, false); out_old: f2fs_folio_put(old_folio, false); out: iput(whiteout); return err; } static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir); struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct folio *old_dir_folio, *new_dir_folio; struct folio *old_folio, *new_folio; struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL; struct f2fs_dir_entry *old_entry, *new_entry; int old_nlink = 0, new_nlink = 0; int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, F2FS_I(old_inode)->i_projid)) || (is_inode_flag_set(old_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(old_dir)->i_projid, F2FS_I(new_inode)->i_projid))) return -EXDEV; err = f2fs_dquot_initialize(old_dir); if (err) goto out; err = f2fs_dquot_initialize(new_dir); if (err) goto out; err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_folio); if (!old_entry) { if (IS_ERR(old_folio)) err = PTR_ERR(old_folio); goto out; } new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_folio); if (!new_entry) { if (IS_ERR(new_folio)) err = PTR_ERR(new_folio); goto out_old; } /* prepare for updating ".." directory entry info later */ if (old_dir != new_dir) { if (S_ISDIR(old_inode->i_mode)) { old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_folio); if (!old_dir_entry) { if (IS_ERR(old_dir_folio)) err = PTR_ERR(old_dir_folio); goto out_new; } } if (S_ISDIR(new_inode->i_mode)) { new_dir_entry = f2fs_parent_dir(new_inode, &new_dir_folio); if (!new_dir_entry) { if (IS_ERR(new_dir_folio)) err = PTR_ERR(new_dir_folio); goto out_old_dir; } } } /* * If cross rename between file and directory those are not * in the same directory, we will inc nlink of file's parent * later, so we should check upper boundary of its nlink. */ if ((!old_dir_entry || !new_dir_entry) && old_dir_entry != new_dir_entry) { old_nlink = old_dir_entry ? -1 : 1; new_nlink = -old_nlink; err = -EMLINK; if ((old_nlink > 0 && old_dir->i_nlink >= F2FS_LINK_MAX) || (new_nlink > 0 && new_dir->i_nlink >= F2FS_LINK_MAX)) goto out_new_dir; } f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); /* update ".." directory entry info of old dentry */ if (old_dir_entry) f2fs_set_link(old_inode, old_dir_entry, old_dir_folio, new_dir); /* update ".." directory entry info of new dentry */ if (new_dir_entry) f2fs_set_link(new_inode, new_dir_entry, new_dir_folio, old_dir); /* update directory entry info of old dir inode */ f2fs_set_link(old_dir, old_entry, old_folio, new_inode); f2fs_down_write(&F2FS_I(old_inode)->i_sem); if (!old_dir_entry) file_lost_pino(old_inode); else /* adjust dir's i_pino to pass fsck check */ f2fs_i_pino_write(old_inode, new_dir->i_ino); f2fs_up_write(&F2FS_I(old_inode)->i_sem); inode_set_ctime_current(old_dir); if (old_nlink) { f2fs_down_write(&F2FS_I(old_dir)->i_sem); f2fs_i_links_write(old_dir, old_nlink > 0); f2fs_up_write(&F2FS_I(old_dir)->i_sem); } f2fs_mark_inode_dirty_sync(old_dir, false); /* update directory entry info of new dir inode */ f2fs_set_link(new_dir, new_entry, new_folio, old_inode); f2fs_down_write(&F2FS_I(new_inode)->i_sem); if (!new_dir_entry) file_lost_pino(new_inode); else /* adjust dir's i_pino to pass fsck check */ f2fs_i_pino_write(new_inode, old_dir->i_ino); f2fs_up_write(&F2FS_I(new_inode)->i_sem); inode_set_ctime_current(new_dir); if (new_nlink) { f2fs_down_write(&F2FS_I(new_dir)->i_sem); f2fs_i_links_write(new_dir, new_nlink > 0); f2fs_up_write(&F2FS_I(new_dir)->i_sem); } f2fs_mark_inode_dirty_sync(new_dir, false); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); } f2fs_unlock_op(sbi); if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); f2fs_update_time(sbi, REQ_TIME); return 0; out_new_dir: if (new_dir_entry) { f2fs_folio_put(new_dir_folio, 0); } out_old_dir: if (old_dir_entry) { f2fs_folio_put(old_dir_folio, 0); } out_new: f2fs_folio_put(new_folio, false); out_old: f2fs_folio_put(old_folio, false); out: return err; } static int f2fs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int err; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; trace_f2fs_rename_start(old_dir, old_dentry, new_dir, new_dentry, flags); err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (err) return err; if (flags & RENAME_EXCHANGE) err = f2fs_cross_rename(old_dir, old_dentry, new_dir, new_dentry); else /* * VFS has already handled the new dentry existence case, * here, we just deal with "RENAME_NOREPLACE" as regular rename. */ err = f2fs_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags); trace_f2fs_rename_end(old_dentry, new_dentry, flags, err); return err; } static const char *f2fs_encrypted_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct page *page; const char *target; if (!dentry) return ERR_PTR(-ECHILD); page = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(page)) return ERR_CAST(page); target = fscrypt_get_symlink(inode, page_address(page), inode->i_sb->s_blocksize, done); put_page(page); return target; } static int f2fs_encrypted_symlink_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { f2fs_getattr(idmap, path, stat, request_mask, query_flags); return fscrypt_symlink_getattr(path, stat); } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { .get_link = f2fs_encrypted_get_link, .getattr = f2fs_encrypted_symlink_getattr, .setattr = f2fs_setattr, .listxattr = f2fs_listxattr, }; const struct inode_operations f2fs_dir_inode_operations = { .create = f2fs_create, .lookup = f2fs_lookup, .link = f2fs_link, .unlink = f2fs_unlink, .symlink = f2fs_symlink, .mkdir = f2fs_mkdir, .rmdir = f2fs_rmdir, .mknod = f2fs_mknod, .rename = f2fs_rename2, .tmpfile = f2fs_tmpfile, .getattr = f2fs_getattr, .setattr = f2fs_setattr, .get_inode_acl = f2fs_get_acl, .set_acl = f2fs_set_acl, .listxattr = f2fs_listxattr, .fiemap = f2fs_fiemap, .fileattr_get = f2fs_fileattr_get, .fileattr_set = f2fs_fileattr_set, }; const struct inode_operations f2fs_symlink_inode_operations = { .get_link = f2fs_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, .listxattr = f2fs_listxattr, }; const struct inode_operations f2fs_special_inode_operations = { .getattr = f2fs_getattr, .setattr = f2fs_setattr, .get_inode_acl = f2fs_get_acl, .set_acl = f2fs_set_acl, .listxattr = f2fs_listxattr, }; |
| 1 2 6 1 4 5 1 9 9 9 9 5 4 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 3 1 2 15 15 2 1 1 118 5 118 118 118 118 19 19 2 10 10 10 4 4 1 2 1 1 1 1 1 6 5 5 1 1 5 5 5 4 4 4 5 3 3 2 4 3 2 5 5 5 6 6 3 1 3 2 2 6 6 3 1 2 2 2 7 7 1 6 1 3 3 3 3 1 1 4 4 1 5 5 4 4 1 1 2 15 15 168 169 169 168 126 163 3 3 2 154 154 37 2 2 2 2 32 116 116 116 116 116 130 47 14 45 45 5 4 10 10 5 5 5 19 19 10 10 3 10 9 8 19 2 2 2 2 2 1 1 6 4 2 2 2 2 4 4 4 4 4 1 113 42 90 41 90 4 113 112 106 106 51 102 112 20 20 8 7 20 2 2 4 4 2 2 7 7 2 5 2 1 2 11 6 5 5 5 6 4 3 3 2 3 3 2 2 2 2 2 2 1 1 1 2 4 4 4 4 4 4 1 1 2 1 1 2 2 2 2 2 2 2 1 1 1 1 7 105 3 3 24 24 3 3 2 3 1 3 3 6 3 2 1 1 2 2 3 2 2 2 2 2 2 26 34 34 32 3 29 28 29 28 28 32 6 6 1 2 2 6 6 4 2 4 4 4 13 13 6 4 4 4 1 1 10 9 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/base.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc base directory handling functions * * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. * Instead of using magical inumbers to determine the kind of object * we allocate and fill in-core inodes upon lookup. They don't even * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. * * * Changelog: * 17-Jan-2005 * Allan Bezerra * Bruna Moreira <bruna.moreira@indt.org.br> * Edjard Mota <edjard.mota@indt.org.br> * Ilias Biris <ilias.biris@indt.org.br> * Mauricio Lin <mauricio.lin@indt.org.br> * * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * * A new process specific entry (smaps) included in /proc. It shows the * size of rss for each memory area. The maps entry lacks information * about physical memory size (rss) for each mapped file, i.e., * rss information for executables and library files. * This additional information is useful for any tools that need to know * about physical memory consumption for a process specific library. * * Changelog: * 21-Feb-2005 * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * Pud inclusion in the page table walking. * * ChangeLog: * 10-Mar-2005 * 10LE Instituto Nokia de Tecnologia - INdT: * A better way to walks through the page table as suggested by Hugh Dickins. * * Simo Piiroinen <simo.piiroinen@nokia.com>: * Smaps information related to shared, private, clean and dirty pages. * * Paul Mundt <paul.mundt@nokia.com>: * Overall revision about smaps. */ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/task_io_accounting_ops.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/generic-radix-tree.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> #include <linux/mnt_namespace.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> #include <linux/resource.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/printk.h> #include <linux/cache.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> #include <linux/nsproxy.h> #include <linux/oom.h> #include <linux/elf.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/fs_parser.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/debug.h> #include <linux/sched/stat.h> #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> #include <linux/cn_proc.h> #include <linux/ksm.h> #include <uapi/linux/lsm.h> #include <trace/events/oom.h> #include "internal.h" #include "fd.h" #include "../../lib/kstrtox.h" /* NOTE: * Implementing inode permission operations in /proc is almost * certainly an error. Permission checks need to happen during * each system call not at open time. The reason is that most of * what we wish to check for permissions in /proc varies at runtime. * * The classic example of a problem is opening file descriptors * in /proc for a task before it execs a suid executable. */ static u8 nlink_tid __ro_after_init; static u8 nlink_tgid __ro_after_init; enum proc_mem_force { PROC_MEM_FORCE_ALWAYS, PROC_MEM_FORCE_PTRACE, PROC_MEM_FORCE_NEVER }; static enum proc_mem_force proc_mem_force_override __ro_after_init = IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : PROC_MEM_FORCE_ALWAYS; static const struct constant_table proc_mem_force_table[] __initconst = { { "always", PROC_MEM_FORCE_ALWAYS }, { "ptrace", PROC_MEM_FORCE_PTRACE }, { "never", PROC_MEM_FORCE_NEVER }, { } }; static int __init early_proc_mem_force_override(char *buf) { if (!buf) return -EINVAL; /* * lookup_constant() defaults to proc_mem_force_override to preseve * the initial Kconfig choice in case an invalid param gets passed. */ proc_mem_force_override = lookup_constant(proc_mem_force_table, buf, proc_mem_force_override); return 0; } early_param("proc_mem.force_override", early_proc_mem_force_override); struct pid_entry { const char *name; unsigned int len; umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op; }; #define NOD(NAME, MODE, IOP, FOP, OP) { \ .name = (NAME), \ .len = sizeof(NAME) - 1, \ .mode = MODE, \ .iop = IOP, \ .fop = FOP, \ .op = OP, \ } #define DIR(NAME, MODE, iops, fops) \ NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} ) #define LNK(NAME, get_link) \ NOD(NAME, (S_IFLNK|S_IRWXUGO), \ &proc_pid_link_inode_operations, NULL, \ { .proc_get_link = get_link } ) #define REG(NAME, MODE, fops) \ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) #define ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } ) #define ATTR(LSMID, NAME, MODE) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_pid_attr_operations, \ { .lsmid = LSMID }) /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. */ static unsigned int __init pid_entry_nlink(const struct pid_entry *entries, unsigned int n) { unsigned int i; unsigned int count; count = 2; for (i = 0; i < n; ++i) { if (S_ISDIR(entries[i].mode)) ++count; } return count; } static int get_task_root(struct task_struct *task, struct path *root) { int result = -ENOENT; task_lock(task); if (task->fs) { get_fs_root(task->fs, root); result = 0; } task_unlock(task); return result; } static int proc_cwd_link(struct dentry *dentry, struct path *path) { struct task_struct *task = get_proc_task(d_inode(dentry)); int result = -ENOENT; if (task) { task_lock(task); if (task->fs) { get_fs_pwd(task->fs, path); result = 0; } task_unlock(task); put_task_struct(task); } return result; } static int proc_root_link(struct dentry *dentry, struct path *path) { struct task_struct *task = get_proc_task(d_inode(dentry)); int result = -ENOENT; if (task) { result = get_task_root(task, path); put_task_struct(task); } return result; } /* * If the user used setproctitle(), we just get the string from * user space at arg_start, and limit it to a maximum of one page. */ static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf, size_t count, unsigned long pos, unsigned long arg_start) { char *page; int ret, got; if (pos >= PAGE_SIZE) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON); if (got > 0) { int len = strnlen(page, got); /* Include the NUL character if it was found */ if (len < got) len++; if (len > pos) { len -= pos; if (len > count) len = count; len -= copy_to_user(buf, page+pos, len); if (!len) len = -EFAULT; ret = len; } } free_page((unsigned long)page); return ret; } static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, size_t count, loff_t *ppos) { unsigned long arg_start, arg_end, env_start, env_end; unsigned long pos, len; char *page, c; /* Check if process spawned far enough to have cmdline. */ if (!mm->env_end) return 0; spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); if (arg_start >= arg_end) return 0; /* * We allow setproctitle() to overwrite the argument * strings, and overflow past the original end. But * only when it overflows into the environment area. */ if (env_start != arg_end || env_end < env_start) env_start = env_end = arg_end; len = env_end - arg_start; /* We're not going to care if "*ppos" has high bits set */ pos = *ppos; if (pos >= len) return 0; if (count > len - pos) count = len - pos; if (!count) return 0; /* * Magical special case: if the argv[] end byte is not * zero, the user has overwritten it with setproctitle(3). * * Possible future enhancement: do this only once when * pos is 0, and set a flag in the 'struct file'. */ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c) return get_mm_proctitle(mm, buf, count, pos, arg_start); /* * For the non-setproctitle() case we limit things strictly * to the [arg_start, arg_end[ range. */ pos += arg_start; if (pos < arg_start || pos >= arg_end) return 0; if (count > arg_end - pos) count = arg_end - pos; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; len = 0; while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); got = access_remote_vm(mm, pos, page, size, FOLL_ANON); if (got <= 0) break; got -= copy_to_user(buf, page, got); if (unlikely(!got)) { if (!len) len = -EFAULT; break; } pos += got; buf += got; len += got; count -= got; } free_page((unsigned long)page); return len; } static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, size_t count, loff_t *pos) { struct mm_struct *mm; ssize_t ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); return ret; } static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct task_struct *tsk; ssize_t ret; BUG_ON(*pos < 0); tsk = get_proc_task(file_inode(file)); if (!tsk) return -ESRCH; ret = get_task_cmdline(tsk, buf, count, pos); put_task_struct(tsk); if (ret > 0) *pos += ret; return ret; } static const struct file_operations proc_pid_cmdline_ops = { .read = proc_pid_cmdline_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_KALLSYMS /* * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol to user space. */ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto print0; wchan = get_wchan(task); if (wchan && !lookup_symbol_name(wchan, symname)) { seq_puts(m, symname); return 0; } print0: seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ static int lock_trace(struct task_struct *task) { int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; } static void unlock_trace(struct task_struct *task) { up_read(&task->signal->exec_update_lock); } #ifdef CONFIG_STACKTRACE #define MAX_STACK_TRACE_DEPTH 64 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long *entries; int err; /* * The ability to racily run the kernel stack unwinder on a running task * and then observe the unwinder output is scary; while it is useful for * debugging kernel issues, it can also allow an attacker to leak kernel * stack contents. * Doing this in a manner that is at least safe from races would require * some work to ensure that the remote task can not be scheduled; and * even then, this would still expose the unwinder as local attack * surface. * Therefore, this interface is restricted to root. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; err = lock_trace(task); if (!err) { unsigned int i, nr_entries; nr_entries = stack_trace_save_tsk(task, entries, MAX_STACK_TRACE_DEPTH, 0); for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } kfree(entries); return err; } #endif #ifdef CONFIG_SCHED_INFO /* * Provides /proc/PID/schedstat */ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); return 0; } #endif #ifdef CONFIG_LATENCYTOP static int lstats_show_proc(struct seq_file *m, void *v) { int i; struct inode *inode = m->private; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; seq_puts(m, "Latency Top version : v0.1\n"); for (i = 0; i < LT_SAVECOUNT; i++) { struct latency_record *lr = &task->latency_record[i]; if (lr->backtrace[0]) { int q; seq_printf(m, "%i %li %li", lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; if (!bt) break; seq_printf(m, " %ps", (void *)bt); } seq_putc(m, '\n'); } } put_task_struct(task); return 0; } static int lstats_open(struct inode *inode, struct file *file) { return single_open(file, lstats_show_proc, inode); } static ssize_t lstats_write(struct file *file, const char __user *buf, size_t count, loff_t *offs) { struct task_struct *task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; clear_tsk_latency_tracing(task); put_task_struct(task); return count; } static const struct file_operations proc_lstats_operations = { .open = lstats_open, .read = seq_read, .write = lstats_write, .llseek = seq_lseek, .release = single_release, }; #endif static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; long badness; badness = oom_badness(task, totalpages); /* * Special case OOM_SCORE_ADJ_MIN for all others scale the * badness value into [0, 2000] range which we have been * exporting for a long time so userspace might depend on it. */ if (badness != LONG_MIN) points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3; seq_printf(m, "%lu\n", points); return 0; } struct limit_names { const char *name; const char *unit; }; static const struct limit_names lnames[RLIM_NLIMITS] = { [RLIMIT_CPU] = {"Max cpu time", "seconds"}, [RLIMIT_FSIZE] = {"Max file size", "bytes"}, [RLIMIT_DATA] = {"Max data size", "bytes"}, [RLIMIT_STACK] = {"Max stack size", "bytes"}, [RLIMIT_CORE] = {"Max core file size", "bytes"}, [RLIMIT_RSS] = {"Max resident set", "bytes"}, [RLIMIT_NPROC] = {"Max processes", "processes"}, [RLIMIT_NOFILE] = {"Max open files", "files"}, [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, [RLIMIT_AS] = {"Max address space", "bytes"}, [RLIMIT_LOCKS] = {"Max file locks", "locks"}, [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, [RLIMIT_NICE] = {"Max nice priority", NULL}, [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, }; /* Display limits for a process */ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned int i; unsigned long flags; struct rlimit rlim[RLIM_NLIMITS]; if (!lock_task_sighand(task, &flags)) return 0; memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); unlock_task_sighand(task, &flags); /* * print the file header */ seq_puts(m, "Limit " "Soft Limit " "Hard Limit " "Units \n"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) seq_printf(m, "%-25s %-20s ", lnames[i].name, "unlimited"); else seq_printf(m, "%-25s %-20lu ", lnames[i].name, rlim[i].rlim_cur); if (rlim[i].rlim_max == RLIM_INFINITY) seq_printf(m, "%-20s ", "unlimited"); else seq_printf(m, "%-20lu ", rlim[i].rlim_max); if (lnames[i].unit) seq_printf(m, "%-10s\n", lnames[i].unit); else seq_putc(m, '\n'); } return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct syscall_info info; u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); else if (info.data.nr < 0) seq_printf(m, "%d 0x%llx 0x%llx\n", info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ /************************************************************************/ /* Here the fs part begins */ /************************************************************************/ /* permission checks */ static bool proc_fd_access_allowed(struct inode *inode) { struct task_struct *task; bool allowed = false; /* Allow access to a task's file descriptors if it is us or we * may use ptrace attach to the process and find out that * information. */ task = get_proc_task(inode); if (task) { allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; } int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); if (attr->ia_valid & ATTR_MODE) return -EPERM; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, attr); return 0; } /* * May current process learn task's sched/cmdline info (for hide_pid_min=1) * or euid/egid (for hide_pid_min=2)? */ static bool has_pid_permissions(struct proc_fs_info *fs_info, struct task_struct *task, enum proc_hidepid hide_pid_min) { /* * If 'hidpid' mount option is set force a ptrace check, * we indicate that we are using a filesystem syscall * by passing PTRACE_MODE_READ_FSCREDS */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); if (fs_info->hide_pid < hide_pid_min) return true; if (in_group_p(fs_info->pid_gid)) return true; return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } static int proc_pid_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; bool has_perms; task = get_proc_task(inode); if (!task) return -ESRCH; has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { if (fs_info->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process * may not stat() a file, it shouldn't be seen * in procfs at all. */ return -ENOENT; } return -EPERM; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_def_inode_operations = { .setattr = proc_setattr, }; static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; ret = PROC_I(inode)->op.proc_show(m, ns, pid, task); put_task_struct(task); return ret; } static int proc_single_open(struct inode *inode, struct file *filp) { return single_open(filp, proc_single_show, inode); } static const struct file_operations proc_single_file_operations = { .open = proc_single_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; /* * proc_mem_open() can return errno, NULL or mm_struct*. * * - Returns NULL if the task has no mm (PF_KTHREAD or PF_EXITING) * - Returns mm_struct* on success * - Returns error code on failure */ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) { struct task_struct *task = get_proc_task(inode); struct mm_struct *mm; if (!task) return ERR_PTR(-ESRCH); mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (IS_ERR(mm)) return mm == ERR_PTR(-ESRCH) ? NULL : mm; /* ensure this mm_struct can't be freed */ mmgrab(mm); /* but do not pin its memory */ mmput(mm); return mm; } static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) { struct mm_struct *mm = proc_mem_open(inode, mode); if (IS_ERR_OR_NULL(mm)) return mm ? PTR_ERR(mm) : -ESRCH; file->private_data = mm; return 0; } static int mem_open(struct inode *inode, struct file *file) { if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) return -EINVAL; return __mem_open(inode, file, PTRACE_MODE_ATTACH); } static bool proc_mem_foll_force(struct file *file, struct mm_struct *mm) { struct task_struct *task; bool ptrace_active = false; switch (proc_mem_force_override) { case PROC_MEM_FORCE_NEVER: return false; case PROC_MEM_FORCE_PTRACE: task = get_proc_task(file_inode(file)); if (task) { ptrace_active = READ_ONCE(task->ptrace) && READ_ONCE(task->mm) == mm && READ_ONCE(task->parent) == current; put_task_struct(task); } return ptrace_active; default: return true; } } static ssize_t mem_rw(struct file *file, char __user *buf, size_t count, loff_t *ppos, int write) { struct mm_struct *mm = file->private_data; unsigned long addr = *ppos; ssize_t copied; char *page; unsigned int flags; if (!mm) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; copied = 0; if (!mmget_not_zero(mm)) goto free; flags = write ? FOLL_WRITE : 0; if (proc_mem_foll_force(file, mm)) flags |= FOLL_FORCE; while (count > 0) { size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; break; } this_len = access_remote_vm(mm, addr, page, this_len, flags); if (!this_len) { if (!copied) copied = -EIO; break; } if (!write && copy_to_user(buf, page, this_len)) { copied = -EFAULT; break; } buf += this_len; addr += this_len; copied += this_len; count -= this_len; } *ppos = addr; mmput(mm); free: free_page((unsigned long) page); return copied; } static ssize_t mem_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, buf, count, ppos, 0); } static ssize_t mem_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, (char __user*)buf, count, ppos, 1); } loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: file->f_pos = offset; break; case 1: file->f_pos += offset; break; default: return -EINVAL; } force_successful_syscall_return(); return file->f_pos; } static int mem_release(struct inode *inode, struct file *file) { struct mm_struct *mm = file->private_data; if (mm) mmdrop(mm); return 0; } static const struct file_operations proc_mem_operations = { .llseek = mem_lseek, .read = mem_read, .write = mem_write, .open = mem_open, .release = mem_release, .fop_flags = FOP_UNSIGNED_OFFSET, }; static int environ_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ); } static ssize_t environ_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *page; unsigned long src = *ppos; int ret = 0; struct mm_struct *mm = file->private_data; unsigned long env_start, env_end; /* Ensure the process spawned far enough to have an environment. */ if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; if (!mmget_not_zero(mm)) goto free; spin_lock(&mm->arg_lock); env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); while (count > 0) { size_t this_len, max_len; int retval; if (src >= (env_end - env_start)) break; this_len = env_end - (env_start + src); max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; break; } if (copy_to_user(buf, page, retval)) { ret = -EFAULT; break; } ret += retval; src += retval; buf += retval; count -= retval; } *ppos = src; mmput(mm); free: free_page((unsigned long) page); return ret; } static const struct file_operations proc_environ_operations = { .open = environ_open, .read = environ_read, .llseek = generic_file_llseek, .release = mem_release, }; static int auxv_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); } static ssize_t auxv_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct mm_struct *mm = file->private_data; unsigned int nwords = 0; if (!mm) return 0; do { nwords += 2; } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0])); } static const struct file_operations proc_auxv_operations = { .open = auxv_open, .read = auxv_read, .llseek = generic_file_llseek, .release = mem_release, }; static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; int oom_adj = OOM_ADJUST_MIN; size_t len; if (!task) return -ESRCH; if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) oom_adj = OOM_ADJUST_MAX; else oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); if (oom_adj > OOM_ADJUST_MAX) oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; mutex_lock(&oom_adj_mutex); if (legacy) { if (oom_adj < task->signal->oom_score_adj && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } /* * /proc/pid/oom_adj is provided for legacy purposes, ask users to use * /proc/pid/oom_score_adj instead. */ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); } else { if ((short)oom_adj < task->signal->oom_score_adj_min && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } } /* * Make sure we will check other processes sharing the mm if this is * not vfrok which wants its own oom_score_adj. * pin the mm so it doesn't go away and get reused after task_unlock */ if (!task->vfork_done) { struct task_struct *p = find_lock_task_mm(task); if (p) { if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) { mm = p->mm; mmgrab(mm); } task_unlock(p); } } task->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = (short)oom_adj; trace_oom_score_adj_update(task); if (mm) { struct task_struct *p; rcu_read_lock(); for_each_process(p) { if (same_thread_group(task, p)) continue; /* do not touch kernel threads or the global init */ if (p->flags & PF_KTHREAD || is_global_init(p)) continue; task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; } task_unlock(p); } rcu_read_unlock(); mmdrop(mm); } err_unlock: mutex_unlock(&oom_adj_mutex); put_task_struct(task); return err; } /* * /proc/pid/oom_adj exists solely for backwards compatibility with previous * kernels. The effective policy is defined by oom_score_adj, which has a * different scale: oom_adj grew exponentially and oom_score_adj grows linearly. * Values written to oom_adj are simply mapped linearly to oom_score_adj. * Processes that become oom disabled via oom_adj will still be oom disabled * with this implementation. * * oom_adj cannot be removed since existing userspace binaries use it. */ static ssize_t oom_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_adj); if (err) goto out; if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && oom_adj != OOM_DISABLE) { err = -EINVAL; goto out; } /* * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum * value is always attainable. */ if (oom_adj == OOM_ADJUST_MAX) oom_adj = OOM_SCORE_ADJ_MAX; else oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; err = __set_oom_adj(file, oom_adj, true); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_adj_operations = { .read = oom_adj_read, .write = oom_adj_write, .llseek = generic_file_llseek, }; static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; short oom_score_adj = OOM_SCORE_ADJ_MIN; size_t len; if (!task) return -ESRCH; oom_score_adj = task->signal->oom_score_adj; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_score_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); if (err) goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || oom_score_adj > OOM_SCORE_ADJ_MAX) { err = -EINVAL; goto out; } err = __set_oom_adj(file, oom_score_adj, false); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_score_adj_operations = { .read = oom_score_adj_read, .write = oom_score_adj_write, .llseek = default_llseek, }; #ifdef CONFIG_AUDIT #define TMPBUFLEN 11 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", from_kuid(file->f_cred->user_ns, audit_get_loginuid(task))); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); uid_t loginuid; kuid_t kloginuid; int rv; /* Don't let kthreads write their own loginuid */ if (current->flags & PF_KTHREAD) return -EPERM; rcu_read_lock(); if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { rcu_read_unlock(); return -EPERM; } rcu_read_unlock(); if (*ppos != 0) { /* No partial writes. */ return -EINVAL; } rv = kstrtou32_from_user(buf, count, 10, &loginuid); if (rv < 0) return rv; /* is userspace tring to explicitly UNSET the loginuid? */ if (loginuid == AUDIT_UID_UNSET) { kloginuid = INVALID_UID; } else { kloginuid = make_kuid(file->f_cred->user_ns, loginuid); if (!uid_valid(kloginuid)) return -EINVAL; } rv = audit_set_loginuid(kloginuid); if (rv < 0) return rv; return count; } static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, .llseek = generic_file_llseek, }; static ssize_t proc_sessionid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", audit_get_sessionid(task)); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations proc_sessionid_operations = { .read = proc_sessionid_read, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_FAULT_INJECTION static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; size_t len; int make_it_fail; if (!task) return -ESRCH; make_it_fail = task->make_it_fail; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t proc_fault_inject_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task; char buffer[PROC_NUMBUF] = {}; int make_it_fail; int rv; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; rv = kstrtoint(strstrip(buffer), 0, &make_it_fail); if (rv < 0) return rv; if (make_it_fail < 0 || make_it_fail > 1) return -EINVAL; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->make_it_fail = make_it_fail; put_task_struct(task); return count; } static const struct file_operations proc_fault_inject_operations = { .read = proc_fault_inject_read, .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; int err; unsigned int n; err = kstrtouint_from_user(buf, count, 0, &n); if (err) return err; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->fail_nth = n; put_task_struct(task); return count; } static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; char numbuf[PROC_NUMBUF]; ssize_t len; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; len = snprintf(numbuf, sizeof(numbuf), "%u\n", task->fail_nth); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, numbuf, len); } static const struct file_operations proc_fail_nth_operations = { .read = proc_fail_nth_read, .write = proc_fail_nth_write, }; #endif /* * Print out various scheduling related per-task fields: */ static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_show_task(p, ns, m); put_task_struct(p); return 0; } static ssize_t sched_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_set_task(p); put_task_struct(p); return count; } static int sched_open(struct inode *inode, struct file *filp) { return single_open(filp, sched_show, inode); } static const struct file_operations proc_pid_sched_operations = { .open = sched_open, .read = seq_read, .write = sched_write, .llseek = seq_lseek, .release = single_release, }; #ifdef CONFIG_SCHED_AUTOGROUP /* * Print out autogroup related information: */ static int sched_autogroup_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_autogroup_show_task(p, m); put_task_struct(p); return 0; } static ssize_t sched_autogroup_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[PROC_NUMBUF] = {}; int nice; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; err = kstrtoint(strstrip(buffer), 0, &nice); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; put_task_struct(p); return count; } static int sched_autogroup_open(struct inode *inode, struct file *filp) { int ret; ret = single_open(filp, sched_autogroup_show, NULL); if (!ret) { struct seq_file *m = filp->private_data; m->private = inode; } return ret; } static const struct file_operations proc_pid_sched_autogroup_operations = { .open = sched_autogroup_open, .read = seq_read, .write = sched_autogroup_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_SCHED_AUTOGROUP */ #ifdef CONFIG_TIME_NS static int timens_offsets_show(struct seq_file *m, void *v) { struct task_struct *p; p = get_proc_task(file_inode(m->file)); if (!p) return -ESRCH; proc_timens_show_offsets(p, m); put_task_struct(p); return 0; } static ssize_t timens_offsets_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct proc_timens_offset offsets[2]; char *kbuf = NULL, *pos, *next_line; struct task_struct *p; int ret, noffsets; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* Parse the user data */ ret = -EINVAL; noffsets = 0; for (pos = kbuf; pos; pos = next_line) { struct proc_timens_offset *off = &offsets[noffsets]; char clock[10]; int err; /* Find the end of line and ensure we don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } err = sscanf(pos, "%9s %lld %lu", clock, &off->val.tv_sec, &off->val.tv_nsec); if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC) goto out; clock[sizeof(clock) - 1] = 0; if (strcmp(clock, "monotonic") == 0 || strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0) off->clockid = CLOCK_MONOTONIC; else if (strcmp(clock, "boottime") == 0 || strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0) off->clockid = CLOCK_BOOTTIME; else goto out; noffsets++; if (noffsets == ARRAY_SIZE(offsets)) { if (next_line) count = next_line - kbuf; break; } } ret = -ESRCH; p = get_proc_task(inode); if (!p) goto out; ret = proc_timens_set_offset(file, p, offsets, noffsets); put_task_struct(p); if (ret) goto out; ret = count; out: kfree(kbuf); return ret; } static int timens_offsets_open(struct inode *inode, struct file *filp) { return single_open(filp, timens_offsets_show, inode); } static const struct file_operations proc_timens_offsets_operations = { .open = timens_offsets_open, .read = seq_read, .write = timens_offsets_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_TIME_NS */ static ssize_t comm_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[TASK_COMM_LEN] = {}; const size_t maxlen = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) return -EFAULT; p = get_proc_task(inode); if (!p) return -ESRCH; if (same_thread_group(current, p)) { set_task_comm(p, buffer); proc_comm_connector(p); } else count = -EINVAL; put_task_struct(p); return count; } static int comm_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_task_name(m, p, false); seq_putc(m, '\n'); put_task_struct(p); return 0; } static int comm_open(struct inode *inode, struct file *filp) { return single_open(filp, comm_show, inode); } static const struct file_operations proc_pid_set_comm_operations = { .open = comm_open, .read = seq_read, .write = comm_write, .llseek = seq_lseek, .release = single_release, }; static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; exe_file = get_task_exe_file(task); put_task_struct(task); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); fput(exe_file); return 0; } else return -ENOENT; } static const char *proc_pid_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct path path; int error = -EACCES; if (!dentry) return ERR_PTR(-ECHILD); /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; error = nd_jump_link(&path); out: return ERR_PTR(error); } static int do_proc_readlink(const struct path *path, char __user *buffer, int buflen) { char *tmp = kmalloc(PATH_MAX, GFP_KERNEL); char *pathname; int len; if (!tmp) return -ENOMEM; pathname = d_path(path, tmp, PATH_MAX); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; len = tmp + PATH_MAX - 1 - pathname; if (len > buflen) len = buflen; if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: kfree(tmp); return len; } static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen) { int error = -EACCES; struct inode *inode = d_inode(dentry); struct path path; /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; error = do_proc_readlink(&path, buffer, buflen); path_put(&path); out: return error; } const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_pid_get_link, .setattr = proc_setattr, }; /* building an inode */ void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid) { /* Depending on the state of dumpable compute who should own a * proc file for a task. */ const struct cred *cred; kuid_t uid; kgid_t gid; if (unlikely(task->flags & PF_KTHREAD)) { *ruid = GLOBAL_ROOT_UID; *rgid = GLOBAL_ROOT_GID; return; } /* Default to the tasks effective ownership */ rcu_read_lock(); cred = __task_cred(task); uid = cred->euid; gid = cred->egid; rcu_read_unlock(); /* * Before the /proc/pid/status file was created the only way to read * the effective uid of a /process was to stat /proc/pid. Reading * /proc/pid/status is slow enough that procps and other packages * kept stating /proc/pid. To keep the rules in /proc simple I have * made this apply to all per process world readable and executable * directories. */ if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) { struct mm_struct *mm; task_lock(task); mm = task->mm; /* Make non-dumpable tasks owned by some root */ if (mm) { if (get_dumpable(mm) != SUID_DUMP_USER) { struct user_namespace *user_ns = mm->user_ns; uid = make_kuid(user_ns, 0); if (!uid_valid(uid)) uid = GLOBAL_ROOT_UID; gid = make_kgid(user_ns, 0); if (!gid_valid(gid)) gid = GLOBAL_ROOT_GID; } } else { uid = GLOBAL_ROOT_UID; gid = GLOBAL_ROOT_GID; } task_unlock(task); } *ruid = uid; *rgid = gid; } void proc_pid_evict_inode(struct proc_inode *ei) { struct pid *pid = ei->pid; if (S_ISDIR(ei->vfs_inode.i_mode)) { spin_lock(&pid->lock); hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(&pid->lock); } } struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; struct pid *pid; /* We need a new inode */ inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); inode->i_mode = mode; inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); inode->i_op = &proc_def_inode_operations; /* * grab the reference to task. */ pid = get_task_pid(task, PIDTYPE_PID); if (!pid) goto out_unlock; /* Let the pid remember us for quick removal */ ei->pid = pid; task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); out: return inode; out_unlock: iput(inode); return NULL; } /* * Generating an inode and adding it into @pid->inodes, so that task will * invalidate inode's dentry before being released. * * This helper is used for creating dir-type entries under '/proc' and * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' * can be released by invalidating '/proc/<tgid>' dentry. * In theory, dentries under '/proc/<tgid>/task' can also be released by * invalidating '/proc/<tgid>' dentry, we reserve it to handle single * thread exiting situation: Any one of threads should invalidate its * '/proc/<tgid>/task/<pid>' dentry before released. */ static struct inode *proc_pid_make_base_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode *inode; struct proc_inode *ei; struct pid *pid; inode = proc_pid_make_inode(sb, task, mode); if (!inode) return NULL; /* Let proc_flush_pid find this directory inode */ ei = PROC_I(inode); pid = ei->pid; spin_lock(&pid->lock); hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); spin_unlock(&pid->lock); return inode; } int pid_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, * it only makes getattr() consistent with readdir(). */ return -ENOENT; } task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid); } rcu_read_unlock(); return 0; } /* dentry stuff */ /* * Set <pid>/... inode ownership (can change due to setuid(), etc.) */ void pid_update_inode(struct task_struct *task, struct inode *inode) { task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); } /* * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * */ static int pid_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; int ret = 0; rcu_read_lock(); inode = d_inode_rcu(dentry); if (!inode) goto out; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { pid_update_inode(task, inode); ret = 1; } out: rcu_read_unlock(); return ret; } static inline bool proc_inode_is_dead(struct inode *inode) { return !proc_pid(inode)->tasks[PIDTYPE_PID].first; } int pid_delete_dentry(const struct dentry *dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ return proc_inode_is_dead(d_inode(dentry)); } const struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; /* Lookups */ /* * Fill a directory entry. * * If possible create the dcache entry and derive our inode number and * file type from dcache entry. * * Since all of the proc inode numbers are dynamically generated, the inode * numbers do not exist until the inode is cache. This means creating * the dcache entry in readdir is necessary to keep the inode numbers * reported by readdir in sync with the inode numbers reported * by stat. */ bool proc_fill_cache(struct file *file, struct dir_context *ctx, const char *name, unsigned int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = file->f_path.dentry; struct qstr qname = QSTR_INIT(name, len); struct inode *inode; unsigned type = DT_UNKNOWN; ino_t ino = 1; child = try_lookup_noperm(&qname, dir); if (!child) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) goto end_instantiate; if (d_in_lookup(child)) { struct dentry *res; res = instantiate(child, task, ptr); d_lookup_done(child); if (unlikely(res)) { dput(child); child = res; if (IS_ERR(child)) goto end_instantiate; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; dput(child); end_instantiate: return dir_emit(ctx, name, len, ino, type); } /* * dname_to_vma_addr - maps a dentry name into two unsigned longs * which represent vma start and end addresses. */ static int dname_to_vma_addr(struct dentry *dentry, unsigned long *start, unsigned long *end) { const char *str = dentry->d_name.name; unsigned long long sval, eval; unsigned int len; if (str[0] == '0' && str[1] != '-') return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (sval != (unsigned long)sval) return -EINVAL; str += len; if (*str != '-') return -EINVAL; str++; if (str[0] == '0' && str[1]) return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (eval != (unsigned long)eval) return -EINVAL; str += len; if (*str != '\0') return -EINVAL; *start = sval; *end = eval; return 0; } static int map_files_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; struct mm_struct *mm = NULL; struct task_struct *task; struct inode *inode; int status = 0; if (flags & LOOKUP_RCU) return -ECHILD; inode = d_inode(dentry); task = get_proc_task(inode); if (!task) goto out_notask; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { status = mmap_read_lock_killable(mm); if (!status) { exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); mmap_read_unlock(mm); } } mmput(mm); if (exact_vma_exists) { task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); status = 1; } out: put_task_struct(task); out_notask: return status; } static const struct dentry_operations tid_map_files_dentry_operations = { .d_revalidate = map_files_d_revalidate, .d_delete = pid_delete_dentry, }; static int map_files_get_link(struct dentry *dentry, struct path *path) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; int rc; rc = -ENOENT; task = get_proc_task(d_inode(dentry)); if (!task) goto out; mm = get_task_mm(task); put_task_struct(task); if (!mm) goto out; rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); if (rc) goto out_mmput; rc = mmap_read_lock_killable(mm); if (rc) goto out_mmput; rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { *path = *file_user_path(vma->vm_file); path_get(path); rc = 0; } mmap_read_unlock(mm); out_mmput: mmput(mm); out: return rc; } struct map_files_info { unsigned long start; unsigned long end; fmode_t mode; }; /* * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due * to concerns about how the symlinks may be used to bypass permissions on * ancestor directories in the path to the file in question. */ static const char * proc_map_files_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { if (!checkpoint_restore_ns_capable(&init_user_ns)) return ERR_PTR(-EPERM); return proc_pid_get_link(dentry, inode, done); } /* * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_map_files_get_link, .setattr = proc_setattr, }; static struct dentry * proc_map_files_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { fmode_t mode = (fmode_t)(unsigned long)ptr; struct proc_inode *ei; struct inode *inode; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | ((mode & FMODE_READ ) ? S_IRUSR : 0) | ((mode & FMODE_WRITE) ? S_IWUSR : 0)); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; return proc_splice_unmountable(inode, dentry, &tid_map_files_dentry_operations); } static struct dentry *proc_map_files_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct dentry *result; struct mm_struct *mm; result = ERR_PTR(-ENOENT); task = get_proc_task(dir); if (!task) goto out; result = ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) goto out_put_task; mm = get_task_mm(task); if (!mm) goto out_put_task; result = ERR_PTR(-EINTR); if (mmap_read_lock_killable(mm)) goto out_put_mm; result = ERR_PTR(-ENOENT); vma = find_exact_vma(mm, vm_start, vm_end); if (!vma) goto out_no_vma; if (vma->vm_file) result = proc_map_files_instantiate(dentry, task, (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: mmap_read_unlock(mm); out_put_mm: mmput(mm); out_put_task: put_task_struct(task); out: return result; } static const struct inode_operations proc_map_files_inode_operations = { .lookup = proc_map_files_lookup, .permission = proc_fd_permission, .setattr = proc_setattr, }; static int proc_map_files_readdir(struct file *file, struct dir_context *ctx) { struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; unsigned long nr_files, pos, i; GENRADIX(struct map_files_info) fa; struct map_files_info *p; int ret; struct vma_iterator vmi; genradix_init(&fa); ret = -ENOENT; task = get_proc_task(file_inode(file)); if (!task) goto out; ret = -EACCES; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; if (!dir_emit_dots(file, ctx)) goto out_put_task; mm = get_task_mm(task); if (!mm) goto out_put_task; ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); goto out_put_task; } nr_files = 0; /* * We need two passes here: * * 1) Collect vmas of mapped files with mmap_lock taken * 2) Release mmap_lock and instantiate entries * * otherwise we get lockdep complained, since filldir() * routine might require mmap_lock taken in might_fault(). */ pos = 2; vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (++pos <= ctx->pos) continue; p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL); if (!p) { ret = -ENOMEM; mmap_read_unlock(mm); mmput(mm); goto out_put_task; } p->start = vma->vm_start; p->end = vma->vm_end; p->mode = vma->vm_file->f_mode; } mmap_read_unlock(mm); mmput(mm); for (i = 0; i < nr_files; i++) { char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ unsigned int len; p = genradix_ptr(&fa, i); len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end); if (!proc_fill_cache(file, ctx, buf, len, proc_map_files_instantiate, task, (void *)(unsigned long)p->mode)) break; ctx->pos++; } out_put_task: put_task_struct(task); out: genradix_free(&fa); return ret; } static const struct file_operations proc_map_files_operations = { .read = generic_read_dir, .iterate_shared = proc_map_files_readdir, .llseek = generic_file_llseek, }; #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; struct pid_namespace *ns; }; static void *timers_start(struct seq_file *m, loff_t *pos) { struct timers_private *tp = m->private; tp->task = get_pid_task(tp->pid, PIDTYPE_PID); if (!tp->task) return ERR_PTR(-ESRCH); rcu_read_lock(); return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; return seq_hlist_next_rcu(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) { struct timers_private *tp = m->private; if (tp->task) { put_task_struct(tp->task); tp->task = NULL; rcu_read_unlock(); } } static int show_timer(struct seq_file *m, void *v) { static const char * const nstr[] = { [SIGEV_SIGNAL] = "signal", [SIGEV_NONE] = "none", [SIGEV_THREAD] = "thread", }; struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); struct timers_private *tp = m->private; int notify = timer->it_sigev_notify; guard(spinlock_irq)(&timer->it_lock); if (!posixtimer_valid(timer)) return 0; seq_printf(m, "ID: %d\n", timer->it_id); seq_printf(m, "signal: %d/%px\n", timer->sigq.info.si_signo, timer->sigq.info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", pid_nr_ns(timer->it_pid, tp->ns)); seq_printf(m, "ClockID: %d\n", timer->it_clock); return 0; } static const struct seq_operations proc_timers_seq_ops = { .start = timers_start, .next = timers_next, .stop = timers_stop, .show = show_timer, }; static int proc_timers_open(struct inode *inode, struct file *file) { struct timers_private *tp; tp = __seq_open_private(file, &proc_timers_seq_ops, sizeof(struct timers_private)); if (!tp) return -ENOMEM; tp->pid = proc_pid(inode); tp->ns = proc_pid_ns(inode->i_sb); return 0; } static const struct file_operations proc_timers_operations = { .open = proc_timers_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; #endif static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; u64 slack_ns; int err; err = kstrtoull_from_user(buf, count, 10, &slack_ns); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); count = -EPERM; goto out; } rcu_read_unlock(); err = security_task_setscheduler(p); if (err) { count = err; goto out; } } task_lock(p); if (rt_or_dl_task_policy(p)) slack_ns = 0; else if (slack_ns == 0) slack_ns = p->default_timer_slack_ns; p->timer_slack_ns = slack_ns; task_unlock(p); out: put_task_struct(p); return count; } static int timerslack_ns_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; int err = 0; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; goto out; } rcu_read_unlock(); err = security_task_getscheduler(p); if (err) goto out; } task_lock(p); seq_printf(m, "%llu\n", p->timer_slack_ns); task_unlock(p); out: put_task_struct(p); return err; } static int timerslack_ns_open(struct inode *inode, struct file *filp) { return single_open(filp, timerslack_ns_show, inode); } static const struct file_operations proc_pid_set_timerslack_ns_operations = { .open = timerslack_ns_open, .read = seq_read, .write = timerslack_ns_write, .llseek = seq_lseek, .release = single_release, }; static struct dentry *proc_pident_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct pid_entry *p = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, p->mode); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); if (S_ISDIR(inode->i_mode)) set_nlink(inode, 2); /* Use getattr to fix if necessary */ if (p->iop) inode->i_op = p->iop; if (p->fop) inode->i_fop = p->fop; ei->op = p->op; pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); return d_splice_alias(inode, dentry); } static struct dentry *proc_pident_lookup(struct inode *dir, struct dentry *dentry, const struct pid_entry *p, const struct pid_entry *end) { struct task_struct *task = get_proc_task(dir); struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; /* * Yes, it does not scale. And it should not. Don't add * new entries into /proc/<tgid>/ without very good reasons. */ for (; p < end; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) { res = proc_pident_instantiate(dentry, task, p); break; } } put_task_struct(task); out_no_task: return res; } static int proc_pident_readdir(struct file *file, struct dir_context *ctx, const struct pid_entry *ents, unsigned int nents) { struct task_struct *task = get_proc_task(file_inode(file)); const struct pid_entry *p; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= nents + 2) goto out; for (p = ents + (ctx->pos - 2); p < ents + nents; p++) { if (!proc_fill_cache(file, ctx, p->name, p->len, proc_pident_instantiate, task, p)) break; ctx->pos++; } out: put_task_struct(task); return 0; } #ifdef CONFIG_SECURITY static int proc_pid_attr_open(struct inode *inode, struct file *file) { file->private_data = NULL; __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); return 0; } static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); char *p = NULL; ssize_t length; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; length = security_getprocattr(task, PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, &p); put_task_struct(task); if (length > 0) length = simple_read_from_buffer(buf, count, ppos, p, length); kfree(p); return length; } static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task; void *page; int rv; /* A task may only write when it was the opener. */ if (file->private_data != current->mm) return -EPERM; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { rcu_read_unlock(); return -ESRCH; } /* A task may only write its own attributes. */ if (current != task) { rcu_read_unlock(); return -EACCES; } /* Prevent changes to overridden credentials. */ if (current_cred() != current_real_cred()) { rcu_read_unlock(); return -EBUSY; } rcu_read_unlock(); if (count > PAGE_SIZE) count = PAGE_SIZE; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user(buf, count); if (IS_ERR(page)) { rv = PTR_ERR(page); goto out; } /* Guard against adverse ptrace interaction */ rv = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); if (rv < 0) goto out_free; rv = security_setprocattr(PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, page, count); mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); out: return rv; } static const struct file_operations proc_pid_attr_operations = { .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, .release = mem_release, }; #define LSM_DIR_OPS(LSM) \ static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ struct dir_context *ctx) \ { \ return proc_pident_readdir(filp, ctx, \ LSM##_attr_dir_stuff, \ ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct file_operations proc_##LSM##_attr_dir_ops = { \ .read = generic_read_dir, \ .iterate_shared = proc_##LSM##_attr_dir_iterate, \ .llseek = default_llseek, \ }; \ \ static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \ struct dentry *dentry, unsigned int flags) \ { \ return proc_pident_lookup(dir, dentry, \ LSM##_attr_dir_stuff, \ LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \ .lookup = proc_##LSM##_attr_dir_lookup, \ .getattr = pid_getattr, \ .setattr = proc_setattr, \ } #ifdef CONFIG_SECURITY_SMACK static const struct pid_entry smack_attr_dir_stuff[] = { ATTR(LSM_ID_SMACK, "current", 0666), }; LSM_DIR_OPS(smack); #endif #ifdef CONFIG_SECURITY_APPARMOR static const struct pid_entry apparmor_attr_dir_stuff[] = { ATTR(LSM_ID_APPARMOR, "current", 0666), ATTR(LSM_ID_APPARMOR, "prev", 0444), ATTR(LSM_ID_APPARMOR, "exec", 0666), }; LSM_DIR_OPS(apparmor); #endif static const struct pid_entry attr_dir_stuff[] = { ATTR(LSM_ID_UNDEF, "current", 0666), ATTR(LSM_ID_UNDEF, "prev", 0444), ATTR(LSM_ID_UNDEF, "exec", 0666), ATTR(LSM_ID_UNDEF, "fscreate", 0666), ATTR(LSM_ID_UNDEF, "keycreate", 0666), ATTR(LSM_ID_UNDEF, "sockcreate", 0666), #ifdef CONFIG_SECURITY_SMACK DIR("smack", 0555, proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), #endif #ifdef CONFIG_SECURITY_APPARMOR DIR("apparmor", 0555, proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops), #endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); } static const struct file_operations proc_attr_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_attr_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, attr_dir_stuff, attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff)); } static const struct inode_operations proc_attr_dir_inode_operations = { .lookup = proc_attr_dir_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; #endif #ifdef CONFIG_ELF_CORE static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; char buffer[PROC_NUMBUF]; size_t len; int ret; if (!task) return -ESRCH; ret = 0; mm = get_task_mm(task); if (mm) { len = snprintf(buffer, sizeof(buffer), "%08lx\n", ((mm->flags & MMF_DUMP_FILTER_MASK) >> MMF_DUMP_FILTER_SHIFT)); mmput(mm); ret = simple_read_from_buffer(buf, count, ppos, buffer, len); } put_task_struct(task); return ret; } static ssize_t proc_coredump_filter_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; struct mm_struct *mm; unsigned int val; int ret; int i; unsigned long mask; ret = kstrtouint_from_user(buf, count, 0, &val); if (ret < 0) return ret; ret = -ESRCH; task = get_proc_task(file_inode(file)); if (!task) goto out_no_task; mm = get_task_mm(task); if (!mm) goto out_no_mm; ret = 0; for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { if (val & mask) set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); else clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); } mmput(mm); out_no_mm: put_task_struct(task); out_no_task: if (ret < 0) return ret; return count; } static const struct file_operations proc_coredump_filter_operations = { .read = proc_coredump_filter_read, .write = proc_coredump_filter_write, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_TASK_IO_ACCOUNTING static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole) { struct task_io_accounting acct; int result; result = down_read_killable(&task->signal->exec_update_lock); if (result) return result; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } if (whole) { struct signal_struct *sig = task->signal; struct task_struct *t; unsigned int seq = 1; unsigned long flags; rcu_read_lock(); do { seq++; /* 2 on the 1st/lockless path, otherwise odd */ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); acct = sig->ioac; __for_each_thread(sig, t) task_io_accounting_add(&acct, &t->ioac); } while (need_seqretry(&sig->stats_lock, seq)); done_seqretry_irqrestore(&sig->stats_lock, seq, flags); rcu_read_unlock(); } else { acct = task->ioac; } seq_printf(m, "rchar: %llu\n" "wchar: %llu\n" "syscr: %llu\n" "syscw: %llu\n" "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", (unsigned long long)acct.rchar, (unsigned long long)acct.wchar, (unsigned long long)acct.syscr, (unsigned long long)acct.syscw, (unsigned long long)acct.read_bytes, (unsigned long long)acct.write_bytes, (unsigned long long)acct.cancelled_write_bytes); result = 0; out_unlock: up_read(&task->signal->exec_update_lock); return result; } static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 0); } static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 1); } #endif /* CONFIG_TASK_IO_ACCOUNTING */ #ifdef CONFIG_USER_NS static int proc_id_map_open(struct inode *inode, struct file *file, const struct seq_operations *seq_ops) { struct user_namespace *ns = NULL; struct task_struct *task; struct seq_file *seq; int ret = -EINVAL; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; ret = seq_open(file, seq_ops); if (ret) goto err_put_ns; seq = file->private_data; seq->private = ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_id_map_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; put_user_ns(ns); return seq_release(inode, file); } static int proc_uid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_uid_seq_operations); } static int proc_gid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_gid_seq_operations); } static int proc_projid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_projid_seq_operations); } static const struct file_operations proc_uid_map_operations = { .open = proc_uid_map_open, .write = proc_uid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_gid_map_operations = { .open = proc_gid_map_open, .write = proc_gid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_projid_map_operations = { .open = proc_projid_map_open, .write = proc_projid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static int proc_setgroups_open(struct inode *inode, struct file *file) { struct user_namespace *ns = NULL; struct task_struct *task; int ret; ret = -ESRCH; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; if (file->f_mode & FMODE_WRITE) { ret = -EACCES; if (!ns_capable(ns, CAP_SYS_ADMIN)) goto err_put_ns; } ret = single_open(file, &proc_setgroups_show, ns); if (ret) goto err_put_ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_setgroups_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; int ret = single_release(inode, file); put_user_ns(ns); return ret; } static const struct file_operations proc_setgroups_operations = { .open = proc_setgroups_open, .write = proc_setgroups_write, .read = seq_read, .llseek = seq_lseek, .release = proc_setgroups_release, }; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { int err = lock_trace(task); if (!err) { seq_printf(m, "%08x\n", task->personality); unlock_trace(task); } return err; } #ifdef CONFIG_LIVEPATCH static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { seq_printf(m, "%d\n", task->patch_state); return 0; } #endif /* CONFIG_LIVEPATCH */ #ifdef CONFIG_KSM static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; mm = get_task_mm(task); if (mm) { seq_printf(m, "%lu\n", mm->ksm_merging_pages); mmput(mm); } return 0; } static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; int ret = 0; mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); seq_printf(m, "ksm_merge_any: %s\n", test_bit(MMF_VM_MERGE_ANY, &mm->flags) ? "yes" : "no"); ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); return ret; } seq_printf(m, "ksm_mergeable: %s\n", ksm_process_mergeable(mm) ? "yes" : "no"); mmap_read_unlock(mm); mmput(mm); } return 0; } #endif /* CONFIG_KSM */ #ifdef CONFIG_STACKLEAK_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long prev_depth = THREAD_SIZE - (task->prev_lowest_stack & (THREAD_SIZE - 1)); unsigned long depth = THREAD_SIZE - (task->lowest_stack & (THREAD_SIZE - 1)); seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", prev_depth, depth); return 0; } #endif /* CONFIG_STACKLEAK_METRICS */ /* * Thread groups */ static const struct file_operations proc_task_operations; static const struct inode_operations proc_task_inode_operations; static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #ifdef CONFIG_SCHED_AUTOGROUP REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), #endif #ifdef CONFIG_TIME_NS REG("timens_offsets", S_IRUGO|S_IWUSR, proc_timens_offsets_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tgid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), REG("mountstats", S_IRUSR, proc_mountstats_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_ELF_CORE REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tgid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_STACKLEAK_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tgid_base_readdir, .llseek = generic_file_llseek, }; struct pid *tgid_pidfd_to_pid(const struct file *file) { if (file->f_op != &proc_tgid_base_operations) return ERR_PTR(-EBADF); return proc_pid(file_inode(file)); } static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tgid_base_stuff, tgid_base_stuff + ARRAY_SIZE(tgid_base_stuff)); } static const struct inode_operations proc_tgid_base_inode_operations = { .lookup = proc_tgid_base_lookup, .getattr = pid_getattr, .setattr = proc_setattr, .permission = proc_pid_permission, }; /** * proc_flush_pid - Remove dcache entries for @pid from the /proc dcache. * @pid: pid that should be flushed. * * This function walks a list of inodes (that belong to any proc * filesystem) that are attached to the pid and flushes them from * the dentry cache. * * It is safe and reasonable to cache /proc entries for a task until * that task exits. After that they just clog up the dcache with * useless entries, possibly causing useful dcache entries to be * flushed instead. This routine is provided to flush those useless * dcache entries when a process is reaped. * * NOTE: This routine is just an optimization so it does not guarantee * that no dcache entries will exist after a process is reaped * it just makes it very unlikely that any will persist. */ void proc_flush_pid(struct pid *pid) { proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); } static struct dentry *proc_pid_instantiate(struct dentry * dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tgid_base_inode_operations; inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; set_nlink(inode, nlink_tgid); pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); return d_splice_alias(inode, dentry); } struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); tgid = name_to_int(&dentry->d_name); if (tgid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; /* Limit procfs to only ptraceable tasks */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) { if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS)) goto out_put_task; } result = proc_pid_instantiate(dentry, task, NULL); out_put_task: put_task_struct(task); out: return result; } /* * Find the first task with tgid >= tgid * */ struct tgid_iter { unsigned int tgid; struct task_struct *task; }; static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) { struct pid *pid; if (iter.task) put_task_struct(iter.task); rcu_read_lock(); retry: iter.task = NULL; pid = find_ge_pid(iter.tgid, ns); if (pid) { iter.tgid = pid_nr_ns(pid, ns); iter.task = pid_task(pid, PIDTYPE_TGID); if (!iter.task) { iter.tgid += 1; goto retry; } get_task_struct(iter.task); } rcu_read_unlock(); return iter; } #define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2) /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb); struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; if (pos == TGID_OFFSET - 2) { struct inode *inode = d_inode(fs_info->proc_self); if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } if (pos == TGID_OFFSET - 1) { struct inode *inode = d_inode(fs_info->proc_thread_self); if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } iter.tgid = pos - TGID_OFFSET; iter.task = NULL; for (iter = next_tgid(ns, iter); iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[10 + 1]; unsigned int len; cond_resched(); if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%u", iter.tgid); ctx->pos = iter.tgid + TGID_OFFSET; if (!proc_fill_cache(file, ctx, name, len, proc_pid_instantiate, iter.task, NULL)) { put_task_struct(iter.task); return 0; } } ctx->pos = PID_MAX_LIMIT + TGID_OFFSET; return 0; } /* * proc_tid_comm_permission is a special permission function exclusively * used for the node /proc/<pid>/task/<tid>/comm. * It bypasses generic permission checks in the case where a task of the same * task group attempts to access the node. * The rationale behind this is that glibc and bionic access this node for * cross thread naming (pthread_set/getname_np(!self)). However, if * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0, * which locks out the cross thread naming implementation. * This function makes sure that the node is always accessible for members of * same thread group. */ static int proc_tid_comm_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { bool is_same_tgroup; struct task_struct *task; task = get_proc_task(inode); if (!task) return -ESRCH; is_same_tgroup = same_thread_group(current, task); put_task_struct(task); if (likely(is_same_tgroup && !(mask & MAY_EXEC))) { /* This file (/proc/<pid>/task/<tid>/comm) can always be * read or written by the members of the corresponding * thread group. */ return 0; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { .setattr = proc_setattr, .permission = proc_tid_comm_permission, }; /* * Tasks */ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), NOD("comm", S_IFREG|S_IRUGO|S_IWUSR, &proc_tid_comm_inode_operations, &proc_pid_set_comm_operations, {}), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_PROC_CHILDREN REG("children", S_IRUGO, proc_tid_children_operations), #endif #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tid_base_stuff, tid_base_stuff + ARRAY_SIZE(tid_base_stuff)); } static const struct file_operations proc_tid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tid_base_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations proc_tid_base_inode_operations = { .lookup = proc_tid_base_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tid_base_inode_operations; inode->i_fop = &proc_tid_base_operations; inode->i_flags |= S_IMMUTABLE; set_nlink(inode, nlink_tid); pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); return d_splice_alias(inode, dentry); } static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); if (!leader) goto out_no_task; tid = name_to_int(&dentry->d_name); if (tid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; if (!same_thread_group(leader, task)) goto out_drop_task; result = proc_task_instantiate(dentry, task, NULL); out_drop_task: put_task_struct(task); out: put_task_struct(leader); out_no_task: return result; } /* * Find the first tid of a thread group to return to user space. * * Usually this is just the thread group leader, but if the users * buffer was too small or there was a seek into the middle of the * directory we have more work todo. * * In the case of a short read we start with find_task_by_pid. * * In the case of a seek we start with the leader and walk nr * threads past it. */ static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, struct pid_namespace *ns) { struct task_struct *pos, *task; unsigned long nr = f_pos; if (nr != f_pos) /* 32bit overflow? */ return NULL; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); if (!task) goto fail; /* Attempt to start with the tid of a thread */ if (tid && nr) { pos = find_task_by_pid_ns(tid, ns); if (pos && same_thread_group(pos, task)) goto found; } /* If nr exceeds the number of threads there is nothing todo */ if (nr >= get_nr_threads(task)) goto fail; /* If we haven't found our starting place yet start * with the leader and walk nr threads forward. */ for_each_thread(task, pos) { if (!nr--) goto found; } fail: pos = NULL; goto out; found: get_task_struct(pos); out: rcu_read_unlock(); return pos; } /* * Find the next thread in the thread list. * Return NULL if there is an error or no next thread. * * The reference to the input task_struct is released. */ static struct task_struct *next_tid(struct task_struct *start) { struct task_struct *pos = NULL; rcu_read_lock(); if (pid_alive(start)) { pos = __next_thread(start); if (pos) get_task_struct(pos); } rcu_read_unlock(); put_task_struct(start); return pos; } /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct task_struct *task; struct pid_namespace *ns; int tid; if (proc_inode_is_dead(inode)) return -ENOENT; if (!dir_emit_dots(file, ctx)) return 0; /* We cache the tgid value that the last readdir call couldn't * return and lseek resets it to 0. */ ns = proc_pid_ns(inode->i_sb); tid = (int)(intptr_t)file->private_data; file->private_data = NULL; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { char name[10 + 1]; unsigned int len; tid = task_pid_nr_ns(task, ns); if (!tid) continue; /* The task has just exited. */ len = snprintf(name, sizeof(name), "%u", tid); if (!proc_fill_cache(file, ctx, name, len, proc_task_instantiate, task, NULL)) { /* returning this tgid failed, save it as the first * pid for the next readir call */ file->private_data = (void *)(intptr_t)tid; put_task_struct(task); break; } } return 0; } static int proc_task_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct task_struct *p = get_proc_task(inode); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (p) { stat->nlink += get_nr_threads(p); put_task_struct(p); } return 0; } /* * proc_task_readdir() set @file->private_data to a positive integer * value, so casting that to u64 is safe. generic_llseek_cookie() will * set @cookie to 0, so casting to an int is safe. The WARN_ON_ONCE() is * here to catch any unexpected change in behavior either in * proc_task_readdir() or generic_llseek_cookie(). */ static loff_t proc_dir_llseek(struct file *file, loff_t offset, int whence) { u64 cookie = (u64)(intptr_t)file->private_data; loff_t off; off = generic_llseek_cookie(file, offset, whence, &cookie); WARN_ON_ONCE(cookie > INT_MAX); file->private_data = (void *)(intptr_t)cookie; /* serialized by f_pos_lock */ return off; } static const struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, .getattr = proc_task_getattr, .setattr = proc_setattr, .permission = proc_pid_permission, }; static const struct file_operations proc_task_operations = { .read = generic_read_dir, .iterate_shared = proc_task_readdir, .llseek = proc_dir_llseek, }; void __init set_proc_pid_nlink(void) { nlink_tid = pid_entry_nlink(tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); nlink_tgid = pid_entry_nlink(tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } |
| 2 2 4 4 1 1 1 1 1 3 3 3 1 1 2 2 2 1 2 2 3 1 1 1 1 3 4 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/super.c * * Copyright (C) 1997-1999 Russell King */ #include <linux/module.h> #include <linux/init.h> #include <linux/fs_parser.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/statfs.h> #include <linux/user_namespace.h> #include <linux/blkdev.h> #include "adfs.h" #include "dir_f.h" #include "dir_fplus.h" #define ADFS_SB_FLAGS SB_NOATIME #define ADFS_DEFAULT_OWNER_MASK S_IRWXU #define ADFS_DEFAULT_OTHER_MASK (S_IRWXG | S_IRWXO) void __adfs_error(struct super_block *sb, const char *function, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "ADFS-fs error (device %s)%s%s: %pV\n", sb->s_id, function ? ": " : "", function ? function : "", &vaf); va_end(args); } void adfs_msg(struct super_block *sb, const char *pfx, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%sADFS-fs (%s): %pV\n", pfx, sb->s_id, &vaf); va_end(args); } static int adfs_checkdiscrecord(struct adfs_discrecord *dr) { unsigned int max_idlen; int i; /* sector size must be 256, 512 or 1024 bytes */ if (dr->log2secsize != 8 && dr->log2secsize != 9 && dr->log2secsize != 10) return 1; /* idlen must be at least log2secsize + 3 */ if (dr->idlen < dr->log2secsize + 3) return 1; /* we cannot have such a large disc that we * are unable to represent sector offsets in * 32 bits. This works out at 2.0 TB. */ if (le32_to_cpu(dr->disc_size_high) >> dr->log2secsize) return 1; /* * Maximum idlen is limited to 16 bits for new directories by * the three-byte storage of an indirect disc address. For * big directories, idlen must be no greater than 19 v2 [1.0] */ max_idlen = dr->format_version ? 19 : 16; if (dr->idlen > max_idlen) return 1; /* reserved bytes should be zero */ for (i = 0; i < sizeof(dr->unused52); i++) if (dr->unused52[i] != 0) return 1; return 0; } static void adfs_put_super(struct super_block *sb) { struct adfs_sb_info *asb = ADFS_SB(sb); adfs_free_map(sb); kfree_rcu(asb, rcu); } static int adfs_show_options(struct seq_file *seq, struct dentry *root) { struct adfs_sb_info *asb = ADFS_SB(root->d_sb); if (!uid_eq(asb->s_uid, GLOBAL_ROOT_UID)) seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, asb->s_uid)); if (!gid_eq(asb->s_gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, asb->s_gid)); if (asb->s_owner_mask != ADFS_DEFAULT_OWNER_MASK) seq_printf(seq, ",ownmask=%o", asb->s_owner_mask); if (asb->s_other_mask != ADFS_DEFAULT_OTHER_MASK) seq_printf(seq, ",othmask=%o", asb->s_other_mask); if (asb->s_ftsuffix != 0) seq_printf(seq, ",ftsuffix=%u", asb->s_ftsuffix); return 0; } enum {Opt_uid, Opt_gid, Opt_ownmask, Opt_othmask, Opt_ftsuffix}; static const struct fs_parameter_spec adfs_param_spec[] = { fsparam_uid ("uid", Opt_uid), fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("ownmask", Opt_ownmask), fsparam_u32oct ("othmask", Opt_othmask), fsparam_u32 ("ftsuffix", Opt_ftsuffix), {} }; static int adfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct adfs_sb_info *asb = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, adfs_param_spec, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: asb->s_uid = result.uid; break; case Opt_gid: asb->s_gid = result.gid; break; case Opt_ownmask: asb->s_owner_mask = result.uint_32; break; case Opt_othmask: asb->s_other_mask = result.uint_32; break; case Opt_ftsuffix: asb->s_ftsuffix = result.uint_32; break; default: return -EINVAL; } return 0; } static int adfs_reconfigure(struct fs_context *fc) { struct adfs_sb_info *new_asb = fc->s_fs_info; struct adfs_sb_info *asb = ADFS_SB(fc->root->d_sb); sync_filesystem(fc->root->d_sb); fc->sb_flags |= ADFS_SB_FLAGS; /* Structure copy newly parsed options */ *asb = *new_asb; return 0; } static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct adfs_sb_info *sbi = ADFS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); adfs_map_statfs(sb, buf); buf->f_type = ADFS_SUPER_MAGIC; buf->f_namelen = sbi->s_namelen; buf->f_bsize = sb->s_blocksize; buf->f_ffree = (long)(buf->f_bfree * buf->f_files) / (long)buf->f_blocks; buf->f_fsid = u64_to_fsid(id); return 0; } static struct kmem_cache *adfs_inode_cachep; static struct inode *adfs_alloc_inode(struct super_block *sb) { struct adfs_inode_info *ei; ei = alloc_inode_sb(sb, adfs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void adfs_free_inode(struct inode *inode) { kmem_cache_free(adfs_inode_cachep, ADFS_I(inode)); } static int adfs_drop_inode(struct inode *inode) { /* always drop inodes if we are read-only */ return !IS_ENABLED(CONFIG_ADFS_FS_RW) || IS_RDONLY(inode); } static void init_once(void *foo) { struct adfs_inode_info *ei = (struct adfs_inode_info *) foo; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { adfs_inode_cachep = kmem_cache_create("adfs_inode_cache", sizeof(struct adfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (adfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(adfs_inode_cachep); } static const struct super_operations adfs_sops = { .alloc_inode = adfs_alloc_inode, .free_inode = adfs_free_inode, .drop_inode = adfs_drop_inode, .write_inode = adfs_write_inode, .put_super = adfs_put_super, .statfs = adfs_statfs, .show_options = adfs_show_options, }; static int adfs_probe(struct super_block *sb, unsigned int offset, int silent, int (*validate)(struct super_block *sb, struct buffer_head *bh, struct adfs_discrecord **bhp)) { struct adfs_sb_info *asb = ADFS_SB(sb); struct adfs_discrecord *dr; struct buffer_head *bh; unsigned int blocksize = BLOCK_SIZE; int ret, try; for (try = 0; try < 2; try++) { /* try to set the requested block size */ if (sb->s_blocksize != blocksize && !sb_set_blocksize(sb, blocksize)) { if (!silent) adfs_msg(sb, KERN_ERR, "error: unsupported blocksize"); return -EINVAL; } /* read the buffer */ bh = sb_bread(sb, offset >> sb->s_blocksize_bits); if (!bh) { adfs_msg(sb, KERN_ERR, "error: unable to read block %u, try %d", offset >> sb->s_blocksize_bits, try); return -EIO; } /* validate it */ ret = validate(sb, bh, &dr); if (ret) { brelse(bh); return ret; } /* does the block size match the filesystem block size? */ blocksize = 1 << dr->log2secsize; if (sb->s_blocksize == blocksize) { asb->s_map = adfs_read_map(sb, dr); brelse(bh); return PTR_ERR_OR_ZERO(asb->s_map); } brelse(bh); } return -EIO; } static int adfs_validate_bblk(struct super_block *sb, struct buffer_head *bh, struct adfs_discrecord **drp) { struct adfs_discrecord *dr; unsigned char *b_data; b_data = bh->b_data + (ADFS_DISCRECORD % sb->s_blocksize); if (adfs_checkbblk(b_data)) return -EILSEQ; /* Do some sanity checks on the ADFS disc record */ dr = (struct adfs_discrecord *)(b_data + ADFS_DR_OFFSET); if (adfs_checkdiscrecord(dr)) return -EILSEQ; *drp = dr; return 0; } static int adfs_validate_dr0(struct super_block *sb, struct buffer_head *bh, struct adfs_discrecord **drp) { struct adfs_discrecord *dr; /* Do some sanity checks on the ADFS disc record */ dr = (struct adfs_discrecord *)(bh->b_data + 4); if (adfs_checkdiscrecord(dr) || dr->nzones_high || dr->nzones != 1) return -EILSEQ; *drp = dr; return 0; } static int adfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct adfs_discrecord *dr; struct object_info root_obj; struct adfs_sb_info *asb = sb->s_fs_info; struct inode *root; int ret = -EINVAL; int silent = fc->sb_flags & SB_SILENT; sb->s_flags |= ADFS_SB_FLAGS; sb->s_fs_info = asb; sb->s_magic = ADFS_SUPER_MAGIC; sb->s_time_gran = 10000000; /* Try to probe the filesystem boot block */ ret = adfs_probe(sb, ADFS_DISCRECORD, 1, adfs_validate_bblk); if (ret == -EILSEQ) ret = adfs_probe(sb, 0, silent, adfs_validate_dr0); if (ret == -EILSEQ) { if (!silent) adfs_msg(sb, KERN_ERR, "error: can't find an ADFS filesystem on dev %s.", sb->s_id); ret = -EINVAL; } if (ret) goto error; /* set up enough so that we can read an inode */ sb->s_op = &adfs_sops; dr = adfs_map_discrecord(asb->s_map); root_obj.parent_id = root_obj.indaddr = le32_to_cpu(dr->root); root_obj.name_len = 0; /* Set root object date as 01 Jan 1987 00:00:00 */ root_obj.loadaddr = 0xfff0003f; root_obj.execaddr = 0xec22c000; root_obj.size = ADFS_NEWDIR_SIZE; root_obj.attr = ADFS_NDA_DIRECTORY | ADFS_NDA_OWNER_READ | ADFS_NDA_OWNER_WRITE | ADFS_NDA_PUBLIC_READ; /* * If this is a F+ disk with variable length directories, * get the root_size from the disc record. */ if (dr->format_version) { root_obj.size = le32_to_cpu(dr->root_size); asb->s_dir = &adfs_fplus_dir_ops; asb->s_namelen = ADFS_FPLUS_NAME_LEN; } else { asb->s_dir = &adfs_f_dir_ops; asb->s_namelen = ADFS_F_NAME_LEN; } /* * ,xyz hex filetype suffix may be added by driver * to files that have valid RISC OS filetype */ if (asb->s_ftsuffix) asb->s_namelen += 4; sb->s_d_op = &adfs_dentry_operations; root = adfs_iget(sb, &root_obj); sb->s_root = d_make_root(root); if (!sb->s_root) { adfs_free_map(sb); adfs_error(sb, "get root inode failed\n"); ret = -EIO; goto error; } return 0; error: sb->s_fs_info = NULL; kfree(asb); return ret; } static int adfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, adfs_fill_super); } static void adfs_free_fc(struct fs_context *fc) { struct adfs_context *asb = fc->s_fs_info; kfree(asb); } static const struct fs_context_operations adfs_context_ops = { .parse_param = adfs_parse_param, .get_tree = adfs_get_tree, .reconfigure = adfs_reconfigure, .free = adfs_free_fc, }; static int adfs_init_fs_context(struct fs_context *fc) { struct adfs_sb_info *asb; asb = kzalloc(sizeof(struct adfs_sb_info), GFP_KERNEL); if (!asb) return -ENOMEM; if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { struct super_block *sb = fc->root->d_sb; struct adfs_sb_info *old_asb = ADFS_SB(sb); /* structure copy existing options before parsing */ *asb = *old_asb; } else { /* set default options */ asb->s_uid = GLOBAL_ROOT_UID; asb->s_gid = GLOBAL_ROOT_GID; asb->s_owner_mask = ADFS_DEFAULT_OWNER_MASK; asb->s_other_mask = ADFS_DEFAULT_OTHER_MASK; asb->s_ftsuffix = 0; } fc->ops = &adfs_context_ops; fc->s_fs_info = asb; return 0; } static struct file_system_type adfs_fs_type = { .owner = THIS_MODULE, .name = "adfs", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = adfs_init_fs_context, .parameters = adfs_param_spec, }; MODULE_ALIAS_FS("adfs"); static int __init init_adfs_fs(void) { int err = init_inodecache(); if (err) goto out1; err = register_filesystem(&adfs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_adfs_fs(void) { unregister_filesystem(&adfs_fs_type); destroy_inodecache(); } module_init(init_adfs_fs) module_exit(exit_adfs_fs) MODULE_DESCRIPTION("Acorn Disc Filing System"); MODULE_LICENSE("GPL"); |
| 39 2 37 36 1 5 32 7 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* MTD-based superblock management * * Copyright © 2001-2007 Red Hat, Inc. All Rights Reserved. * Copyright © 2001-2010 David Woodhouse <dwmw2@infradead.org> * * Written by: David Howells <dhowells@redhat.com> * David Woodhouse <dwmw2@infradead.org> */ #include <linux/mtd/super.h> #include <linux/namei.h> #include <linux/export.h> #include <linux/ctype.h> #include <linux/slab.h> #include <linux/major.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include "mtdcore.h" /* * get a superblock on an MTD-backed filesystem */ static int mtd_get_sb(struct fs_context *fc, struct mtd_info *mtd, int (*fill_super)(struct super_block *, struct fs_context *)) { struct super_block *sb; int ret; sb = sget_dev(fc, MKDEV(MTD_BLOCK_MAJOR, mtd->index)); if (IS_ERR(sb)) return PTR_ERR(sb); if (sb->s_root) { /* new mountpoint for an already mounted superblock */ pr_debug("MTDSB: Device %d (\"%s\") is already mounted\n", mtd->index, mtd->name); put_mtd_device(mtd); } else { /* fresh new superblock */ pr_debug("MTDSB: New superblock for device %d (\"%s\")\n", mtd->index, mtd->name); /* * Would usually have been set with @sb_lock held but in * contrast to sb->s_bdev that's checked with only * @sb_lock held, nothing checks sb->s_mtd without also * holding sb->s_umount and we're holding sb->s_umount * here. */ sb->s_mtd = mtd; sb->s_bdi = bdi_get(mtd_bdi); ret = fill_super(sb, fc); if (ret < 0) goto error_sb; sb->s_flags |= SB_ACTIVE; } BUG_ON(fc->root); fc->root = dget(sb->s_root); return 0; error_sb: deactivate_locked_super(sb); return ret; } /* * get a superblock on an MTD-backed filesystem by MTD device number */ static int mtd_get_sb_by_nr(struct fs_context *fc, int mtdnr, int (*fill_super)(struct super_block *, struct fs_context *)) { struct mtd_info *mtd; mtd = get_mtd_device(NULL, mtdnr); if (IS_ERR(mtd)) { errorf(fc, "MTDSB: Device #%u doesn't appear to exist\n", mtdnr); return PTR_ERR(mtd); } return mtd_get_sb(fc, mtd, fill_super); } /** * get_tree_mtd - Get a superblock based on a single MTD device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock */ int get_tree_mtd(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { #ifdef CONFIG_BLOCK dev_t dev; int ret; #endif int mtdnr; if (!fc->source) return invalf(fc, "No source specified"); pr_debug("MTDSB: dev_name \"%s\"\n", fc->source); /* the preferred way of mounting in future; especially when * CONFIG_BLOCK=n - we specify the underlying MTD device by number or * by name, so that we don't require block device support to be present * in the kernel. */ if (fc->source[0] == 'm' && fc->source[1] == 't' && fc->source[2] == 'd') { if (fc->source[3] == ':') { struct mtd_info *mtd; /* mount by MTD device name */ pr_debug("MTDSB: mtd:%%s, name \"%s\"\n", fc->source + 4); mtd = get_mtd_device_nm(fc->source + 4); if (!IS_ERR(mtd)) return mtd_get_sb(fc, mtd, fill_super); errorf(fc, "MTD: MTD device with name \"%s\" not found", fc->source + 4); } else if (isdigit(fc->source[3])) { /* mount by MTD device number name */ char *endptr; mtdnr = simple_strtoul(fc->source + 3, &endptr, 0); if (!*endptr) { /* It was a valid number */ pr_debug("MTDSB: mtd%%d, mtdnr %d\n", mtdnr); return mtd_get_sb_by_nr(fc, mtdnr, fill_super); } } } #ifdef CONFIG_BLOCK /* try the old way - the hack where we allowed users to mount * /dev/mtdblock$(n) but didn't actually _use_ the blockdev */ ret = lookup_bdev(fc->source, &dev); if (ret) { errorf(fc, "MTD: Couldn't look up '%s': %d", fc->source, ret); return ret; } pr_debug("MTDSB: lookup_bdev() returned 0\n"); if (MAJOR(dev) == MTD_BLOCK_MAJOR) return mtd_get_sb_by_nr(fc, MINOR(dev), fill_super); #endif /* CONFIG_BLOCK */ if (!(fc->sb_flags & SB_SILENT)) errorf(fc, "MTD: Attempt to mount non-MTD device \"%s\"", fc->source); return -EINVAL; } EXPORT_SYMBOL_GPL(get_tree_mtd); /* * destroy an MTD-based superblock */ void kill_mtd_super(struct super_block *sb) { generic_shutdown_super(sb); put_mtd_device(sb->s_mtd); sb->s_mtd = NULL; } EXPORT_SYMBOL_GPL(kill_mtd_super); |
| 5 5 5 5 5 5 1 9 9 8 3 8 8 6 2 1 4 6 2 6 6 4 8 5 9 9 1 6 2 1 1 8 8 8 8 5 3 3 9 9 2 7 7 7 2 5 7 1 8 9 1 5 9 9 3 6 3 6 6 161 161 161 161 161 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2019 Oracle. All Rights Reserved. * Author: Darrick J. Wong <darrick.wong@oracle.com> */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_iwalk.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_health.h" #include "xfs_trans.h" #include "xfs_pwork.h" #include "xfs_ag.h" #include "xfs_bit.h" /* * Walking Inodes in the Filesystem * ================================ * * This iterator function walks a subset of filesystem inodes in increasing * order from @startino until there are no more inodes. For each allocated * inode it finds, it calls a walk function with the relevant inode number and * a pointer to caller-provided data. The walk function can return the usual * negative error code to stop the iteration; 0 to continue the iteration; or * -ECANCELED to stop the iteration. This return value is returned to the * caller. * * Internally, we allow the walk function to do anything, which means that we * cannot maintain the inobt cursor or our lock on the AGI buffer. We * therefore cache the inobt records in kernel memory and only call the walk * function when our memory buffer is full. @nr_recs is the number of records * that we've cached, and @sz_recs is the size of our cache. * * It is the responsibility of the walk function to ensure it accesses * allocated inodes, as the inobt records may be stale by the time they are * acted upon. */ struct xfs_iwalk_ag { /* parallel work control data; will be null if single threaded */ struct xfs_pwork pwork; struct xfs_mount *mp; struct xfs_trans *tp; struct xfs_perag *pag; /* Where do we start the traversal? */ xfs_ino_t startino; /* What was the last inode number we saw when iterating the inobt? */ xfs_ino_t lastino; /* Array of inobt records we cache. */ struct xfs_inobt_rec_incore *recs; /* Number of entries allocated for the @recs array. */ unsigned int sz_recs; /* Number of entries in the @recs array that are in use. */ unsigned int nr_recs; /* Inode walk function and data pointer. */ xfs_iwalk_fn iwalk_fn; xfs_inobt_walk_fn inobt_walk_fn; void *data; /* * Make it look like the inodes up to startino are free so that * bulkstat can start its inode iteration at the correct place without * needing to special case everywhere. */ unsigned int trim_start:1; /* Skip empty inobt records? */ unsigned int skip_empty:1; /* Drop the (hopefully empty) transaction when calling iwalk_fn. */ unsigned int drop_trans:1; }; /* * Loop over all clusters in a chunk for a given incore inode allocation btree * record. Do a readahead if there are any allocated inodes in that cluster. */ STATIC void xfs_iwalk_ichunk_ra( struct xfs_mount *mp, struct xfs_perag *pag, struct xfs_inobt_rec_incore *irec) { struct xfs_ino_geometry *igeo = M_IGEO(mp); xfs_agblock_t agbno; struct blk_plug plug; int i; /* inode chunk index */ agbno = XFS_AGINO_TO_AGBNO(mp, irec->ir_startino); blk_start_plug(&plug); for (i = 0; i < XFS_INODES_PER_CHUNK; i += igeo->inodes_per_cluster) { xfs_inofree_t imask; imask = xfs_inobt_maskn(i, igeo->inodes_per_cluster); if (imask & ~irec->ir_free) { xfs_buf_readahead(mp->m_ddev_targp, xfs_agbno_to_daddr(pag, agbno), igeo->blocks_per_cluster * mp->m_bsize, &xfs_inode_buf_ops); } agbno += igeo->blocks_per_cluster; } blk_finish_plug(&plug); } /* * Set the bits in @irec's free mask that correspond to the inodes before * @agino so that we skip them. This is how we restart an inode walk that was * interrupted in the middle of an inode record. */ STATIC void xfs_iwalk_adjust_start( xfs_agino_t agino, /* starting inode of chunk */ struct xfs_inobt_rec_incore *irec) /* btree record */ { int idx; /* index into inode chunk */ idx = agino - irec->ir_startino; irec->ir_free |= xfs_inobt_maskn(0, idx); irec->ir_freecount = hweight64(irec->ir_free); } /* Allocate memory for a walk. */ STATIC int xfs_iwalk_alloc( struct xfs_iwalk_ag *iwag) { size_t size; ASSERT(iwag->recs == NULL); iwag->nr_recs = 0; /* Allocate a prefetch buffer for inobt records. */ size = iwag->sz_recs * sizeof(struct xfs_inobt_rec_incore); iwag->recs = kmalloc(size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (iwag->recs == NULL) return -ENOMEM; return 0; } /* Free memory we allocated for a walk. */ STATIC void xfs_iwalk_free( struct xfs_iwalk_ag *iwag) { kfree(iwag->recs); iwag->recs = NULL; } /* For each inuse inode in each cached inobt record, call our function. */ STATIC int xfs_iwalk_ag_recs( struct xfs_iwalk_ag *iwag) { struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_perag *pag = iwag->pag; unsigned int i, j; int error; for (i = 0; i < iwag->nr_recs; i++) { struct xfs_inobt_rec_incore *irec = &iwag->recs[i]; trace_xfs_iwalk_ag_rec(pag, irec); if (xfs_pwork_want_abort(&iwag->pwork)) return 0; if (iwag->inobt_walk_fn) { error = iwag->inobt_walk_fn(mp, tp, pag_agno(pag), irec, iwag->data); if (error) return error; } if (!iwag->iwalk_fn) continue; for (j = 0; j < XFS_INODES_PER_CHUNK; j++) { if (xfs_pwork_want_abort(&iwag->pwork)) return 0; /* Skip if this inode is free */ if (XFS_INOBT_MASK(j) & irec->ir_free) continue; /* Otherwise call our function. */ error = iwag->iwalk_fn(mp, tp, xfs_agino_to_ino(pag, irec->ir_startino + j), iwag->data); if (error) return error; } } return 0; } /* Delete cursor and let go of AGI. */ static inline void xfs_iwalk_del_inobt( struct xfs_trans *tp, struct xfs_btree_cur **curpp, struct xfs_buf **agi_bpp, int error) { if (*curpp) { xfs_btree_del_cursor(*curpp, error); *curpp = NULL; } if (*agi_bpp) { xfs_trans_brelse(tp, *agi_bpp); *agi_bpp = NULL; } } /* * Set ourselves up for walking inobt records starting from a given point in * the filesystem. * * If caller passed in a nonzero start inode number, load the record from the * inobt and make the record look like all the inodes before agino are free so * that we skip them, and then move the cursor to the next inobt record. This * is how we support starting an iwalk in the middle of an inode chunk. * * If the caller passed in a start number of zero, move the cursor to the first * inobt record. * * The caller is responsible for cleaning up the cursor and buffer pointer * regardless of the error status. */ STATIC int xfs_iwalk_ag_start( struct xfs_iwalk_ag *iwag, xfs_agino_t agino, struct xfs_btree_cur **curpp, struct xfs_buf **agi_bpp, int *has_more) { struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_perag *pag = iwag->pag; struct xfs_inobt_rec_incore *irec; int error; /* Set up a fresh cursor and empty the inobt cache. */ iwag->nr_recs = 0; error = xfs_ialloc_read_agi(pag, tp, 0, agi_bpp); if (error) return error; *curpp = xfs_inobt_init_cursor(pag, tp, *agi_bpp); /* Starting at the beginning of the AG? That's easy! */ if (agino == 0) return xfs_inobt_lookup(*curpp, 0, XFS_LOOKUP_GE, has_more); /* * Otherwise, we have to grab the inobt record where we left off, stuff * the record into our cache, and then see if there are more records. * We require a lookup cache of at least two elements so that the * caller doesn't have to deal with tearing down the cursor to walk the * records. */ error = xfs_inobt_lookup(*curpp, agino, XFS_LOOKUP_LE, has_more); if (error) return error; /* * If the LE lookup at @agino yields no records, jump ahead to the * inobt cursor increment to see if there are more records to process. */ if (!*has_more) goto out_advance; /* Get the record, should always work */ irec = &iwag->recs[iwag->nr_recs]; error = xfs_inobt_get_rec(*curpp, irec, has_more); if (error) return error; if (XFS_IS_CORRUPT(mp, *has_more != 1)) { xfs_btree_mark_sick(*curpp); return -EFSCORRUPTED; } iwag->lastino = xfs_agino_to_ino(pag, irec->ir_startino + XFS_INODES_PER_CHUNK - 1); /* * If the LE lookup yielded an inobt record before the cursor position, * skip it and see if there's another one after it. */ if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) goto out_advance; /* * If agino fell in the middle of the inode record, make it look like * the inodes up to agino are free so that we don't return them again. */ if (iwag->trim_start) xfs_iwalk_adjust_start(agino, irec); /* * The prefetch calculation is supposed to give us a large enough inobt * record cache that grab_ichunk can stage a partial first record and * the loop body can cache a record without having to check for cache * space until after it reads an inobt record. */ iwag->nr_recs++; ASSERT(iwag->nr_recs < iwag->sz_recs); out_advance: return xfs_btree_increment(*curpp, 0, has_more); } /* * The inobt record cache is full, so preserve the inobt cursor state and * run callbacks on the cached inobt records. When we're done, restore the * cursor state to wherever the cursor would have been had the cache not been * full (and therefore we could've just incremented the cursor) if *@has_more * is true. On exit, *@has_more will indicate whether or not the caller should * try for more inode records. */ STATIC int xfs_iwalk_run_callbacks( struct xfs_iwalk_ag *iwag, struct xfs_btree_cur **curpp, struct xfs_buf **agi_bpp, int *has_more) { struct xfs_mount *mp = iwag->mp; xfs_agino_t next_agino; int error; next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1; ASSERT(iwag->nr_recs > 0); /* Delete cursor but remember the last record we cached... */ xfs_iwalk_del_inobt(iwag->tp, curpp, agi_bpp, 0); ASSERT(next_agino >= iwag->recs[iwag->nr_recs - 1].ir_startino + XFS_INODES_PER_CHUNK); if (iwag->drop_trans) { xfs_trans_cancel(iwag->tp); iwag->tp = NULL; } error = xfs_iwalk_ag_recs(iwag); if (error) return error; /* ...empty the cache... */ iwag->nr_recs = 0; if (!has_more) return 0; if (iwag->drop_trans) { error = xfs_trans_alloc_empty(mp, &iwag->tp); if (error) return error; } /* ...and recreate the cursor just past where we left off. */ error = xfs_ialloc_read_agi(iwag->pag, iwag->tp, 0, agi_bpp); if (error) return error; *curpp = xfs_inobt_init_cursor(iwag->pag, iwag->tp, *agi_bpp); return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more); } /* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ STATIC int xfs_iwalk_ag( struct xfs_iwalk_ag *iwag) { struct xfs_mount *mp = iwag->mp; struct xfs_perag *pag = iwag->pag; struct xfs_buf *agi_bp = NULL; struct xfs_btree_cur *cur = NULL; xfs_agino_t agino; int has_more; int error = 0; /* Set up our cursor at the right place in the inode btree. */ ASSERT(pag_agno(pag) == XFS_INO_TO_AGNO(mp, iwag->startino)); agino = XFS_INO_TO_AGINO(mp, iwag->startino); error = xfs_iwalk_ag_start(iwag, agino, &cur, &agi_bp, &has_more); while (!error && has_more) { struct xfs_inobt_rec_incore *irec; xfs_ino_t rec_fsino; cond_resched(); if (xfs_pwork_want_abort(&iwag->pwork)) goto out; /* Fetch the inobt record. */ irec = &iwag->recs[iwag->nr_recs]; error = xfs_inobt_get_rec(cur, irec, &has_more); if (error || !has_more) break; /* Make sure that we always move forward. */ rec_fsino = xfs_agino_to_ino(pag, irec->ir_startino); if (iwag->lastino != NULLFSINO && XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto out; } iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1; /* No allocated inodes in this chunk; skip it. */ if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { error = xfs_btree_increment(cur, 0, &has_more); if (error) break; continue; } /* * Start readahead for this inode chunk in anticipation of * walking the inodes. */ if (iwag->iwalk_fn) xfs_iwalk_ichunk_ra(mp, pag, irec); /* * If there's space in the buffer for more records, increment * the btree cursor and grab more. */ if (++iwag->nr_recs < iwag->sz_recs) { error = xfs_btree_increment(cur, 0, &has_more); if (error || !has_more) break; continue; } /* * Otherwise, we need to save cursor state and run the callback * function on the cached records. The run_callbacks function * is supposed to return a cursor pointing to the record where * we would be if we had been able to increment like above. */ ASSERT(has_more); error = xfs_iwalk_run_callbacks(iwag, &cur, &agi_bp, &has_more); } if (iwag->nr_recs == 0 || error) goto out; /* Walk the unprocessed records in the cache. */ error = xfs_iwalk_run_callbacks(iwag, &cur, &agi_bp, &has_more); out: xfs_iwalk_del_inobt(iwag->tp, &cur, &agi_bp, error); return error; } /* * We experimentally determined that the reduction in ioctl call overhead * diminishes when userspace asks for more than 2048 inodes, so we'll cap * prefetch at this point. */ #define IWALK_MAX_INODE_PREFETCH (2048U) /* * Given the number of inodes to prefetch, set the number of inobt records that * we cache in memory, which controls the number of inodes we try to read * ahead. Set the maximum if @inodes == 0. */ static inline unsigned int xfs_iwalk_prefetch( unsigned int inodes) { unsigned int inobt_records; /* * If the caller didn't tell us the number of inodes they wanted, * assume the maximum prefetch possible for best performance. * Otherwise, cap prefetch at that maximum so that we don't start an * absurd amount of prefetch. */ if (inodes == 0) inodes = IWALK_MAX_INODE_PREFETCH; inodes = min(inodes, IWALK_MAX_INODE_PREFETCH); /* Round the inode count up to a full chunk. */ inodes = round_up(inodes, XFS_INODES_PER_CHUNK); /* * In order to convert the number of inodes to prefetch into an * estimate of the number of inobt records to cache, we require a * conversion factor that reflects our expectations of the average * loading factor of an inode chunk. Based on data gathered, most * (but not all) filesystems manage to keep the inode chunks totally * full, so we'll underestimate slightly so that our readahead will * still deliver the performance we want on aging filesystems: * * inobt = inodes / (INODES_PER_CHUNK * (4 / 5)); * * The funny math is to avoid integer division. */ inobt_records = (inodes * 5) / (4 * XFS_INODES_PER_CHUNK); /* * Allocate enough space to prefetch at least two inobt records so that * we can cache both the record where the iwalk started and the next * record. This simplifies the AG inode walk loop setup code. */ return max(inobt_records, 2U); } static int xfs_iwalk_args( struct xfs_iwalk_ag *iwag, unsigned int flags) { struct xfs_mount *mp = iwag->mp; xfs_agnumber_t start_agno; int error; start_agno = XFS_INO_TO_AGNO(iwag->mp, iwag->startino); ASSERT(start_agno < iwag->mp->m_sb.sb_agcount); ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL)); error = xfs_iwalk_alloc(iwag); if (error) return error; while ((iwag->pag = xfs_perag_next_from(mp, iwag->pag, start_agno))) { error = xfs_iwalk_ag(iwag); if (error || (flags & XFS_IWALK_SAME_AG)) { xfs_perag_rele(iwag->pag); break; } iwag->startino = XFS_AGINO_TO_INO(mp, pag_agno(iwag->pag) + 1, 0); } xfs_iwalk_free(iwag); return error; } /* * Walk all inodes in the filesystem starting from @startino. The @iwalk_fn * will be called for each allocated inode, being passed the inode's number and * @data. @max_prefetch controls how many inobt records' worth of inodes we * try to readahead. */ int xfs_iwalk( struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t startino, unsigned int flags, xfs_iwalk_fn iwalk_fn, unsigned int inode_records, void *data) { struct xfs_iwalk_ag iwag = { .mp = mp, .tp = tp, .iwalk_fn = iwalk_fn, .data = data, .startino = startino, .sz_recs = xfs_iwalk_prefetch(inode_records), .trim_start = 1, .skip_empty = 1, .pwork = XFS_PWORK_SINGLE_THREADED, .lastino = NULLFSINO, }; return xfs_iwalk_args(&iwag, flags); } /* Run per-thread iwalk work. */ static int xfs_iwalk_ag_work( struct xfs_mount *mp, struct xfs_pwork *pwork) { struct xfs_iwalk_ag *iwag; int error = 0; iwag = container_of(pwork, struct xfs_iwalk_ag, pwork); if (xfs_pwork_want_abort(pwork)) goto out; error = xfs_iwalk_alloc(iwag); if (error) goto out; /* * Grab an empty transaction so that we can use its recursive buffer * locking abilities to detect cycles in the inobt without deadlocking. */ error = xfs_trans_alloc_empty(mp, &iwag->tp); if (error) goto out; iwag->drop_trans = 1; error = xfs_iwalk_ag(iwag); if (iwag->tp) xfs_trans_cancel(iwag->tp); xfs_iwalk_free(iwag); out: xfs_perag_put(iwag->pag); kfree(iwag); return error; } /* * Walk all the inodes in the filesystem using multiple threads to process each * AG. */ int xfs_iwalk_threaded( struct xfs_mount *mp, xfs_ino_t startino, unsigned int flags, xfs_iwalk_fn iwalk_fn, unsigned int inode_records, bool polled, void *data) { xfs_agnumber_t start_agno = XFS_INO_TO_AGNO(mp, startino); struct xfs_pwork_ctl pctl; struct xfs_perag *pag = NULL; int error; ASSERT(start_agno < mp->m_sb.sb_agcount); ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL)); error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk"); if (error) return error; while ((pag = xfs_perag_next_from(mp, pag, start_agno))) { struct xfs_iwalk_ag *iwag; if (xfs_pwork_ctl_want_abort(&pctl)) break; iwag = kzalloc(sizeof(struct xfs_iwalk_ag), GFP_KERNEL | __GFP_NOFAIL); iwag->mp = mp; /* * perag is being handed off to async work, so take a passive * reference for the async work to release. */ iwag->pag = xfs_perag_hold(pag); iwag->iwalk_fn = iwalk_fn; iwag->data = data; iwag->startino = startino; iwag->sz_recs = xfs_iwalk_prefetch(inode_records); iwag->lastino = NULLFSINO; xfs_pwork_queue(&pctl, &iwag->pwork); startino = XFS_AGINO_TO_INO(mp, pag_agno(pag) + 1, 0); if (flags & XFS_IWALK_SAME_AG) break; } if (pag) xfs_perag_rele(pag); if (polled) xfs_pwork_poll(&pctl); return xfs_pwork_destroy(&pctl); } /* * Allow callers to cache up to a page's worth of inobt records. This reflects * the existing inumbers prefetching behavior. Since the inobt walk does not * itself do anything with the inobt records, we can set a fairly high limit * here. */ #define MAX_INOBT_WALK_PREFETCH \ (PAGE_SIZE / sizeof(struct xfs_inobt_rec_incore)) /* * Given the number of records that the user wanted, set the number of inobt * records that we buffer in memory. Set the maximum if @inobt_records == 0. */ static inline unsigned int xfs_inobt_walk_prefetch( unsigned int inobt_records) { /* * If the caller didn't tell us the number of inobt records they * wanted, assume the maximum prefetch possible for best performance. */ if (inobt_records == 0) inobt_records = MAX_INOBT_WALK_PREFETCH; /* * Allocate enough space to prefetch at least two inobt records so that * we can cache both the record where the iwalk started and the next * record. This simplifies the AG inode walk loop setup code. */ inobt_records = max(inobt_records, 2U); /* * Cap prefetch at that maximum so that we don't use an absurd amount * of memory. */ return min_t(unsigned int, inobt_records, MAX_INOBT_WALK_PREFETCH); } /* * Walk all inode btree records in the filesystem starting from @startino. The * @inobt_walk_fn will be called for each btree record, being passed the incore * record and @data. @max_prefetch controls how many inobt records we try to * cache ahead of time. */ int xfs_inobt_walk( struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t startino, unsigned int flags, xfs_inobt_walk_fn inobt_walk_fn, unsigned int inobt_records, void *data) { struct xfs_iwalk_ag iwag = { .mp = mp, .tp = tp, .inobt_walk_fn = inobt_walk_fn, .data = data, .startino = startino, .sz_recs = xfs_inobt_walk_prefetch(inobt_records), .pwork = XFS_PWORK_SINGLE_THREADED, .lastino = NULLFSINO, }; return xfs_iwalk_args(&iwag, flags); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. */ #include <linux/export.h> #include <net/ipv6.h> #include <net/ipv6_stubs.h> #include <net/addrconf.h> #include <net/ip.h> /* if ipv6 module registers this function is used by xfrm to force all * sockets to relookup their nodes - this is fairly expensive, be * careful */ void (*__fib6_flush_trees)(struct net *); EXPORT_SYMBOL(__fib6_flush_trees); #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) static inline unsigned int ipv6_addr_scope2type(unsigned int scope) { switch (scope) { case IPV6_ADDR_SCOPE_NODELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_NODELOCAL) | IPV6_ADDR_LOOPBACK); case IPV6_ADDR_SCOPE_LINKLOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL) | IPV6_ADDR_LINKLOCAL); case IPV6_ADDR_SCOPE_SITELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL) | IPV6_ADDR_SITELOCAL); } return IPV6_ADDR_SCOPE_TYPE(scope); } int __ipv6_addr_type(const struct in6_addr *addr) { __be32 st; st = addr->s6_addr32[0]; /* Consider all addresses with the first three bits different of 000 and 111 as unicasts. */ if ((st & htonl(0xE0000000)) != htonl(0x00000000) && (st & htonl(0xE0000000)) != htonl(0xE0000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); if ((st & htonl(0xFF000000)) == htonl(0xFF000000)) { /* multicast */ /* addr-select 3.1 */ return (IPV6_ADDR_MULTICAST | ipv6_addr_scope2type(IPV6_ADDR_MC_SCOPE(addr))); } if ((st & htonl(0xFFC00000)) == htonl(0xFE800000)) return (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFFC00000)) == htonl(0xFEC00000)) return (IPV6_ADDR_SITELOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFE000000)) == htonl(0xFC000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* RFC 4193 */ if ((addr->s6_addr32[0] | addr->s6_addr32[1]) == 0) { if (addr->s6_addr32[2] == 0) { if (addr->s6_addr32[3] == 0) return IPV6_ADDR_ANY; if (addr->s6_addr32[3] == htonl(0x00000001)) return (IPV6_ADDR_LOOPBACK | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.4 */ return (IPV6_ADDR_COMPATv4 | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } if (addr->s6_addr32[2] == htonl(0x0000ffff)) return (IPV6_ADDR_MAPPED | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */ } EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&inet6addr_chain, nb); } EXPORT_SYMBOL(register_inet6addr_notifier); int unregister_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&inet6addr_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_notifier); int inet6addr_notifier_call_chain(unsigned long val, void *v) { return atomic_notifier_call_chain(&inet6addr_chain, val, v); } EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) { return -EAFNOSUPPORT; } static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id) { return NULL; } static int eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return -EAFNOSUPPORT; } static int eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return -EAFNOSUPPORT; } static void eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { } static u32 eafnosupport_ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { return 0; } static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EAFNOSUPPORT; } static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { return -EAFNOSUPPORT; } static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { kfree_skb(skb); return -EAFNOSUPPORT; } static struct net_device *eafnosupport_ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev) { return ERR_PTR(-EAFNOSUPPORT); } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, .fib6_lookup = eafnosupport_fib6_lookup, .fib6_select_path = eafnosupport_fib6_select_path, .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, .ip6_del_rt = eafnosupport_ip6_del_rt, .ipv6_fragment = eafnosupport_ipv6_fragment, .ipv6_dev_find = eafnosupport_ipv6_dev_find, }; EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) { kfree(idev->stats.icmpv6msgdev); kfree(idev->stats.icmpv6dev); free_percpu(idev->stats.ipv6); } static void in6_dev_finish_destroy_rcu(struct rcu_head *head) { struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); snmp6_free_dev(idev); kfree(idev); } /* Nobody refers to this device, we may destroy it. */ void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; WARN_ON(!list_empty(&idev->addr_list)); WARN_ON(rcu_access_pointer(idev->mc_list)); WARN_ON(timer_pending(&idev->rs_timer)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) { pr_warn("Freeing alive inet6 device %p\n", idev); return; } call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } EXPORT_SYMBOL(in6_dev_finish_destroy); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BOOTMEM_INFO_H #define __LINUX_BOOTMEM_INFO_H #include <linux/mm.h> #include <linux/kmemleak.h> /* * Types for free bootmem stored in the low bits of page->private. */ enum bootmem_type { MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 1, SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, MIX_SECTION_INFO, NODE_INFO, MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, }; #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void __init register_page_bootmem_info_node(struct pglist_data *pgdat); void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); void get_page_bootmem(unsigned long info, struct page *page, enum bootmem_type type); void put_page_bootmem(struct page *page); static inline enum bootmem_type bootmem_type(const struct page *page) { return (unsigned long)page->private & 0xf; } static inline unsigned long bootmem_info(const struct page *page) { return (unsigned long)page->private >> 4; } /* * Any memory allocated via the memblock allocator and not via the * buddy will be marked reserved already in the memmap. For those * pages, we can call this function to free it to buddy allocator. */ static inline void free_bootmem_page(struct page *page) { enum bootmem_type type = bootmem_type(page); /* * The reserve_bootmem_region sets the reserved flag on bootmem * pages. */ VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); if (type == SECTION_INFO || type == MIX_SECTION_INFO) put_page_bootmem(page); else VM_BUG_ON_PAGE(1, page); } #else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } static inline void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages) { } static inline void put_page_bootmem(struct page *page) { } static inline enum bootmem_type bootmem_type(const struct page *page) { return SECTION_INFO; } static inline unsigned long bootmem_info(const struct page *page) { return 0; } static inline void get_page_bootmem(unsigned long info, struct page *page, enum bootmem_type type) { } static inline void free_bootmem_page(struct page *page) { kmemleak_free_part_phys(PFN_PHYS(page_to_pfn(page)), PAGE_SIZE); free_reserved_page(page); } #endif #endif /* __LINUX_BOOTMEM_INFO_H */ |
| 2 2 1 1 11 7 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 | // SPDX-License-Identifier: MIT #include <linux/fb.h> #include <drm/drm_drv.h> #include <drm/drm_fbdev_shmem.h> #include <drm/drm_fb_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_gem_shmem_helper.h> /* * struct fb_ops */ static int drm_fbdev_shmem_fb_open(struct fb_info *info, int user) { struct drm_fb_helper *fb_helper = info->par; /* No need to take a ref for fbcon because it unbinds on unregister */ if (user && !try_module_get(fb_helper->dev->driver->fops->owner)) return -ENODEV; return 0; } static int drm_fbdev_shmem_fb_release(struct fb_info *info, int user) { struct drm_fb_helper *fb_helper = info->par; if (user) module_put(fb_helper->dev->driver->fops->owner); return 0; } FB_GEN_DEFAULT_DEFERRED_SYSMEM_OPS(drm_fbdev_shmem, drm_fb_helper_damage_range, drm_fb_helper_damage_area); static int drm_fbdev_shmem_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) { struct drm_fb_helper *fb_helper = info->par; struct drm_framebuffer *fb = fb_helper->fb; struct drm_gem_object *obj = drm_gem_fb_get_obj(fb, 0); struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); if (shmem->map_wc) vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); return fb_deferred_io_mmap(info, vma); } static void drm_fbdev_shmem_fb_destroy(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; if (!fb_helper->dev) return; fb_deferred_io_cleanup(info); drm_fb_helper_fini(fb_helper); drm_client_buffer_vunmap(fb_helper->buffer); drm_client_framebuffer_delete(fb_helper->buffer); drm_client_release(&fb_helper->client); drm_fb_helper_unprepare(fb_helper); kfree(fb_helper); } static const struct fb_ops drm_fbdev_shmem_fb_ops = { .owner = THIS_MODULE, .fb_open = drm_fbdev_shmem_fb_open, .fb_release = drm_fbdev_shmem_fb_release, __FB_DEFAULT_DEFERRED_OPS_RDWR(drm_fbdev_shmem), DRM_FB_HELPER_DEFAULT_OPS, __FB_DEFAULT_DEFERRED_OPS_DRAW(drm_fbdev_shmem), .fb_mmap = drm_fbdev_shmem_fb_mmap, .fb_destroy = drm_fbdev_shmem_fb_destroy, }; static struct page *drm_fbdev_shmem_get_page(struct fb_info *info, unsigned long offset) { struct drm_fb_helper *fb_helper = info->par; struct drm_framebuffer *fb = fb_helper->fb; struct drm_gem_object *obj = drm_gem_fb_get_obj(fb, 0); struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); unsigned int i = offset >> PAGE_SHIFT; struct page *page; if (fb_WARN_ON_ONCE(info, offset > obj->size)) return NULL; page = shmem->pages[i]; // protected by active vmap if (page) get_page(page); fb_WARN_ON_ONCE(info, !page); return page; } /* * struct drm_fb_helper */ static int drm_fbdev_shmem_helper_fb_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) { struct drm_device *dev = helper->dev; int ret; /* Call damage handlers only if necessary */ if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2)) return 0; if (helper->fb->funcs->dirty) { ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret)) return ret; } return 0; } static const struct drm_fb_helper_funcs drm_fbdev_shmem_helper_funcs = { .fb_dirty = drm_fbdev_shmem_helper_fb_dirty, }; /* * struct drm_driver */ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; struct drm_client_buffer *buffer; struct drm_gem_shmem_object *shmem; struct drm_framebuffer *fb; struct fb_info *info; u32 format; struct iosys_map map; int ret; drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n", sizes->surface_width, sizes->surface_height, sizes->surface_bpp); format = drm_driver_legacy_fb_format(dev, sizes->surface_bpp, sizes->surface_depth); buffer = drm_client_framebuffer_create(client, sizes->surface_width, sizes->surface_height, format); if (IS_ERR(buffer)) return PTR_ERR(buffer); shmem = to_drm_gem_shmem_obj(buffer->gem); fb = buffer->fb; ret = drm_client_buffer_vmap(buffer, &map); if (ret) { goto err_drm_client_buffer_delete; } else if (drm_WARN_ON(dev, map.is_iomem)) { ret = -ENODEV; /* I/O memory not supported; use generic emulation */ goto err_drm_client_buffer_delete; } fb_helper->funcs = &drm_fbdev_shmem_helper_funcs; fb_helper->buffer = buffer; fb_helper->fb = fb; info = drm_fb_helper_alloc_info(fb_helper); if (IS_ERR(info)) { ret = PTR_ERR(info); goto err_drm_client_buffer_vunmap; } drm_fb_helper_fill_info(info, fb_helper, sizes); info->fbops = &drm_fbdev_shmem_fb_ops; /* screen */ info->flags |= FBINFO_VIRTFB; /* system memory */ if (!shmem->map_wc) info->flags |= FBINFO_READS_FAST; /* signal caching */ info->screen_size = sizes->surface_height * fb->pitches[0]; info->screen_buffer = map.vaddr; info->fix.smem_len = info->screen_size; /* deferred I/O */ fb_helper->fbdefio.delay = HZ / 20; fb_helper->fbdefio.get_page = drm_fbdev_shmem_get_page; fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; info->fbdefio = &fb_helper->fbdefio; ret = fb_deferred_io_init(info); if (ret) goto err_drm_fb_helper_release_info; return 0; err_drm_fb_helper_release_info: drm_fb_helper_release_info(fb_helper); err_drm_client_buffer_vunmap: fb_helper->fb = NULL; fb_helper->buffer = NULL; drm_client_buffer_vunmap(buffer); err_drm_client_buffer_delete: drm_client_framebuffer_delete(buffer); return ret; } EXPORT_SYMBOL(drm_fbdev_shmem_driver_fbdev_probe); |
| 141 141 141 174 103 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * CRC32C chksum * *@Article{castagnoli-crc, * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 * and 32 Parity Bits}}, * journal = IEEE Transactions on Communication, * year = {1993}, * volume = {41}, * number = {6}, * pages = {}, * month = {June}, *} * Used by the iSCSI driver, possibly others, and derived from * the iscsi-crc.c module of the linux-iscsi driver at * http://linux-iscsi.sourceforge.net. * * Following the example of lib/crc32, this function is intended to be * flexible and useful for all users. Modules that currently have their * own crc32c, but hopefully may be able to use this one are: * net/sctp (please add all your doco to here if you change to * use this one!) * <endoflist> * * Copyright (c) 2004 Cisco Systems, Inc. * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/unaligned.h> #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/crc32.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 struct chksum_ctx { u32 key; }; struct chksum_desc_ctx { u32 crc; }; /* * Steps through buffer one byte at a time, calculates reflected * crc using table. */ static int chksum_init(struct shash_desc *desc) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = mctx->key; return 0; } /* * Setting the seed allows arbitrary accumulators and flexible XOR policy * If your algorithm starts with ~0, then XOR with ~0 before you set * the seed. */ static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct chksum_ctx *mctx = crypto_shash_ctx(tfm); if (keylen != sizeof(mctx->key)) return -EINVAL; mctx->key = get_unaligned_le32(key); return 0; } static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = crc32c_base(ctx->crc, data, length); return 0; } static int chksum_update_arch(struct shash_desc *desc, const u8 *data, unsigned int length) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); ctx->crc = crc32c(ctx->crc, data, length); return 0; } static int chksum_final(struct shash_desc *desc, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); put_unaligned_le32(~ctx->crc, out); return 0; } static int __chksum_finup(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { put_unaligned_le32(~crc32c_base(*crcp, data, len), out); return 0; } static int __chksum_finup_arch(u32 *crcp, const u8 *data, unsigned int len, u8 *out) { put_unaligned_le32(~crc32c(*crcp, data, len), out); return 0; } static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); return __chksum_finup(&ctx->crc, data, len, out); } static int chksum_finup_arch(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); return __chksum_finup_arch(&ctx->crc, data, len, out); } static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); return __chksum_finup(&mctx->key, data, length, out); } static int chksum_digest_arch(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); return __chksum_finup_arch(&mctx->key, data, length, out); } static int crc32c_cra_init(struct crypto_tfm *tfm) { struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); mctx->key = ~0; return 0; } static struct shash_alg algs[] = {{ .digestsize = CHKSUM_DIGEST_SIZE, .setkey = chksum_setkey, .init = chksum_init, .update = chksum_update, .final = chksum_final, .finup = chksum_finup, .digest = chksum_digest, .descsize = sizeof(struct chksum_desc_ctx), .base.cra_name = "crc32c", .base.cra_driver_name = "crc32c-generic", .base.cra_priority = 100, .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .base.cra_blocksize = CHKSUM_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct chksum_ctx), .base.cra_module = THIS_MODULE, .base.cra_init = crc32c_cra_init, }, { .digestsize = CHKSUM_DIGEST_SIZE, .setkey = chksum_setkey, .init = chksum_init, .update = chksum_update_arch, .final = chksum_final, .finup = chksum_finup_arch, .digest = chksum_digest_arch, .descsize = sizeof(struct chksum_desc_ctx), .base.cra_name = "crc32c", .base.cra_driver_name = "crc32c-" __stringify(ARCH), .base.cra_priority = 150, .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .base.cra_blocksize = CHKSUM_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct chksum_ctx), .base.cra_module = THIS_MODULE, .base.cra_init = crc32c_cra_init, }}; static int num_algs; static int __init crc32c_mod_init(void) { /* register the arch flavor only if it differs from the generic one */ num_algs = 1 + ((crc32_optimizations() & CRC32C_OPTIMIZATION) != 0); return crypto_register_shashes(algs, num_algs); } static void __exit crc32c_mod_fini(void) { crypto_unregister_shashes(algs, num_algs); } module_init(crc32c_mod_init); module_exit(crc32c_mod_fini); MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("crc32c"); MODULE_ALIAS_CRYPTO("crc32c-generic"); |
| 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 | /* netfilter.c: look after the filters for various protocols. * Heavily influenced by the old firewall.c by David Bonn and Alan Cox. * * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any * way. * * This code is GPL. */ #include <linux/kernel.h> #include <linux/netfilter.h> #include <net/protocol.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/netfilter_ipv6.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netfilter/nf_queue.h> #include <net/sock.h> #include "nf_internals.h" const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); #ifdef CONFIG_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif static DEFINE_MUTEX(nf_hook_mutex); /* max hooks per family/hooknum */ #define MAX_HOOK_COUNT 1024 #define nf_entry_dereference(e) \ rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) static struct nf_hook_entries *allocate_hook_entries_size(u16 num) { struct nf_hook_entries *e; size_t alloc = sizeof(*e) + sizeof(struct nf_hook_entry) * num + sizeof(struct nf_hook_ops *) * num + sizeof(struct nf_hook_entries_rcu_head); if (num == 0) return NULL; e = kvzalloc(alloc, GFP_KERNEL_ACCOUNT); if (e) e->num_hook_entries = num; return e; } static void __nf_hook_entries_free(struct rcu_head *h) { struct nf_hook_entries_rcu_head *head; head = container_of(h, struct nf_hook_entries_rcu_head, head); kvfree(head->allocation); } static void nf_hook_entries_free(struct nf_hook_entries *e) { struct nf_hook_entries_rcu_head *head; struct nf_hook_ops **ops; unsigned int num; if (!e) return; num = e->num_hook_entries; ops = nf_hook_entries_get_hook_ops(e); head = (void *)&ops[num]; head->allocation = e; call_rcu(&head->head, __nf_hook_entries_free); } static unsigned int accept_all(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return NF_ACCEPT; /* ACCEPT makes nf_hook_slow call next hook */ } static const struct nf_hook_ops dummy_ops = { .hook = accept_all, .priority = INT_MIN, }; static struct nf_hook_entries * nf_hook_entries_grow(const struct nf_hook_entries *old, const struct nf_hook_ops *reg) { unsigned int i, alloc_entries, nhooks, old_entries; struct nf_hook_ops **orig_ops = NULL; struct nf_hook_ops **new_ops; struct nf_hook_entries *new; bool inserted = false; alloc_entries = 1; old_entries = old ? old->num_hook_entries : 0; if (old) { orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old_entries; i++) { if (orig_ops[i] != &dummy_ops) alloc_entries++; /* Restrict BPF hook type to force a unique priority, not * shared at attach time. * * This is mainly to avoid ordering issues between two * different bpf programs, this doesn't prevent a normal * hook at same priority as a bpf one (we don't want to * prevent defrag, conntrack, iptables etc from attaching). */ if (reg->priority == orig_ops[i]->priority && reg->hook_ops_type == NF_HOOK_OP_BPF) return ERR_PTR(-EBUSY); } } if (alloc_entries > MAX_HOOK_COUNT) return ERR_PTR(-E2BIG); new = allocate_hook_entries_size(alloc_entries); if (!new) return ERR_PTR(-ENOMEM); new_ops = nf_hook_entries_get_hook_ops(new); i = 0; nhooks = 0; while (i < old_entries) { if (orig_ops[i] == &dummy_ops) { ++i; continue; } if (inserted || reg->priority > orig_ops[i]->priority) { new_ops[nhooks] = (void *)orig_ops[i]; new->hooks[nhooks] = old->hooks[i]; i++; } else { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; inserted = true; } nhooks++; } if (!inserted) { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; } return new; } static void hooks_validate(const struct nf_hook_entries *hooks) { #ifdef CONFIG_DEBUG_MISC struct nf_hook_ops **orig_ops; int prio = INT_MIN; size_t i = 0; orig_ops = nf_hook_entries_get_hook_ops(hooks); for (i = 0; i < hooks->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; WARN_ON(orig_ops[i]->priority < prio); if (orig_ops[i]->priority > prio) prio = orig_ops[i]->priority; } #endif } int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *new_hooks; struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } EXPORT_SYMBOL_GPL(nf_hook_entries_insert_raw); /* * __nf_hook_entries_try_shrink - try to shrink hook array * * @old -- current hook blob at @pp * @pp -- location of hook blob * * Hook unregistration must always succeed, so to-be-removed hooks * are replaced by a dummy one that will just move to next hook. * * This counts the current dummy hooks, attempts to allocate new blob, * copies the live hooks, then replaces and discards old one. * * return values: * * Returns address to free, or NULL. */ static void *__nf_hook_entries_try_shrink(struct nf_hook_entries *old, struct nf_hook_entries __rcu **pp) { unsigned int i, j, skip = 0, hook_entries; struct nf_hook_entries *new = NULL; struct nf_hook_ops **orig_ops; struct nf_hook_ops **new_ops; if (WARN_ON_ONCE(!old)) return NULL; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) skip++; } /* if skip == hook_entries all hooks have been removed */ hook_entries = old->num_hook_entries; if (skip == hook_entries) goto out_assign; if (skip == 0) return NULL; hook_entries -= skip; new = allocate_hook_entries_size(hook_entries); if (!new) return NULL; new_ops = nf_hook_entries_get_hook_ops(new); for (i = 0, j = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; new->hooks[j] = old->hooks[i]; new_ops[j] = (void *)orig_ops[i]; j++; } hooks_validate(new); out_assign: rcu_assign_pointer(*pp, new); return old; } static struct nf_hook_entries __rcu ** nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, struct net_device *dev) { switch (pf) { case NFPROTO_NETDEV: break; #ifdef CONFIG_NETFILTER_FAMILY_ARP case NFPROTO_ARP: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_arp) <= hooknum)) return NULL; return net->nf.hooks_arp + hooknum; #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum)) return NULL; return net->nf.hooks_bridge + hooknum; #endif #ifdef CONFIG_NETFILTER_INGRESS case NFPROTO_INET: if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS)) return NULL; if (!dev || dev_net(dev) != net) { WARN_ON_ONCE(1); return NULL; } return &dev->nf_hooks_ingress; #endif case NFPROTO_IPV4: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum)) return NULL; return net->nf.hooks_ipv4 + hooknum; case NFPROTO_IPV6: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; default: WARN_ON_ONCE(1); return NULL; } #ifdef CONFIG_NETFILTER_INGRESS if (hooknum == NF_NETDEV_INGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } #endif #ifdef CONFIG_NETFILTER_EGRESS if (hooknum == NF_NETDEV_EGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_egress; } #endif WARN_ON_ONCE(1); return NULL; } static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, int hooknum) { #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == hooknum) return -EOPNOTSUPP; #endif if (reg->hooknum != hooknum || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; return 0; } static inline bool __maybe_unused nf_ingress_hook(const struct nf_hook_ops *reg, int pf) { if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) return true; return false; } static inline bool __maybe_unused nf_egress_hook(const struct nf_hook_ops *reg, int pf) { return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; } static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_inc(&nf_hooks_needed[pf][hooknum]); #endif } static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_dec(&nf_hooks_needed[pf][hooknum]); #endif } static int __nf_register_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries *p, *new_hooks; struct nf_hook_entries __rcu **pp; int err; switch (pf) { case NFPROTO_NETDEV: #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == NF_NETDEV_INGRESS) return -EOPNOTSUPP; #endif #ifndef CONFIG_NETFILTER_EGRESS if (reg->hooknum == NF_NETDEV_EGRESS) return -EOPNOTSUPP; #endif if ((reg->hooknum != NF_NETDEV_INGRESS && reg->hooknum != NF_NETDEV_EGRESS) || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) break; err = nf_ingress_check(net, reg, NF_INET_INGRESS); if (err < 0) return err; break; } pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return -EINVAL; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (!IS_ERR(new_hooks)) { hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); #endif #ifdef CONFIG_NETFILTER_EGRESS if (nf_egress_hook(reg, pf)) net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } /* * nf_remove_net_hook - remove a hook from blob * * @oldp: current address of hook blob * @unreg: hook to unregister * * This cannot fail, hook unregistration must always succeed. * Therefore replace the to-be-removed hook with a dummy hook. */ static bool nf_remove_net_hook(struct nf_hook_entries *old, const struct nf_hook_ops *unreg) { struct nf_hook_ops **orig_ops; unsigned int i; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] != unreg) continue; WRITE_ONCE(old->hooks[i].hook, accept_all); WRITE_ONCE(orig_ops[i], (void *)&dummy_ops); return true; } return false; } static void __nf_unregister_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries __rcu **pp; struct nf_hook_entries *p; pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); if (WARN_ON_ONCE(!p)) { mutex_unlock(&nf_hook_mutex); return; } if (nf_remove_net_hook(p, reg)) { #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); #endif #ifdef CONFIG_NETFILTER_EGRESS if (nf_egress_hook(reg, pf)) net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); } p = __nf_hook_entries_try_shrink(p, pp); mutex_unlock(&nf_hook_mutex); if (!p) return; nf_queue_nf_hook_drop(net); nf_hook_entries_free(p); } void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { __nf_unregister_net_hook(net, NFPROTO_INET, reg); } else { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); } } else { __nf_unregister_net_hook(net, reg->pf, reg); } } EXPORT_SYMBOL(nf_unregister_net_hook); void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); if (nf_remove_net_hook(p, reg)) { p = __nf_hook_entries_try_shrink(p, pp); nf_hook_entries_free(p); } } EXPORT_SYMBOL_GPL(nf_hook_entries_delete_raw); int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { int err; if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { err = __nf_register_net_hook(net, NFPROTO_INET, reg); if (err < 0) return err; } else { err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); if (err < 0) return err; err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); if (err < 0) { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); return err; } } } else { err = __nf_register_net_hook(net, reg->pf, reg); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(nf_register_net_hook); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_register_net_hook(net, ®[i]); if (err) goto err; } return err; err: if (i > 0) nf_unregister_net_hooks(net, reg, i); return err; } EXPORT_SYMBOL(nf_register_net_hooks); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int hookcount) { unsigned int i; for (i = 0; i < hookcount; i++) nf_unregister_net_hook(net, ®[i]); } EXPORT_SYMBOL(nf_unregister_net_hooks); /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int s) { unsigned int verdict; int ret; for (; s < e->num_hook_entries; s++) { verdict = nf_hook_entry_hookfn(&e->hooks[s], skb, state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: break; case NF_DROP: kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; return ret; case NF_QUEUE: ret = nf_queue(skb, state, s, verdict); if (ret == 1) continue; return ret; case NF_STOLEN: return NF_DROP_GETERR(verdict); default: WARN_ON_ONCE(1); return 0; } } return 1; } EXPORT_SYMBOL(nf_hook_slow); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e) { struct sk_buff *skb, *next; LIST_HEAD(sublist); int ret; list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); ret = nf_hook_slow(skb, state, e, 0); if (ret == 1) list_add_tail(&skb->list, &sublist); } /* Put passed packets back on main list */ list_splice(&sublist, head); } EXPORT_SYMBOL(nf_hook_slow_list); /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ const struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); const struct nf_defrag_hook __rcu *nf_defrag_v4_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_defrag_v4_hook); const struct nf_defrag_hook __rcu *nf_defrag_v6_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_defrag_v6_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) u8 nf_ctnetlink_has_listener; EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener); const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); /* This does not belong here, but locally generated errors need it if connection * tracking in use: without this, connection may not be in hash table, and hence * manufactured ICMP or RST packets will not be associated with it. */ void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; if (skb->_nfct) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->attach(new, skb); rcu_read_unlock(); } } EXPORT_SYMBOL(nf_ct_attach); void nf_conntrack_destroy(struct nf_conntrack *nfct) { const struct nf_ct_hook *ct_hook; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->destroy(nfct); rcu_read_unlock(); WARN_ON(!ct_hook); } EXPORT_SYMBOL(nf_conntrack_destroy); void nf_ct_set_closing(struct nf_conntrack *nfct) { const struct nf_ct_hook *ct_hook; if (!nfct) return; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->set_closing(nfct); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_ct_set_closing); bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; bool ret = false; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ret = ct_hook->get_tuple_skb(dst_tuple, skb); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(nf_ct_get_tuple_skb); /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, .dir = NF_CT_DEFAULT_ZONE_DIR, }; EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ static void __net_init __netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { int h; for (h = 0; h < max; h++) RCU_INIT_POINTER(e[h], NULL); } static int __net_init netfilter_net_init(struct net *net) { __netfilter_net_init(net->nf.hooks_ipv4, ARRAY_SIZE(net->nf.hooks_ipv4)); __netfilter_net_init(net->nf.hooks_ipv6, ARRAY_SIZE(net->nf.hooks_ipv6)); #ifdef CONFIG_NETFILTER_FAMILY_ARP __netfilter_net_init(net->nf.hooks_arp, ARRAY_SIZE(net->nf.hooks_arp)); #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); if (!net->nf.proc_netfilter) { if (!net_eq(net, &init_net)) pr_err("cannot create netfilter proc entry"); return -ENOMEM; } #endif return 0; } static void __net_exit netfilter_net_exit(struct net *net) { remove_proc_entry("netfilter", net->proc_net); } static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, }; int __init netfilter_init(void) { int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) goto err; #ifdef CONFIG_LWTUNNEL ret = netfilter_lwtunnel_init(); if (ret < 0) goto err_lwtunnel_pernet; #endif ret = netfilter_log_init(); if (ret < 0) goto err_log_pernet; return 0; err_log_pernet: #ifdef CONFIG_LWTUNNEL netfilter_lwtunnel_fini(); err_lwtunnel_pernet: #endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; } |
| 3 1 1 53 53 21 21 21 21 21 21 21 23 23 3 18 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/hexdump.c */ #include <linux/types.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/minmax.h> #include <linux/export.h> #include <linux/unaligned.h> const char hex_asc[] = "0123456789abcdef"; EXPORT_SYMBOL(hex_asc); const char hex_asc_upper[] = "0123456789ABCDEF"; EXPORT_SYMBOL(hex_asc_upper); /** * hex_to_bin - convert a hex digit to its real value * @ch: ascii character represents hex digit * * hex_to_bin() converts one hex digit to its actual value or -1 in case of bad * input. * * This function is used to load cryptographic keys, so it is coded in such a * way that there are no conditions or memory accesses that depend on data. * * Explanation of the logic: * (ch - '9' - 1) is negative if ch <= '9' * ('0' - 1 - ch) is negative if ch >= '0' * we "and" these two values, so the result is negative if ch is in the range * '0' ... '9' * we are only interested in the sign, so we do a shift ">> 8"; note that right * shift of a negative value is implementation-defined, so we cast the * value to (unsigned) before the shift --- we have 0xffffff if ch is in * the range '0' ... '9', 0 otherwise * we "and" this value with (ch - '0' + 1) --- we have a value 1 ... 10 if ch is * in the range '0' ... '9', 0 otherwise * we add this value to -1 --- we have a value 0 ... 9 if ch is in the range '0' * ... '9', -1 otherwise * the next line is similar to the previous one, but we need to decode both * uppercase and lowercase letters, so we use (ch & 0xdf), which converts * lowercase to uppercase */ int hex_to_bin(unsigned char ch) { unsigned char cu = ch & 0xdf; return -1 + ((ch - '0' + 1) & (unsigned)((ch - '9' - 1) & ('0' - 1 - ch)) >> 8) + ((cu - 'A' + 11) & (unsigned)((cu - 'F' - 1) & ('A' - 1 - cu)) >> 8); } EXPORT_SYMBOL(hex_to_bin); /** * hex2bin - convert an ascii hexadecimal string to its binary representation * @dst: binary result * @src: ascii hexadecimal string * @count: result length * * Return 0 on success, -EINVAL in case of bad input. */ int hex2bin(u8 *dst, const char *src, size_t count) { while (count--) { int hi, lo; hi = hex_to_bin(*src++); if (unlikely(hi < 0)) return -EINVAL; lo = hex_to_bin(*src++); if (unlikely(lo < 0)) return -EINVAL; *dst++ = (hi << 4) | lo; } return 0; } EXPORT_SYMBOL(hex2bin); /** * bin2hex - convert binary data to an ascii hexadecimal string * @dst: ascii hexadecimal result * @src: binary data * @count: binary data length */ char *bin2hex(char *dst, const void *src, size_t count) { const unsigned char *_src = src; while (count--) dst = hex_byte_pack(dst, *_src++); return dst; } EXPORT_SYMBOL(bin2hex); /** * hex_dump_to_buffer - convert a blob of data to "hex ASCII" in memory * @buf: data blob to dump * @len: number of bytes in the @buf * @rowsize: number of bytes to print per line; must be 16 or 32 * @groupsize: number of bytes to print at a time (1, 2, 4, 8; default = 1) * @linebuf: where to put the converted data * @linebuflen: total size of @linebuf, including space for terminating NUL * @ascii: include ASCII after the hex output * * hex_dump_to_buffer() works on one "line" of output at a time, i.e., * 16 or 32 bytes of input data converted to hex + ASCII output. * * Given a buffer of u8 data, hex_dump_to_buffer() converts the input data * to a hex + ASCII dump at the supplied memory location. * The converted output is always NUL-terminated. * * E.g.: * hex_dump_to_buffer(frame->data, frame->len, 16, 1, * linebuf, sizeof(linebuf), true); * * example output buffer: * 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f @ABCDEFGHIJKLMNO * * Return: * The amount of bytes placed in the buffer without terminating NUL. If the * output was truncated, then the return value is the number of bytes * (excluding the terminating NUL) which would have been written to the final * string if enough space had been available. */ int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize, char *linebuf, size_t linebuflen, bool ascii) { const u8 *ptr = buf; int ngroups; u8 ch; int j, lx = 0; int ascii_column; int ret; if (rowsize != 16 && rowsize != 32) rowsize = 16; if (len > rowsize) /* limit to one line at a time */ len = rowsize; if (!is_power_of_2(groupsize) || groupsize > 8) groupsize = 1; if ((len % groupsize) != 0) /* no mixed size output */ groupsize = 1; ngroups = len / groupsize; ascii_column = rowsize * 2 + rowsize / groupsize + 1; if (!linebuflen) goto overflow1; if (!len) goto nil; if (groupsize == 8) { const u64 *ptr8 = buf; for (j = 0; j < ngroups; j++) { ret = snprintf(linebuf + lx, linebuflen - lx, "%s%16.16llx", j ? " " : "", get_unaligned(ptr8 + j)); if (ret >= linebuflen - lx) goto overflow1; lx += ret; } } else if (groupsize == 4) { const u32 *ptr4 = buf; for (j = 0; j < ngroups; j++) { ret = snprintf(linebuf + lx, linebuflen - lx, "%s%8.8x", j ? " " : "", get_unaligned(ptr4 + j)); if (ret >= linebuflen - lx) goto overflow1; lx += ret; } } else if (groupsize == 2) { const u16 *ptr2 = buf; for (j = 0; j < ngroups; j++) { ret = snprintf(linebuf + lx, linebuflen - lx, "%s%4.4x", j ? " " : "", get_unaligned(ptr2 + j)); if (ret >= linebuflen - lx) goto overflow1; lx += ret; } } else { for (j = 0; j < len; j++) { if (linebuflen < lx + 2) goto overflow2; ch = ptr[j]; linebuf[lx++] = hex_asc_hi(ch); if (linebuflen < lx + 2) goto overflow2; linebuf[lx++] = hex_asc_lo(ch); if (linebuflen < lx + 2) goto overflow2; linebuf[lx++] = ' '; } if (j) lx--; } if (!ascii) goto nil; while (lx < ascii_column) { if (linebuflen < lx + 2) goto overflow2; linebuf[lx++] = ' '; } for (j = 0; j < len; j++) { if (linebuflen < lx + 2) goto overflow2; ch = ptr[j]; linebuf[lx++] = (isascii(ch) && isprint(ch)) ? ch : '.'; } nil: linebuf[lx] = '\0'; return lx; overflow2: linebuf[lx++] = '\0'; overflow1: return ascii ? ascii_column + len : (groupsize * 2 + 1) * ngroups - 1; } EXPORT_SYMBOL(hex_dump_to_buffer); #ifdef CONFIG_PRINTK /** * print_hex_dump - print a text hex dump to syslog for a binary blob of data * @level: kernel log level (e.g. KERN_DEBUG) * @prefix_str: string to prefix each line with; * caller supplies trailing spaces for alignment if desired * @prefix_type: controls whether prefix of an offset, address, or none * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) * @rowsize: number of bytes to print per line; must be 16 or 32 * @groupsize: number of bytes to print at a time (1, 2, 4, 8; default = 1) * @buf: data blob to dump * @len: number of bytes in the @buf * @ascii: include ASCII after the hex output * * Given a buffer of u8 data, print_hex_dump() prints a hex + ASCII dump * to the kernel log at the specified kernel log level, with an optional * leading prefix. * * print_hex_dump() works on one "line" of output at a time, i.e., * 16 or 32 bytes of input data converted to hex + ASCII output. * print_hex_dump() iterates over the entire input @buf, breaking it into * "line size" chunks to format and print. * * E.g.: * print_hex_dump(KERN_DEBUG, "raw data: ", DUMP_PREFIX_ADDRESS, * 16, 1, frame->data, frame->len, true); * * Example output using %DUMP_PREFIX_OFFSET and 1-byte mode: * 0009ab42: 40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f @ABCDEFGHIJKLMNO * Example output using %DUMP_PREFIX_ADDRESS and 4-byte mode: * ffffffff88089af0: 73727170 77767574 7b7a7978 7f7e7d7c pqrstuvwxyz{|}~. */ void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { const u8 *ptr = buf; int i, linelen, remaining = len; unsigned char linebuf[32 * 3 + 2 + 32 + 1]; if (rowsize != 16 && rowsize != 32) rowsize = 16; for (i = 0; i < len; i += rowsize) { linelen = min(remaining, rowsize); remaining -= rowsize; hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize, linebuf, sizeof(linebuf), ascii); switch (prefix_type) { case DUMP_PREFIX_ADDRESS: printk("%s%s%p: %s\n", level, prefix_str, ptr + i, linebuf); break; case DUMP_PREFIX_OFFSET: printk("%s%s%.8x: %s\n", level, prefix_str, i, linebuf); break; default: printk("%s%s%s\n", level, prefix_str, linebuf); break; } } } EXPORT_SYMBOL(print_hex_dump); #endif /* defined(CONFIG_PRINTK) */ |
| 86 4 69 34 913 942 70 921 7 30 8 16 44 4 44 958 958 939 28 26 911 912 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_H #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> #include <uapi/linux/filter.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> #include <linux/mm_types.h> #include <linux/wait.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/stddef.h> #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> #include <linux/cfi.h> #include <asm/rqspinlock.h> struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; struct bpf_arena; struct sock; struct seq_file; struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; struct bpf_token; struct user_namespace; struct super_block; struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); typedef unsigned int (*bpf_func_t)(const void *, const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; }; /* map is generic key/value storage optionally accessible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); long (*map_delete_elem)(struct bpf_map *map, void *key); long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure * an inner map can be inserted to an outer map. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ bool (*map_meta_equal)(const struct bpf_map *meta0, const struct bpf_map *meta1); int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); u64 (*map_mem_usage)(const struct bpf_map *map); /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; enum { /* Support at most 11 fields in a BTF type */ BTF_FIELDS_MAX = 11, }; enum btf_field_type { BPF_SPIN_LOCK = (1 << 0), BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR_PERCPU = (1 << 4), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, BPF_LIST_HEAD = (1 << 5), BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), BPF_UPTR = (1 << 11), BPF_RES_SPIN_LOCK = (1 << 12), }; typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { struct btf *btf; struct module *module; /* dtor used if btf_is_kernel(btf), otherwise the type is * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used */ btf_dtor_kfunc_t dtor; u32 btf_id; }; struct btf_field_graph_root { struct btf *btf; u32 value_btf_id; u32 node_offset; struct btf_record *value_rec; }; struct btf_field { u32 offset; u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; struct btf_field_graph_root graph_root; }; }; struct btf_record { u32 cnt; u32 field_mask; int spin_lock_off; int res_spin_lock_off; int timer_off; int wq_off; int refcount_off; struct btf_field fields[]; }; /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ struct bpf_rb_node_kern { struct rb_node rb_node; void *owner; } __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ struct bpf_list_node_kern { struct list_head list_head; void *owner; } __attribute__((aligned(8))); struct bpf_map { const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; #endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; u32 id; struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; struct mutex freeze_mutex; atomic64_t refcnt; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program * that is going to use this map or by the first program which FD is * stored in the map to make sure that all callers and callees have the * same prog type, JITed flag and xdp_has_frags flag. */ struct { const struct btf_type *attach_func_proto; spinlock_t lock; enum bpf_prog_type type; bool jited; bool xdp_has_frags; } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; bool free_after_rcu_gp; atomic64_t sleepable_refcnt; s64 __percpu *elem_count; }; static inline const char *btf_field_type_name(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return "bpf_spin_lock"; case BPF_RES_SPIN_LOCK: return "bpf_res_spin_lock"; case BPF_TIMER: return "bpf_timer"; case BPF_WORKQUEUE: return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; case BPF_UPTR: return "uptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; case BPF_RB_ROOT: return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; } } #if IS_ENABLED(CONFIG_DEBUG_KERNEL) #define BPF_WARN_ONCE(cond, format...) WARN_ONCE(cond, format) #else #define BPF_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return sizeof(struct bpf_spin_lock); case BPF_RES_SPIN_LOCK: return sizeof(struct bpf_res_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); case BPF_WORKQUEUE: return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); case BPF_RB_ROOT: return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline u32 btf_field_type_align(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return __alignof__(struct bpf_spin_lock); case BPF_RES_SPIN_LOCK: return __alignof__(struct bpf_res_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); case BPF_WORKQUEUE: return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); case BPF_RB_ROOT: return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) { memset(addr, 0, field->size); switch (field->type) { case BPF_REFCOUNT: refcount_set((refcount_t *)addr, 1); break; case BPF_RB_NODE: RB_CLEAR_NODE((struct rb_node *)addr); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: INIT_LIST_HEAD((struct list_head *)addr); break; case BPF_RB_ROOT: /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: break; default: WARN_ON_ONCE(1); return; } } static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) return false; return rec->field_mask & type; } static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being * used in parallel by a bpf program or bpf syscall, otherwise the access from * the bpf program or bpf syscall may be corrupted by the reinitialization, * leading to weird problems. Even 'dst' is newly-allocated from bpf memory * allocator, it is still possible for 'dst' to be used in parallel by a bpf * program or bpf syscall. */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) { const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) data_race(*ldst++ = *lsrc++); } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(size, 8)); else memcpy(dst, src, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); curr_off += rec->fields[i].size + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src) { unsigned long *src_uptr, *dst_uptr; const struct btf_field *field; int i; if (!btf_record_has_field(rec, BPF_UPTR)) return; for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { if (field->type != BPF_UPTR) continue; src_uptr = src + field->offset; dst_uptr = dst + field->offset; swap(*src_uptr, *dst_uptr); } } static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { memset(dst, 0, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); curr_off += rec->fields[i].size + sz; } memset(dst + curr_off, 0, size - curr_off); } static inline void zero_map_value(struct bpf_map *map, void *dst) { bpf_obj_memzero(map->record, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock); u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena); u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { int (*map_get_next_key)(struct bpf_offloaded_map *map, void *key, void *next_key); int (*map_lookup_elem)(struct bpf_offloaded_map *map, void *key, void *value); int (*map_update_elem)(struct bpf_offloaded_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); }; struct bpf_offloaded_map { struct bpf_map map; struct net_device *netdev; const struct bpf_map_dev_ops *dev_ops; void *dev_priv; struct list_head offloads; }; static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) { return container_of(map, struct bpf_offloaded_map, map); } static inline bool bpf_map_offload_neutral(const struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && map->ops->map_seq_show_elem; } int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); bool bpf_map_meta_equal(const struct bpf_map *meta0, const struct bpf_map *meta1); extern const struct bpf_map_ops bpf_map_offload_ops; /* bpf_type_flag contains a set of flags that are applicable to the values of * arg_type, ret_type and reg_type. For example, a pointer value may be null, * or a memory is read-only. We classify types into two categories: base types * and extended types. Extended types are base types combined with a type flag. * * Currently there are no more than 32 base types in arg_type, ret_type and * reg_types. */ #define BPF_BASE_TYPE_BITS 8 enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), /* MEM is read-only. When applied on bpf_arg, it indicates the arg is * compatible with both mutable and immutable memory. */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), /* MEM points to BPF ring buffer reservation. */ MEM_RINGBUF = BIT(2 + BPF_BASE_TYPE_BITS), /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In * order to drop this tag, it must be passed into bpf_per_cpu_ptr() * or bpf_this_cpu_ptr(), which will return the pointer corresponding * to the specified cpu. */ MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), /* Indicates that the argument will be released. */ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark * unreferenced and referenced kptr loaded from map value using a load * instruction, so that they can only be dereferenced but not escape the * BPF program into the kernel (i.e. cannot be passed as arguments to * kfunc or bpf helpers). */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), /* DYNPTR points to a kernel-produced ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), /* MEM is of an allocated object of type in program BTF. This is used to * tag PTR_TO_BTF_ID allocated using bpf_obj_new. */ MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), /* PTR was passed from the kernel in a trusted context, and may be * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions. * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above. * PTR_UNTRUSTED refers to a kptr that was read directly from a map * without invoking bpf_kptr_xchg(). What we really need to know is * whether a pointer is safe to pass to a kfunc or BPF helper function. * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF * helpers, they do not cover all possible instances of unsafe * pointers. For example, a pointer that was obtained from walking a * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the * fact that it may be NULL, invalid, etc. This is due to backwards * compatibility requirements, as this was the behavior that was first * introduced when kptrs were added. The behavior is now considered * deprecated, and PTR_UNTRUSTED will eventually be removed. * * PTR_TRUSTED, on the other hand, is a pointer that the kernel * guarantees to be valid and safe to pass to kfuncs and BPF helpers. * For example, pointers passed to tracepoint arguments are considered * PTR_TRUSTED, as are pointers that are passed to struct_ops * callbacks. As alluded to above, pointers that are obtained from * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a * struct task_struct *task is PTR_TRUSTED, then accessing * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored * in a BPF register. Similarly, pointers passed to certain programs * types such as kretprobes are not guaranteed to be valid, as they may * for example contain an object that was recently freed. */ PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), /* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */ MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), /* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning. * Currently only valid for linked-list and rbtree nodes. If the nodes * have a bpf_refcount_field, they must be tagged MEM_RCU as well. */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), /* DYNPTR points to sk_buff */ DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), /* Memory must be aligned on some architectures, used in combination with * MEM_FIXED_SIZE. */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), /* MEM is being written to, often combined with MEM_UNINIT. Non-presence * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the * MEM_UNINIT means that memory needs to be initialized since it is also * read. */ MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; #define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ | DYNPTR_TYPE_XDP) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) /* Max number of all types. */ #define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ /* the following constraints used to prototype * bpf_map_lookup/update/delete_elem() functions */ ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ /* Used to prototype bpf_memcmp() and other functions that access data * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ ARG_PTR_TO_ARENA, ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ ARG_KPTR_XCHG_DEST, /* pointer to destination that kptrs are bpf_kptr_xchg'd into */ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* Pointer to memory does not need to be initialized, since helper function * fills all bytes or clears them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ RET_PTR_TO_MEM, /* returns a pointer to memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, /* Extended ret_types. */ RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL * instructions after verifying */ struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; bool pkt_access; bool might_sleep; /* set to true if helper follows contract for llvm * attribute bpf_fastcall: * - void functions do not scratch r0 * - functions taking N arguments scratch only registers r1-rN */ bool allow_fastcall; enum bpf_return_type ret_type; union { struct { enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; enum bpf_arg_type arg3_type; enum bpf_arg_type arg4_type; enum bpf_arg_type arg5_type; }; enum bpf_arg_type arg_type[5]; }; union { struct { u32 *arg1_btf_id; u32 *arg2_btf_id; u32 *arg3_btf_id; u32 *arg4_btf_id; u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; struct { size_t arg1_size; size_t arg2_size; size_t arg3_size; size_t arg4_size; size_t arg5_size; }; size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is * the first argument to eBPF programs. * For socket filters: 'struct bpf_context *' == 'struct sk_buff *' */ struct bpf_context; enum bpf_access_type { BPF_READ = 1, BPF_WRITE = 2 }; /* types of values stored in eBPF registers */ /* Pointer types represent: * pointer * pointer + imm * pointer + (u16) var * pointer + (u16) var + imm * if (range > 0) then [ptr, ptr + range - off) is safe to access * if (id > 0) means that some 'var' was added * if (off > 0) means that 'imm' was added */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need * to be null checked by the BPF program. This does not imply the * pointer is _not_ null and in practice this can easily be a null * pointer when reading pointer chains. The assumption is program * context will handle null pointer dereference typically via fault * handling. The verifier must keep this in mind and can make no * assumptions about null or non-null when doing branch analysis. * Further, when passed into helpers the helpers can not, without * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_ARENA, PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; bool is_ldsx; union { int ctx_field_size; struct { struct btf *btf; u32 btf_id; u32 ref_obj_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ bool is_retval; /* is accessing function return value ? */ }; static inline void bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) { aux->ctx_field_size = size; } static bool bpf_is_ldimm64(const struct bpf_insn *insn) { return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } /* Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an * atomic load or store, and false if it is a read-modify-write instruction. */ static inline bool bpf_atomic_is_load_store(const struct bpf_insn *atomic_insn) { switch (atomic_insn->imm) { case BPF_LOAD_ACQ: case BPF_STORE_REL: return true; default: return false; } } struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); }; struct bpf_reg_state; struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto * (*get_func_proto)(enum bpf_func_id func_id, const struct bpf_prog *prog); /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); int (*gen_epilogue)(struct bpf_insn *insn, const struct bpf_prog *prog, s16 ctx_stack_off); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); }; struct bpf_prog_offload_ops { /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); /* verifier optimization callbacks (called after .finalize) */ int (*replace_insn)(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; bool opt_failed; void *jited_image; u32 jited_len; }; enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ #define MAX_BPF_FUNC_ARGS 12 /* The maximum number of arguments passed through registers * a single function may have. */ #define MAX_BPF_FUNC_REG_ARGS 5 /* The argument is a structure. */ #define BTF_FMODEL_STRUCT_ARG BIT(0) /* The argument is signed. */ #define BTF_FMODEL_SIGNED_ARG BIT(1) struct btf_func_model { u8 ret_size; u8 ret_flags; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; u8 arg_flags[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function * continue executing. This flag is used for fentry progs when there are no * fexit progs. */ #define BPF_TRAMP_F_RESTORE_REGS BIT(0) /* Call original function after fentry progs, but before fexit progs. * Makes sense for fentry/fexit, normal calls and indirect calls. */ #define BPF_TRAMP_F_CALL_ORIG BIT(1) /* Skip current frame and return to parent. Makes sense for fentry/fexit * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) /* Return the return value of fentry prog. Only used by bpf_struct_ops. */ #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Get original function from stack instead of from provided direct address. * Makes sense for trampolines with fexit or fmod_ret programs. */ #define BPF_TRAMP_F_ORIG_STACK BIT(5) /* This trampoline is on a function with another ftrace_ops with IPMODIFY, * e.g., a live patch. This flag is set and cleared by ftrace call backs, */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) /* Indicate that current trampoline is in a tail call context. Then, it has to * cache and restore tail_call_cnt to avoid infinite tail call loop. */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) /* * Indicate the trampoline should be suitable to receive indirect calls; * without this indirectly calling the generated code can result in #UD/#CP, * depending on the CFI options. * * Used by bpf_struct_ops. * * Incompatible with FENTRY usage, overloads @func_addr argument. */ #define BPF_TRAMP_F_INDIRECT BIT(8) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ enum { #if defined(__s390x__) BPF_MAX_TRAMP_LINKS = 27, #else BPF_MAX_TRAMP_LINKS = 38, #endif }; struct bpf_tramp_links { struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; int nr_links; }; struct bpf_tramp_run_ctx; /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS * fentry = a set of programs to run before returning from trampoline * * 2. replace nop at the function entry (kprobe + kretprobe equivalent) * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME * orig_call = fentry_ip + MCOUNT_INSN_SIZE * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function * * 3. replace direct call instruction anywhere in the function body * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) * With flags = 0 * fentry = a set of programs to run before returning from trampoline * With flags = BPF_TRAMP_F_CALL_ORIG * orig_call = original callback addr or direct function addr * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog); bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog); struct bpf_ksym { unsigned long start; unsigned long end; char name[KSYM_NAME_LEN]; struct list_head lnode; struct latch_tree_node tnode; bool prog; }; enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; struct bpf_tramp_image { void *image; int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; void *ip_epilogue; union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; struct ftrace_ops *fops; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; u32 flags; u64 key; struct { struct btf_func_model model; void *addr; bool ftrace_managed; } func; /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF * program by replacing one of its functions. func.addr is the address * of the function it replaced. */ struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; }; struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { struct bpf_prog *prog; refcount_t users; }; struct bpf_dispatcher { /* dispatcher mutex */ struct mutex mutex; void *func; struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; void *rw_image; u32 image_off; struct bpf_ksym ksym; #ifdef CONFIG_HAVE_STATIC_CALL struct static_call_key *sc_key; void *sc_tramp; #endif }; #ifndef __bpfcall #define __bpfcall __nocfi #endif static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) { return bpf_func(ctx, insnsi); } /* the implementation of the opaque uapi struct bpf_dynptr */ struct bpf_dynptr_kern { void *data; /* Size represents the number of usable bytes of dynptr data. * If for example the offset is at 4 for a local dynptr whose data is * of type u64, the number of usable bytes is 4. * * The upper 8 bits are reserved. It is as follows: * Bits 0 - 23 = size * Bits 24 - 30 = dynptr type * Bit 31 = whether dynptr is read-only */ u32 size; u32 offset; } __aligned(8); enum bpf_dynptr_type { BPF_DYNPTR_TYPE_INVALID, /* Points to memory that is local to the bpf program */ BPF_DYNPTR_TYPE_LOCAL, /* Underlying data is a ringbuf record */ BPF_DYNPTR_TYPE_RINGBUF, /* Underlying data is a sk_buff */ BPF_DYNPTR_TYPE_SKB, /* Underlying data is a xdp_buff */ BPF_DYNPTR_TYPE_XDP, }; int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src, u32 len, u64 flags); void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u32 offset, void *buffer__opt, u32 buffer__szk); static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) { u32 size = __bpf_dynptr_size(ptr); if (len > size || offset > size - len) return -E2BIG; return 0; } #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog); int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); /* * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn * indirection with a direct call to the bpf program. If the architecture does * not have STATIC_CALL, avoid a double-indirection. */ #ifdef CONFIG_HAVE_STATIC_CALL #define __BPF_DISPATCHER_SC_INIT(_name) \ .sc_key = &STATIC_CALL_KEY(_name), \ .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name), #define __BPF_DISPATCHER_SC(name) \ DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func) #define __BPF_DISPATCHER_CALL(name) \ static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func) #define __BPF_DISPATCHER_UPDATE(_d, _new) \ __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new)) #else #define __BPF_DISPATCHER_SC_INIT(name) #define __BPF_DISPATCHER_SC(name) #define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi) #define __BPF_DISPATCHER_UPDATE(_d, _new) #endif #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ .progs = {}, \ .num_progs = 0, \ .image = NULL, \ .image_off = 0, \ .ksym = { \ .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ __BPF_DISPATCHER_SC_INIT(_name##_call) \ } #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ { \ return __BPF_DISPATCHER_CALL(name); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_add(struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 size); void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) {} static inline bool is_bpf_image_address(unsigned long address) { return false; } static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) { return false; } #endif struct bpf_func_info_aux { u16 linkage; bool unreliable; bool called : 1; bool verified : 1; }; enum bpf_jit_poke_reason { BPF_POKE_REASON_TAIL_CALL, }; /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; void *aux; union { struct { struct bpf_map *map; u32 key; } tail_call; }; bool tailcall_target_stable; u8 adj_off; u16 reason; u32 insn_idx; }; /* reg_type info for ctx arguments */ struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; struct btf *btf; u32 btf_id; u32 ref_obj_id; bool refcounted; }; struct btf_mod_pair { struct btf *btf; struct module *module; }; struct bpf_kfunc_desc_tab; struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 attach_st_ops_member_off; u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; struct btf *attach_btf; struct bpf_ctx_arg_aux *ctx_arg_info; void __percpu *priv_stack_ptr; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; enum bpf_prog_type saved_dst_prog_type; enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool dev_bound; /* Program is bound to the netdev. */ bool offload_requested; /* Program is bound and offloaded to the netdev. */ bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool attach_tracing_prog; /* true if tracing another tracing program */ bool func_proto_unreliable; bool tail_call_reachable; bool xdp_has_frags; bool exception_cb; bool exception_boundary; bool is_extended; /* true if extended by freplace program */ bool jits_use_priv_stack; bool priv_stack_requested; bool changes_pkt_data; bool might_sleep; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */ /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; #ifdef CONFIG_FINEIBT struct bpf_ksym ksym_prefix; #endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; const struct bpf_struct_ops *st_ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. * The subprog can access its first linfo by * using the linfo_idx. */ struct bpf_line_info *linfo; /* jited_linfo is the jited addr of the linfo. It has a * one to one mapping to linfo: * jited_linfo[i] is the jited addr for the linfo[i]->insn_off. * Both the main and sub prog share the same jited_linfo. * The subprog can access its first jited_linfo by * using the linfo_idx. */ void **jited_linfo; u32 func_info_cnt; u32 nr_linfo; /* subprog can use linfo_idx to access its first linfo and * jited_linfo. * main prog always has linfo_idx == 0 */ u32 linfo_idx; struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { struct work_struct work; struct rcu_head rcu; }; }; struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */ sleepable:1; /* BPF program is sleepable */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_stats __percpu *stats; int __percpu *active; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ union { DECLARE_FLEX_ARRAY(struct sock_filter, insns); DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); }; }; struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; struct mutex poke_mutex; struct work_struct work; }; struct bpf_link { atomic64_t refcnt; u32 id; enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; /* whether BPF link itself has "sleepable" semantics, which can differ * from underlying BPF program having a "sleepable" semantics, as BPF * link's semantics is determined by target attach hook */ bool sleepable; /* rcu is used before freeing, work can be used to schedule that * RCU-based freeing before that, so they never overlap */ union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); /* deallocate link resources callback, called without RCU grace period * waiting */ void (*dealloc)(struct bpf_link *link); /* deallocate link resources callback, called after RCU grace period; * if either the underlying BPF program is sleepable or BPF link's * target hook is sleepable, we'll go through tasks trace RCU GP and * then "classic" RCU GP; this need for chaining tasks trace and * classic RCU GPs is designated by setting bpf_link->sleepable flag */ void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, struct bpf_map *old_map); __poll_t (*poll)(struct file *file, struct poll_table_struct *pts); }; struct bpf_tramp_link { struct bpf_link link; struct hlist_node tramp_hlist; u64 cookie; }; struct bpf_shim_tramp_link { struct bpf_tramp_link link; struct bpf_trampoline *trampoline; }; struct bpf_tracing_link { struct bpf_tramp_link link; enum bpf_attach_type attach_type; struct bpf_trampoline *trampoline; struct bpf_prog *tgt_prog; }; struct bpf_raw_tp_link { struct bpf_link link; struct bpf_raw_event_map *btp; u64 cookie; }; struct bpf_link_primer { struct bpf_link *link; struct file *file; int fd; u32 id; }; struct bpf_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; /* BPF token-related delegation options */ u64 delegate_cmds; u64 delegate_maps; u64 delegate_progs; u64 delegate_attachs; }; struct bpf_token { struct work_struct work; atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; u64 allowed_progs; u64 allowed_attachs; #ifdef CONFIG_SECURITY void *security; #endif }; struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 /** * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to * define a BPF_MAP_TYPE_STRUCT_OPS map type composed * of BPF_PROG_TYPE_STRUCT_OPS progs. * @verifier_ops: A structure of callbacks that are invoked by the verifier * when determining whether the struct_ops progs in the * struct_ops map are valid. * @init: A callback that is invoked a single time, and before any other * callback, to initialize the structure. A nonzero return value means * the subsystem could not be initialized. * @check_member: When defined, a callback invoked by the verifier to allow * the subsystem to determine if an entry in the struct_ops map * is valid. A nonzero return value means that the map is * invalid and should be rejected by the verifier. * @init_member: A callback that is invoked for each member of the struct_ops * map to allow the subsystem to initialize the member. A nonzero * value means the member could not be initialized. This callback * is exclusive with the @type, @type_id, @value_type, and * @value_id fields. * @reg: A callback that is invoked when the struct_ops map has been * initialized and is being attached to. Zero means the struct_ops map * has been successfully registered and is live. A nonzero return value * means the struct_ops map could not be registered. * @unreg: A callback that is invoked when the struct_ops map should be * unregistered. * @update: A callback that is invoked when the live struct_ops map is being * updated to contain new values. This callback is only invoked when * the struct_ops map is loaded with BPF_F_LINK. If not defined, the * it is assumed that the struct_ops map cannot be updated. * @validate: A callback that is invoked after all of the members have been * initialized. This callback should perform static checks on the * map, meaning that it should either fail or succeed * deterministically. A struct_ops map that has been validated may * not necessarily succeed in being registered if the call to @reg * fails. For example, a valid struct_ops map may be loaded, but * then fail to be registered due to there being another active * struct_ops map on the system in the subsystem already. For this * reason, if this callback is not defined, the check is skipped as * the struct_ops map will have final verification performed in * @reg. * @type: BTF type. * @value_type: Value type. * @name: The name of the struct bpf_struct_ops object. * @func_models: Func models * @type_id: BTF type id. * @value_id: BTF value id. */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); int (*check_member)(const struct btf_type *t, const struct btf_member *member, const struct bpf_prog *prog); int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); int (*reg)(void *kdata, struct bpf_link *link); void (*unreg)(void *kdata, struct bpf_link *link); int (*update)(void *kdata, void *old_kdata, struct bpf_link *link); int (*validate)(void *kdata); void *cfi_stubs; struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; }; /* Every member of a struct_ops type has an instance even a member is not * an operator (function pointer). The "info" field will be assigned to * prog->aux->ctx_arg_info of BPF struct_ops programs to provide the * argument information required by the verifier to verify the program. * * btf_ctx_access() will lookup prog->aux->ctx_arg_info to find the * corresponding entry for an given argument. */ struct bpf_struct_ops_arg_info { struct bpf_ctx_arg_aux *info; u32 cnt; }; struct bpf_struct_ops_desc { struct bpf_struct_ops *st_ops; const struct btf_type *type; const struct btf_type *value_type; u32 type_id; u32 value_id; /* Collection of argument information for each member */ struct bpf_struct_ops_arg_info *arg_info; }; enum bpf_struct_ops_state { BPF_STRUCT_OPS_STATE_INIT, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE, BPF_STRUCT_OPS_STATE_READY, }; struct bpf_struct_ops_common_value { refcount_t refcnt; enum bpf_struct_ops_state state; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) /* This macro helps developer to register a struct_ops type and generate * type information correctly. Developers should use this macro to register * a struct_ops type instead of calling __register_bpf_struct_ops() directly. */ #define register_bpf_struct_ops(st_ops, type) \ ({ \ struct bpf_struct_ops_##type { \ struct bpf_struct_ops_common_value common; \ struct type data ____cacheline_aligned_in_smp; \ }; \ BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ __register_bpf_struct_ops(st_ops); \ }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, void *stub_func, void **image, u32 *image_off, bool allow_alloc); void bpf_struct_ops_image_free(void *image); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) return bpf_struct_ops_get(data); else return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) bpf_struct_ops_put(data); else module_put(owner); } int bpf_struct_ops_link_create(union bpf_attr *attr); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ struct bpf_dummy_ops_state { int val; }; struct bpf_dummy_ops { int (*test_1)(struct bpf_dummy_ops_state *cb); int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, char a3, unsigned long a4); int (*test_sleepable)(struct bpf_dummy_ops_state *cb); }; int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc); #else #define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } static inline int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) { return -ENOTSUPP; } static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EINVAL; } static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) { } static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) { } #endif int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, const struct bpf_ctx_arg_aux *info, u32 cnt); #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype); void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype) { return -EOPNOTSUPP; } static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) { } #endif struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; struct bpf_array_aux *aux; union { DECLARE_FLEX_ARRAY(char, value) __aligned(8); DECLARE_FLEX_ARRAY(void *, ptrs) __aligned(8); DECLARE_FLEX_ARRAY(void __percpu *, pptrs) __aligned(8); }; }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 /* Maximum number of loops for bpf_loop and bpf_iter_num. * It's enum to expose it (and thus make it discoverable) through BTF. */ enum { BPF_MAX_LOOPS = 8 * 1024 * 1024, BPF_MAX_TIMED_LOOPS = 0xffff, }; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ BPF_F_WRONLY_PROG) #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) /* Maximum number of user-producer ring buffer samples that can be drained in * a call to bpf_user_ringbuf_drain(). */ #define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024) static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is * not possible. */ if (access_flags & BPF_F_RDONLY_PROG) return BPF_MAP_CAN_READ; else if (access_flags & BPF_F_WRONLY_PROG) return BPF_MAP_CAN_WRITE; else return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; } static inline bool bpf_map_flags_access_ok(u32 access_flags) { return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } struct bpf_event_entry { struct perf_event *event; struct file *perf_file; struct file *map_file; struct rcu_head rcu; }; static inline bool map_type_contains_progs(struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || map->map_type == BPF_MAP_TYPE_DEVMAP || map->map_type == BPF_MAP_TYPE_CPUMAP; } bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); /* an array of programs to be executed under rcu_lock. * * Typical usage: * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. * The user has to keep refcnt on the program and make sure the program * is removed from the array before bpf_prog_put(). * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ struct bpf_prog_array_item { struct bpf_prog *prog; union { struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; u64 bpf_cookie; }; }; struct bpf_prog_array { struct rcu_head rcu; struct bpf_prog_array_item items[]; }; struct bpf_empty_prog_array { struct bpf_prog_array hdr; struct bpf_prog *null_prog; }; /* to avoid allocating empty bpf_prog_array for cgroups that * don't have bpf program attached use one global 'bpf_empty_prog_array' * It will not be modified the caller of bpf_prog_array_alloc() * (since caller requested prog_cnt == 0) * that pointer should be 'freed' by bpf_prog_array_free() */ extern struct bpf_empty_prog_array bpf_empty_prog_array; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); /* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array); struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; int retval; }; struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; bool is_uprobe; }; struct bpf_tramp_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; struct bpf_run_ctx *saved_run_ctx; }; static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; #ifdef CONFIG_BPF_SYSCALL old_ctx = current->bpf_ctx; current->bpf_ctx = new_ctx; #endif return old_ctx; } static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) { #ifdef CONFIG_BPF_SYSCALL current->bpf_ctx = old_ctx; #endif } /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline u32 bpf_prog_run_array(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); if (unlikely(!array)) return ret; run_ctx.is_uprobe = false; migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); migrate_enable(); return ret; } /* Notes on RCU design for bpf_prog_arrays containing sleepable programs: * * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array * overall. As a result, we must use the bpf_prog_array_free_sleepable * in order to use the tasks_trace rcu grace period. * * When a non-sleepable program is inside the array, we take the rcu read * section and disable preemption for that program alone, so it can access * rcu-protected dynamically sized maps. */ static __always_inline u32 bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); if (unlikely(!array)) return ret; migrate_disable(); run_ctx.is_uprobe = true; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { if (!prog->sleepable) rcu_read_lock(); run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; if (!prog->sleepable) rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); migrate_enable(); return ret; } #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { this_cpu_dec(bpf_prog_active); migrate_enable(); } extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); /* * The __bpf_map_get() and __btf_get_by_fd() functions parse a file * descriptor and return a corresponding map or btf object. * Their names are double underscored to emphasize the fact that they * do not increase refcnt. To also increase refcnt use corresponding * bpf_map_get() and btf_get_by_fd() functions. */ static inline struct bpf_map *__bpf_map_get(struct fd f) { if (fd_empty(f)) return ERR_PTR(-EBADF); if (unlikely(fd_file(f)->f_op != &bpf_map_fops)) return ERR_PTR(-EINVAL); return fd_file(f)->private_data; } static inline struct btf *__btf_get_by_fd(struct fd f) { if (fd_empty(f)) return ERR_PTR(-EBADF); if (unlikely(fd_file(f)->f_op != &btf_fops)) return ERR_PTR(-EINVAL); return fd_file(f)->private_data; } void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, int nid, unsigned long nr_pages, struct page **page_array); #ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags); void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else /* * These specialized allocators have to be macros for their allocations to be * accounted separately (to have separate alloc_tag). */ #define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ kmalloc_node(_size, _flags, _node) #define bpf_map_kzalloc(_map, _size, _flags) \ kzalloc(_size, _flags) #define bpf_map_kvcalloc(_map, _n, _size, _flags) \ kvcalloc(_n, _size, _flags) #define bpf_map_alloc_percpu(_map, _size, _align, _flags) \ __alloc_percpu_gfp(_size, _align, _flags) #endif static inline int bpf_map_init_elem_count(struct bpf_map *map) { size_t size = sizeof(*map->elem_count), align = size; gfp_t flags = GFP_USER | __GFP_NOWARN; map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); if (!map->elem_count) return -ENOMEM; return 0; } static inline void bpf_map_free_elem_count(struct bpf_map *map) { free_percpu(map->elem_count); } static inline void bpf_map_inc_elem_count(struct bpf_map *map) { this_cpu_inc(*map->elem_count); } static inline void bpf_map_dec_elem_count(struct bpf_map *map) { this_cpu_dec(*map->elem_count); } extern int sysctl_unprivileged_bpf_disabled; bool bpf_token_capable(const struct bpf_token *token, int cap); static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { return bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { return bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, bool sleepable); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); void bpf_token_inc(struct bpf_token *token); void bpf_token_put(struct bpf_token *token); int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } /* * The task type of iterators. * * For BPF task iterators, they can be parameterized with various * parameters to visit only some of tasks. * * BPF_TASK_ITER_ALL (default) * Iterate over resources of every task. * * BPF_TASK_ITER_TID * Iterate over resources of a task/tid. * * BPF_TASK_ITER_TGID * Iterate over resources of every task of a process / task group. */ enum bpf_iter_task_type { BPF_TASK_ITER_ALL = 0, BPF_TASK_ITER_TID, BPF_TASK_ITER_TGID, }; struct bpf_iter_aux_info { /* for map_elem iter */ struct bpf_map *map; /* for cgroup iter */ struct { struct cgroup *start; /* starting cgroup */ enum bpf_cgroup_iter_order order; } cgroup; struct { enum bpf_iter_task_type type; u32 pid; } task; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); typedef const struct bpf_func_proto * (*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), }; #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { __bpf_md_ptr(struct seq_file *, seq); u64 session_id; u64 seq_num; }; struct bpf_iter__bpf_map_elem { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(void *, value); }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); int bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq); int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); #endif struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(struct list_head *flush_list); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, const struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, const struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { return (attr->map_flags & BPF_F_NUMA_NODE) ? attr->numa_node : NUMA_NO_NODE; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_nf(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); static inline bool bpf_tracing_ctx_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; return true; } static inline bool bpf_tracing_btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_tracing_ctx_access(off, size, type)) return false; return btf_ctx_access(off, size, type, prog, info); } int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func_proto, const char *func_name, struct btf_func_model *m); struct bpf_reg_state; int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key); int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key, int last_id); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr); struct bpf_core_ctx { struct bpf_verifier_log *log; const struct btf *btf; }; bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, const struct btf *arg_btf, u32 arg_id); int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn); static inline bool unprivileged_ebpf_enabled(void) { return !sysctl_unprivileged_bpf_disabled; } /* Not all bpf prog type has the bpf_ctx. * For the bpf prog type that has initialized the bpf_ctx, * this function can be used to decide if a kernel function * is called by a bpf program. */ static inline bool has_current_bpf_ctx(void) { return !!current->bpf_ctx; } void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_add(struct bpf_prog *prog, int i) { } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) { } static inline void bpf_prog_put(struct bpf_prog *prog) { } static inline void bpf_prog_inc(struct bpf_prog *prog) { } static inline struct bpf_prog *__must_check bpf_prog_inc_not_zero(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { } static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, bool sleepable) { } static inline int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline int bpf_link_settle(struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline void bpf_link_cleanup(struct bpf_link_primer *primer) { } static inline void bpf_link_inc(struct bpf_link *link) { } static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return NULL; } static inline void bpf_link_put(struct bpf_link *link) { } static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } static inline bool bpf_token_capable(const struct bpf_token *token, int cap) { return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); } static inline void bpf_token_inc(struct bpf_token *token) { } static inline void bpf_token_put(struct bpf_token *token) { } static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline void __dev_flush(struct list_head *flush_list) { } struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; } struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, const struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, const struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { return 0; } static inline void __cpu_map_flush(struct list_head *flush_list) { } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { return ERR_PTR(-EOPNOTSUPP); } static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline void bpf_map_put(struct bpf_map *map) { } static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name) { return -EACCES; } static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline void bpf_task_storage_free(struct task_struct *task) { } static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return false; } static inline const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { return NULL; } static inline int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr) { return -ENOTSUPP; } static inline bool unprivileged_ebpf_enabled(void) { return false; } static inline bool has_current_bpf_ctx(void) { return false; } static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) { } static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) { } static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size) { } static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) { } static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) { } #endif /* CONFIG_BPF_SYSCALL */ static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { int ret = -EFAULT; if (IS_ENABLED(CONFIG_BPF_EVENTS)) ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { return bpf_prog_get_type_dev(ufd, type, false); } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_dev_bound_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map); int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_map_offload_update_elem(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); void unpriv_ebpf_notify(int new_state); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux); void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id); int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr); int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog); void bpf_dev_bound_netdev_unregister(struct net_device *dev); static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->dev_bound; } static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux) { return aux->offload_requested; } bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs); static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return unlikely(map->ops == &bpf_map_offload_ops); } struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux) { return -EOPNOTSUPP; } static inline void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) { return NULL; } static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } static inline int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev) { } static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs) { return false; } static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return false; } static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_map_offload_map_free(struct bpf_map *map) { } static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) { return 0; } static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EOPNOTSUPP; } static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { return -EOPNOTSUPP; } static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ static __always_inline void bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) { const struct bpf_prog_array_item *item; struct bpf_prog *prog; if (unlikely(!array)) return; item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { bpf_prog_inc_misses_counter(prog); item++; } } #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags); #else static inline void bpf_sk_reuseport_detach(struct sock *sk) { } #ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EOPNOTSUPP; } static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; extern const struct bpf_func_proto bpf_current_task_under_cgroup_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; extern const struct bpf_func_proto bpf_ringbuf_output_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; extern const struct bpf_func_proto bpf_cgrp_storage_get_proto; extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_INET struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; bool bind_inany; }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } #endif /* CONFIG_INET */ enum bpf_text_poke_type { BPF_MOD_CALL, BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, struct bpf_prog *new, struct bpf_prog *old); void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 #define MAX_BPRINTF_BUF 1024 struct bpf_bprintf_data { u32 *bin_args; char *buf; bool get_bin_args; bool get_buf; }; int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); void bpf_cgroup_atype_put(int cgroup_atype); #else static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} static inline void bpf_cgroup_atype_put(int cgroup_atype) {} #endif /* CONFIG_BPF_LSM */ struct key; #ifdef CONFIG_KEYS struct bpf_key { struct key *key; bool has_ref; }; #endif /* CONFIG_KEYS */ static inline bool type_is_alloc(u32 type) { return type & MEM_ALLOC; } static inline gfp_t bpf_memcg_flags(gfp_t flags) { if (memcg_bpf_enabled()) return flags | __GFP_ACCOUNT; return flags; } static inline bool bpf_is_subprog(const struct bpf_prog *prog) { return prog->aux->func_idx != 0; } #endif /* _LINUX_BPF_H */ |
| 6 6 25 20 39 39 38 39 39 39 39 39 25 20 39 39 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * Cipher operations. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * 2002 Adam J. Richter <adam@yggdrasil.com> * 2004 Jean-Luc Cooke <jlcooke@certainkey.com> */ #include <crypto/scatterwalk.h> #include <linux/crypto.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/slab.h> enum { SKCIPHER_WALK_SLOW = 1 << 0, SKCIPHER_WALK_COPY = 1 << 1, SKCIPHER_WALK_DIFF = 1 << 2, SKCIPHER_WALK_SLEEP = 1 << 3, }; static inline gfp_t skcipher_walk_gfp(struct skcipher_walk *walk) { return walk->flags & SKCIPHER_WALK_SLEEP ? GFP_KERNEL : GFP_ATOMIC; } void scatterwalk_skip(struct scatter_walk *walk, unsigned int nbytes) { struct scatterlist *sg = walk->sg; nbytes += walk->offset - sg->offset; while (nbytes > sg->length) { nbytes -= sg->length; sg = sg_next(sg); } walk->sg = sg; walk->offset = sg->offset + nbytes; } EXPORT_SYMBOL_GPL(scatterwalk_skip); inline void memcpy_from_scatterwalk(void *buf, struct scatter_walk *walk, unsigned int nbytes) { do { unsigned int to_copy; to_copy = scatterwalk_next(walk, nbytes); memcpy(buf, walk->addr, to_copy); scatterwalk_done_src(walk, to_copy); buf += to_copy; nbytes -= to_copy; } while (nbytes); } EXPORT_SYMBOL_GPL(memcpy_from_scatterwalk); inline void memcpy_to_scatterwalk(struct scatter_walk *walk, const void *buf, unsigned int nbytes) { do { unsigned int to_copy; to_copy = scatterwalk_next(walk, nbytes); memcpy(walk->addr, buf, to_copy); scatterwalk_done_dst(walk, to_copy); buf += to_copy; nbytes -= to_copy; } while (nbytes); } EXPORT_SYMBOL_GPL(memcpy_to_scatterwalk); void memcpy_from_sglist(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes) { struct scatter_walk walk; if (unlikely(nbytes == 0)) /* in case sg == NULL */ return; scatterwalk_start_at_pos(&walk, sg, start); memcpy_from_scatterwalk(buf, &walk, nbytes); } EXPORT_SYMBOL_GPL(memcpy_from_sglist); void memcpy_to_sglist(struct scatterlist *sg, unsigned int start, const void *buf, unsigned int nbytes) { struct scatter_walk walk; if (unlikely(nbytes == 0)) /* in case sg == NULL */ return; scatterwalk_start_at_pos(&walk, sg, start); memcpy_to_scatterwalk(&walk, buf, nbytes); } EXPORT_SYMBOL_GPL(memcpy_to_sglist); void memcpy_sglist(struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { struct skcipher_walk walk = {}; if (unlikely(nbytes == 0)) /* in case sg == NULL */ return; walk.total = nbytes; scatterwalk_start(&walk.in, src); scatterwalk_start(&walk.out, dst); skcipher_walk_first(&walk, true); do { if (walk.src.virt.addr != walk.dst.virt.addr) memcpy(walk.dst.virt.addr, walk.src.virt.addr, walk.nbytes); skcipher_walk_done(&walk, 0); } while (walk.nbytes); } EXPORT_SYMBOL_GPL(memcpy_sglist); struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2], struct scatterlist *src, unsigned int len) { for (;;) { if (!len) return src; if (src->length > len) break; len -= src->length; src = sg_next(src); } sg_init_table(dst, 2); sg_set_page(dst, sg_page(src), src->length - len, src->offset + len); scatterwalk_crypto_chain(dst, sg_next(src), 2); return dst; } EXPORT_SYMBOL_GPL(scatterwalk_ffwd); static int skcipher_next_slow(struct skcipher_walk *walk, unsigned int bsize) { unsigned alignmask = walk->alignmask; unsigned n; void *buffer; if (!walk->buffer) walk->buffer = walk->page; buffer = walk->buffer; if (!buffer) { /* Min size for a buffer of bsize bytes aligned to alignmask */ n = bsize + (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); buffer = kzalloc(n, skcipher_walk_gfp(walk)); if (!buffer) return skcipher_walk_done(walk, -ENOMEM); walk->buffer = buffer; } buffer = PTR_ALIGN(buffer, alignmask + 1); memcpy_from_scatterwalk(buffer, &walk->in, bsize); walk->out.__addr = buffer; walk->in.__addr = walk->out.addr; walk->nbytes = bsize; walk->flags |= SKCIPHER_WALK_SLOW; return 0; } static int skcipher_next_copy(struct skcipher_walk *walk) { void *tmp = walk->page; scatterwalk_map(&walk->in); memcpy(tmp, walk->in.addr, walk->nbytes); scatterwalk_unmap(&walk->in); /* * walk->in is advanced later when the number of bytes actually * processed (which might be less than walk->nbytes) is known. */ walk->in.__addr = tmp; walk->out.__addr = tmp; return 0; } static int skcipher_next_fast(struct skcipher_walk *walk) { unsigned long diff; diff = offset_in_page(walk->in.offset) - offset_in_page(walk->out.offset); diff |= (u8 *)(sg_page(walk->in.sg) + (walk->in.offset >> PAGE_SHIFT)) - (u8 *)(sg_page(walk->out.sg) + (walk->out.offset >> PAGE_SHIFT)); scatterwalk_map(&walk->out); walk->in.__addr = walk->out.__addr; if (diff) { walk->flags |= SKCIPHER_WALK_DIFF; scatterwalk_map(&walk->in); } return 0; } static int skcipher_walk_next(struct skcipher_walk *walk) { unsigned int bsize; unsigned int n; n = walk->total; bsize = min(walk->stride, max(n, walk->blocksize)); n = scatterwalk_clamp(&walk->in, n); n = scatterwalk_clamp(&walk->out, n); if (unlikely(n < bsize)) { if (unlikely(walk->total < walk->blocksize)) return skcipher_walk_done(walk, -EINVAL); slow_path: return skcipher_next_slow(walk, bsize); } walk->nbytes = n; if (unlikely((walk->in.offset | walk->out.offset) & walk->alignmask)) { if (!walk->page) { gfp_t gfp = skcipher_walk_gfp(walk); walk->page = (void *)__get_free_page(gfp); if (!walk->page) goto slow_path; } walk->flags |= SKCIPHER_WALK_COPY; return skcipher_next_copy(walk); } return skcipher_next_fast(walk); } static int skcipher_copy_iv(struct skcipher_walk *walk) { unsigned alignmask = walk->alignmask; unsigned ivsize = walk->ivsize; unsigned aligned_stride = ALIGN(walk->stride, alignmask + 1); unsigned size; u8 *iv; /* Min size for a buffer of stride + ivsize, aligned to alignmask */ size = aligned_stride + ivsize + (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); walk->buffer = kmalloc(size, skcipher_walk_gfp(walk)); if (!walk->buffer) return -ENOMEM; iv = PTR_ALIGN(walk->buffer, alignmask + 1) + aligned_stride; walk->iv = memcpy(iv, walk->iv, walk->ivsize); return 0; } int skcipher_walk_first(struct skcipher_walk *walk, bool atomic) { if (WARN_ON_ONCE(in_hardirq())) return -EDEADLK; walk->flags = atomic ? 0 : SKCIPHER_WALK_SLEEP; walk->buffer = NULL; if (unlikely(((unsigned long)walk->iv & walk->alignmask))) { int err = skcipher_copy_iv(walk); if (err) return err; } walk->page = NULL; return skcipher_walk_next(walk); } EXPORT_SYMBOL_GPL(skcipher_walk_first); /** * skcipher_walk_done() - finish one step of a skcipher_walk * @walk: the skcipher_walk * @res: number of bytes *not* processed (>= 0) from walk->nbytes, * or a -errno value to terminate the walk due to an error * * This function cleans up after one step of walking through the source and * destination scatterlists, and advances to the next step if applicable. * walk->nbytes is set to the number of bytes available in the next step, * walk->total is set to the new total number of bytes remaining, and * walk->{src,dst}.virt.addr is set to the next pair of data pointers. If there * is no more data, or if an error occurred (i.e. -errno return), then * walk->nbytes and walk->total are set to 0 and all resources owned by the * skcipher_walk are freed. * * Return: 0 or a -errno value. If @res was a -errno value then it will be * returned, but other errors may occur too. */ int skcipher_walk_done(struct skcipher_walk *walk, int res) { unsigned int n = walk->nbytes; /* num bytes processed this step */ unsigned int total = 0; /* new total remaining */ if (!n) goto finish; if (likely(res >= 0)) { n -= res; /* subtract num bytes *not* processed */ total = walk->total - n; } if (likely(!(walk->flags & (SKCIPHER_WALK_SLOW | SKCIPHER_WALK_COPY | SKCIPHER_WALK_DIFF)))) { scatterwalk_advance(&walk->in, n); } else if (walk->flags & SKCIPHER_WALK_DIFF) { scatterwalk_done_src(&walk->in, n); } else if (walk->flags & SKCIPHER_WALK_COPY) { scatterwalk_advance(&walk->in, n); scatterwalk_map(&walk->out); memcpy(walk->out.addr, walk->page, n); } else { /* SKCIPHER_WALK_SLOW */ if (res > 0) { /* * Didn't process all bytes. Either the algorithm is * broken, or this was the last step and it turned out * the message wasn't evenly divisible into blocks but * the algorithm requires it. */ res = -EINVAL; total = 0; } else memcpy_to_scatterwalk(&walk->out, walk->out.addr, n); goto dst_done; } scatterwalk_done_dst(&walk->out, n); dst_done: if (res > 0) res = 0; walk->total = total; walk->nbytes = 0; if (total) { if (walk->flags & SKCIPHER_WALK_SLEEP) cond_resched(); walk->flags &= ~(SKCIPHER_WALK_SLOW | SKCIPHER_WALK_COPY | SKCIPHER_WALK_DIFF); return skcipher_walk_next(walk); } finish: /* Short-circuit for the common/fast path. */ if (!((unsigned long)walk->buffer | (unsigned long)walk->page)) goto out; if (walk->iv != walk->oiv) memcpy(walk->oiv, walk->iv, walk->ivsize); if (walk->buffer != walk->page) kfree(walk->buffer); if (walk->page) free_page((unsigned long)walk->page); out: return res; } EXPORT_SYMBOL_GPL(skcipher_walk_done); |
| 466 232 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2000,2002,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_BIT_H__ #define __XFS_BIT_H__ /* * XFS bit manipulation routines. */ /* * masks with n high/low bits set, 64-bit values */ static inline uint64_t xfs_mask64hi(int n) { return (uint64_t)-1 << (64 - (n)); } static inline uint32_t xfs_mask32lo(int n) { return ((uint32_t)1 << (n)) - 1; } static inline uint64_t xfs_mask64lo(int n) { return ((uint64_t)1 << (n)) - 1; } /* Get high bit set out of 32-bit argument, -1 if none set */ static inline int xfs_highbit32(uint32_t v) { return fls(v) - 1; } /* Get high bit set out of 64-bit argument, -1 if none set */ static inline int xfs_highbit64(uint64_t v) { return fls64(v) - 1; } /* Get low bit set out of 32-bit argument, -1 if none set */ static inline int xfs_lowbit32(uint32_t v) { return ffs(v) - 1; } /* Get low bit set out of 64-bit argument, -1 if none set */ static inline int xfs_lowbit64(uint64_t v) { uint32_t w = (uint32_t)v; int n = 0; if (w) { /* lower bits */ n = ffs(w); } else { /* upper bits */ w = (uint32_t)(v >> 32); if (w) { n = ffs(w); if (n) n += 32; } } return n - 1; } /* Return whether bitmap is empty (1 == empty) */ extern int xfs_bitmap_empty(uint *map, uint size); /* Count continuous one bits in map starting with start_bit */ extern int xfs_contig_bits(uint *map, uint size, uint start_bit); /* Find next set bit in map */ extern int xfs_next_bit(uint *map, uint size, uint start_bit); #endif /* __XFS_BIT_H__ */ |
| 160 157 157 157 157 157 157 157 157 157 157 157 157 157 157 157 33 33 334 334 3 5 5 5 5 5 4 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * Copyright (c) 2013 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_quota.h" #include "xfs_trans.h" #include "xfs_qm.h" #include "xfs_error.h" #include "xfs_health.h" #include "xfs_metadir.h" #include "xfs_metafile.h" int xfs_calc_dquots_per_chunk( unsigned int nbblks) /* basic block units */ { ASSERT(nbblks > 0); return BBTOB(nbblks) / sizeof(struct xfs_dqblk); } /* * Do some primitive error checking on ondisk dquot data structures. * * The xfs_dqblk structure /contains/ the xfs_disk_dquot structure; * we verify them separately because at some points we have only the * smaller xfs_disk_dquot structure available. */ xfs_failaddr_t xfs_dquot_verify( struct xfs_mount *mp, struct xfs_disk_dquot *ddq, xfs_dqid_t id) /* used only during quotacheck */ { __u8 ddq_type; /* * We can encounter an uninitialized dquot buffer for 2 reasons: * 1. If we crash while deleting the quotainode(s), and those blks got * used for user data. This is because we take the path of regular * file deletion; however, the size field of quotainodes is never * updated, so all the tricks that we play in itruncate_finish * don't quite matter. * * 2. We don't play the quota buffers when there's a quotaoff logitem. * But the allocation will be replayed so we'll end up with an * uninitialized quota block. * * This is all fine; things are still consistent, and we haven't lost * any quota information. Just don't complain about bad dquot blks. */ if (ddq->d_magic != cpu_to_be16(XFS_DQUOT_MAGIC)) return __this_address; if (ddq->d_version != XFS_DQUOT_VERSION) return __this_address; if (ddq->d_type & ~XFS_DQTYPE_ANY) return __this_address; ddq_type = ddq->d_type & XFS_DQTYPE_REC_MASK; if (ddq_type != XFS_DQTYPE_USER && ddq_type != XFS_DQTYPE_PROJ && ddq_type != XFS_DQTYPE_GROUP) return __this_address; if ((ddq->d_type & XFS_DQTYPE_BIGTIME) && !xfs_has_bigtime(mp)) return __this_address; if ((ddq->d_type & XFS_DQTYPE_BIGTIME) && !ddq->d_id) return __this_address; if (id != -1 && id != be32_to_cpu(ddq->d_id)) return __this_address; if (!ddq->d_id) return NULL; if (ddq->d_blk_softlimit && be64_to_cpu(ddq->d_bcount) > be64_to_cpu(ddq->d_blk_softlimit) && !ddq->d_btimer) return __this_address; if (ddq->d_ino_softlimit && be64_to_cpu(ddq->d_icount) > be64_to_cpu(ddq->d_ino_softlimit) && !ddq->d_itimer) return __this_address; if (ddq->d_rtb_softlimit && be64_to_cpu(ddq->d_rtbcount) > be64_to_cpu(ddq->d_rtb_softlimit) && !ddq->d_rtbtimer) return __this_address; return NULL; } xfs_failaddr_t xfs_dqblk_verify( struct xfs_mount *mp, struct xfs_dqblk *dqb, xfs_dqid_t id) /* used only during quotacheck */ { if (xfs_has_crc(mp) && !uuid_equal(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; return xfs_dquot_verify(mp, &dqb->dd_diskdq, id); } /* * Do some primitive error checking on ondisk dquot data structures. */ void xfs_dqblk_repair( struct xfs_mount *mp, struct xfs_dqblk *dqb, xfs_dqid_t id, xfs_dqtype_t type) { /* * Typically, a repair is only requested by quotacheck. */ ASSERT(id != -1); memset(dqb, 0, sizeof(struct xfs_dqblk)); dqb->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC); dqb->dd_diskdq.d_version = XFS_DQUOT_VERSION; dqb->dd_diskdq.d_type = type; dqb->dd_diskdq.d_id = cpu_to_be32(id); if (xfs_has_crc(mp)) { uuid_copy(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid); xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } } STATIC bool xfs_dquot_buf_verify_crc( struct xfs_mount *mp, struct xfs_buf *bp, bool readahead) { struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr; int ndquots; int i; if (!xfs_has_crc(mp)) return true; /* * if we are in log recovery, the quota subsystem has not been * initialised so we have no quotainfo structure. In that case, we need * to manually calculate the number of dquots in the buffer. */ if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else ndquots = xfs_calc_dquots_per_chunk(bp->b_length); for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF)) { if (!readahead) xfs_buf_verifier_error(bp, -EFSBADCRC, __func__, d, sizeof(*d), __this_address); return false; } } return true; } STATIC xfs_failaddr_t xfs_dquot_buf_verify( struct xfs_mount *mp, struct xfs_buf *bp, bool readahead) { struct xfs_dqblk *dqb = bp->b_addr; xfs_failaddr_t fa; xfs_dqid_t id = 0; int ndquots; int i; /* * if we are in log recovery, the quota subsystem has not been * initialised so we have no quotainfo structure. In that case, we need * to manually calculate the number of dquots in the buffer. */ if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else ndquots = xfs_calc_dquots_per_chunk(bp->b_length); /* * On the first read of the buffer, verify that each dquot is valid. * We don't know what the id of the dquot is supposed to be, just that * they should be increasing monotonically within the buffer. If the * first id is corrupt, then it will fail on the second dquot in the * buffer so corruptions could point to the wrong dquot in this case. */ for (i = 0; i < ndquots; i++) { struct xfs_disk_dquot *ddq; ddq = &dqb[i].dd_diskdq; if (i == 0) id = be32_to_cpu(ddq->d_id); fa = xfs_dqblk_verify(mp, &dqb[i], id + i); if (fa) { if (!readahead) xfs_buf_verifier_error(bp, -EFSCORRUPTED, __func__, &dqb[i], sizeof(struct xfs_dqblk), fa); return fa; } } return NULL; } static xfs_failaddr_t xfs_dquot_buf_verify_struct( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; return xfs_dquot_buf_verify(mp, bp, false); } static void xfs_dquot_buf_read_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; if (!xfs_dquot_buf_verify_crc(mp, bp, false)) return; xfs_dquot_buf_verify(mp, bp, false); } /* * readahead errors are silent and simply leave the buffer as !done so a real * read will then be run with the xfs_dquot_buf_ops verifier. See * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than * reporting the failure. */ static void xfs_dquot_buf_readahead_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; if (!xfs_dquot_buf_verify_crc(mp, bp, true) || xfs_dquot_buf_verify(mp, bp, true) != NULL) { xfs_buf_ioerror(bp, -EIO); bp->b_flags &= ~XBF_DONE; } } /* * we don't calculate the CRC here as that is done when the dquot is flushed to * the buffer after the update is done. This ensures that the dquot in the * buffer always has an up-to-date CRC value. */ static void xfs_dquot_buf_write_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; xfs_dquot_buf_verify(mp, bp, false); } const struct xfs_buf_ops xfs_dquot_buf_ops = { .name = "xfs_dquot", .magic16 = { cpu_to_be16(XFS_DQUOT_MAGIC), cpu_to_be16(XFS_DQUOT_MAGIC) }, .verify_read = xfs_dquot_buf_read_verify, .verify_write = xfs_dquot_buf_write_verify, .verify_struct = xfs_dquot_buf_verify_struct, }; const struct xfs_buf_ops xfs_dquot_buf_ra_ops = { .name = "xfs_dquot_ra", .magic16 = { cpu_to_be16(XFS_DQUOT_MAGIC), cpu_to_be16(XFS_DQUOT_MAGIC) }, .verify_read = xfs_dquot_buf_readahead_verify, .verify_write = xfs_dquot_buf_write_verify, }; /* Convert an on-disk timer value into an incore timer value. */ time64_t xfs_dquot_from_disk_ts( struct xfs_disk_dquot *ddq, __be32 dtimer) { uint32_t t = be32_to_cpu(dtimer); if (t != 0 && (ddq->d_type & XFS_DQTYPE_BIGTIME)) return xfs_dq_bigtime_to_unix(t); return t; } /* Convert an incore timer value into an on-disk timer value. */ __be32 xfs_dquot_to_disk_ts( struct xfs_dquot *dqp, time64_t timer) { uint32_t t = timer; if (timer != 0 && (dqp->q_type & XFS_DQTYPE_BIGTIME)) t = xfs_dq_unix_to_bigtime(timer); return cpu_to_be32(t); } inline unsigned int xfs_dqinode_sick_mask(xfs_dqtype_t type) { switch (type) { case XFS_DQTYPE_USER: return XFS_SICK_FS_UQUOTA; case XFS_DQTYPE_GROUP: return XFS_SICK_FS_GQUOTA; case XFS_DQTYPE_PROJ: return XFS_SICK_FS_PQUOTA; } ASSERT(0); return 0; } /* * Load the inode for a given type of quota, assuming that the sb fields have * been sorted out. This is not true when switching quota types on a V4 * filesystem, so do not use this function for that. If metadir is enabled, * @dp must be the /quota metadir. * * Returns -ENOENT if the quota inode field is NULLFSINO; 0 and an inode on * success; or a negative errno. */ int xfs_dqinode_load( struct xfs_trans *tp, struct xfs_inode *dp, xfs_dqtype_t type, struct xfs_inode **ipp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_inode *ip; enum xfs_metafile_type metafile_type = xfs_dqinode_metafile_type(type); int error; if (!xfs_has_metadir(mp)) { xfs_ino_t ino; switch (type) { case XFS_DQTYPE_USER: ino = mp->m_sb.sb_uquotino; break; case XFS_DQTYPE_GROUP: ino = mp->m_sb.sb_gquotino; break; case XFS_DQTYPE_PROJ: ino = mp->m_sb.sb_pquotino; break; default: ASSERT(0); return -EFSCORRUPTED; } /* Should have set 0 to NULLFSINO when loading superblock */ if (ino == NULLFSINO) return -ENOENT; error = xfs_trans_metafile_iget(tp, ino, metafile_type, &ip); } else { error = xfs_metadir_load(tp, dp, xfs_dqinode_path(type), metafile_type, &ip); if (error == -ENOENT) return error; } if (error) { if (xfs_metadata_is_sick(error)) xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type)); return error; } if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) { xfs_irele(ip); xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type)); return -EFSCORRUPTED; } if (XFS_IS_CORRUPT(mp, ip->i_projid != 0)) { xfs_irele(ip); xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type)); return -EFSCORRUPTED; } *ipp = ip; return 0; } /* Create a metadata directory quota inode. */ int xfs_dqinode_metadir_create( struct xfs_inode *dp, xfs_dqtype_t type, struct xfs_inode **ipp) { struct xfs_metadir_update upd = { .dp = dp, .metafile_type = xfs_dqinode_metafile_type(type), .path = xfs_dqinode_path(type), }; int error; error = xfs_metadir_start_create(&upd); if (error) return error; error = xfs_metadir_create(&upd, S_IFREG); if (error) return error; xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE); error = xfs_metadir_commit(&upd); if (error) return error; xfs_finish_inode_setup(upd.ip); *ipp = upd.ip; return 0; } #ifndef __KERNEL__ /* Link a metadata directory quota inode. */ int xfs_dqinode_metadir_link( struct xfs_inode *dp, xfs_dqtype_t type, struct xfs_inode *ip) { struct xfs_metadir_update upd = { .dp = dp, .metafile_type = xfs_dqinode_metafile_type(type), .path = xfs_dqinode_path(type), .ip = ip, }; int error; error = xfs_metadir_start_link(&upd); if (error) return error; error = xfs_metadir_link(&upd); if (error) return error; xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE); return xfs_metadir_commit(&upd); } #endif /* __KERNEL__ */ /* Create the parent directory for all quota inodes and load it. */ int xfs_dqinode_mkdir_parent( struct xfs_mount *mp, struct xfs_inode **dpp) { if (!mp->m_metadirip) { xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); return -EFSCORRUPTED; } return xfs_metadir_mkdir(mp->m_metadirip, "quota", dpp); } /* * Load the parent directory of all quota inodes. Pass the inode to the caller * because quota functions (e.g. QUOTARM) can be called on the quota files even * if quotas are not enabled. */ int xfs_dqinode_load_parent( struct xfs_trans *tp, struct xfs_inode **dpp) { struct xfs_mount *mp = tp->t_mountp; if (!mp->m_metadirip) { xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); return -EFSCORRUPTED; } return xfs_metadir_load(tp, mp->m_metadirip, "quota", XFS_METAFILE_DIR, dpp); } |
| 161 219 219 220 167 227 34 54 519 285 404 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_MOUNT_H__ #define __XFS_MOUNT_H__ struct xlog; struct xfs_inode; struct xfs_mru_cache; struct xfs_ail; struct xfs_quotainfo; struct xfs_da_geometry; struct xfs_perag; /* dynamic preallocation free space thresholds, 5% down to 1% */ enum { XFS_LOWSP_1_PCNT = 0, XFS_LOWSP_2_PCNT, XFS_LOWSP_3_PCNT, XFS_LOWSP_4_PCNT, XFS_LOWSP_5_PCNT, XFS_LOWSP_MAX, }; /* * Error Configuration * * Error classes define the subsystem the configuration belongs to. * Error numbers define the errors that are configurable. */ enum { XFS_ERR_METADATA, XFS_ERR_CLASS_MAX, }; enum { XFS_ERR_DEFAULT, XFS_ERR_EIO, XFS_ERR_ENOSPC, XFS_ERR_ENODEV, XFS_ERR_ERRNO_MAX, }; #define XFS_ERR_RETRY_FOREVER -1 /* * Although retry_timeout is in jiffies which is normally an unsigned long, * we limit the retry timeout to 86400 seconds, or one day. So even a * signed 32-bit long is sufficient for a HZ value up to 24855. Making it * signed lets us store the special "-1" value, meaning retry forever. */ struct xfs_error_cfg { struct xfs_kobj kobj; int max_retries; long retry_timeout; /* in jiffies, -1 = infinite */ }; /* * Per-cpu deferred inode inactivation GC lists. */ struct xfs_inodegc { struct xfs_mount *mp; struct llist_head list; struct delayed_work work; int error; /* approximate count of inodes in the list */ unsigned int items; unsigned int shrinker_hits; unsigned int cpu; }; /* * Container for each type of groups, used to look up individual groups and * describes the geometry. */ struct xfs_groups { struct xarray xa; /* * Maximum capacity of the group in FSBs. * * Each group is laid out densely in the daddr space. For the * degenerate case of a pre-rtgroups filesystem, the incore rtgroup * pretends to have a zero-block and zero-blklog rtgroup. */ uint32_t blocks; /* * Log(2) of the logical size of each group. * * Compared to the blocks field above this is rounded up to the next * power of two, and thus lays out the xfs_fsblock_t/xfs_rtblock_t * space sparsely with a hole from blocks to (1 << blklog) at the end * of each group. */ uint8_t blklog; /* * Zoned devices can have gaps beyond the usable capacity of a zone and * the end in the LBA/daddr address space. In other words, the hardware * equivalent to the RT groups already takes care of the power of 2 * alignment for us. In this case the sparse FSB/RTB address space maps * 1:1 to the device address space. */ bool has_daddr_gaps; /* * Mask to extract the group-relative block number from a FSB. * For a pre-rtgroups filesystem we pretend to have one very large * rtgroup, so this mask must be 64-bit. */ uint64_t blkmask; /* * Start of the first group in the device. This is used to support a * RT device following the data device on the same block device for * SMR hard drives. */ xfs_fsblock_t start_fsb; /* * Maximum length of an atomic write for files stored in this * collection of allocation groups, in fsblocks. */ xfs_extlen_t awu_max; }; struct xfs_freecounter { /* free blocks for general use: */ struct percpu_counter count; /* total reserved blocks: */ uint64_t res_total; /* available reserved blocks: */ uint64_t res_avail; /* reserved blks @ remount,ro: */ uint64_t res_saved; }; /* * The struct xfsmount layout is optimised to separate read-mostly variables * from variables that are frequently modified. We put the read-mostly variables * first, then place all the other variables at the end. * * Typically, read-mostly variables are those that are set at mount time and * never changed again, or only change rarely as a result of things like sysfs * knobs being tweaked. */ typedef struct xfs_mount { struct xfs_sb m_sb; /* copy of fs superblock */ struct super_block *m_super; struct xfs_ail *m_ail; /* fs active log item list */ struct xfs_buf *m_sb_bp; /* buffer for superblock */ struct xfs_buf *m_rtsb_bp; /* realtime superblock */ char *m_rtname; /* realtime device name */ char *m_logname; /* external log device name */ struct xfs_da_geometry *m_dir_geo; /* directory block geometry */ struct xfs_da_geometry *m_attr_geo; /* attribute block geometry */ struct xlog *m_log; /* log specific stuff */ struct xfs_inode *m_rootip; /* pointer to root directory */ struct xfs_inode *m_metadirip; /* ptr to metadata directory */ struct xfs_inode *m_rtdirip; /* ptr to realtime metadir */ struct xfs_quotainfo *m_quotainfo; /* disk quota information */ struct xfs_buftarg *m_ddev_targp; /* data device */ struct xfs_buftarg *m_logdev_targp;/* log device */ struct xfs_buftarg *m_rtdev_targp; /* rt device */ void __percpu *m_inodegc; /* percpu inodegc structures */ struct xfs_mru_cache *m_filestream; /* per-mount filestream data */ struct workqueue_struct *m_buf_workqueue; struct workqueue_struct *m_unwritten_workqueue; struct workqueue_struct *m_reclaim_workqueue; struct workqueue_struct *m_sync_workqueue; struct workqueue_struct *m_blockgc_wq; struct workqueue_struct *m_inodegc_wq; int m_bsize; /* fs logical block size */ uint8_t m_blkbit_log; /* blocklog + NBBY */ uint8_t m_blkbb_log; /* blocklog - BBSHIFT */ uint8_t m_agno_log; /* log #ag's */ uint8_t m_sectbb_log; /* sectlog - BBSHIFT */ int8_t m_rtxblklog; /* log2 of rextsize, if possible */ uint m_blockmask; /* sb_blocksize-1 */ uint m_blockwsize; /* sb_blocksize in words */ /* number of rt extents per rt bitmap block if rtgroups enabled */ unsigned int m_rtx_per_rbmblock; uint m_alloc_mxr[2]; /* max alloc btree records */ uint m_alloc_mnr[2]; /* min alloc btree records */ uint m_bmap_dmxr[2]; /* max bmap btree records */ uint m_bmap_dmnr[2]; /* min bmap btree records */ uint m_rmap_mxr[2]; /* max rmap btree records */ uint m_rmap_mnr[2]; /* min rmap btree records */ uint m_rtrmap_mxr[2]; /* max rtrmap btree records */ uint m_rtrmap_mnr[2]; /* min rtrmap btree records */ uint m_refc_mxr[2]; /* max refc btree records */ uint m_refc_mnr[2]; /* min refc btree records */ uint m_rtrefc_mxr[2]; /* max rtrefc btree records */ uint m_rtrefc_mnr[2]; /* min rtrefc btree records */ uint m_alloc_maxlevels; /* max alloc btree levels */ uint m_bm_maxlevels[2]; /* max bmap btree levels */ uint m_rmap_maxlevels; /* max rmap btree levels */ uint m_rtrmap_maxlevels; /* max rtrmap btree level */ uint m_refc_maxlevels; /* max refcount btree level */ uint m_rtrefc_maxlevels; /* max rtrefc btree level */ unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */ unsigned int m_rtbtree_maxlevels; /* max level of all rt btrees */ xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */ uint m_alloc_set_aside; /* space we can't use */ uint m_ag_max_usable; /* max space per AG */ int m_dalign; /* stripe unit */ int m_swidth; /* stripe width */ xfs_agnumber_t m_maxagi; /* highest inode alloc group */ uint m_allocsize_log;/* min write size log bytes */ uint m_allocsize_blocks; /* min write size blocks */ int m_logbufs; /* number of log buffers */ int m_logbsize; /* size of each log buffer */ unsigned int m_rsumlevels; /* rt summary levels */ xfs_filblks_t m_rsumblocks; /* size of rt summary, FSBs */ int m_fixedfsid[2]; /* unchanged for life of FS */ uint m_qflags; /* quota status flags */ uint64_t m_features; /* active filesystem features */ uint64_t m_low_space[XFS_LOWSP_MAX]; uint64_t m_low_rtexts[XFS_LOWSP_MAX]; uint64_t m_rtxblkmask; /* rt extent block mask */ struct xfs_ino_geometry m_ino_geo; /* inode geometry */ struct xfs_trans_resv m_resv; /* precomputed res values */ /* low free space thresholds */ unsigned long m_opstate; /* dynamic state flags */ bool m_always_cow; bool m_fail_unmount; bool m_finobt_nores; /* no per-AG finobt resv. */ bool m_update_sb; /* sb needs update in mount */ unsigned int m_max_open_zones; unsigned int m_zonegc_low_space; struct xfs_mru_cache *m_zone_cache; /* Inode to open zone cache */ /* max_atomic_write mount option value */ unsigned long long m_awu_max_bytes; /* * Bitsets of per-fs metadata that have been checked and/or are sick. * Callers must hold m_sb_lock to access these two fields. */ uint8_t m_fs_checked; uint8_t m_fs_sick; /* * Bitsets of rt metadata that have been checked and/or are sick. * Callers must hold m_sb_lock to access this field. */ uint8_t m_rt_checked; uint8_t m_rt_sick; /* * End of read-mostly variables. Frequently written variables and locks * should be placed below this comment from now on. The first variable * here is marked as cacheline aligned so they it is separated from * the read-mostly variables. */ spinlock_t ____cacheline_aligned m_sb_lock; /* sb counter lock */ struct percpu_counter m_icount; /* allocated inodes counter */ struct percpu_counter m_ifree; /* free inodes counter */ struct xfs_freecounter m_free[XC_FREE_NR]; /* * Count of data device blocks reserved for delayed allocations, * including indlen blocks. Does not include allocated CoW staging * extents or anything related to the rt device. */ struct percpu_counter m_delalloc_blks; /* * RT version of the above. */ struct percpu_counter m_delalloc_rtextents; /* * Global count of allocation btree blocks in use across all AGs. Only * used when perag reservation is enabled. Helps prevent block * reservation from attempting to reserve allocation btree blocks. */ atomic64_t m_allocbt_blks; struct xfs_groups m_groups[XG_TYPE_MAX]; struct delayed_work m_reclaim_work; /* background inode reclaim */ struct xfs_zone_info *m_zone_info; /* zone allocator information */ struct dentry *m_debugfs; /* debugfs parent */ struct xfs_kobj m_kobj; struct xfs_kobj m_error_kobj; struct xfs_kobj m_error_meta_kobj; struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX]; struct xstats m_stats; /* per-fs stats */ #ifdef CONFIG_XFS_ONLINE_SCRUB_STATS struct xchk_stats *m_scrub_stats; #endif struct xfs_kobj m_zoned_kobj; xfs_agnumber_t m_agfrotor; /* last ag where space found */ atomic_t m_agirotor; /* last ag dir inode alloced */ atomic_t m_rtgrotor; /* last rtgroup rtpicked */ struct mutex m_metafile_resv_lock; uint64_t m_metafile_resv_target; uint64_t m_metafile_resv_used; uint64_t m_metafile_resv_avail; /* Memory shrinker to throttle and reprioritize inodegc */ struct shrinker *m_inodegc_shrinker; /* * Workqueue item so that we can coalesce multiple inode flush attempts * into a single flush. */ struct work_struct m_flush_inodes_work; /* * Generation of the filesysyem layout. This is incremented by each * growfs, and used by the pNFS server to ensure the client updates * its view of the block device once it gets a layout that might * reference the newly added blocks. Does not need to be persistent * as long as we only allow file system size increments, but if we * ever support shrinks it would have to be persisted in addition * to various other kinds of pain inflicted on the pNFS server. */ uint32_t m_generation; struct mutex m_growlock; /* growfs mutex */ #ifdef DEBUG /* * Frequency with which errors are injected. Replaces xfs_etest; the * value stored in here is the inverse of the frequency with which the * error triggers. 1 = always, 2 = half the time, etc. */ unsigned int *m_errortag; struct xfs_kobj m_errortag_kobj; #endif /* cpus that have inodes queued for inactivation */ struct cpumask m_inodegc_cpumask; /* Hook to feed dirent updates to an active online repair. */ struct xfs_hooks m_dir_update_hooks; } xfs_mount_t; #define M_IGEO(mp) (&(mp)->m_ino_geo) /* * Flags for m_features. * * These are all the active features in the filesystem, regardless of how * they are configured. */ #define XFS_FEAT_ATTR (1ULL << 0) /* xattrs present in fs */ #define XFS_FEAT_NLINK (1ULL << 1) /* 32 bit link counts */ #define XFS_FEAT_QUOTA (1ULL << 2) /* quota active */ #define XFS_FEAT_ALIGN (1ULL << 3) /* inode alignment */ #define XFS_FEAT_DALIGN (1ULL << 4) /* data alignment */ #define XFS_FEAT_LOGV2 (1ULL << 5) /* version 2 logs */ #define XFS_FEAT_SECTOR (1ULL << 6) /* sector size > 512 bytes */ #define XFS_FEAT_EXTFLG (1ULL << 7) /* unwritten extents */ #define XFS_FEAT_ASCIICI (1ULL << 8) /* ASCII only case-insens. */ #define XFS_FEAT_LAZYSBCOUNT (1ULL << 9) /* Superblk counters */ #define XFS_FEAT_ATTR2 (1ULL << 10) /* dynamic attr fork */ #define XFS_FEAT_PARENT (1ULL << 11) /* parent pointers */ #define XFS_FEAT_PROJID32 (1ULL << 12) /* 32 bit project id */ #define XFS_FEAT_CRC (1ULL << 13) /* metadata CRCs */ #define XFS_FEAT_V3INODES (1ULL << 14) /* Version 3 inodes */ #define XFS_FEAT_PQUOTINO (1ULL << 15) /* non-shared proj/grp quotas */ #define XFS_FEAT_FTYPE (1ULL << 16) /* inode type in dir */ #define XFS_FEAT_FINOBT (1ULL << 17) /* free inode btree */ #define XFS_FEAT_RMAPBT (1ULL << 18) /* reverse map btree */ #define XFS_FEAT_REFLINK (1ULL << 19) /* reflinked files */ #define XFS_FEAT_SPINODES (1ULL << 20) /* sparse inode chunks */ #define XFS_FEAT_META_UUID (1ULL << 21) /* metadata UUID */ #define XFS_FEAT_REALTIME (1ULL << 22) /* realtime device present */ #define XFS_FEAT_INOBTCNT (1ULL << 23) /* inobt block counts */ #define XFS_FEAT_BIGTIME (1ULL << 24) /* large timestamps */ #define XFS_FEAT_NEEDSREPAIR (1ULL << 25) /* needs xfs_repair */ #define XFS_FEAT_NREXT64 (1ULL << 26) /* large extent counters */ #define XFS_FEAT_EXCHANGE_RANGE (1ULL << 27) /* exchange range */ #define XFS_FEAT_METADIR (1ULL << 28) /* metadata directory tree */ #define XFS_FEAT_ZONED (1ULL << 29) /* zoned RT device */ /* Mount features */ #define XFS_FEAT_NOLIFETIME (1ULL << 47) /* disable lifetime hints */ #define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */ #define XFS_FEAT_NOALIGN (1ULL << 49) /* ignore alignment */ #define XFS_FEAT_ALLOCSIZE (1ULL << 50) /* user specified allocation size */ #define XFS_FEAT_LARGE_IOSIZE (1ULL << 51) /* report large preferred * I/O size in stat() */ #define XFS_FEAT_WSYNC (1ULL << 52) /* synchronous metadata ops */ #define XFS_FEAT_DIRSYNC (1ULL << 53) /* synchronous directory ops */ #define XFS_FEAT_DISCARD (1ULL << 54) /* discard unused blocks */ #define XFS_FEAT_GRPID (1ULL << 55) /* group-ID assigned from directory */ #define XFS_FEAT_SMALL_INUMS (1ULL << 56) /* user wants 32bit inodes */ #define XFS_FEAT_IKEEP (1ULL << 57) /* keep empty inode clusters*/ #define XFS_FEAT_SWALLOC (1ULL << 58) /* stripe width allocation */ #define XFS_FEAT_FILESTREAMS (1ULL << 59) /* use filestreams allocator */ #define XFS_FEAT_DAX_ALWAYS (1ULL << 60) /* DAX always enabled */ #define XFS_FEAT_DAX_NEVER (1ULL << 61) /* DAX never enabled */ #define XFS_FEAT_NORECOVERY (1ULL << 62) /* no recovery - dirty fs */ #define XFS_FEAT_NOUUID (1ULL << 63) /* ignore uuid during mount */ #define __XFS_HAS_FEAT(name, NAME) \ static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \ { \ return mp->m_features & XFS_FEAT_ ## NAME; \ } /* Some features can be added dynamically so they need a set wrapper, too. */ #define __XFS_ADD_FEAT(name, NAME) \ __XFS_HAS_FEAT(name, NAME); \ static inline void xfs_add_ ## name (struct xfs_mount *mp) \ { \ mp->m_features |= XFS_FEAT_ ## NAME; \ xfs_sb_version_add ## name(&mp->m_sb); \ } /* Superblock features */ __XFS_ADD_FEAT(attr, ATTR) __XFS_HAS_FEAT(nlink, NLINK) __XFS_ADD_FEAT(quota, QUOTA) __XFS_HAS_FEAT(dalign, DALIGN) __XFS_HAS_FEAT(sector, SECTOR) __XFS_HAS_FEAT(asciici, ASCIICI) __XFS_HAS_FEAT(parent, PARENT) __XFS_HAS_FEAT(ftype, FTYPE) __XFS_HAS_FEAT(finobt, FINOBT) __XFS_HAS_FEAT(rmapbt, RMAPBT) __XFS_HAS_FEAT(reflink, REFLINK) __XFS_HAS_FEAT(sparseinodes, SPINODES) __XFS_HAS_FEAT(metauuid, META_UUID) __XFS_HAS_FEAT(realtime, REALTIME) __XFS_HAS_FEAT(inobtcounts, INOBTCNT) __XFS_HAS_FEAT(bigtime, BIGTIME) __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR) __XFS_HAS_FEAT(large_extent_counts, NREXT64) __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE) __XFS_HAS_FEAT(metadir, METADIR) __XFS_HAS_FEAT(zoned, ZONED) __XFS_HAS_FEAT(nolifetime, NOLIFETIME) static inline bool xfs_has_rtgroups(const struct xfs_mount *mp) { /* all metadir file systems also allow rtgroups */ return xfs_has_metadir(mp); } static inline bool xfs_has_rtsb(const struct xfs_mount *mp) { /* all rtgroups filesystems with an rt section have an rtsb */ return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) && !xfs_has_zoned(mp); } static inline bool xfs_has_rtrmapbt(const struct xfs_mount *mp) { return xfs_has_rtgroups(mp) && xfs_has_realtime(mp) && xfs_has_rmapbt(mp); } static inline bool xfs_has_rtreflink(const struct xfs_mount *mp) { return xfs_has_metadir(mp) && xfs_has_realtime(mp) && xfs_has_reflink(mp); } static inline bool xfs_has_nonzoned(const struct xfs_mount *mp) { return !xfs_has_zoned(mp); } static inline bool xfs_can_sw_atomic_write(struct xfs_mount *mp) { return xfs_has_reflink(mp); } /* * Some features are always on for v5 file systems, allow the compiler to * eliminiate dead code when building without v4 support. */ #define __XFS_HAS_V4_FEAT(name, NAME) \ static inline bool xfs_has_ ## name (struct xfs_mount *mp) \ { \ return !IS_ENABLED(CONFIG_XFS_SUPPORT_V4) || \ (mp->m_features & XFS_FEAT_ ## NAME); \ } #define __XFS_ADD_V4_FEAT(name, NAME) \ __XFS_HAS_V4_FEAT(name, NAME); \ static inline void xfs_add_ ## name (struct xfs_mount *mp) \ { \ if (IS_ENABLED(CONFIG_XFS_SUPPORT_V4)) { \ mp->m_features |= XFS_FEAT_ ## NAME; \ xfs_sb_version_add ## name(&mp->m_sb); \ } \ } __XFS_HAS_V4_FEAT(align, ALIGN) __XFS_HAS_V4_FEAT(logv2, LOGV2) __XFS_HAS_V4_FEAT(extflg, EXTFLG) __XFS_HAS_V4_FEAT(lazysbcount, LAZYSBCOUNT) __XFS_ADD_V4_FEAT(attr2, ATTR2) __XFS_ADD_V4_FEAT(projid32, PROJID32) __XFS_HAS_V4_FEAT(v3inodes, V3INODES) __XFS_HAS_V4_FEAT(crc, CRC) __XFS_HAS_V4_FEAT(pquotino, PQUOTINO) /* * Mount features * * These do not change dynamically - features that can come and go, such as 32 * bit inodes and read-only state, are kept as operational state rather than * features. */ __XFS_HAS_FEAT(noattr2, NOATTR2) __XFS_HAS_FEAT(noalign, NOALIGN) __XFS_HAS_FEAT(allocsize, ALLOCSIZE) __XFS_HAS_FEAT(large_iosize, LARGE_IOSIZE) __XFS_HAS_FEAT(wsync, WSYNC) __XFS_HAS_FEAT(dirsync, DIRSYNC) __XFS_HAS_FEAT(discard, DISCARD) __XFS_HAS_FEAT(grpid, GRPID) __XFS_HAS_FEAT(small_inums, SMALL_INUMS) __XFS_HAS_FEAT(ikeep, IKEEP) __XFS_HAS_FEAT(swalloc, SWALLOC) __XFS_HAS_FEAT(filestreams, FILESTREAMS) __XFS_HAS_FEAT(dax_always, DAX_ALWAYS) __XFS_HAS_FEAT(dax_never, DAX_NEVER) __XFS_HAS_FEAT(norecovery, NORECOVERY) __XFS_HAS_FEAT(nouuid, NOUUID) /* * Operational mount state flags * * Use these with atomic bit ops only! */ #define XFS_OPSTATE_UNMOUNTING 0 /* filesystem is unmounting */ #define XFS_OPSTATE_CLEAN 1 /* mount was clean */ #define XFS_OPSTATE_SHUTDOWN 2 /* stop all fs operations */ #define XFS_OPSTATE_INODE32 3 /* inode32 allocator active */ #define XFS_OPSTATE_READONLY 4 /* read-only fs */ /* * If set, inactivation worker threads will be scheduled to process queued * inodegc work. If not, queued inodes remain in memory waiting to be * processed. */ #define XFS_OPSTATE_INODEGC_ENABLED 5 /* * If set, background speculative prealloc gc worker threads will be scheduled * to process queued blockgc work. If not, inodes retain their preallocations * until explicitly deleted. */ #define XFS_OPSTATE_BLOCKGC_ENABLED 6 /* Kernel has logged a warning about shrink being used on this fs. */ #define XFS_OPSTATE_WARNED_SHRINK 9 /* Kernel has logged a warning about logged xattr updates being used. */ #define XFS_OPSTATE_WARNED_LARP 10 /* Mount time quotacheck is running */ #define XFS_OPSTATE_QUOTACHECK_RUNNING 11 /* Do we want to clear log incompat flags? */ #define XFS_OPSTATE_UNSET_LOG_INCOMPAT 12 /* Filesystem can use logged extended attributes */ #define XFS_OPSTATE_USE_LARP 13 /* Kernel has logged a warning about blocksize > pagesize on this fs. */ #define XFS_OPSTATE_WARNED_LBS 14 /* Kernel has logged a warning about metadata dirs being used on this fs. */ #define XFS_OPSTATE_WARNED_METADIR 17 /* Filesystem should use qflags to determine quotaon status */ #define XFS_OPSTATE_RESUMING_QUOTAON 18 /* Kernel has logged a warning about zoned RT device being used on this fs. */ #define XFS_OPSTATE_WARNED_ZONED 19 /* (Zoned) GC is in progress */ #define XFS_OPSTATE_ZONEGC_RUNNING 20 #define __XFS_IS_OPSTATE(name, NAME) \ static inline bool xfs_is_ ## name (struct xfs_mount *mp) \ { \ return test_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \ } \ static inline bool xfs_clear_ ## name (struct xfs_mount *mp) \ { \ return test_and_clear_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \ } \ static inline bool xfs_set_ ## name (struct xfs_mount *mp) \ { \ return test_and_set_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \ } __XFS_IS_OPSTATE(unmounting, UNMOUNTING) __XFS_IS_OPSTATE(clean, CLEAN) __XFS_IS_OPSTATE(shutdown, SHUTDOWN) __XFS_IS_OPSTATE(inode32, INODE32) __XFS_IS_OPSTATE(readonly, READONLY) __XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED) __XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED) #ifdef CONFIG_XFS_QUOTA __XFS_IS_OPSTATE(quotacheck_running, QUOTACHECK_RUNNING) __XFS_IS_OPSTATE(resuming_quotaon, RESUMING_QUOTAON) #else static inline bool xfs_is_quotacheck_running(struct xfs_mount *mp) { return false; } static inline bool xfs_is_resuming_quotaon(struct xfs_mount *mp) { return false; } static inline void xfs_set_resuming_quotaon(struct xfs_mount *m) { } static inline bool xfs_clear_resuming_quotaon(struct xfs_mount *mp) { return false; } #endif /* CONFIG_XFS_QUOTA */ __XFS_IS_OPSTATE(done_with_log_incompat, UNSET_LOG_INCOMPAT) __XFS_IS_OPSTATE(using_logged_xattrs, USE_LARP) __XFS_IS_OPSTATE(zonegc_running, ZONEGC_RUNNING) static inline bool xfs_should_warn(struct xfs_mount *mp, long nr) { return !test_and_set_bit(nr, &mp->m_opstate); } #define XFS_OPSTATE_STRINGS \ { (1UL << XFS_OPSTATE_UNMOUNTING), "unmounting" }, \ { (1UL << XFS_OPSTATE_CLEAN), "clean" }, \ { (1UL << XFS_OPSTATE_SHUTDOWN), "shutdown" }, \ { (1UL << XFS_OPSTATE_INODE32), "inode32" }, \ { (1UL << XFS_OPSTATE_READONLY), "read_only" }, \ { (1UL << XFS_OPSTATE_INODEGC_ENABLED), "inodegc" }, \ { (1UL << XFS_OPSTATE_BLOCKGC_ENABLED), "blockgc" }, \ { (1UL << XFS_OPSTATE_WARNED_SHRINK), "wshrink" }, \ { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" }, \ { (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING), "quotacheck" }, \ { (1UL << XFS_OPSTATE_UNSET_LOG_INCOMPAT), "unset_log_incompat" }, \ { (1UL << XFS_OPSTATE_USE_LARP), "logged_xattrs" } /* * Max and min values for mount-option defined I/O * preallocation sizes. */ #define XFS_MAX_IO_LOG 30 /* 1G */ #define XFS_MIN_IO_LOG PAGE_SHIFT void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, int lnnum); #define xfs_force_shutdown(m,f) \ xfs_do_force_shutdown(m, f, __FILE__, __LINE__) #define SHUTDOWN_META_IO_ERROR (1u << 0) /* write attempt to metadata failed */ #define SHUTDOWN_LOG_IO_ERROR (1u << 1) /* write attempt to the log failed */ #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ #define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ #define SHUTDOWN_DEVICE_REMOVED (1u << 5) /* device removed underneath us */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ { SHUTDOWN_LOG_IO_ERROR, "log_io" }, \ { SHUTDOWN_FORCE_UMOUNT, "force_umount" }, \ { SHUTDOWN_CORRUPT_INCORE, "corruption" }, \ { SHUTDOWN_DEVICE_REMOVED, "device_removed" } /* * Flags for xfs_mountfs */ #define XFS_MFSI_QUIET 0x40 /* Be silent if mount errors found */ static inline xfs_agnumber_t xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d) { xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d); do_div(ld, mp->m_sb.sb_agblocks); return (xfs_agnumber_t) ld; } static inline xfs_agblock_t xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) { xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d); return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks); } extern void xfs_uuid_table_free(void); uint64_t xfs_default_resblks(struct xfs_mount *mp, enum xfs_free_counter ctr); extern int xfs_mountfs(xfs_mount_t *mp); extern void xfs_unmountfs(xfs_mount_t *); /* * Deltas for the block count can vary from 1 to very large, but lock contention * only occurs on frequent small block count updates such as in the delayed * allocation path for buffered writes (page a time updates). Hence we set * a large batch count (1024) to minimise global counter updates except when * we get near to ENOSPC and we have to be very accurate with our updates. */ #define XFS_FDBLOCKS_BATCH 1024 uint64_t xfs_freecounter_unavailable(struct xfs_mount *mp, enum xfs_free_counter ctr); /* * Sum up the freecount, but never return negative values. */ static inline s64 xfs_sum_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr) { return percpu_counter_sum_positive(&mp->m_free[ctr].count); } /* * Same as above, but does return negative values. Mostly useful for * special cases like repair and tracing. */ static inline s64 xfs_sum_freecounter_raw(struct xfs_mount *mp, enum xfs_free_counter ctr) { return percpu_counter_sum(&mp->m_free[ctr].count); } /* * This just provides and estimate without the cpu-local updates, use * xfs_sum_freecounter for the exact value. */ static inline s64 xfs_estimate_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr) { return percpu_counter_read_positive(&mp->m_free[ctr].count); } static inline int xfs_compare_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr, s64 rhs, s32 batch) { return __percpu_counter_compare(&mp->m_free[ctr].count, rhs, batch); } static inline void xfs_set_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr, uint64_t val) { percpu_counter_set(&mp->m_free[ctr].count, val); } int xfs_dec_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr, uint64_t delta, bool rsvd); void xfs_add_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr, uint64_t delta); static inline int xfs_dec_fdblocks(struct xfs_mount *mp, uint64_t delta, bool reserved) { return xfs_dec_freecounter(mp, XC_FREE_BLOCKS, delta, reserved); } static inline void xfs_add_fdblocks(struct xfs_mount *mp, uint64_t delta) { xfs_add_freecounter(mp, XC_FREE_BLOCKS, delta); } static inline int xfs_dec_frextents(struct xfs_mount *mp, uint64_t delta) { return xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, delta, false); } static inline void xfs_add_frextents(struct xfs_mount *mp, uint64_t delta) { xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, delta); } extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); extern bool xfs_fs_writable(struct xfs_mount *mp, int level); extern int xfs_sb_validate_fsb_count(struct xfs_sb *, uint64_t); extern int xfs_dev_is_read_only(struct xfs_mount *, char *); extern void xfs_set_low_space_thresholds(struct xfs_mount *); int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb, xfs_off_t count_fsb); struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp, int error_class, int error); void xfs_force_summary_recalc(struct xfs_mount *mp); int xfs_add_incompat_log_feature(struct xfs_mount *mp, uint32_t feature); bool xfs_clear_incompat_log_features(struct xfs_mount *mp); void xfs_mod_delalloc(struct xfs_inode *ip, int64_t data_delta, int64_t ind_delta); static inline void xfs_mod_sb_delalloc(struct xfs_mount *mp, int64_t delta) { percpu_counter_add(&mp->m_delalloc_blks, delta); } int xfs_set_max_atomic_write_opt(struct xfs_mount *mp, unsigned long long new_max_bytes); static inline struct xfs_buftarg * xfs_group_type_buftarg( struct xfs_mount *mp, enum xfs_group_type type) { switch (type) { case XG_TYPE_AG: return mp->m_ddev_targp; case XG_TYPE_RTG: return mp->m_rtdev_targp; default: ASSERT(0); break; } return NULL; } #endif /* __XFS_MOUNT_H__ */ |
| 6 251 6 145 251 23 5 5 5 251 249 251 251 228 147 147 144 5 147 145 251 251 251 248 32 250 249 250 3 3 249 249 250 2 250 25 6 25 25 25 24 11 6 5 11 11 11 11 3 3 3 213 214 212 213 1 208 36 6 8 4 3 214 2 246 36 246 206 209 208 246 244 205 213 115 73 2 86 2 85 87 59 59 3 244 244 202 211 214 214 213 8 214 249 31 249 250 250 250 250 250 212 199 9 214 214 214 214 213 214 214 214 214 213 213 214 214 214 214 214 214 208 214 31 29 27 29 1 27 1 27 31 7 7 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 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 | // SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/transaction.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * Generic filesystem transaction handling code; part of the ext2fs * journaling system. * * This file manages transactions (compound commits managed by the * journaling code) and handles (individual atomic operations by the * filesystem). */ #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/hrtimer.h> #include <linux/backing-dev.h> #include <linux/bug.h> #include <linux/module.h> #include <linux/sched/mm.h> #include <trace/events/jbd2.h> static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); static void __jbd2_journal_unfile_buffer(struct journal_head *jh); static struct kmem_cache *transaction_cache; int __init jbd2_journal_init_transaction_cache(void) { J_ASSERT(!transaction_cache); transaction_cache = kmem_cache_create("jbd2_transaction_s", sizeof(transaction_t), 0, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY, NULL); if (!transaction_cache) { pr_emerg("JBD2: failed to create transaction cache\n"); return -ENOMEM; } return 0; } void jbd2_journal_destroy_transaction_cache(void) { kmem_cache_destroy(transaction_cache); transaction_cache = NULL; } void jbd2_journal_free_transaction(transaction_t *transaction) { if (unlikely(ZERO_OR_NULL_PTR(transaction))) return; kmem_cache_free(transaction_cache, transaction); } /* * jbd2_get_transaction: obtain a new transaction_t object. * * Simply initialise a new transaction. Initialize it in * RUNNING state and add it to the current journal (which should not * have an existing running transaction: we only make a new transaction * once we have started to commit the old one). * * Preconditions: * The journal MUST be locked. We don't perform atomic mallocs on the * new transaction and we can't block without protecting against other * processes trying to touch the journal while it is in transition. * */ static void jbd2_get_transaction(journal_t *journal, transaction_t *transaction) { transaction->t_journal = journal; transaction->t_state = T_RUNNING; transaction->t_start_time = ktime_get(); transaction->t_tid = journal->j_transaction_sequence++; transaction->t_expires = jiffies + journal->j_commit_interval; atomic_set(&transaction->t_updates, 0); atomic_set(&transaction->t_outstanding_credits, journal->j_transaction_overhead_buffers + atomic_read(&journal->j_reserved_credits)); atomic_set(&transaction->t_outstanding_revokes, 0); atomic_set(&transaction->t_handle_count, 0); INIT_LIST_HEAD(&transaction->t_inode_list); /* Set up the commit timer for the new transaction. */ journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires); add_timer(&journal->j_commit_timer); J_ASSERT(journal->j_running_transaction == NULL); journal->j_running_transaction = transaction; transaction->t_max_wait = 0; transaction->t_start = jiffies; transaction->t_requested = 0; } /* * Handle management. * * A handle_t is an object which represents a single atomic update to a * filesystem, and which tracks all of the modifications which form part * of that one update. */ /* * t_max_wait is carefully updated here with use of atomic compare exchange. * Note that there could be multiplre threads trying to do this simultaneously * hence using cmpxchg to avoid any use of locks in this case. */ static inline void update_t_max_wait(transaction_t *transaction, unsigned long ts) { unsigned long oldts, newts; if (time_after(transaction->t_start, ts)) { newts = jbd2_time_diff(ts, transaction->t_start); oldts = READ_ONCE(transaction->t_max_wait); while (oldts < newts) oldts = cmpxchg(&transaction->t_max_wait, oldts, newts); } } /* * Wait until running transaction passes to T_FLUSH state and new transaction * can thus be started. Also starts the commit if needed. The function expects * running transaction to exist and releases j_state_lock. */ static void wait_transaction_locked(journal_t *journal) __releases(journal->j_state_lock) { DEFINE_WAIT(wait); int need_to_start; tid_t tid = journal->j_running_transaction->t_tid; prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); jbd2_might_wait_for_commit(journal); schedule(); finish_wait(&journal->j_wait_transaction_locked, &wait); } /* * Wait until running transaction transitions from T_SWITCH to T_FLUSH * state and new transaction can thus be started. The function releases * j_state_lock. */ static void wait_transaction_switching(journal_t *journal) __releases(journal->j_state_lock) { DEFINE_WAIT(wait); if (WARN_ON(!journal->j_running_transaction || journal->j_running_transaction->t_state != T_SWITCH)) { read_unlock(&journal->j_state_lock); return; } prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); /* * We don't call jbd2_might_wait_for_commit() here as there's no * waiting for outstanding handles happening anymore in T_SWITCH state * and handling of reserved handles actually relies on that for * correctness. */ schedule(); finish_wait(&journal->j_wait_transaction_locked, &wait); } static void sub_reserved_credits(journal_t *journal, int blocks) { atomic_sub(blocks, &journal->j_reserved_credits); wake_up(&journal->j_wait_reserved); } /* Maximum number of blocks for user transaction payload */ static int jbd2_max_user_trans_buffers(journal_t *journal) { return journal->j_max_transaction_buffers - journal->j_transaction_overhead_buffers; } /* * Wait until we can add credits for handle to the running transaction. Called * with j_state_lock held for reading. Returns 0 if handle joined the running * transaction. Returns 1 if we had to wait, j_state_lock is dropped, and * caller must retry. * * Note: because j_state_lock may be dropped depending on the return * value, we need to fake out sparse so ti doesn't complain about a * locking imbalance. Callers of add_transaction_credits will need to * make a similar accomodation. */ static int add_transaction_credits(journal_t *journal, int blocks, int rsv_blocks) __must_hold(&journal->j_state_lock) { transaction_t *t = journal->j_running_transaction; int needed; int total = blocks + rsv_blocks; /* * If the current transaction is locked down for commit, wait * for the lock to be released. */ if (t->t_state != T_RUNNING) { WARN_ON_ONCE(t->t_state >= T_FLUSH); wait_transaction_locked(journal); __acquire(&journal->j_state_lock); /* fake out sparse */ return 1; } /* * If there is not enough space left in the log to write all * potential buffers requested by this operation, we need to * stall pending a log checkpoint to free some more log space. */ needed = atomic_add_return(total, &t->t_outstanding_credits); if (needed > journal->j_max_transaction_buffers) { /* * If the current transaction is already too large, * then start to commit it: we can then go back and * attach this handle to a new transaction. */ atomic_sub(total, &t->t_outstanding_credits); /* * Is the number of reserved credits in the current transaction too * big to fit this handle? Wait until reserved credits are freed. */ if (atomic_read(&journal->j_reserved_credits) + total > jbd2_max_user_trans_buffers(journal)) { read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); wait_event(journal->j_wait_reserved, atomic_read(&journal->j_reserved_credits) + total <= jbd2_max_user_trans_buffers(journal)); __acquire(&journal->j_state_lock); /* fake out sparse */ return 1; } wait_transaction_locked(journal); __acquire(&journal->j_state_lock); /* fake out sparse */ return 1; } /* * The commit code assumes that it can get enough log space * without forcing a checkpoint. This is *critical* for * correctness: a checkpoint of a buffer which is also * associated with a committing transaction creates a deadlock, * so commit simply cannot force through checkpoints. * * We must therefore ensure the necessary space in the journal * *before* starting to dirty potentially checkpointed buffers * in the new transaction. */ if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) { atomic_sub(total, &t->t_outstanding_credits); read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); write_lock(&journal->j_state_lock); if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) __jbd2_log_wait_for_space(journal); write_unlock(&journal->j_state_lock); __acquire(&journal->j_state_lock); /* fake out sparse */ return 1; } /* No reservation? We are done... */ if (!rsv_blocks) return 0; needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits); /* We allow at most half of a transaction to be reserved */ if (needed > jbd2_max_user_trans_buffers(journal) / 2) { sub_reserved_credits(journal, rsv_blocks); atomic_sub(total, &t->t_outstanding_credits); read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); wait_event(journal->j_wait_reserved, atomic_read(&journal->j_reserved_credits) + rsv_blocks <= jbd2_max_user_trans_buffers(journal) / 2); __acquire(&journal->j_state_lock); /* fake out sparse */ return 1; } return 0; } /* * start_this_handle: Given a handle, deal with any locking or stalling * needed to make sure that there is enough journal space for the handle * to begin. Attach the handle to a transaction and set up the * transaction's buffer credits. */ static int start_this_handle(journal_t *journal, handle_t *handle, gfp_t gfp_mask) { transaction_t *transaction, *new_transaction = NULL; int blocks = handle->h_total_credits; int rsv_blocks = 0; unsigned long ts = jiffies; if (handle->h_rsv_handle) rsv_blocks = handle->h_rsv_handle->h_total_credits; /* * Limit the number of reserved credits to 1/2 of maximum transaction * size and limit the number of total credits to not exceed maximum * transaction size per operation. */ if (rsv_blocks > jbd2_max_user_trans_buffers(journal) / 2 || rsv_blocks + blocks > jbd2_max_user_trans_buffers(journal)) { printk(KERN_ERR "JBD2: %s wants too many credits " "credits:%d rsv_credits:%d max:%d\n", current->comm, blocks, rsv_blocks, jbd2_max_user_trans_buffers(journal)); WARN_ON(1); return -ENOSPC; } alloc_transaction: /* * This check is racy but it is just an optimization of allocating new * transaction early if there are high chances we'll need it. If we * guess wrong, we'll retry or free unused transaction. */ if (!data_race(journal->j_running_transaction)) { /* * If __GFP_FS is not present, then we may be being called from * inside the fs writeback layer, so we MUST NOT fail. */ if ((gfp_mask & __GFP_FS) == 0) gfp_mask |= __GFP_NOFAIL; new_transaction = kmem_cache_zalloc(transaction_cache, gfp_mask); if (!new_transaction) return -ENOMEM; } jbd2_debug(3, "New handle %p going live.\n", handle); /* * We need to hold j_state_lock until t_updates has been incremented, * for proper journal barrier handling */ repeat: read_lock(&journal->j_state_lock); BUG_ON(journal->j_flags & JBD2_UNMOUNT); if (is_journal_aborted(journal) || (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) { read_unlock(&journal->j_state_lock); jbd2_journal_free_transaction(new_transaction); return -EROFS; } /* * Wait on the journal's transaction barrier if necessary. Specifically * we allow reserved handles to proceed because otherwise commit could * deadlock on page writeback not being able to complete. */ if (!handle->h_reserved && journal->j_barrier_count) { read_unlock(&journal->j_state_lock); wait_event(journal->j_wait_transaction_locked, journal->j_barrier_count == 0); goto repeat; } if (!journal->j_running_transaction) { read_unlock(&journal->j_state_lock); if (!new_transaction) goto alloc_transaction; write_lock(&journal->j_state_lock); if (!journal->j_running_transaction && (handle->h_reserved || !journal->j_barrier_count)) { jbd2_get_transaction(journal, new_transaction); new_transaction = NULL; } write_unlock(&journal->j_state_lock); goto repeat; } transaction = journal->j_running_transaction; if (!handle->h_reserved) { /* We may have dropped j_state_lock - restart in that case */ if (add_transaction_credits(journal, blocks, rsv_blocks)) { /* * add_transaction_credits releases * j_state_lock on a non-zero return */ __release(&journal->j_state_lock); goto repeat; } } else { /* * We have handle reserved so we are allowed to join T_LOCKED * transaction and we don't have to check for transaction size * and journal space. But we still have to wait while running * transaction is being switched to a committing one as it * won't wait for any handles anymore. */ if (transaction->t_state == T_SWITCH) { wait_transaction_switching(journal); goto repeat; } sub_reserved_credits(journal, blocks); handle->h_reserved = 0; } /* OK, account for the buffers that this operation expects to * use and add the handle to the running transaction. */ update_t_max_wait(transaction, ts); handle->h_transaction = transaction; handle->h_requested_credits = blocks; handle->h_revoke_credits_requested = handle->h_revoke_credits; handle->h_start_jiffies = jiffies; atomic_inc(&transaction->t_updates); atomic_inc(&transaction->t_handle_count); jbd2_debug(4, "Handle %p given %d credits (total %d, free %lu)\n", handle, blocks, atomic_read(&transaction->t_outstanding_credits), jbd2_log_space_left(journal)); read_unlock(&journal->j_state_lock); current->journal_info = handle; rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_); jbd2_journal_free_transaction(new_transaction); /* * Ensure that no allocations done while the transaction is open are * going to recurse back to the fs layer. */ handle->saved_alloc_context = memalloc_nofs_save(); return 0; } /* Allocate a new handle. This should probably be in a slab... */ static handle_t *new_handle(int nblocks) { handle_t *handle = jbd2_alloc_handle(GFP_NOFS); if (!handle) return NULL; handle->h_total_credits = nblocks; handle->h_ref = 1; return handle; } handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no) { handle_t *handle = journal_current_handle(); int err; if (!journal) return ERR_PTR(-EROFS); if (handle) { J_ASSERT(handle->h_transaction->t_journal == journal); handle->h_ref++; return handle; } nblocks += DIV_ROUND_UP(revoke_records, journal->j_revoke_records_per_block); handle = new_handle(nblocks); if (!handle) return ERR_PTR(-ENOMEM); if (rsv_blocks) { handle_t *rsv_handle; rsv_handle = new_handle(rsv_blocks); if (!rsv_handle) { jbd2_free_handle(handle); return ERR_PTR(-ENOMEM); } rsv_handle->h_reserved = 1; rsv_handle->h_journal = journal; handle->h_rsv_handle = rsv_handle; } handle->h_revoke_credits = revoke_records; err = start_this_handle(journal, handle, gfp_mask); if (err < 0) { if (handle->h_rsv_handle) jbd2_free_handle(handle->h_rsv_handle); jbd2_free_handle(handle); return ERR_PTR(err); } handle->h_type = type; handle->h_line_no = line_no; trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, handle->h_transaction->t_tid, type, line_no, nblocks); return handle; } EXPORT_SYMBOL(jbd2__journal_start); /** * jbd2_journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * * We make sure that the transaction can guarantee at least nblocks of * modified buffers in the log. We block until the log can guarantee * that much space. Additionally, if rsv_blocks > 0, we also create another * handle with rsv_blocks reserved blocks in the journal. This handle is * stored in h_rsv_handle. It is not attached to any particular transaction * and thus doesn't block transaction commit. If the caller uses this reserved * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() * on the parent handle will dispose the reserved one. Reserved handle has to * be converted to a normal handle using jbd2_journal_start_reserved() before * it can be used. * * Return a pointer to a newly allocated handle, or an ERR_PTR() value * on failure. */ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) { return jbd2__journal_start(journal, nblocks, 0, 0, GFP_NOFS, 0, 0); } EXPORT_SYMBOL(jbd2_journal_start); static void __jbd2_journal_unreserve_handle(handle_t *handle, transaction_t *t) { journal_t *journal = handle->h_journal; WARN_ON(!handle->h_reserved); sub_reserved_credits(journal, handle->h_total_credits); if (t) atomic_sub(handle->h_total_credits, &t->t_outstanding_credits); } void jbd2_journal_free_reserved(handle_t *handle) { journal_t *journal = handle->h_journal; /* Get j_state_lock to pin running transaction if it exists */ read_lock(&journal->j_state_lock); __jbd2_journal_unreserve_handle(handle, journal->j_running_transaction); read_unlock(&journal->j_state_lock); jbd2_free_handle(handle); } EXPORT_SYMBOL(jbd2_journal_free_reserved); /** * jbd2_journal_start_reserved() - start reserved handle * @handle: handle to start * @type: for handle statistics * @line_no: for handle statistics * * Start handle that has been previously reserved with jbd2_journal_reserve(). * This attaches @handle to the running transaction (or creates one if there's * not transaction running). Unlike jbd2_journal_start() this function cannot * block on journal commit, checkpointing, or similar stuff. It can block on * memory allocation or frozen journal though. * * Return 0 on success, non-zero on error - handle is freed in that case. */ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no) { journal_t *journal = handle->h_journal; int ret = -EIO; if (WARN_ON(!handle->h_reserved)) { /* Someone passed in normal handle? Just stop it. */ jbd2_journal_stop(handle); return ret; } /* * Usefulness of mixing of reserved and unreserved handles is * questionable. So far nobody seems to need it so just error out. */ if (WARN_ON(current->journal_info)) { jbd2_journal_free_reserved(handle); return ret; } handle->h_journal = NULL; /* * GFP_NOFS is here because callers are likely from writeback or * similarly constrained call sites */ ret = start_this_handle(journal, handle, GFP_NOFS); if (ret < 0) { handle->h_journal = journal; jbd2_journal_free_reserved(handle); return ret; } handle->h_type = type; handle->h_line_no = line_no; trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, handle->h_transaction->t_tid, type, line_no, handle->h_total_credits); return 0; } EXPORT_SYMBOL(jbd2_journal_start_reserved); /** * jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. * @revoke_records: number of revoke records to try to extend by. * * Some transactions, such as large extends and truncates, can be done * atomically all at once or in several stages. The operation requests * a credit for a number of buffer modifications in advance, but can * extend its credit if it needs more. * * jbd2_journal_extend tries to give the running handle more buffer credits. * It does not guarantee that allocation - this is a best-effort only. * The calling process MUST be able to deal cleanly with a failure to * extend here. * * Return 0 on success, non-zero on failure. * * return code < 0 implies an error * return code > 0 implies normal transaction-full status. */ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) { transaction_t *transaction = handle->h_transaction; journal_t *journal; int result; int wanted; if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; result = 1; read_lock(&journal->j_state_lock); /* Don't extend a locked-down transaction! */ if (transaction->t_state != T_RUNNING) { jbd2_debug(3, "denied handle %p %d blocks: " "transaction not running\n", handle, nblocks); goto error_out; } nblocks += DIV_ROUND_UP( handle->h_revoke_credits_requested + revoke_records, journal->j_revoke_records_per_block) - DIV_ROUND_UP( handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); wanted = atomic_add_return(nblocks, &transaction->t_outstanding_credits); if (wanted > journal->j_max_transaction_buffers) { jbd2_debug(3, "denied handle %p %d blocks: " "transaction too large\n", handle, nblocks); atomic_sub(nblocks, &transaction->t_outstanding_credits); goto error_out; } trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev, transaction->t_tid, handle->h_type, handle->h_line_no, handle->h_total_credits, nblocks); handle->h_total_credits += nblocks; handle->h_requested_credits += nblocks; handle->h_revoke_credits += revoke_records; handle->h_revoke_credits_requested += revoke_records; result = 0; jbd2_debug(3, "extended handle %p by %d\n", handle, nblocks); error_out: read_unlock(&journal->j_state_lock); return result; } static void stop_this_handle(handle_t *handle) { transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; int revokes; J_ASSERT(journal_current_handle() == handle); J_ASSERT(atomic_read(&transaction->t_updates) > 0); current->journal_info = NULL; /* * Subtract necessary revoke descriptor blocks from handle credits. We * take care to account only for revoke descriptor blocks the * transaction will really need as large sequences of transactions with * small numbers of revokes are relatively common. */ revokes = handle->h_revoke_credits_requested - handle->h_revoke_credits; if (revokes) { int t_revokes, revoke_descriptors; int rr_per_blk = journal->j_revoke_records_per_block; WARN_ON_ONCE(DIV_ROUND_UP(revokes, rr_per_blk) > handle->h_total_credits); t_revokes = atomic_add_return(revokes, &transaction->t_outstanding_revokes); revoke_descriptors = DIV_ROUND_UP(t_revokes, rr_per_blk) - DIV_ROUND_UP(t_revokes - revokes, rr_per_blk); handle->h_total_credits -= revoke_descriptors; } atomic_sub(handle->h_total_credits, &transaction->t_outstanding_credits); if (handle->h_rsv_handle) __jbd2_journal_unreserve_handle(handle->h_rsv_handle, transaction); if (atomic_dec_and_test(&transaction->t_updates)) wake_up(&journal->j_wait_updates); rwsem_release(&journal->j_trans_commit_map, _THIS_IP_); /* * Scope of the GFP_NOFS context is over here and so we can restore the * original alloc context. */ memalloc_nofs_restore(handle->saved_alloc_context); } /** * jbd2__journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested * @revoke_records: number of revoke record credits requested * @gfp_mask: memory allocation flags (for start_this_handle) * * Restart a handle for a multi-transaction filesystem * operation. * * If the jbd2_journal_extend() call above fails to grant new buffer credits * to a running handle, a call to jbd2_journal_restart will commit the * handle's transaction so far and reattach the handle to a new * transaction capable of guaranteeing the requested number of * credits. We preserve reserved handle if there's any attached to the * passed in handle. */ int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records, gfp_t gfp_mask) { transaction_t *transaction = handle->h_transaction; journal_t *journal; tid_t tid; int need_to_start; int ret; /* If we've had an abort of any type, don't even think about * actually doing the restart! */ if (is_handle_aborted(handle)) return 0; journal = transaction->t_journal; tid = transaction->t_tid; /* * First unlink the handle from its current transaction, and start the * commit on that. */ jbd2_debug(2, "restarting handle %p\n", handle); stop_this_handle(handle); handle->h_transaction = NULL; /* * TODO: If we use READ_ONCE / WRITE_ONCE for j_commit_request we can * get rid of pointless j_state_lock traffic like this. */ read_lock(&journal->j_state_lock); need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); handle->h_total_credits = nblocks + DIV_ROUND_UP(revoke_records, journal->j_revoke_records_per_block); handle->h_revoke_credits = revoke_records; ret = start_this_handle(journal, handle, gfp_mask); trace_jbd2_handle_restart(journal->j_fs_dev->bd_dev, ret ? 0 : handle->h_transaction->t_tid, handle->h_type, handle->h_line_no, handle->h_total_credits); return ret; } EXPORT_SYMBOL(jbd2__journal_restart); int jbd2_journal_restart(handle_t *handle, int nblocks) { return jbd2__journal_restart(handle, nblocks, 0, GFP_NOFS); } EXPORT_SYMBOL(jbd2_journal_restart); /* * Waits for any outstanding t_updates to finish. * This is called with write j_state_lock held. */ void jbd2_journal_wait_updates(journal_t *journal) { DEFINE_WAIT(wait); while (1) { /* * Note that the running transaction can get freed under us if * this transaction is getting committed in * jbd2_journal_commit_transaction() -> * jbd2_journal_free_transaction(). This can only happen when we * release j_state_lock -> schedule() -> acquire j_state_lock. * Hence we should everytime retrieve new j_running_transaction * value (after j_state_lock release acquire cycle), else it may * lead to use-after-free of old freed transaction. */ transaction_t *transaction = journal->j_running_transaction; if (!transaction) break; prepare_to_wait(&journal->j_wait_updates, &wait, TASK_UNINTERRUPTIBLE); if (!atomic_read(&transaction->t_updates)) { finish_wait(&journal->j_wait_updates, &wait); break; } write_unlock(&journal->j_state_lock); schedule(); finish_wait(&journal->j_wait_updates, &wait); write_lock(&journal->j_state_lock); } } /** * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. * * This locks out any further updates from being started, and blocks * until all existing updates have completed, returning only once the * journal is in a quiescent state with no updates running. * * The journal lock should not be held on entry. */ void jbd2_journal_lock_updates(journal_t *journal) { jbd2_might_wait_for_commit(journal); write_lock(&journal->j_state_lock); ++journal->j_barrier_count; /* Wait until there are no reserved handles */ if (atomic_read(&journal->j_reserved_credits)) { write_unlock(&journal->j_state_lock); wait_event(journal->j_wait_reserved, atomic_read(&journal->j_reserved_credits) == 0); write_lock(&journal->j_state_lock); } /* Wait until there are no running t_updates */ jbd2_journal_wait_updates(journal); write_unlock(&journal->j_state_lock); /* * We have now established a barrier against other normal updates, but * we also need to barrier against other jbd2_journal_lock_updates() calls * to make sure that we serialise special journal-locked operations * too. */ mutex_lock(&journal->j_barrier); } /** * jbd2_journal_unlock_updates () - release barrier * @journal: Journal to release the barrier on. * * Release a transaction barrier obtained with jbd2_journal_lock_updates(). * * Should be called without the journal lock held. */ void jbd2_journal_unlock_updates (journal_t *journal) { J_ASSERT(journal->j_barrier_count != 0); mutex_unlock(&journal->j_barrier); write_lock(&journal->j_state_lock); --journal->j_barrier_count; write_unlock(&journal->j_state_lock); wake_up_all(&journal->j_wait_transaction_locked); } static void warn_dirty_buffer(struct buffer_head *bh) { printk(KERN_WARNING "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). " "There's a risk of filesystem corruption in case of system " "crash.\n", bh->b_bdev, (unsigned long long)bh->b_blocknr); } /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */ static void jbd2_freeze_jh_data(struct journal_head *jh) { char *source; struct buffer_head *bh = jh2bh(jh); J_EXPECT_JH(jh, buffer_uptodate(bh), "Possible IO failure.\n"); source = kmap_local_folio(bh->b_folio, bh_offset(bh)); /* Fire data frozen trigger just before we copy the data */ jbd2_buffer_frozen_trigger(jh, source, jh->b_triggers); memcpy(jh->b_frozen_data, source, bh->b_size); kunmap_local(source); /* * Now that the frozen data is saved off, we need to store any matching * triggers. */ jh->b_frozen_triggers = jh->b_triggers; } /* * If the buffer is already part of the current transaction, then there * is nothing we need to do. If it is already part of a prior * transaction which we are still committing to disk, then we need to * make sure that we do not overwrite the old copy: we do copy-out to * preserve the copy going to disk. We also account the buffer against * the handle's metadata buffer credits (unless the buffer is already * part of the transaction, that is). * */ static int do_get_write_access(handle_t *handle, struct journal_head *jh, int force_copy) { struct buffer_head *bh; transaction_t *transaction = handle->h_transaction; journal_t *journal; int error; char *frozen_buffer = NULL; unsigned long start_lock, time_lock; journal = transaction->t_journal; jbd2_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); JBUFFER_TRACE(jh, "entry"); repeat: bh = jh2bh(jh); /* @@@ Need to check for errors here at some point. */ start_lock = jiffies; lock_buffer(bh); spin_lock(&jh->b_state_lock); /* If it takes too long to lock the buffer, trace it */ time_lock = jbd2_time_diff(start_lock, jiffies); if (time_lock > HZ/10) trace_jbd2_lock_buffer_stall(bh->b_bdev->bd_dev, jiffies_to_msecs(time_lock)); /* We now hold the buffer lock so it is safe to query the buffer * state. Is the buffer dirty? * * If so, there are two possibilities. The buffer may be * non-journaled, and undergoing a quite legitimate writeback. * Otherwise, it is journaled, and we don't expect dirty buffers * in that state (the buffers should be marked JBD_Dirty * instead.) So either the IO is being done under our own * control and this is a bug, or it's a third party IO such as * dump(8) (which may leave the buffer scheduled for read --- * ie. locked but not dirty) or tune2fs (which may actually have * the buffer dirtied, ugh.) */ if (buffer_dirty(bh) && jh->b_transaction) { warn_dirty_buffer(bh); /* * We need to clean the dirty flag and we must do it under the * buffer lock to be sure we don't race with running write-out. */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); clear_buffer_dirty(bh); /* * The buffer is going to be added to BJ_Reserved list now and * nothing guarantees jbd2_journal_dirty_metadata() will be * ever called for it. So we need to set jbddirty bit here to * make sure the buffer is dirtied and written out when the * journaling machinery is done with it. */ set_buffer_jbddirty(bh); } error = -EROFS; if (is_handle_aborted(handle)) { spin_unlock(&jh->b_state_lock); unlock_buffer(bh); goto out; } error = 0; /* * The buffer is already part of this transaction if b_transaction or * b_next_transaction points to it */ if (jh->b_transaction == transaction || jh->b_next_transaction == transaction) { unlock_buffer(bh); goto done; } /* * this is the first time this transaction is touching this buffer, * reset the modified flag */ jh->b_modified = 0; /* * If the buffer is not journaled right now, we need to make sure it * doesn't get written to disk before the caller actually commits the * new data */ if (!jh->b_transaction) { JBUFFER_TRACE(jh, "no transaction"); J_ASSERT_JH(jh, !jh->b_next_transaction); JBUFFER_TRACE(jh, "file as BJ_Reserved"); /* * Make sure all stores to jh (b_modified, b_frozen_data) are * visible before attaching it to the running transaction. * Paired with barrier in jbd2_write_access_granted() */ smp_wmb(); spin_lock(&journal->j_list_lock); if (test_clear_buffer_dirty(bh)) { /* * Execute buffer dirty clearing and jh->b_transaction * assignment under journal->j_list_lock locked to * prevent bh being removed from checkpoint list if * the buffer is in an intermediate state (not dirty * and jh->b_transaction is NULL). */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); set_buffer_jbddirty(bh); } __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); unlock_buffer(bh); goto done; } unlock_buffer(bh); /* * If there is already a copy-out version of this buffer, then we don't * need to make another one */ if (jh->b_frozen_data) { JBUFFER_TRACE(jh, "has frozen data"); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); goto attach_next; } JBUFFER_TRACE(jh, "owned by older transaction"); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, jh->b_transaction == journal->j_committing_transaction); /* * There is one case we have to be very careful about. If the * committing transaction is currently writing this buffer out to disk * and has NOT made a copy-out, then we cannot modify the buffer * contents at all right now. The essence of copy-out is that it is * the extra copy, not the primary copy, which gets journaled. If the * primary copy is already going to disk then we cannot do copy-out * here. */ if (buffer_shadow(bh)) { JBUFFER_TRACE(jh, "on shadow: sleep"); spin_unlock(&jh->b_state_lock); wait_on_bit_io(&bh->b_state, BH_Shadow, TASK_UNINTERRUPTIBLE); goto repeat; } /* * Only do the copy if the currently-owning transaction still needs it. * If buffer isn't on BJ_Metadata list, the committing transaction is * past that stage (here we use the fact that BH_Shadow is set under * bh_state lock together with refiling to BJ_Shadow list and at this * point we know the buffer doesn't have BH_Shadow set). * * Subtle point, though: if this is a get_undo_access, then we will be * relying on the frozen_data to contain the new value of the * committed_data record after the transaction, so we HAVE to force the * frozen_data copy in that case. */ if (jh->b_jlist == BJ_Metadata || force_copy) { JBUFFER_TRACE(jh, "generate frozen data"); if (!frozen_buffer) { JBUFFER_TRACE(jh, "allocate memory for buffer"); spin_unlock(&jh->b_state_lock); frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS | __GFP_NOFAIL); goto repeat; } jh->b_frozen_data = frozen_buffer; frozen_buffer = NULL; jbd2_freeze_jh_data(jh); } attach_next: /* * Make sure all stores to jh (b_modified, b_frozen_data) are visible * before attaching it to the running transaction. Paired with barrier * in jbd2_write_access_granted() */ smp_wmb(); jh->b_next_transaction = transaction; done: spin_unlock(&jh->b_state_lock); /* * If we are about to journal a buffer, then any revoke pending on it is * no longer valid */ jbd2_journal_cancel_revoke(handle, jh); out: if (unlikely(frozen_buffer)) /* It's usually NULL */ jbd2_free(frozen_buffer, bh->b_size); JBUFFER_TRACE(jh, "exit"); return error; } /* Fast check whether buffer is already attached to the required transaction */ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, bool undo) { struct journal_head *jh; bool ret = false; /* Dirty buffers require special handling... */ if (buffer_dirty(bh)) return false; /* * RCU protects us from dereferencing freed pages. So the checks we do * are guaranteed not to oops. However the jh slab object can get freed * & reallocated while we work with it. So we have to be careful. When * we see jh attached to the running transaction, we know it must stay * so until the transaction is committed. Thus jh won't be freed and * will be attached to the same bh while we run. However it can * happen jh gets freed, reallocated, and attached to the transaction * just after we get pointer to it from bh. So we have to be careful * and recheck jh still belongs to our bh before we return success. */ rcu_read_lock(); if (!buffer_jbd(bh)) goto out; /* This should be bh2jh() but that doesn't work with inline functions */ jh = READ_ONCE(bh->b_private); if (!jh) goto out; /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; if (READ_ONCE(jh->b_transaction) != handle->h_transaction && READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: * 1) Make sure to fetch b_bh after we did previous checks so that we * detect when jh went through free, realloc, attach to transaction * while we were checking. Paired with implicit barrier in that path. * 2) So that access to bh done after jbd2_write_access_granted() * doesn't get reordered and see inconsistent state of concurrent * do_get_write_access(). */ smp_mb(); if (unlikely(jh->b_bh != bh)) goto out; ret = true; out: rcu_read_unlock(); return ret; } /** * jbd2_journal_get_write_access() - notify intent to modify a buffer * for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * * Returns: error code or 0 on success. * * In full data journalling mode the buffer may be of type BJ_AsyncData, * because we're ``write()ing`` a buffer which is also part of a shared mapping. */ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) { struct journal_head *jh; journal_t *journal; int rc; if (is_handle_aborted(handle)) return -EROFS; journal = handle->h_transaction->t_journal; if (jbd2_check_fs_dev_write_error(journal)) { /* * If the fs dev has writeback errors, it may have failed * to async write out metadata buffers in the background. * In this case, we could read old data from disk and write * it out again, which may lead to on-disk filesystem * inconsistency. Aborting journal can avoid it happen. */ jbd2_journal_abort(journal, -EIO); return -EIO; } if (jbd2_write_access_granted(handle, bh, false)) return 0; jh = jbd2_journal_add_journal_head(bh); /* We do not want to get caught playing with fields which the * log thread also manipulates. Make sure that the buffer * completes any outstanding IO before proceeding. */ rc = do_get_write_access(handle, jh, 0); jbd2_journal_put_journal_head(jh); return rc; } /* * When the user wants to journal a newly created buffer_head * (ie. getblk() returned a new buffer and we are going to populate it * manually rather than reading off disk), then we need to keep the * buffer_head locked until it has been completely filled with new * data. In this case, we should be able to make the assertion that * the bh is not already part of an existing transaction. * * The buffer should already be locked by the caller by this point. * There is no lock ranking violation: it was a newly created, * unlocked buffer beforehand. */ /** * jbd2_journal_get_create_access () - notify intent to use newly created bh * @handle: transaction to new buffer to * @bh: new buffer. * * Call this if you create a new bh. */ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal; struct journal_head *jh = jbd2_journal_add_journal_head(bh); int err; jbd2_debug(5, "journal_head %p\n", jh); err = -EROFS; if (is_handle_aborted(handle)) goto out; journal = transaction->t_journal; err = 0; JBUFFER_TRACE(jh, "entry"); /* * The buffer may already belong to this transaction due to pre-zeroing * in the filesystem's new_block code. It may also be on the previous, * committing transaction's lists, but it HAS to be in Forget state in * that case: the transaction must have deleted the buffer for it to be * reused here. */ spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, (jh->b_transaction == transaction || jh->b_transaction == NULL || (jh->b_transaction == journal->j_committing_transaction && jh->b_jlist == BJ_Forget))); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, buffer_locked(jh2bh(jh))); if (jh->b_transaction == NULL) { /* * Previous jbd2_journal_forget() could have left the buffer * with jbddirty bit set because it was being committed. When * the commit finished, we've filed the buffer for * checkpointing and marked it dirty. Now we are reallocating * the buffer so the transaction freeing it must have * committed and so it's safe to clear the dirty bit. */ clear_buffer_dirty(jh2bh(jh)); /* first access by this transaction */ jh->b_modified = 0; JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction == journal->j_committing_transaction) { /* first access by this transaction */ jh->b_modified = 0; JBUFFER_TRACE(jh, "set next transaction"); spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); } spin_unlock(&jh->b_state_lock); /* * akpm: I added this. ext3_alloc_branch can pick up new indirect * blocks which contain freed but then revoked metadata. We need * to cancel the revoke in case we end up freeing it yet again * and the reallocating as data - this would cause a second revoke, * which hits an assertion error. */ JBUFFER_TRACE(jh, "cancelling revoke"); jbd2_journal_cancel_revoke(handle, jh); out: jbd2_journal_put_journal_head(jh); return err; } /** * jbd2_journal_get_undo_access() - Notify intent to modify metadata with * non-rewindable consequences * @handle: transaction * @bh: buffer to undo * * Sometimes there is a need to distinguish between metadata which has * been committed to disk and that which has not. The ext3fs code uses * this for freeing and allocating space, we have to make sure that we * do not reuse freed space until the deallocation has been committed, * since if we overwrote that space we would make the delete * un-rewindable in case of a crash. * * To deal with that, jbd2_journal_get_undo_access requests write access to a * buffer for parts of non-rewindable operations such as delete * operations on the bitmaps. The journaling code must keep a copy of * the buffer's contents prior to the undo_access call until such time * as we know that the buffer has definitely been committed to disk. * * We never need to know which transaction the committed data is part * of, buffers touched here are guaranteed to be dirtied later and so * will be committed to a new transaction in due course, at which point * we can discard the old committed data pointer. * * Returns error number or 0 on success. */ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) { int err; struct journal_head *jh; char *committed_data = NULL; if (is_handle_aborted(handle)) return -EROFS; if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); JBUFFER_TRACE(jh, "entry"); /* * Do this first --- it can drop the journal lock, so we want to * make sure that obtaining the committed_data is done * atomically wrt. completion of any outstanding commits. */ err = do_get_write_access(handle, jh, 1); if (err) goto out; repeat: if (!jh->b_committed_data) committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS|__GFP_NOFAIL); spin_lock(&jh->b_state_lock); if (!jh->b_committed_data) { /* Copy out the current buffer contents into the * preserved, committed copy. */ JBUFFER_TRACE(jh, "generate b_committed data"); if (!committed_data) { spin_unlock(&jh->b_state_lock); goto repeat; } jh->b_committed_data = committed_data; committed_data = NULL; memcpy(jh->b_committed_data, bh->b_data, bh->b_size); } spin_unlock(&jh->b_state_lock); out: jbd2_journal_put_journal_head(jh); if (unlikely(committed_data)) jbd2_free(committed_data, bh->b_size); return err; } /** * jbd2_journal_set_triggers() - Add triggers for commit writeout * @bh: buffer to trigger on * @type: struct jbd2_buffer_trigger_type containing the trigger(s). * * Set any triggers on this journal_head. This is always safe, because * triggers for a committing buffer will be saved off, and triggers for * a running transaction will match the buffer in that transaction. * * Call with NULL to clear the triggers. */ void jbd2_journal_set_triggers(struct buffer_head *bh, struct jbd2_buffer_trigger_type *type) { struct journal_head *jh = jbd2_journal_grab_journal_head(bh); if (WARN_ON_ONCE(!jh)) return; jh->b_triggers = type; jbd2_journal_put_journal_head(jh); } void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers) { struct buffer_head *bh = jh2bh(jh); if (!triggers || !triggers->t_frozen) return; triggers->t_frozen(triggers, bh, mapped_data, bh->b_size); } void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers) { if (!triggers || !triggers->t_abort) return; triggers->t_abort(triggers, jh2bh(jh)); } /** * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. * @bh: buffer to mark * * mark dirty metadata which needs to be journaled as part of the current * transaction. * * The buffer must have previously had jbd2_journal_get_write_access() * called so that it has a valid journal_head attached to the buffer * head. * * The buffer is placed on the transaction's metadata list and is marked * as belonging to the transaction. * * Returns error number or 0 on success. * * Special care needs to be taken if the buffer already belongs to the * current committing transaction (in which case we should have frozen * data present for that commit). In that case, we don't relink the * buffer: that only gets done when the old transaction finally * completes its commit. */ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal; struct journal_head *jh; int ret = 0; if (!buffer_jbd(bh)) return -EUCLEAN; /* * We don't grab jh reference here since the buffer must be part * of the running transaction. */ jh = bh2jh(bh); jbd2_debug(5, "journal_head %p\n", jh); JBUFFER_TRACE(jh, "entry"); /* * This and the following assertions are unreliable since we may see jh * in inconsistent state unless we grab bh_state lock. But this is * crucial to catch bugs so let's do a reliable check until the * lockless handling is fully proven. */ if (data_race(jh->b_transaction != transaction && jh->b_next_transaction != transaction)) { spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_next_transaction == transaction); spin_unlock(&jh->b_state_lock); } if (data_race(jh->b_modified == 1)) { /* If it's in our transaction it must be in BJ_Metadata list. */ if (data_race(jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata)) { spin_lock(&jh->b_state_lock); if (jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata) pr_err("JBD2: assertion failure: h_type=%u " "h_line_no=%u block_no=%llu jlist=%u\n", handle->h_type, handle->h_line_no, (unsigned long long) bh->b_blocknr, jh->b_jlist); J_ASSERT_JH(jh, jh->b_transaction != transaction || jh->b_jlist == BJ_Metadata); spin_unlock(&jh->b_state_lock); } goto out; } spin_lock(&jh->b_state_lock); if (is_handle_aborted(handle)) { /* * Check journal aborting with @jh->b_state_lock locked, * since 'jh->b_transaction' could be replaced with * 'jh->b_next_transaction' during old transaction * committing if journal aborted, which may fail * assertion on 'jh->b_frozen_data == NULL'. */ ret = -EROFS; goto out_unlock_bh; } journal = transaction->t_journal; if (jh->b_modified == 0) { /* * This buffer's got modified and becoming part * of the transaction. This needs to be done * once a transaction -bzzz */ if (WARN_ON_ONCE(jbd2_handle_buffer_credits(handle) <= 0)) { ret = -ENOSPC; goto out_unlock_bh; } jh->b_modified = 1; handle->h_total_credits--; } /* * fastpath, to avoid expensive locking. If this buffer is already * on the running transaction's metadata list there is nothing to do. * Nobody can take it off again because there is a handle open. * I _think_ we're OK here with SMP barriers - a mistaken decision will * result in this test being false, so we go in and take the locks. */ if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) { JBUFFER_TRACE(jh, "fastpath"); if (unlikely(jh->b_transaction != journal->j_running_transaction)) { printk(KERN_ERR "JBD2: %s: " "jh->b_transaction (%llu, %p, %u) != " "journal->j_running_transaction (%p, %u)\n", journal->j_devname, (unsigned long long) bh->b_blocknr, jh->b_transaction, jh->b_transaction ? jh->b_transaction->t_tid : 0, journal->j_running_transaction, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); ret = -EINVAL; } goto out_unlock_bh; } set_buffer_jbddirty(bh); /* * Metadata already on the current transaction list doesn't * need to be filed. Metadata on another transaction's list must * be committing, and will be refiled once the commit completes: * leave it alone for now. */ if (jh->b_transaction != transaction) { JBUFFER_TRACE(jh, "already on other transaction"); if (unlikely(((jh->b_transaction != journal->j_committing_transaction)) || (jh->b_next_transaction != transaction))) { printk(KERN_ERR "jbd2_journal_dirty_metadata: %s: " "bad jh for block %llu: " "transaction (%p, %u), " "jh->b_transaction (%p, %u), " "jh->b_next_transaction (%p, %u), jlist %u\n", journal->j_devname, (unsigned long long) bh->b_blocknr, transaction, transaction->t_tid, jh->b_transaction, jh->b_transaction ? jh->b_transaction->t_tid : 0, jh->b_next_transaction, jh->b_next_transaction ? jh->b_next_transaction->t_tid : 0, jh->b_jlist); WARN_ON(1); ret = -EINVAL; } /* And this case is illegal: we can't reuse another * transaction's data buffer, ever. */ goto out_unlock_bh; } /* That test should have eliminated the following case: */ J_ASSERT_JH(jh, jh->b_frozen_data == NULL); JBUFFER_TRACE(jh, "file as BJ_Metadata"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Metadata); spin_unlock(&journal->j_list_lock); out_unlock_bh: spin_unlock(&jh->b_state_lock); out: JBUFFER_TRACE(jh, "exit"); return ret; } /** * jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * * We can only do the bforget if there are no commits pending against the * buffer. If the buffer is dirty in the current running transaction we * can safely unlink it. * * bh may not be a journalled buffer at all - it may be a non-JBD * buffer which came off the hashtable. Check for this. * * Decrements bh->b_count by one. * * Allow this call even if the handle has aborted --- it may be part of * the caller's cleanup after an abort. */ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; journal_t *journal; struct journal_head *jh; int drop_reserve = 0; int err = 0; int was_modified = 0; if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; BUFFER_TRACE(bh, "entry"); jh = jbd2_journal_grab_journal_head(bh); if (!jh) { __bforget(bh); return 0; } spin_lock(&jh->b_state_lock); /* Critical error: attempting to delete a bitmap buffer, maybe? * Don't do any jbd operations, and return an error. */ if (!J_EXPECT_JH(jh, !jh->b_committed_data, "inconsistent data on disk")) { err = -EIO; goto drop; } /* keep track of whether or not this transaction modified us */ was_modified = jh->b_modified; /* * The buffer's going from the transaction, we must drop * all references -bzzz */ jh->b_modified = 0; if (jh->b_transaction == transaction) { J_ASSERT_JH(jh, !jh->b_frozen_data); /* If we are forgetting a buffer which is already part * of this transaction, then we can just drop it from * the transaction immediately. */ clear_buffer_dirty(bh); clear_buffer_jbddirty(bh); JBUFFER_TRACE(jh, "belongs to current transaction: unfile"); /* * we only want to drop a reference if this transaction * modified the buffer */ if (was_modified) drop_reserve = 1; /* * We are no longer going to journal this buffer. * However, the commit of this transaction is still * important to the buffer: the delete that we are now * processing might obsolete an old log entry, so by * committing, we can satisfy the buffer's checkpoint. * * So, if we have a checkpoint on the buffer, we should * now refile the buffer on our BJ_Forget list so that * we know to remove the checkpoint after we commit. */ spin_lock(&journal->j_list_lock); if (jh->b_cp_transaction) { __jbd2_journal_temp_unlink_buffer(jh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); jbd2_journal_put_journal_head(jh); } spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction) { J_ASSERT_JH(jh, (jh->b_transaction == journal->j_committing_transaction)); /* However, if the buffer is still owned by a prior * (committing) transaction, we can't drop it yet... */ JBUFFER_TRACE(jh, "belongs to older transaction"); /* ... but we CAN drop it from the new transaction through * marking the buffer as freed and set j_next_transaction to * the new transaction, so that not only the commit code * knows it should clear dirty bits when it is done with the * buffer, but also the buffer can be checkpointed only * after the new transaction commits. */ set_buffer_freed(bh); if (!jh->b_next_transaction) { spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); } else { J_ASSERT(jh->b_next_transaction == transaction); /* * only drop a reference if this transaction modified * the buffer */ if (was_modified) drop_reserve = 1; } } else { /* * Finally, if the buffer is not belongs to any * transaction, we can just drop it now if it has no * checkpoint. */ spin_lock(&journal->j_list_lock); if (!jh->b_cp_transaction) { JBUFFER_TRACE(jh, "belongs to none transaction"); spin_unlock(&journal->j_list_lock); goto drop; } /* * Otherwise, if the buffer has been written to disk, * it is safe to remove the checkpoint and drop it. */ if (jbd2_journal_try_remove_checkpoint(jh) >= 0) { spin_unlock(&journal->j_list_lock); goto drop; } /* * The buffer is still not written to disk, we should * attach this buffer to current transaction so that the * buffer can be checkpointed only after the current * transaction commits. */ clear_buffer_dirty(bh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); spin_unlock(&journal->j_list_lock); } drop: __brelse(bh); spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); if (drop_reserve) { /* no need to reserve log space for this block -bzzz */ handle->h_total_credits++; } return err; } /** * jbd2_journal_stop() - complete a transaction * @handle: transaction to complete. * * All done for a particular handle. * * There is not much action needed here. We just return any remaining * buffer credits to the transaction and remove the handle. The only * complication is that we need to start a commit operation if the * filesystem is marked for synchronous update. * * jbd2_journal_stop itself will not usually return an error, but it may * do so in unusual circumstances. In particular, expect it to * return -EIO if a jbd2_journal_abort has been executed since the * transaction began. */ int jbd2_journal_stop(handle_t *handle) { transaction_t *transaction = handle->h_transaction; journal_t *journal; int err = 0, wait_for_commit = 0; tid_t tid; pid_t pid; if (--handle->h_ref > 0) { jbd2_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, handle->h_ref); if (is_handle_aborted(handle)) return -EIO; return 0; } if (!transaction) { /* * Handle is already detached from the transaction so there is * nothing to do other than free the handle. */ memalloc_nofs_restore(handle->saved_alloc_context); goto free_and_exit; } journal = transaction->t_journal; tid = transaction->t_tid; if (is_handle_aborted(handle)) err = -EIO; jbd2_debug(4, "Handle %p going down\n", handle); trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev, tid, handle->h_type, handle->h_line_no, jiffies - handle->h_start_jiffies, handle->h_sync, handle->h_requested_credits, (handle->h_requested_credits - handle->h_total_credits)); /* * Implement synchronous transaction batching. If the handle * was synchronous, don't force a commit immediately. Let's * yield and let another thread piggyback onto this * transaction. Keep doing that while new threads continue to * arrive. It doesn't cost much - we're about to run a commit * and sleep on IO anyway. Speeds up many-threaded, many-dir * operations by 30x or more... * * We try and optimize the sleep time against what the * underlying disk can do, instead of having a static sleep * time. This is useful for the case where our storage is so * fast that it is more optimal to go ahead and force a flush * and wait for the transaction to be committed than it is to * wait for an arbitrary amount of time for new writers to * join the transaction. We achieve this by measuring how * long it takes to commit a transaction, and compare it with * how long this transaction has been running, and if run time * < commit time then we sleep for the delta and commit. This * greatly helps super fast disks that would see slowdowns as * more threads started doing fsyncs. * * But don't do this if this process was the most recent one * to perform a synchronous write. We do this to detect the * case where a single process is doing a stream of sync * writes. No point in waiting for joiners in that case. * * Setting max_batch_time to 0 disables this completely. */ pid = current->pid; if (handle->h_sync && journal->j_last_sync_writer != pid && journal->j_max_batch_time) { u64 commit_time, trans_time; journal->j_last_sync_writer = pid; read_lock(&journal->j_state_lock); commit_time = journal->j_average_commit_time; read_unlock(&journal->j_state_lock); trans_time = ktime_to_ns(ktime_sub(ktime_get(), transaction->t_start_time)); commit_time = max_t(u64, commit_time, 1000*journal->j_min_batch_time); commit_time = min_t(u64, commit_time, 1000*journal->j_max_batch_time); if (trans_time < commit_time) { ktime_t expires = ktime_add_ns(ktime_get(), commit_time); set_current_state(TASK_UNINTERRUPTIBLE); schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); } } if (handle->h_sync) transaction->t_synchronous_commit = 1; /* * If the handle is marked SYNC, we need to set another commit * going! We also want to force a commit if the transaction is too * old now. */ if (handle->h_sync || time_after_eq(jiffies, transaction->t_expires)) { /* Do this even for aborted journals: an abort still * completes the commit thread, it just doesn't write * anything to disk. */ jbd2_debug(2, "transaction too old, requesting commit for " "handle %p\n", handle); /* This is non-blocking */ jbd2_log_start_commit(journal, tid); /* * Special case: JBD2_SYNC synchronous updates require us * to wait for the commit to complete. */ if (handle->h_sync && !(current->flags & PF_MEMALLOC)) wait_for_commit = 1; } /* * Once stop_this_handle() drops t_updates, the transaction could start * committing on us and eventually disappear. So we must not * dereference transaction pointer again after calling * stop_this_handle(). */ stop_this_handle(handle); if (wait_for_commit) err = jbd2_log_wait_commit(journal, tid); free_and_exit: if (handle->h_rsv_handle) jbd2_free_handle(handle->h_rsv_handle); jbd2_free_handle(handle); return err; } /* * * List management code snippets: various functions for manipulating the * transaction buffer lists. * */ /* * Append a buffer to a transaction list, given the transaction's list head * pointer. * * j_list_lock is held. * * jh->b_state_lock is held. */ static inline void __blist_add_buffer(struct journal_head **list, struct journal_head *jh) { if (!*list) { jh->b_tnext = jh->b_tprev = jh; *list = jh; } else { /* Insert at the tail of the list to preserve order */ struct journal_head *first = *list, *last = first->b_tprev; jh->b_tprev = last; jh->b_tnext = first; last->b_tnext = first->b_tprev = jh; } } /* * Remove a buffer from a transaction list, given the transaction's list * head pointer. * * Called with j_list_lock held, and the journal may not be locked. * * jh->b_state_lock is held. */ static inline void __blist_del_buffer(struct journal_head **list, struct journal_head *jh) { if (*list == jh) { *list = jh->b_tnext; if (*list == jh) *list = NULL; } jh->b_tprev->b_tnext = jh->b_tnext; jh->b_tnext->b_tprev = jh->b_tprev; } /* * Remove a buffer from the appropriate transaction list. * * Note that this function can *change* the value of * bh->b_transaction->t_buffers, t_forget, t_shadow_list, t_log_list or * t_reserved_list. If the caller is holding onto a copy of one of these * pointers, it could go bad. Generally the caller needs to re-read the * pointer from the transaction_t. * * Called under j_list_lock. */ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) { struct journal_head **list = NULL; transaction_t *transaction; struct buffer_head *bh = jh2bh(jh); lockdep_assert_held(&jh->b_state_lock); transaction = jh->b_transaction; if (transaction) assert_spin_locked(&transaction->t_journal->j_list_lock); J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); if (jh->b_jlist != BJ_None) J_ASSERT_JH(jh, transaction != NULL); switch (jh->b_jlist) { case BJ_None: return; case BJ_Metadata: transaction->t_nr_buffers--; J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0); list = &transaction->t_buffers; break; case BJ_Forget: list = &transaction->t_forget; break; case BJ_Shadow: list = &transaction->t_shadow_list; break; case BJ_Reserved: list = &transaction->t_reserved_list; break; } __blist_del_buffer(list, jh); jh->b_jlist = BJ_None; if (transaction && is_journal_aborted(transaction->t_journal)) clear_buffer_jbddirty(bh); else if (test_clear_buffer_jbddirty(bh)) mark_buffer_dirty(bh); /* Expose it to the VM */ } /* * Remove buffer from all transactions. The caller is responsible for dropping * the jh reference that belonged to the transaction. * * Called with bh_state lock and j_list_lock */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { J_ASSERT_JH(jh, jh->b_transaction != NULL); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; } /** * jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @folio: Folio to detach data from. * * For all the buffers on this page, * if they are fully written out ordered data, move them onto BUF_CLEAN * so try_to_free_buffers() can reap them. * * This function returns non-zero if we wish try_to_free_buffers() * to be called. We do this if the page is releasable by try_to_free_buffers(). * We also do it if the page has locked or dirty buffers and the caller wants * us to perform sync or async writeout. * * This complicates JBD locking somewhat. We aren't protected by the * BKL here. We wish to remove the buffer from its committing or * running transaction's ->t_datalist via __jbd2_journal_unfile_buffer. * * This may *change* the value of transaction_t->t_datalist, so anyone * who looks at t_datalist needs to lock against this function. * * Even worse, someone may be doing a jbd2_journal_dirty_data on this * buffer. So we need to lock against that. jbd2_journal_dirty_data() * will come out of the lock with the buffer dirty, which makes it * ineligible for release here. * * Who else is affected by this? hmm... Really the only contender * is do_get_write_access() - it could be looking at the buffer while * journal_try_to_free_buffer() is changing its state. But that * cannot happen because we never reallocate freed data as metadata * while the data is part of a transaction. Yes? * * Return false on failure, true on success */ bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio) { struct buffer_head *head; struct buffer_head *bh; bool ret = false; J_ASSERT(folio_test_locked(folio)); head = folio_buffers(folio); bh = head; do { struct journal_head *jh; /* * We take our own ref against the journal_head here to avoid * having to add tons of locking around each instance of * jbd2_journal_put_journal_head(). */ jh = jbd2_journal_grab_journal_head(bh); if (!jh) continue; spin_lock(&jh->b_state_lock); if (!jh->b_transaction && !jh->b_next_transaction) { spin_lock(&journal->j_list_lock); /* Remove written-back checkpointed metadata buffer */ if (jh->b_cp_transaction != NULL) jbd2_journal_try_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); } spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); if (buffer_jbd(bh)) goto busy; } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(folio); busy: return ret; } /* * This buffer is no longer needed. If it is on an older transaction's * checkpoint list we need to record it on this transaction's forget list * to pin this buffer (and hence its checkpointing transaction) down until * this transaction commits. If the buffer isn't on a checkpoint list, we * release it. * Returns non-zero if JBD no longer has an interest in the buffer. * * Called under j_list_lock. * * Called under jh->b_state_lock. */ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) { int may_free = 1; struct buffer_head *bh = jh2bh(jh); if (jh->b_cp_transaction) { JBUFFER_TRACE(jh, "on running+cp transaction"); __jbd2_journal_temp_unlink_buffer(jh); /* * We don't want to write the buffer anymore, clear the * bit so that we don't confuse checks in * __jbd2_journal_file_buffer */ clear_buffer_dirty(bh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); may_free = 0; } else { JBUFFER_TRACE(jh, "on running transaction"); __jbd2_journal_unfile_buffer(jh); jbd2_journal_put_journal_head(jh); } return may_free; } /* * jbd2_journal_invalidate_folio * * This code is tricky. It has a number of cases to deal with. * * There are two invariants which this code relies on: * * i_size must be updated on disk before we start calling invalidate_folio * on the data. * * This is done in ext3 by defining an ext3_setattr method which * updates i_size before truncate gets going. By maintaining this * invariant, we can be sure that it is safe to throw away any buffers * attached to the current transaction: once the transaction commits, * we know that the data will not be needed. * * Note however that we can *not* throw away data belonging to the * previous, committing transaction! * * Any disk blocks which *are* part of the previous, committing * transaction (and which therefore cannot be discarded immediately) are * not going to be reused in the new running transaction * * The bitmap committed_data images guarantee this: any block which is * allocated in one transaction and removed in the next will be marked * as in-use in the committed_data bitmap, so cannot be reused until * the next transaction to delete the block commits. This means that * leaving committing buffers dirty is quite safe: the disk blocks * cannot be reallocated to a different file and so buffer aliasing is * not possible. * * * The above applies mainly to ordered data mode. In writeback mode we * don't make guarantees about the order in which data hits disk --- in * particular we don't guarantee that new dirty data is flushed before * transaction commit --- so it is always safe just to discard data * immediately in that mode. --sct */ /* * The journal_unmap_buffer helper function returns zero if the buffer * concerned remains pinned as an anonymous buffer belonging to an older * transaction. * * We're outside-transaction here. Either or both of j_running_transaction * and j_committing_transaction may be NULL. */ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, int partial_page) { transaction_t *transaction; struct journal_head *jh; int may_free = 1; BUFFER_TRACE(bh, "entry"); /* * It is safe to proceed here without the j_list_lock because the * buffers cannot be stolen by try_to_free_buffers as long as we are * holding the page lock. --sct */ jh = jbd2_journal_grab_journal_head(bh); if (!jh) goto zap_buffer_unlocked; /* OK, we have data buffer in journaled mode */ write_lock(&journal->j_state_lock); spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); /* * We cannot remove the buffer from checkpoint lists until the * transaction adding inode to orphan list (let's call it T) * is committed. Otherwise if the transaction changing the * buffer would be cleaned from the journal before T is * committed, a crash will cause that the correct contents of * the buffer will be lost. On the other hand we have to * clear the buffer dirty bit at latest at the moment when the * transaction marking the buffer as freed in the filesystem * structures is committed because from that moment on the * block can be reallocated and used by a different page. * Since the block hasn't been freed yet but the inode has * already been added to orphan list, it is safe for us to add * the buffer to BJ_Forget list of the newest transaction. * * Also we have to clear buffer_mapped flag of a truncated buffer * because the buffer_head may be attached to the page straddling * i_size (can happen only when blocksize < pagesize) and thus the * buffer_head can be reused when the file is extended again. So we end * up keeping around invalidated buffers attached to transactions' * BJ_Forget list just to stop checkpointing code from cleaning up * the transaction this buffer was modified in. */ transaction = jh->b_transaction; if (transaction == NULL) { /* First case: not on any transaction. If it * has no checkpoint link, then we can zap it: * it's a writeback-mode buffer so we don't care * if it hits disk safely. */ if (!jh->b_cp_transaction) { JBUFFER_TRACE(jh, "not on any transaction: zap"); goto zap_buffer; } if (!buffer_dirty(bh)) { /* bdflush has written it. We can drop it now */ __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } /* OK, it must be in the journal but still not * written fully to disk: it's metadata or * journaled data... */ if (journal->j_running_transaction) { /* ... and once the current transaction has * committed, the buffer won't be needed any * longer. */ JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget"); may_free = __dispose_buffer(jh, journal->j_running_transaction); goto zap_buffer; } else { /* There is no currently-running transaction. So the * orphan record which we wrote for this file must have * passed into commit. We must attach this buffer to * the committing transaction, if it exists. */ if (journal->j_committing_transaction) { JBUFFER_TRACE(jh, "give to committing trans"); may_free = __dispose_buffer(jh, journal->j_committing_transaction); goto zap_buffer; } else { /* The orphan record's transaction has * committed. We can cleanse this buffer */ clear_buffer_jbddirty(bh); __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } } } else if (transaction == journal->j_committing_transaction) { JBUFFER_TRACE(jh, "on committing transaction"); /* * The buffer is committing, we simply cannot touch * it. If the page is straddling i_size we have to wait * for commit and try again. */ if (partial_page) { spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); /* Already zapped buffer? Nothing to do... */ if (!bh->b_bdev) return 0; return -EBUSY; } /* * OK, buffer won't be reachable after truncate. We just clear * b_modified to not confuse transaction credit accounting, and * set j_next_transaction to the running transaction (if there * is one) and mark buffer as freed so that commit code knows * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; jh->b_modified = 0; spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); return 0; } else { /* Good, the buffer belongs to the running transaction. * We are writing our own transaction's data, not any * previous one's, so it is safe to throw it away * (remember that we expect the filesystem to have set * i_size already for this truncate so recovery will not * expose the disk blocks we are discarding here.) */ J_ASSERT_JH(jh, transaction == journal->j_running_transaction); JBUFFER_TRACE(jh, "on running transaction"); may_free = __dispose_buffer(jh, transaction); } zap_buffer: /* * This is tricky. Although the buffer is truncated, it may be reused * if blocksize < pagesize and it is attached to the page straddling * EOF. Since the buffer might have been added to BJ_Forget list of the * running transaction, journal_get_write_access() won't clear * b_modified and credit accounting gets confused. So clear b_modified * here. */ jh->b_modified = 0; spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); zap_buffer_unlocked: clear_buffer_dirty(bh); J_ASSERT_BH(bh, !buffer_jbddirty(bh)); clear_buffer_mapped(bh); clear_buffer_req(bh); clear_buffer_new(bh); clear_buffer_delay(bh); clear_buffer_unwritten(bh); bh->b_bdev = NULL; return may_free; } /** * jbd2_journal_invalidate_folio() * @journal: journal to use for flush... * @folio: folio to flush * @offset: start of the range to invalidate * @length: length of the range to invalidate * * Reap page buffers containing data after in the specified range in page. * Can return -EBUSY if buffers are part of the committing transaction and * the page is straddling i_size. Caller then has to wait for current commit * and try again. */ int jbd2_journal_invalidate_folio(journal_t *journal, struct folio *folio, size_t offset, size_t length) { struct buffer_head *head, *bh, *next; unsigned int stop = offset + length; unsigned int curr_off = 0; int partial_page = (offset || length < folio_size(folio)); int may_free = 1; int ret = 0; if (!folio_test_locked(folio)) BUG(); head = folio_buffers(folio); if (!head) return 0; BUG_ON(stop > folio_size(folio) || stop < length); /* We will potentially be playing with lists other than just the * data lists (especially for journaled data mode), so be * cautious in our locking. */ bh = head; do { unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; if (next_off > stop) return 0; if (offset <= curr_off) { /* This block is wholly outside the truncation point */ lock_buffer(bh); ret = journal_unmap_buffer(journal, bh, partial_page); unlock_buffer(bh); if (ret < 0) return ret; may_free &= ret; } curr_off = next_off; bh = next; } while (bh != head); if (!partial_page) { if (may_free && try_to_free_buffers(folio)) J_ASSERT(!folio_buffers(folio)); } return 0; } /* * File a buffer on the given transaction list. */ void __jbd2_journal_file_buffer(struct journal_head *jh, transaction_t *transaction, int jlist) { struct journal_head **list = NULL; int was_dirty = 0; struct buffer_head *bh = jh2bh(jh); lockdep_assert_held(&jh->b_state_lock); assert_spin_locked(&transaction->t_journal->j_list_lock); J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_transaction == NULL); if (jh->b_transaction && jh->b_jlist == jlist) return; if (jlist == BJ_Metadata || jlist == BJ_Reserved || jlist == BJ_Shadow || jlist == BJ_Forget) { /* * For metadata buffers, we track dirty bit in buffer_jbddirty * instead of buffer_dirty. We should not see a dirty bit set * here because we clear it in do_get_write_access but e.g. * tune2fs can modify the sb and set the dirty bit at any time * so we try to gracefully handle that. */ if (buffer_dirty(bh)) warn_dirty_buffer(bh); if (test_clear_buffer_dirty(bh) || test_clear_buffer_jbddirty(bh)) was_dirty = 1; } if (jh->b_transaction) __jbd2_journal_temp_unlink_buffer(jh); else jbd2_journal_grab_journal_head(bh); jh->b_transaction = transaction; switch (jlist) { case BJ_None: J_ASSERT_JH(jh, !jh->b_committed_data); J_ASSERT_JH(jh, !jh->b_frozen_data); return; case BJ_Metadata: transaction->t_nr_buffers++; list = &transaction->t_buffers; break; case BJ_Forget: list = &transaction->t_forget; break; case BJ_Shadow: list = &transaction->t_shadow_list; break; case BJ_Reserved: list = &transaction->t_reserved_list; break; } __blist_add_buffer(list, jh); jh->b_jlist = jlist; if (was_dirty) set_buffer_jbddirty(bh); } void jbd2_journal_file_buffer(struct journal_head *jh, transaction_t *transaction, int jlist) { spin_lock(&jh->b_state_lock); spin_lock(&transaction->t_journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, jlist); spin_unlock(&transaction->t_journal->j_list_lock); spin_unlock(&jh->b_state_lock); } /* * Remove a buffer from its current buffer list in preparation for * dropping it from its current transaction entirely. If the buffer has * already started to be used by a subsequent transaction, refile the * buffer on that transaction's metadata list. * * Called under j_list_lock * Called under jh->b_state_lock * * When this function returns true, there's no next transaction to refile to * and the caller has to drop jh reference through * jbd2_journal_put_journal_head(). */ bool __jbd2_journal_refile_buffer(struct journal_head *jh) { int was_dirty, jlist; struct buffer_head *bh = jh2bh(jh); lockdep_assert_held(&jh->b_state_lock); if (jh->b_transaction) assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock); /* If the buffer is now unused, just drop it. */ if (jh->b_next_transaction == NULL) { __jbd2_journal_unfile_buffer(jh); return true; } /* * It has been modified by a later transaction: add it to the new * transaction's metadata list. */ was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); /* * b_transaction must be set, otherwise the new b_transaction won't * be holding jh reference */ J_ASSERT_JH(jh, jh->b_transaction != NULL); /* * We set b_transaction here because b_next_transaction will inherit * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) jlist = BJ_Metadata; else jlist = BJ_Reserved; __jbd2_journal_file_buffer(jh, jh->b_transaction, jlist); J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING); if (was_dirty) set_buffer_jbddirty(bh); return false; } /* * __jbd2_journal_refile_buffer() with necessary locking added. We take our * bh reference so that we can safely unlock bh. * * The jh and bh may be freed by this call. */ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) { bool drop; spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); drop = __jbd2_journal_refile_buffer(jh); spin_unlock(&jh->b_state_lock); spin_unlock(&journal->j_list_lock); if (drop) jbd2_journal_put_journal_head(jh); } /* * File inode in the inode list of the handle's transaction */ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, unsigned long flags, loff_t start_byte, loff_t end_byte) { transaction_t *transaction = handle->h_transaction; journal_t *journal; if (is_handle_aborted(handle)) return -EROFS; journal = transaction->t_journal; jbd2_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); spin_lock(&journal->j_list_lock); jinode->i_flags |= flags; if (jinode->i_dirty_end) { jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte); jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte); } else { jinode->i_dirty_start = start_byte; jinode->i_dirty_end = end_byte; } /* Is inode already attached where we need it? */ if (jinode->i_transaction == transaction || jinode->i_next_transaction == transaction) goto done; /* * We only ever set this variable to 1 so the test is safe. Since * t_need_data_flush is likely to be set, we do the test to save some * cacheline bouncing */ if (!transaction->t_need_data_flush) transaction->t_need_data_flush = 1; /* On some different transaction's list - should be * the committing one */ if (jinode->i_transaction) { J_ASSERT(jinode->i_next_transaction == NULL); J_ASSERT(jinode->i_transaction == journal->j_committing_transaction); jinode->i_next_transaction = transaction; goto done; } /* Not on any transaction list... */ J_ASSERT(!jinode->i_next_transaction); jinode->i_transaction = transaction; list_add(&jinode->i_list, &transaction->t_inode_list); done: spin_unlock(&journal->j_list_lock); return 0; } int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *jinode, loff_t start_byte, loff_t length) { return jbd2_journal_file_inode(handle, jinode, JI_WRITE_DATA | JI_WAIT_DATA, start_byte, start_byte + length - 1); } int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode, loff_t start_byte, loff_t length) { return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, start_byte, start_byte + length - 1); } /* * File truncate and transaction commit interact with each other in a * non-trivial way. If a transaction writing data block A is * committing, we cannot discard the data by truncate until we have * written them. Otherwise if we crashed after the transaction with * write has committed but before the transaction with truncate has * committed, we could see stale data in block A. This function is a * helper to solve this problem. It starts writeout of the truncated * part in case it is in the committing transaction. * * Filesystem code must call this function when inode is journaled in * ordered mode before truncation happens and after the inode has been * placed on orphan list with the new inode size. The second condition * avoids the race that someone writes new data and we start * committing the transaction after this function has been called but * before a transaction for truncate is started (and furthermore it * allows us to optimize the case where the addition to orphan list * happens in the same transaction as write --- we don't have to write * any data in such case). */ int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *jinode, loff_t new_size) { transaction_t *inode_trans, *commit_trans; int ret = 0; /* This is a quick check to avoid locking if not necessary */ if (!jinode->i_transaction) goto out; /* Locks are here just to force reading of recent values, it is * enough that the transaction was not committing before we started * a transaction adding the inode to orphan list */ read_lock(&journal->j_state_lock); commit_trans = journal->j_committing_transaction; read_unlock(&journal->j_state_lock); spin_lock(&journal->j_list_lock); inode_trans = jinode->i_transaction; spin_unlock(&journal->j_list_lock); if (inode_trans == commit_trans) { ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping, new_size, LLONG_MAX); if (ret) jbd2_journal_abort(journal, ret); } out: return ret; } |
| 3 3 3 3 3 3 2 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved. */ #include <rdma/rdma_cm.h> #include <rdma/ib_verbs.h> #include <rdma/restrack.h> #include <rdma/rdma_counter.h> #include <linux/mutex.h> #include <linux/sched/task.h> #include <linux/pid_namespace.h> #include "cma_priv.h" #include "restrack.h" /** * rdma_restrack_init() - initialize and allocate resource tracking * @dev: IB device * * Return: 0 on success */ int rdma_restrack_init(struct ib_device *dev) { struct rdma_restrack_root *rt; int i; dev->res = kcalloc(RDMA_RESTRACK_MAX, sizeof(*rt), GFP_KERNEL); if (!dev->res) return -ENOMEM; rt = dev->res; for (i = 0; i < RDMA_RESTRACK_MAX; i++) xa_init_flags(&rt[i].xa, XA_FLAGS_ALLOC); return 0; } /** * rdma_restrack_clean() - clean resource tracking * @dev: IB device */ void rdma_restrack_clean(struct ib_device *dev) { struct rdma_restrack_root *rt = dev->res; int i; for (i = 0 ; i < RDMA_RESTRACK_MAX; i++) { struct xarray *xa = &dev->res[i].xa; WARN_ON(!xa_empty(xa)); xa_destroy(xa); } kfree(rt); } /** * rdma_restrack_count() - the current usage of specific object * @dev: IB device * @type: actual type of object to operate * @show_details: count driver specific objects */ int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type, bool show_details) { struct rdma_restrack_root *rt = &dev->res[type]; struct rdma_restrack_entry *e; XA_STATE(xas, &rt->xa, 0); u32 cnt = 0; xa_lock(&rt->xa); xas_for_each(&xas, e, U32_MAX) { if (xa_get_mark(&rt->xa, e->id, RESTRACK_DD) && !show_details) continue; cnt++; } xa_unlock(&rt->xa); return cnt; } EXPORT_SYMBOL(rdma_restrack_count); static struct ib_device *res_to_dev(struct rdma_restrack_entry *res) { switch (res->type) { case RDMA_RESTRACK_PD: return container_of(res, struct ib_pd, res)->device; case RDMA_RESTRACK_CQ: return container_of(res, struct ib_cq, res)->device; case RDMA_RESTRACK_QP: return container_of(res, struct ib_qp, res)->device; case RDMA_RESTRACK_CM_ID: return container_of(res, struct rdma_id_private, res)->id.device; case RDMA_RESTRACK_MR: return container_of(res, struct ib_mr, res)->device; case RDMA_RESTRACK_CTX: return container_of(res, struct ib_ucontext, res)->device; case RDMA_RESTRACK_COUNTER: return container_of(res, struct rdma_counter, res)->device; case RDMA_RESTRACK_SRQ: return container_of(res, struct ib_srq, res)->device; default: WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type); return NULL; } } /** * rdma_restrack_attach_task() - attach the task onto this resource, * valid for user space restrack entries. * @res: resource entry * @task: the task to attach */ static void rdma_restrack_attach_task(struct rdma_restrack_entry *res, struct task_struct *task) { if (WARN_ON_ONCE(!task)) return; if (res->task) put_task_struct(res->task); get_task_struct(task); res->task = task; res->user = true; } /** * rdma_restrack_set_name() - set the task for this resource * @res: resource entry * @caller: kernel name, the current task will be used if the caller is NULL. */ void rdma_restrack_set_name(struct rdma_restrack_entry *res, const char *caller) { if (caller) { res->kern_name = caller; return; } rdma_restrack_attach_task(res, current); } EXPORT_SYMBOL(rdma_restrack_set_name); /** * rdma_restrack_parent_name() - set the restrack name properties based * on parent restrack * @dst: destination resource entry * @parent: parent resource entry */ void rdma_restrack_parent_name(struct rdma_restrack_entry *dst, const struct rdma_restrack_entry *parent) { if (rdma_is_kernel_res(parent)) dst->kern_name = parent->kern_name; else rdma_restrack_attach_task(dst, parent->task); } EXPORT_SYMBOL(rdma_restrack_parent_name); /** * rdma_restrack_new() - Initializes new restrack entry to allow _put() interface * to release memory in fully automatic way. * @res: Entry to initialize * @type: REstrack type */ void rdma_restrack_new(struct rdma_restrack_entry *res, enum rdma_restrack_type type) { kref_init(&res->kref); init_completion(&res->comp); res->type = type; } EXPORT_SYMBOL(rdma_restrack_new); /** * rdma_restrack_add() - add object to the reource tracking database * @res: resource entry */ void rdma_restrack_add(struct rdma_restrack_entry *res) { struct ib_device *dev = res_to_dev(res); struct rdma_restrack_root *rt; int ret = 0; if (!dev) return; if (res->no_track) goto out; rt = &dev->res[res->type]; if (res->type == RDMA_RESTRACK_QP) { /* Special case to ensure that LQPN points to right QP */ struct ib_qp *qp = container_of(res, struct ib_qp, res); WARN_ONCE(qp->qp_num >> 24 || qp->port >> 8, "QP number 0x%0X and port 0x%0X", qp->qp_num, qp->port); res->id = qp->qp_num; if (qp->qp_type == IB_QPT_SMI || qp->qp_type == IB_QPT_GSI) res->id |= qp->port << 24; ret = xa_insert(&rt->xa, res->id, res, GFP_KERNEL); if (ret) res->id = 0; if (qp->qp_type >= IB_QPT_DRIVER) xa_set_mark(&rt->xa, res->id, RESTRACK_DD); } else if (res->type == RDMA_RESTRACK_COUNTER) { /* Special case to ensure that cntn points to right counter */ struct rdma_counter *counter; counter = container_of(res, struct rdma_counter, res); ret = xa_insert(&rt->xa, counter->id, res, GFP_KERNEL); res->id = ret ? 0 : counter->id; } else { ret = xa_alloc_cyclic(&rt->xa, &res->id, res, xa_limit_32b, &rt->next_id, GFP_KERNEL); ret = (ret < 0) ? ret : 0; } out: if (!ret) res->valid = true; } EXPORT_SYMBOL(rdma_restrack_add); int __must_check rdma_restrack_get(struct rdma_restrack_entry *res) { return kref_get_unless_zero(&res->kref); } EXPORT_SYMBOL(rdma_restrack_get); /** * rdma_restrack_get_byid() - translate from ID to restrack object * @dev: IB device * @type: resource track type * @id: ID to take a look * * Return: Pointer to restrack entry or -ENOENT in case of error. */ struct rdma_restrack_entry * rdma_restrack_get_byid(struct ib_device *dev, enum rdma_restrack_type type, u32 id) { struct rdma_restrack_root *rt = &dev->res[type]; struct rdma_restrack_entry *res; xa_lock(&rt->xa); res = xa_load(&rt->xa, id); if (!res || !rdma_restrack_get(res)) res = ERR_PTR(-ENOENT); xa_unlock(&rt->xa); return res; } EXPORT_SYMBOL(rdma_restrack_get_byid); static void restrack_release(struct kref *kref) { struct rdma_restrack_entry *res; res = container_of(kref, struct rdma_restrack_entry, kref); if (res->task) { put_task_struct(res->task); res->task = NULL; } complete(&res->comp); } int rdma_restrack_put(struct rdma_restrack_entry *res) { return kref_put(&res->kref, restrack_release); } EXPORT_SYMBOL(rdma_restrack_put); /** * rdma_restrack_del() - delete object from the reource tracking database * @res: resource entry */ void rdma_restrack_del(struct rdma_restrack_entry *res) { struct rdma_restrack_entry *old; struct rdma_restrack_root *rt; struct ib_device *dev; if (!res->valid) { if (res->task) { put_task_struct(res->task); res->task = NULL; } return; } if (res->no_track) goto out; dev = res_to_dev(res); if (WARN_ON(!dev)) return; rt = &dev->res[res->type]; old = xa_erase(&rt->xa, res->id); WARN_ON(old != res); out: res->valid = false; rdma_restrack_put(res); wait_for_completion(&res->comp); } EXPORT_SYMBOL(rdma_restrack_del); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef IOU_KBUF_H #define IOU_KBUF_H #include <uapi/linux/io_uring.h> #include <linux/io_uring_types.h> enum { /* ring mapped provided buffers */ IOBL_BUF_RING = 1, /* buffers are consumed incrementally rather than always fully */ IOBL_INC = 2, }; struct io_buffer_list { /* * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not, * then these are classic provided buffers and ->buf_list is used. */ union { struct list_head buf_list; struct io_uring_buf_ring *buf_ring; }; /* count of classic/legacy buffers in buffer list */ int nbufs; __u16 bgid; /* below is for ring provided buffers */ __u16 buf_nr_pages; __u16 nr_entries; __u16 head; __u16 mask; __u16 flags; struct io_mapped_region region; }; struct io_buffer { struct list_head list; __u64 addr; __u32 len; __u16 bid; __u16 bgid; }; enum { /* can alloc a bigger vec */ KBUF_MODE_EXPAND = 1, /* if bigger vec allocated, free old one */ KBUF_MODE_FREE = 2, }; struct buf_sel_arg { struct iovec *iovs; size_t out_len; size_t max_len; unsigned short nr_iovs; unsigned short mode; unsigned short buf_group; unsigned short partial_map; }; void __user *io_buffer_select(struct io_kiocb *req, size_t *len, unsigned buf_group, unsigned int issue_flags); int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg, unsigned int issue_flags); int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg); void io_destroy_buffers(struct io_ring_ctx *ctx); int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_manage_buffers_legacy(struct io_kiocb *req, unsigned int issue_flags); int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg); bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); void io_kbuf_drop_legacy(struct io_kiocb *req); unsigned int __io_put_kbufs(struct io_kiocb *req, int len, int nbufs); bool io_kbuf_commit(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr); struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx, unsigned int bgid); static inline bool io_kbuf_recycle_ring(struct io_kiocb *req) { /* * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear * the flag and hence ensure that bl->head doesn't get incremented. * If the tail has already been incremented, hang on to it. * The exception is partial io, that case we should increment bl->head * to monopolize the buffer. */ if (req->buf_list) { req->flags &= ~(REQ_F_BUFFER_RING|REQ_F_BUFFERS_COMMIT); return true; } return false; } static inline bool io_do_buffer_select(struct io_kiocb *req) { if (!(req->flags & REQ_F_BUFFER_SELECT)) return false; return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); } static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) { if (req->flags & REQ_F_BL_NO_RECYCLE) return false; if (req->flags & REQ_F_BUFFER_SELECTED) return io_kbuf_recycle_legacy(req, issue_flags); if (req->flags & REQ_F_BUFFER_RING) return io_kbuf_recycle_ring(req); return false; } static inline unsigned int io_put_kbuf(struct io_kiocb *req, int len, unsigned issue_flags) { if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED))) return 0; return __io_put_kbufs(req, len, 1); } static inline unsigned int io_put_kbufs(struct io_kiocb *req, int len, int nbufs, unsigned issue_flags) { if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED))) return 0; return __io_put_kbufs(req, len, nbufs); } #endif |
| 1 1 1 1 1 1 1 1 1 2459 3 2463 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entries_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset); static inline void unlock_cluster(struct swap_cluster_info *ci); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); struct percpu_swap_cluster { struct swap_info_struct *si[SWAP_NR_ORDERS]; unsigned long offset[SWAP_NR_ORDERS]; local_lock_t lock; }; static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = { .si = { NULL }, .offset = { SWAP_ENTRY_INVALID }, .lock = INIT_LOCAL_LOCK(), }; static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* * Use the second highest bit of inuse_pages counter as the indicator * if one swap device is on the available plist, so the atomic can * still be updated arithmetically while having special data embedded. * * inuse_pages counter is the only thing indicating if a device should * be on avail_lists or not (except swapon / swapoff). By embedding the * off-list bit in the atomic counter, updates no longer need any lock * to check the list status. * * This bit will be set if the device is not on the plist and not * usable, will be cleared if the device is on the plist. */ #define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) #define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) static long swap_usage_in_pages(struct swap_info_struct *si) { return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 static bool swap_only_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1 && swap_count(count) != SWAP_MAP_SHMEM) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct address_space *address_space = swap_address_space(entry); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; again: folio = filemap_get_folio(address_space, swap_cache_index(entry)); if (IS_ERR(folio)) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; /* * Offset could point to the middle of a large folio, or folio * may no longer point to the expected offset before it's locked. */ entry = folio->swap; if (offset < swp_offset(entry) || offset >= swp_offset(entry) + nr_pages) { folio_unlock(folio); folio_put(folio); goto again; } offset = swp_offset(entry); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = lock_cluster(si, offset); need_reclaim = swap_only_has_cache(si, offset, nr_pages); unlock_cluster(ci); if (!need_reclaim) goto out_unlock; delete_from_swap_cache(folio); folio_set_dirty(folio); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = swp_swap_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 static inline bool cluster_is_empty(struct swap_cluster_info *info) { return info->count == 0; } static inline bool cluster_is_discard(struct swap_cluster_info *info) { return info->flags == CLUSTER_FLAG_DISCARD; } static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) { if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) return false; if (!order) return true; return cluster_is_empty(ci) || order == ci->order; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si, unsigned long offset) { return &si->cluster_info[offset / SWAPFILE_CLUSTER]; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = offset_to_cluster(si, offset); spin_lock(&ci->lock); return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { spin_unlock(&ci->lock); } static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags) { VM_WARN_ON(ci->flags == new_flags); BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); lockdep_assert_held(&ci->lock); spin_lock(&si->lock); if (ci->flags == CLUSTER_FLAG_NONE) list_add_tail(&ci->list, list); else list_move_tail(&ci->list, list); spin_unlock(&si->lock); if (ci->flags == CLUSTER_FLAG_FRAG) atomic_long_dec(&si->frag_cluster_nr[ci->order]); else if (new_flags == CLUSTER_FLAG_FRAG) atomic_long_inc(&si->frag_cluster_nr[ci->order]); ci->flags = new_flags; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); ci->order = 0; } /* * Isolate and lock the first cluster that is not contented on a list, * clean its flag before taken off-list. Cluster flag must be in sync * with list status, so cluster updaters can always know the cluster * list status without touching si lock. * * Note it's possible that all clusters on a list are contented so * this returns NULL for an non-empty list. */ static struct swap_cluster_info *isolate_lock_cluster( struct swap_info_struct *si, struct list_head *list) { struct swap_cluster_info *ci, *ret = NULL; spin_lock(&si->lock); if (unlikely(!(si->flags & SWP_WRITEOK))) goto out; list_for_each_entry(ci, list, list) { if (!spin_trylock(&ci->lock)) continue; /* We may only isolate and clear flags of following lists */ VM_BUG_ON(!ci->flags); VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && ci->flags != CLUSTER_FLAG_FULL); list_del(&ci->list); ci->flags = CLUSTER_FLAG_NONE; ret = ci; break; } out: spin_unlock(&si->lock); return ret; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. Discard cluster is a bit special as * they don't participate in allocation or reclaim, so clusters marked as * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. */ static bool swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; bool ret = false; unsigned int idx; spin_lock(&si->lock); while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); /* * Delete the cluster from list to prepare for discard, but keep * the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be * pointing to it, or ran into by relocate_cluster. */ list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&ci->lock); /* * Discard is done, clear its flags as it's off-list, then * return the cluster to allocation list. */ ci->flags = CLUSTER_FLAG_NONE; __free_cluster(si, ci); spin_unlock(&ci->lock); ret = true; spin_lock(&si->lock); } spin_unlock(&si->lock); return ret; } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); swap_do_scheduled_discard(si); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } /* * Must be called after freeing if ci->count == 0, moves the cluster to free * or discard list. */ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); lockdep_assert_held(&ci->lock); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * Must be called after freeing if ci->count != 0, moves the cluster to * nonfull list. */ static void partial_free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); lockdep_assert_held(&ci->lock); if (ci->flags != CLUSTER_FLAG_NONFULL) move_cluster(si, ci, &si->nonfull_clusters[ci->order], CLUSTER_FLAG_NONFULL); } /* * Must be called after allocation, moves the cluster to full or frag list. * Note: allocation doesn't acquire si lock, and may drop the ci lock for * reclaim, so the cluster could be any where when called. */ static void relocate_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); /* Discard cluster must remain off-list or on discard list */ if (cluster_is_discard(ci)) return; if (!ci->count) { if (ci->flags != CLUSTER_FLAG_FREE) free_cluster(si, ci); } else if (ci->count != SWAPFILE_CLUSTER) { if (ci->flags != CLUSTER_FLAG_FRAG) move_cluster(si, ci, &si->frag_clusters[ci->order], CLUSTER_FLAG_FRAG); } else { if (ci->flags != CLUSTER_FLAG_FULL) move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL); } } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static void inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = cluster_info + idx; ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset = start; int nr_reclaim; spin_unlock(&ci->lock); do { switch (READ_ONCE(map[offset])) { case 0: offset++; break; case SWAP_HAS_CACHE: nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); if (nr_reclaim > 0) offset += nr_reclaim; else goto out; break; default: goto out; } } while (offset < end); out: spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages, bool *need_reclaim) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; if (cluster_is_empty(ci)) return true; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; *need_reclaim = true; continue; default: return false; } } return true; } static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; lockdep_assert_held(&ci->lock); if (!(si->flags & SWP_WRITEOK)) return false; /* * The first allocation in a cluster makes the * cluster exclusive to this order */ if (cluster_is_empty(ci)) ci->order = order; memset(si->swap_map + start, usage, nr_pages); swap_range_alloc(si, nr_pages); ci->count += nr_pages; return true; } /* Try use a new cluster for current CPU and allocate from it. */ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long offset, unsigned int order, unsigned char usage) { unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; bool need_reclaim, ret; lockdep_assert_held(&ci->lock); if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) goto out; for (end -= nr_pages; offset <= end; offset += nr_pages) { need_reclaim = false; if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) continue; if (need_reclaim) { ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); /* * Reclaim drops ci->lock and cluster could be used * by another order. Not checking flag as off-list * cluster has no flag set, and change of list * won't cause fragmentation. */ if (!cluster_is_usable(ci, order)) goto out; if (cluster_is_empty(ci)) offset = start; /* Reclaim failed but cluster is usable, try next */ if (!ret) continue; } if (!cluster_alloc_range(si, ci, offset, usage, order)) break; found = offset; offset += nr_pages; if (ci->count < SWAPFILE_CLUSTER && offset <= end) next = offset; break; } out: relocate_cluster(si, ci); unlock_cluster(ci); if (si->flags & SWP_SOLIDSTATE) { this_cpu_write(percpu_swap_cluster.offset[order], next); this_cpu_write(percpu_swap_cluster.si[order], si); } else { si->global_cluster->next[order] = next; } return found; } static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim; if (force) to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; while ((ci = isolate_lock_cluster(si, &si->full_clusters))) { offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { spin_unlock(&ci->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&ci->lock); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } /* in case no swap cache is reclaimed */ if (ci->flags == CLUSTER_FLAG_NONE) relocate_cluster(si, ci); unlock_cluster(ci); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); swap_reclaim_full_clusters(si, true); } /* * Try to allocate swap entries with specified order and try set a new * cluster for current CPU too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct swap_cluster_info *ci; unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; /* * Swapfile is not block device so unable * to allocate large entries. */ if (order && !(si->flags & SWP_BLKDEV)) return 0; if (!(si->flags & SWP_SOLIDSTATE)) { /* Serialize HDD SWAP allocation for each device. */ spin_lock(&si->global_cluster_lock); offset = si->global_cluster->next[order]; if (offset == SWAP_ENTRY_INVALID) goto new_cluster; ci = lock_cluster(si, offset); /* Cluster could have been used by another order */ if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, usage); } else { unlock_cluster(ci); } if (found) goto done; } new_cluster: ci = isolate_lock_cluster(si, &si->free_clusters); if (ci) { found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), order, usage); if (found) goto done; } /* Try reclaim from full clusters if free clusters list is drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { unsigned int frags = 0, frags_existing; while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) { found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), order, usage); if (found) goto done; /* Clusters failed to allocate are moved to frag_clusters */ frags++; } frags_existing = atomic_long_read(&si->frag_cluster_nr[order]); while (frags < frags_existing && (ci = isolate_lock_cluster(si, &si->frag_clusters[order]))) { atomic_long_dec(&si->frag_cluster_nr[order]); /* * Rotate the frag list to iterate, they were all * failing high order allocation or moved here due to * per-CPU usage, but they could contain newly released * reclaimable (eg. lazy-freed swap cache) slots. */ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), order, usage); if (found) goto done; frags++; } } /* * We don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) goto new_cluster; if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) { atomic_long_dec(&si->frag_cluster_nr[o]); found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), 0, usage); if (found) goto done; } while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) { found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci), 0, usage); if (found) goto done; } } done: if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); return found; } /* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { int nid; unsigned long pages; spin_lock(&swap_avail_lock); if (swapoff) { /* * Forcefully remove it. Clear the SWP_WRITEOK flags for * swapoff here so it's synchronized by both si->lock and * swap_avail_lock, to ensure the result can be seen by * add_to_avail_list. */ lockdep_assert_held(&si->lock); si->flags &= ~SWP_WRITEOK; atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); } else { /* * If not called by swapoff, take it off-list only if it's * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly * si->inuse_pages == pages), any concurrent slot freeing, * or device already removed from plist by someone else * will make this return false. */ pages = si->pages; if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ static void add_to_avail_list(struct swap_info_struct *si, bool swapon) { int nid; long val; unsigned long pages; spin_lock(&swap_avail_lock); /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ if (swapon) { lockdep_assert_held(&si->lock); si->flags |= SWP_WRITEOK; } else { if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) goto skip; } if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) goto skip; val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); /* * When device is full and device is on the plist, only one updater will * see (inuse_pages == si->pages) and will call del_from_avail_list. If * that updater happen to be here, just skip adding. */ pages = si->pages; if (val == pages) { /* Just like the cmpxchg in del_from_avail_list */ if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock * within each cluster, so the total contribution to the global counter should * always be positive and cannot exceed the total number of usable slots. */ static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, * remove it from the plist. */ if (unlikely(val == si->pages)) { del_from_avail_list(si, false); return true; } return false; } static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, * add it to the plist. */ if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) add_to_avail_list(si, false); } static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries) { if (swap_usage_add(si, nr_entries)) { if (vm_swap_full()) schedule_work(&si->reclaim_work); } } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) { clear_bit(offset + i, si->zeromap); zswap_invalidate(swp_entry(si->type, offset + i)); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); swap_usage_sub(si, nr_entries); } static bool get_swap_device_info(struct swap_info_struct *si) { if (!percpu_ref_tryget_live(&si->users)) return false; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is * up to dated. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(), and smp_wmb() in swapoff. */ smp_rmb(); return true; } /* * Fast path try to get swap entries with specified order from current * CPU's swap entry pool (a cluster). */ static bool swap_alloc_fast(swp_entry_t *entry, int order) { struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned int offset, found = SWAP_ENTRY_INVALID; /* * Once allocated, swap_info_struct will never be completely freed, * so checking it's liveness by get_swap_device_info is enough. */ si = this_cpu_read(percpu_swap_cluster.si[order]); offset = this_cpu_read(percpu_swap_cluster.offset[order]); if (!si || !offset || !get_swap_device_info(si)) return false; ci = lock_cluster(si, offset); if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, SWAP_HAS_CACHE); if (found) *entry = swp_entry(si->type, found); } else { unlock_cluster(ci); } put_swap_device(si); return !!found; } /* Rotate the device and switch to a new cluster */ static bool swap_alloc_slow(swp_entry_t *entry, int order) { int node; unsigned long offset; struct swap_info_struct *si, *next; node = numa_node_id(); spin_lock(&swap_avail_lock); start_over: plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* Rotate the device and switch to a new cluster */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); if (get_swap_device_info(si)) { offset = cluster_alloc_swap_entry(si, order, SWAP_HAS_CACHE); put_swap_device(si); if (offset) { *entry = swp_entry(si->type, offset); return true; } if (order) return false; } spin_lock(&swap_avail_lock); /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); return false; } /** * folio_alloc_swap - allocate swap space for a folio * @folio: folio we want to move to swap * @gfp: gfp mask for shadow nodes * * Allocate swap space for the folio and add the folio to the * swap cache. * * Context: Caller needs to hold the folio lock. * Return: Whether the folio was added to the swap cache. */ int folio_alloc_swap(struct folio *folio, gfp_t gfp) { unsigned int order = folio_order(folio); unsigned int size = 1 << order; swp_entry_t entry = {}; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); if (order) { /* * Reject large allocation when THP_SWAP is disabled, * the caller should split the folio and try again. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) return -EAGAIN; /* * Allocation size should never exceed cluster size * (HPAGE_PMD_SIZE). */ if (size > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return -EINVAL; } } local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(&entry, order)) swap_alloc_slow(&entry, order); local_unlock(&percpu_swap_cluster.lock); /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ if (mem_cgroup_try_charge_swap(folio, entry)) goto out_free; if (!entry.val) return -ENOMEM; /* * XArray node allocations from PF_MEMALLOC contexts could * completely exhaust the page allocator. __GFP_NOMEMALLOC * stops emergency reserves from being allocated. * * TODO: this could cause a theoretical memory reclaim * deadlock in the swap out path. */ if (add_to_swap_cache(folio, entry, gfp | __GFP_NOMEMALLOC, NULL)) goto out_free; atomic_long_sub(size, &nr_swap_pages); return 0; out_free: put_swap_folio(folio, entry); return -ENOMEM; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static unsigned char swap_entry_put_locked(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned char usage) { unsigned long offset = swp_offset(entry); unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else swap_entries_free(si, ci, entry, 1); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!get_swap_device_info(si)) goto out; offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static void swap_entries_put_cache(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; ci = lock_cluster(si, offset); if (swap_only_has_cache(si, offset, nr)) swap_entries_free(si, ci, entry, nr); else { for (int i = 0; i < nr; i++, entry.val++) swap_entry_put_locked(si, ci, entry, SWAP_HAS_CACHE); } unlock_cluster(ci); } static bool swap_entries_put_map(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1) goto fallback; count = swap_count(data_race(si->swap_map[offset])); if (count != 1 && count != SWAP_MAP_SHMEM) goto fallback; ci = lock_cluster(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { goto locked_fallback; } if (!has_cache) swap_entries_free(si, ci, entry, nr); else for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); unlock_cluster(ci); return has_cache; fallback: ci = lock_cluster(si, offset); locked_fallback: for (i = 0; i < nr; i++, entry.val++) { count = swap_entry_put_locked(si, ci, entry, 1); if (count == SWAP_HAS_CACHE) has_cache = true; } unlock_cluster(ci); return has_cache; } /* * Only functions with "_nr" suffix are able to free entries spanning * cross multi clusters, so ensure the range is within a single cluster * when freeing entries with functions without "_nr" suffix. */ static bool swap_entries_put_map_nr(struct swap_info_struct *si, swp_entry_t entry, int nr) { int cluster_nr, cluster_rest; unsigned long offset = swp_offset(entry); bool has_cache = false; cluster_rest = SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER; while (nr) { cluster_nr = min(nr, cluster_rest); has_cache |= swap_entries_put_map(si, entry, cluster_nr); cluster_rest = SWAPFILE_CLUSTER; nr -= cluster_nr; entry.val += cluster_nr; } return has_cache; } /* * Check if it's the last ref of swap entry in the freeing path. * Qualified vlaue includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM. */ static inline bool __maybe_unused swap_is_last_ref(unsigned char count) { return (count == SWAP_HAS_CACHE) || (count == 1) || (count == SWAP_MAP_SHMEM); } /* * Drop the last ref of swap entries, caller have to ensure all entries * belong to the same cgroup and cluster. */ static void swap_entries_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; /* It should never free entries across different clusters */ VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1)); VM_BUG_ON(cluster_is_empty(ci)); VM_BUG_ON(ci->count < nr_pages); ci->count -= nr_pages; do { VM_BUG_ON(!swap_is_last_ref(*map)); *map = 0; } while (++map < map_end); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); if (!ci->count) free_cluster(si, ci); else partial_free_cluster(si, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); swap_entries_put_map(sis, swp_entry(sis->type, offset), nr); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; swap_entries_put_cache(si, entry, size); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster(ci); return !!count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster(ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster(si, offset); if (nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster(ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_entry_swapped(si, entry); return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = swap_entries_put_map_nr(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); unsigned long offset; swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ if (get_swap_device_info(si)) { if (si->flags & SWP_WRITEOK) { offset = cluster_alloc_swap_entry(si, 0, 1); if (offset) { entry = swp_entry(si->type, offset); atomic_long_dec(&nr_swap_pages); } } put_swap_device(si); } fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!swap_usage_in_pages(si)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (swap_usage_in_pages(si) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (swap_usage_in_pages(si) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writeout() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (swap_usage_in_pages(si)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* Add back to available list */ add_to_avail_list(si, true); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } /* * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range * see the updated flags, so there will be no more allocations. */ static void wait_for_allocation(struct swap_info_struct *si) { unsigned long offset; unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); struct swap_cluster_info *ci; BUG_ON(si->flags & SWP_WRITEOK); for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { ci = lock_cluster(si, offset); unlock_cluster(ci); } } /* * Called after swap device's reference count is dead, so * neither scan nor allocation will use it. */ static void flush_percpu_swap_cluster(struct swap_info_struct *si) { int cpu, i; struct swap_info_struct **pcp_si; for_each_possible_cpu(cpu) { pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu); /* * Invalidate the percpu swap cluster cache, si->users * is dead, so no new user will point to it, just flush * any existing user. */ for (i = 0; i < SWAP_NR_ORDERS; i++) cmpxchg(&pcp_si[i], si, NULL); } } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p, true); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; spin_unlock(&p->lock); spin_unlock(&swap_lock); wait_for_allocation(p); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); goto out_dput; } /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); flush_percpu_swap_cluster(p); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); kfree(p->global_cluster); p->global_cluster = NULL; vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(swap_usage_in_pages(si)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } static int setup_swap_map_and_extents(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages, sector_t *span) { unsigned int nr_good_pages; unsigned long i; int nr_extents; nr_good_pages = maxpages - 1; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; } } if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; si->max = maxpages; si->pages = nr_good_pages; nr_extents = setup_swap_extents(si, span); if (nr_extents < 0) return nr_extents; nr_good_pages = si->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return nr_extents; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); struct swap_cluster_info *cluster_info; unsigned long i, j, idx; int err = -ENOMEM; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); if (!(si->flags & SWP_SOLIDSTATE)) { si->global_cluster = kmalloc(sizeof(*si->global_cluster), GFP_KERNEL); if (!si->global_cluster) goto err_free; for (i = 0; i < SWAP_NR_ORDERS; i++) si->global_cluster->next[i] = SWAP_ENTRY_INVALID; spin_lock_init(&si->global_cluster_lock); } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map_and_extents(): header page, bad pages, * and the EOF part of the last cluster. */ inc_cluster_info_page(si, cluster_info, 0); for (i = 0; i < swap_header->info.nr_badpages; i++) inc_cluster_info_page(si, cluster_info, swap_header->info.badpages[i]); for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(si, cluster_info, i); INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); atomic_long_set(&si->frag_cluster_nr[i], 0); } /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (j = 0; j < SWAP_CLUSTER_COLS; j++) { for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; ci = cluster_info + idx; if (idx >= nr_clusters) continue; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); continue; } ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: kvfree(cluster_info); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * The swap subsystem needs a major overhaul to support this. * It doesn't work yet so just disable it for now. */ if (mapping_min_folio_order(mapping) > 0) { error = -EINVAL; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = init_swap_address_space(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = zswap_swapon(si->type, maxpages); if (error) goto free_swap_address_space; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = swap_flags & SWAP_FLAG_PRIO_MASK; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); free_swap_address_space: exit_swap_address_space(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: kfree(si->global_cluster); si->global_cluster = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swp_swap_info(entry); if (WARN_ON_ONCE(!si)) { pr_err("%s%08lx\n", Bad_file, entry.val); return -EINVAL; } offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: unlock_cluster(ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } /* * Caller should ensure entries belong to the same folio so * the entries won't span cross cluster boundary. */ void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { swap_entries_put_cache(si, entry, nr); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or caller of swap_entry_put_locked() * holds cluster lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 2 2 2 2 11 8 8 8 8 8 4 1 2 2 2 1 1 1 1 3 3 1 2 2 2 1 1 2 2 2 1 1 1 1 1 1 1 6 2 4 4 4 2 3 3 3 1 2 3 3 10 10 10 1 4 1 3 1 3 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * Provide access to virtual console memory. * /dev/vcs: the screen as it is being viewed right now (possibly scrolled) * /dev/vcsN: the screen of /dev/ttyN (1 <= N <= 63) * [minor: N] * * /dev/vcsaN: idem, but including attributes, and prefixed with * the 4 bytes lines,columns,x,y (as screendump used to give). * Attribute/character pair is in native endianity. * [minor: N+128] * * /dev/vcsuN: similar to /dev/vcsaN but using 4-byte unicode values * instead of 1-byte screen glyph values. * [minor: N+64] * * /dev/vcsuaN: same idea as /dev/vcsaN for unicode (not yet implemented). * * This replaces screendump and part of selection, so that the system * administrator can control access using file system permissions. * * aeb@cwi.nl - efter Friedas begravelse - 950211 * * machek@k332.feld.cvut.cz - modified not to send characters to wrong console * - fixed some fatal off-by-one bugs (0-- no longer == -1 -> looping and looping and looping...) * - making it shorter - scr_readw are macros which expand in PRETTY long code */ #include <linux/kernel.h> #include <linux/major.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/tty.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/vt_kern.h> #include <linux/selection.h> #include <linux/kbd_kern.h> #include <linux/console.h> #include <linux/device.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/signal.h> #include <linux/slab.h> #include <linux/notifier.h> #include <linux/uaccess.h> #include <asm/byteorder.h> #include <linux/unaligned.h> #define HEADER_SIZE 4u #define CON_BUF_SIZE (IS_ENABLED(CONFIG_BASE_SMALL) ? 256 : PAGE_SIZE) /* * Our minor space: * * 0 ... 63 glyph mode without attributes * 64 ... 127 unicode mode without attributes * 128 ... 191 glyph mode with attributes * 192 ... 255 unused (reserved for unicode with attributes) * * This relies on MAX_NR_CONSOLES being <= 63, meaning 63 actual consoles * with minors 0, 64, 128 and 192 being proxies for the foreground console. */ #if MAX_NR_CONSOLES > 63 #warning "/dev/vcs* devices may not accommodate more than 63 consoles" #endif #define console(inode) (iminor(inode) & 63) #define use_unicode(inode) (iminor(inode) & 64) #define use_attributes(inode) (iminor(inode) & 128) struct vcs_poll_data { struct notifier_block notifier; unsigned int cons_num; int event; wait_queue_head_t waitq; struct fasync_struct *fasync; }; static int vcs_notifier(struct notifier_block *nb, unsigned long code, void *_param) { struct vt_notifier_param *param = _param; struct vc_data *vc = param->vc; struct vcs_poll_data *poll = container_of(nb, struct vcs_poll_data, notifier); int currcons = poll->cons_num; int fa_band; switch (code) { case VT_UPDATE: fa_band = POLL_PRI; break; case VT_DEALLOCATE: fa_band = POLL_HUP; break; default: return NOTIFY_DONE; } if (currcons == 0) currcons = fg_console; else currcons--; if (currcons != vc->vc_num) return NOTIFY_DONE; poll->event = code; wake_up_interruptible(&poll->waitq); kill_fasync(&poll->fasync, SIGIO, fa_band); return NOTIFY_OK; } static void vcs_poll_data_free(struct vcs_poll_data *poll) { unregister_vt_notifier(&poll->notifier); kfree(poll); } static struct vcs_poll_data * vcs_poll_data_get(struct file *file) { struct vcs_poll_data *poll = file->private_data, *kill = NULL; if (poll) return poll; poll = kzalloc(sizeof(*poll), GFP_KERNEL); if (!poll) return NULL; poll->cons_num = console(file_inode(file)); init_waitqueue_head(&poll->waitq); poll->notifier.notifier_call = vcs_notifier; /* * In order not to lose any update event, we must pretend one might * have occurred before we have a chance to register our notifier. * This is also how user space has come to detect which kernels * support POLLPRI on /dev/vcs* devices i.e. using poll() with * POLLPRI and a zero timeout. */ poll->event = VT_UPDATE; if (register_vt_notifier(&poll->notifier) != 0) { kfree(poll); return NULL; } /* * This code may be called either through ->poll() or ->fasync(). * If we have two threads using the same file descriptor, they could * both enter this function, both notice that the structure hasn't * been allocated yet and go ahead allocating it in parallel, but * only one of them must survive and be shared otherwise we'd leak * memory with a dangling notifier callback. */ spin_lock(&file->f_lock); if (!file->private_data) { file->private_data = poll; } else { /* someone else raced ahead of us */ kill = poll; poll = file->private_data; } spin_unlock(&file->f_lock); if (kill) vcs_poll_data_free(kill); return poll; } /** * vcs_vc - return VC for @inode * @inode: inode for which to return a VC * @viewed: returns whether this console is currently foreground (viewed) * * Must be called with console_lock. */ static struct vc_data *vcs_vc(struct inode *inode, bool *viewed) { unsigned int currcons = console(inode); WARN_CONSOLE_UNLOCKED(); if (currcons == 0) { currcons = fg_console; if (viewed) *viewed = true; } else { currcons--; if (viewed) *viewed = false; } return vc_cons[currcons].d; } /** * vcs_size - return size for a VC in @vc * @vc: which VC * @attr: does it use attributes? * @unicode: is it unicode? * * Must be called with console_lock. */ static int vcs_size(const struct vc_data *vc, bool attr, bool unicode) { int size; WARN_CONSOLE_UNLOCKED(); size = vc->vc_rows * vc->vc_cols; if (attr) { if (unicode) return -EOPNOTSUPP; size = 2 * size + HEADER_SIZE; } else if (unicode) size *= 4; return size; } static loff_t vcs_lseek(struct file *file, loff_t offset, int orig) { struct inode *inode = file_inode(file); struct vc_data *vc; int size; console_lock(); vc = vcs_vc(inode, NULL); if (!vc) { console_unlock(); return -ENXIO; } size = vcs_size(vc, use_attributes(inode), use_unicode(inode)); console_unlock(); if (size < 0) return size; return fixed_size_llseek(file, offset, orig, size); } static int vcs_read_buf_uni(struct vc_data *vc, char *con_buf, unsigned int pos, unsigned int count, bool viewed) { unsigned int nr, row, col, maxcol = vc->vc_cols; int ret; ret = vc_uniscr_check(vc); if (ret) return ret; pos /= 4; row = pos / maxcol; col = pos % maxcol; nr = maxcol - col; do { if (nr > count / 4) nr = count / 4; vc_uniscr_copy_line(vc, con_buf, viewed, row, col, nr); con_buf += nr * 4; count -= nr * 4; row++; col = 0; nr = maxcol; } while (count); return 0; } static void vcs_read_buf_noattr(const struct vc_data *vc, char *con_buf, unsigned int pos, unsigned int count, bool viewed) { u16 *org; unsigned int col, maxcol = vc->vc_cols; org = screen_pos(vc, pos, viewed); col = pos % maxcol; pos += maxcol - col; while (count-- > 0) { *con_buf++ = (vcs_scr_readw(vc, org++) & 0xff); if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } } static unsigned int vcs_read_buf(const struct vc_data *vc, char *con_buf, unsigned int pos, unsigned int count, bool viewed, unsigned int *skip) { u16 *org, *con_buf16; unsigned int col, maxcol = vc->vc_cols; unsigned int filled = count; if (pos < HEADER_SIZE) { /* clamp header values if they don't fit */ con_buf[0] = min(vc->vc_rows, 0xFFu); con_buf[1] = min(vc->vc_cols, 0xFFu); getconsxy(vc, con_buf + 2); *skip += pos; count += pos; if (count > CON_BUF_SIZE) { count = CON_BUF_SIZE; filled = count - pos; } /* Advance state pointers and move on. */ count -= min(HEADER_SIZE, count); pos = HEADER_SIZE; con_buf += HEADER_SIZE; /* If count >= 0, then pos is even... */ } else if (pos & 1) { /* * Skip first byte for output if start address is odd. Update * region sizes up/down depending on free space in buffer. */ (*skip)++; if (count < CON_BUF_SIZE) count++; else filled--; } if (!count) return filled; pos -= HEADER_SIZE; pos /= 2; col = pos % maxcol; org = screen_pos(vc, pos, viewed); pos += maxcol - col; /* * Buffer has even length, so we can always copy character + attribute. * We do not copy last byte to userspace if count is odd. */ count = (count + 1) / 2; con_buf16 = (u16 *)con_buf; while (count) { *con_buf16++ = vcs_scr_readw(vc, org++); count--; if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } return filled; } static ssize_t vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct vc_data *vc; struct vcs_poll_data *poll; unsigned int read; ssize_t ret; char *con_buf; loff_t pos; bool viewed, attr, uni_mode; con_buf = (char *) __get_free_page(GFP_KERNEL); if (!con_buf) return -ENOMEM; pos = *ppos; /* Select the proper current console and verify * sanity of the situation under the console lock. */ console_lock(); uni_mode = use_unicode(inode); attr = use_attributes(inode); ret = -EINVAL; if (pos < 0) goto unlock_out; /* we enforce 32-bit alignment for pos and count in unicode mode */ if (uni_mode && (pos | count) & 3) goto unlock_out; poll = file->private_data; if (count && poll) poll->event = 0; read = 0; ret = 0; while (count) { unsigned int this_round, skip = 0; int size; vc = vcs_vc(inode, &viewed); if (!vc) { ret = -ENXIO; break; } /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. */ size = vcs_size(vc, attr, uni_mode); if (size < 0) { ret = size; break; } if (pos >= size) break; if (count > size - pos) count = size - pos; this_round = count; if (this_round > CON_BUF_SIZE) this_round = CON_BUF_SIZE; /* Perform the whole read into the local con_buf. * Then we can drop the console spinlock and safely * attempt to move it to userspace. */ if (uni_mode) { ret = vcs_read_buf_uni(vc, con_buf, pos, this_round, viewed); if (ret) break; } else if (!attr) { vcs_read_buf_noattr(vc, con_buf, pos, this_round, viewed); } else { this_round = vcs_read_buf(vc, con_buf, pos, this_round, viewed, &skip); } /* Finally, release the console semaphore while we push * all the data to userspace from our temporary buffer. * * AKPM: Even though it's a semaphore, we should drop it because * the pagefault handling code may want to call printk(). */ console_unlock(); ret = copy_to_user(buf, con_buf + skip, this_round); console_lock(); if (ret) { read += this_round - ret; ret = -EFAULT; break; } buf += this_round; pos += this_round; read += this_round; count -= this_round; } *ppos += read; if (read) ret = read; unlock_out: console_unlock(); free_page((unsigned long) con_buf); return ret; } static u16 *vcs_write_buf_noattr(struct vc_data *vc, const char *con_buf, unsigned int pos, unsigned int count, bool viewed, u16 **org0) { u16 *org; unsigned int col, maxcol = vc->vc_cols; *org0 = org = screen_pos(vc, pos, viewed); col = pos % maxcol; pos += maxcol - col; while (count > 0) { unsigned char c = *con_buf++; count--; vcs_scr_writew(vc, (vcs_scr_readw(vc, org) & 0xff00) | c, org); org++; if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } return org; } /* * Compilers (gcc 10) are unable to optimize the swap in cpu_to_le16. So do it * the poor man way. */ static inline u16 vc_compile_le16(u8 hi, u8 lo) { #ifdef __BIG_ENDIAN return (lo << 8u) | hi; #else return (hi << 8u) | lo; #endif } static u16 *vcs_write_buf(struct vc_data *vc, const char *con_buf, unsigned int pos, unsigned int count, bool viewed, u16 **org0) { u16 *org; unsigned int col, maxcol = vc->vc_cols; unsigned char c; /* header */ if (pos < HEADER_SIZE) { char header[HEADER_SIZE]; getconsxy(vc, header + 2); while (pos < HEADER_SIZE && count > 0) { count--; header[pos++] = *con_buf++; } if (!viewed) putconsxy(vc, header + 2); } if (!count) return NULL; pos -= HEADER_SIZE; col = (pos/2) % maxcol; *org0 = org = screen_pos(vc, pos/2, viewed); /* odd pos -- the first single character */ if (pos & 1) { count--; c = *con_buf++; vcs_scr_writew(vc, vc_compile_le16(c, vcs_scr_readw(vc, org)), org); org++; pos++; if (++col == maxcol) { org = screen_pos(vc, pos/2, viewed); col = 0; } } pos /= 2; pos += maxcol - col; /* even pos -- handle attr+character pairs */ while (count > 1) { unsigned short w; w = get_unaligned(((unsigned short *)con_buf)); vcs_scr_writew(vc, w, org++); con_buf += 2; count -= 2; if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } if (!count) return org; /* odd pos -- the remaining character */ c = *con_buf++; vcs_scr_writew(vc, vc_compile_le16(vcs_scr_readw(vc, org) >> 8, c), org); return org; } static ssize_t vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct vc_data *vc; char *con_buf; u16 *org0, *org; unsigned int written; int size; ssize_t ret; loff_t pos; bool viewed, attr; if (use_unicode(inode)) return -EOPNOTSUPP; con_buf = (char *) __get_free_page(GFP_KERNEL); if (!con_buf) return -ENOMEM; pos = *ppos; /* Select the proper current console and verify * sanity of the situation under the console lock. */ console_lock(); attr = use_attributes(inode); ret = -ENXIO; vc = vcs_vc(inode, &viewed); if (!vc) goto unlock_out; size = vcs_size(vc, attr, false); if (size < 0) { ret = size; goto unlock_out; } ret = -EINVAL; if (pos < 0 || pos > size) goto unlock_out; if (count > size - pos) count = size - pos; written = 0; while (count) { unsigned int this_round = count; if (this_round > CON_BUF_SIZE) this_round = CON_BUF_SIZE; /* Temporarily drop the console lock so that we can read * in the write data from userspace safely. */ console_unlock(); ret = copy_from_user(con_buf, buf, this_round); console_lock(); if (ret) { this_round -= ret; if (!this_round) { /* Abort loop if no data were copied. Otherwise * fail with -EFAULT. */ if (written) break; ret = -EFAULT; goto unlock_out; } } /* The vc might have been freed or vcs_size might have changed * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ vc = vcs_vc(inode, &viewed); if (!vc) { if (written) break; ret = -ENXIO; goto unlock_out; } size = vcs_size(vc, attr, false); if (size < 0) { if (written) break; ret = size; goto unlock_out; } if (pos >= size) break; if (this_round > size - pos) this_round = size - pos; /* OK, now actually push the write to the console * under the lock using the local kernel buffer. */ if (attr) org = vcs_write_buf(vc, con_buf, pos, this_round, viewed, &org0); else org = vcs_write_buf_noattr(vc, con_buf, pos, this_round, viewed, &org0); count -= this_round; written += this_round; buf += this_round; pos += this_round; if (org) update_region(vc, (unsigned long)(org0), org - org0); } *ppos += written; ret = written; if (written) vcs_scr_updated(vc); unlock_out: console_unlock(); free_page((unsigned long) con_buf); return ret; } static __poll_t vcs_poll(struct file *file, poll_table *wait) { struct vcs_poll_data *poll = vcs_poll_data_get(file); __poll_t ret = DEFAULT_POLLMASK|EPOLLERR; if (poll) { poll_wait(file, &poll->waitq, wait); switch (poll->event) { case VT_UPDATE: ret = DEFAULT_POLLMASK|EPOLLPRI; break; case VT_DEALLOCATE: ret = DEFAULT_POLLMASK|EPOLLHUP|EPOLLERR; break; case 0: ret = DEFAULT_POLLMASK; break; } } return ret; } static int vcs_fasync(int fd, struct file *file, int on) { struct vcs_poll_data *poll = file->private_data; if (!poll) { /* don't allocate anything if all we want is disable fasync */ if (!on) return 0; poll = vcs_poll_data_get(file); if (!poll) return -ENOMEM; } return fasync_helper(fd, file, on, &poll->fasync); } static int vcs_open(struct inode *inode, struct file *filp) { unsigned int currcons = console(inode); bool attr = use_attributes(inode); bool uni_mode = use_unicode(inode); int ret = 0; /* we currently don't support attributes in unicode mode */ if (attr && uni_mode) return -EOPNOTSUPP; console_lock(); if(currcons && !vc_cons_allocated(currcons-1)) ret = -ENXIO; console_unlock(); return ret; } static int vcs_release(struct inode *inode, struct file *file) { struct vcs_poll_data *poll = file->private_data; if (poll) vcs_poll_data_free(poll); return 0; } static const struct file_operations vcs_fops = { .llseek = vcs_lseek, .read = vcs_read, .write = vcs_write, .poll = vcs_poll, .fasync = vcs_fasync, .open = vcs_open, .release = vcs_release, }; static const struct class vc_class = { .name = "vc", }; void vcs_make_sysfs(int index) { device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, index + 1), NULL, "vcs%u", index + 1); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, index + 65), NULL, "vcsu%u", index + 1); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, index + 129), NULL, "vcsa%u", index + 1); } void vcs_remove_sysfs(int index) { device_destroy(&vc_class, MKDEV(VCS_MAJOR, index + 1)); device_destroy(&vc_class, MKDEV(VCS_MAJOR, index + 65)); device_destroy(&vc_class, MKDEV(VCS_MAJOR, index + 129)); } int __init vcs_init(void) { unsigned int i; if (register_chrdev(VCS_MAJOR, "vcs", &vcs_fops)) panic("unable to get major %d for vcs device", VCS_MAJOR); if (class_register(&vc_class)) panic("unable to create vc_class"); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, 0), NULL, "vcs"); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, 64), NULL, "vcsu"); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, 128), NULL, "vcsa"); for (i = 0; i < MIN_NR_CONSOLES; i++) vcs_make_sysfs(i); return 0; } |
| 4 5 5 2 2 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 1 5 5 5 5 5 4 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* procfs files for key database enumeration * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/init.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <asm/errno.h> #include "internal.h" static void *proc_keys_start(struct seq_file *p, loff_t *_pos); static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos); static void proc_keys_stop(struct seq_file *p, void *v); static int proc_keys_show(struct seq_file *m, void *v); static const struct seq_operations proc_keys_ops = { .start = proc_keys_start, .next = proc_keys_next, .stop = proc_keys_stop, .show = proc_keys_show, }; static void *proc_key_users_start(struct seq_file *p, loff_t *_pos); static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos); static void proc_key_users_stop(struct seq_file *p, void *v); static int proc_key_users_show(struct seq_file *m, void *v); static const struct seq_operations proc_key_users_ops = { .start = proc_key_users_start, .next = proc_key_users_next, .stop = proc_key_users_stop, .show = proc_key_users_show, }; /* * Declare the /proc files. */ static int __init key_proc_init(void) { struct proc_dir_entry *p; p = proc_create_seq("keys", 0, NULL, &proc_keys_ops); if (!p) panic("Cannot create /proc/keys\n"); p = proc_create_seq("key-users", 0, NULL, &proc_key_users_ops); if (!p) panic("Cannot create /proc/key-users\n"); return 0; } __initcall(key_proc_init); /* * Implement "/proc/keys" to provide a list of the keys on the system that * grant View permission to the caller. */ static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n) { struct user_namespace *user_ns = seq_user_ns(p); n = rb_next(n); while (n) { struct key *key = rb_entry(n, struct key, serial_node); if (kuid_has_mapping(user_ns, key->user->uid)) break; n = rb_next(n); } return n; } static struct key *find_ge_key(struct seq_file *p, key_serial_t id) { struct user_namespace *user_ns = seq_user_ns(p); struct rb_node *n = key_serial_tree.rb_node; struct key *minkey = NULL; while (n) { struct key *key = rb_entry(n, struct key, serial_node); if (id < key->serial) { if (!minkey || minkey->serial > key->serial) minkey = key; n = n->rb_left; } else if (id > key->serial) { n = n->rb_right; } else { minkey = key; break; } key = NULL; } if (!minkey) return NULL; for (;;) { if (kuid_has_mapping(user_ns, minkey->user->uid)) return minkey; n = rb_next(&minkey->serial_node); if (!n) return NULL; minkey = rb_entry(n, struct key, serial_node); } } static void *proc_keys_start(struct seq_file *p, loff_t *_pos) __acquires(key_serial_lock) { key_serial_t pos = *_pos; struct key *key; spin_lock(&key_serial_lock); if (*_pos > INT_MAX) return NULL; key = find_ge_key(p, pos); if (!key) return NULL; *_pos = key->serial; return &key->serial_node; } static inline key_serial_t key_node_serial(struct rb_node *n) { struct key *key = rb_entry(n, struct key, serial_node); return key->serial; } static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos) { struct rb_node *n; n = key_serial_next(p, v); if (n) *_pos = key_node_serial(n); else (*_pos)++; return n; } static void proc_keys_stop(struct seq_file *p, void *v) __releases(key_serial_lock) { spin_unlock(&key_serial_lock); } static int proc_keys_show(struct seq_file *m, void *v) { struct rb_node *_p = v; struct key *key = rb_entry(_p, struct key, serial_node); unsigned long flags; key_ref_t key_ref, skey_ref; time64_t now, expiry; char xbuf[16]; short state; u64 timo; int rc; struct keyring_search_context ctx = { .index_key = key->index_key, .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_RECURSE), }; key_ref = make_key_ref(key, 0); /* determine if the key is possessed by this process (a test we can * skip if the key does not indicate the possessor can view it */ if (key->perm & KEY_POS_VIEW) { rcu_read_lock(); skey_ref = search_cred_keyrings_rcu(&ctx); rcu_read_unlock(); if (!IS_ERR(skey_ref)) { key_ref_put(skey_ref); key_ref = make_key_ref(key, 1); } } /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; now = ktime_get_real_seconds(); rcu_read_lock(); /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5); } else { timo = expiry - now; if (timo < 60) sprintf(xbuf, "%llus", timo); else if (timo < 60*60) sprintf(xbuf, "%llum", div_u64(timo, 60)); else if (timo < 60*60*24) sprintf(xbuf, "%lluh", div_u64(timo, 60 * 60)); else if (timo < 60*60*24*7) sprintf(xbuf, "%llud", div_u64(timo, 60 * 60 * 24)); else sprintf(xbuf, "%lluw", div_u64(timo, 60 * 60 * 24 * 7)); } state = key_read_state(key); #define showflag(FLAGS, LETTER, FLAG) \ ((FLAGS & (1 << FLAG)) ? LETTER : '-') flags = READ_ONCE(key->flags); seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ", key->serial, state != KEY_IS_UNINSTANTIATED ? 'I' : '-', showflag(flags, 'R', KEY_FLAG_REVOKED), showflag(flags, 'D', KEY_FLAG_DEAD), showflag(flags, 'Q', KEY_FLAG_IN_QUOTA), showflag(flags, 'U', KEY_FLAG_USER_CONSTRUCT), state < 0 ? 'N' : '-', showflag(flags, 'i', KEY_FLAG_INVALIDATED), refcount_read(&key->usage), xbuf, key->perm, from_kuid_munged(seq_user_ns(m), key->uid), from_kgid_munged(seq_user_ns(m), key->gid), key->type->name); #undef showflag if (key->type->describe) key->type->describe(key, m); seq_putc(m, '\n'); rcu_read_unlock(); return 0; } static struct rb_node *__key_user_next(struct user_namespace *user_ns, struct rb_node *n) { while (n) { struct key_user *user = rb_entry(n, struct key_user, node); if (kuid_has_mapping(user_ns, user->uid)) break; n = rb_next(n); } return n; } static struct rb_node *key_user_next(struct user_namespace *user_ns, struct rb_node *n) { return __key_user_next(user_ns, rb_next(n)); } static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_root *r) { struct rb_node *n = rb_first(r); return __key_user_next(user_ns, n); } static void *proc_key_users_start(struct seq_file *p, loff_t *_pos) __acquires(key_user_lock) { struct rb_node *_p; loff_t pos = *_pos; spin_lock(&key_user_lock); _p = key_user_first(seq_user_ns(p), &key_user_tree); while (pos > 0 && _p) { pos--; _p = key_user_next(seq_user_ns(p), _p); } return _p; } static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos) { (*_pos)++; return key_user_next(seq_user_ns(p), (struct rb_node *)v); } static void proc_key_users_stop(struct seq_file *p, void *v) __releases(key_user_lock) { spin_unlock(&key_user_lock); } static int proc_key_users_show(struct seq_file *m, void *v) { struct rb_node *_p = v; struct key_user *user = rb_entry(_p, struct key_user, node); unsigned maxkeys = uid_eq(user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; seq_printf(m, "%5u: %5d %d/%d %d/%d %d/%d\n", from_kuid_munged(seq_user_ns(m), user->uid), refcount_read(&user->usage), atomic_read(&user->nkeys), atomic_read(&user->nikeys), user->qnkeys, maxkeys, user->qnbytes, maxbytes); return 0; } |
| 44 44 34 33 44 39 38 23 2 37 7 44 44 21 38 2 42 7 1 38 25 28 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 */ #include <linux/fs.h> #include <linux/quotaops.h> #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_superblock.h" #include "jfs_dmap.h" #include "jfs_extent.h" #include "jfs_debug.h" /* * forward references */ static int extBalloc(struct inode *, s64, s64 *, s64 *); static s64 extRoundDown(s64 nb); #define DPD(a) (printk("(a): %d\n",(a))) #define DPC(a) (printk("(a): %c\n",(a))) #define DPL1(a) \ { \ if ((a) >> 32) \ printk("(a): %x%08x ",(a)); \ else \ printk("(a): %x ",(a) << 32); \ } #define DPL(a) \ { \ if ((a) >> 32) \ printk("(a): %x%08x\n",(a)); \ else \ printk("(a): %x\n",(a) << 32); \ } #define DPD1(a) (printk("(a): %d ",(a))) #define DPX(a) (printk("(a): %08x\n",(a))) #define DPX1(a) (printk("(a): %08x ",(a))) #define DPS(a) (printk("%s\n",(a))) #define DPE(a) (printk("\nENTERING: %s\n",(a))) #define DPE1(a) (printk("\nENTERING: %s",(a))) #define DPS1(a) (printk(" %s ",(a))) /* * NAME: extAlloc() * * FUNCTION: allocate an extent for a specified page range within a * file. * * PARAMETERS: * ip - the inode of the file. * xlen - requested extent length. * pno - the starting page number with the file. * xp - pointer to an xad. on entry, xad describes an * extent that is used as an allocation hint if the * xaddr of the xad is non-zero. on successful exit, * the xad describes the newly allocated extent. * abnr - bool indicating whether the newly allocated extent * should be marked as allocated but not recorded. * * RETURN VALUES: * 0 - success * -EIO - i/o error. * -ENOSPC - insufficient disk resources. */ int extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, bool abnr) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); s64 nxlen, nxaddr, xoff, hint, xaddr = 0; int rc; int xflag; if (isReadOnly(ip)) { jfs_error(ip->i_sb, "read-only filesystem\n"); return -EIO; } /* This blocks if we are low on resources */ txBeginAnon(ip->i_sb); /* Avoid race with jfs_commit_inode() */ mutex_lock(&JFS_IP(ip)->commit_mutex); /* validate extent length */ if (xlen > MAXXLEN) xlen = MAXXLEN; /* get the page's starting extent offset */ xoff = pno << sbi->l2nbperpage; /* check if an allocation hint was provided */ if ((hint = addressXAD(xp))) { /* get the size of the extent described by the hint */ nxlen = lengthXAD(xp); /* check if the hint is for the portion of the file * immediately previous to the current allocation * request and if hint extent has the same abnr * value as the current request. if so, we can * extend the hint extent to include the current * extent if we can allocate the blocks immediately * following the hint extent. */ if (offsetXAD(xp) + nxlen == xoff && abnr == ((xp->flag & XAD_NOTRECORDED) ? true : false)) xaddr = hint + nxlen; /* adjust the hint to the last block of the extent */ hint += (nxlen - 1); } /* allocate the disk blocks for the extent. initially, extBalloc() * will try to allocate disk blocks for the requested size (xlen). * if this fails (xlen contiguous free blocks not available), it'll * try to allocate a smaller number of blocks (producing a smaller * extent), with this smaller number of blocks consisting of the * requested number of blocks rounded down to the next smaller * power of 2 number (i.e. 16 -> 8). it'll continue to round down * and retry the allocation until the number of blocks to allocate * is smaller than the number of blocks per page. */ nxlen = xlen; if ((rc = extBalloc(ip, hint ? hint : INOHINT(ip), &nxlen, &nxaddr))) { mutex_unlock(&JFS_IP(ip)->commit_mutex); return (rc); } /* Allocate blocks to quota. */ rc = dquot_alloc_block(ip, nxlen); if (rc) { dbFree(ip, nxaddr, (s64) nxlen); mutex_unlock(&JFS_IP(ip)->commit_mutex); return rc; } /* determine the value of the extent flag */ xflag = abnr ? XAD_NOTRECORDED : 0; /* if we can extend the hint extent to cover the current request, * extend it. otherwise, insert a new extent to * cover the current request. */ if (xaddr && xaddr == nxaddr) rc = xtExtend(0, ip, xoff, (int) nxlen, 0); else rc = xtInsert(0, ip, xflag, xoff, (int) nxlen, &nxaddr, 0); /* if the extend or insert failed, * free the newly allocated blocks and return the error. */ if (rc) { dbFree(ip, nxaddr, nxlen); dquot_free_block(ip, nxlen); mutex_unlock(&JFS_IP(ip)->commit_mutex); return (rc); } /* set the results of the extent allocation */ XADaddress(xp, nxaddr); XADlength(xp, nxlen); XADoffset(xp, xoff); xp->flag = xflag; mark_inode_dirty(ip); mutex_unlock(&JFS_IP(ip)->commit_mutex); /* * COMMIT_SyncList flags an anonymous tlock on page that is on * sync list. * We need to commit the inode to get the page written to the disk. */ if (test_and_clear_cflag(COMMIT_Synclist,ip)) jfs_commit_inode(ip, 0); return (0); } /* * NAME: extHint() * * FUNCTION: produce an extent allocation hint for a file offset. * * PARAMETERS: * ip - the inode of the file. * offset - file offset for which the hint is needed. * xp - pointer to the xad that is to be filled in with * the hint. * * RETURN VALUES: * 0 - success * -EIO - i/o error. */ int extHint(struct inode *ip, s64 offset, xad_t * xp) { struct super_block *sb = ip->i_sb; int nbperpage = JFS_SBI(sb)->nbperpage; s64 prev; int rc = 0; s64 xaddr; int xlen; int xflag; /* init the hint as "no hint provided" */ XADaddress(xp, 0); /* determine the starting extent offset of the page previous * to the page containing the offset. */ prev = ((offset & ~POFFSET) >> JFS_SBI(sb)->l2bsize) - nbperpage; /* if the offset is in the first page of the file, no hint provided. */ if (prev < 0) goto out; rc = xtLookup(ip, prev, nbperpage, &xflag, &xaddr, &xlen, 0); if ((rc == 0) && xlen) { if (xlen != nbperpage) { jfs_error(ip->i_sb, "corrupt xtree\n"); rc = -EIO; } XADaddress(xp, xaddr); XADlength(xp, xlen); XADoffset(xp, prev); /* * only preserve the abnr flag within the xad flags * of the returned hint. */ xp->flag = xflag & XAD_NOTRECORDED; } else rc = 0; out: return (rc); } /* * NAME: extRecord() * * FUNCTION: change a page with a file from not recorded to recorded. * * PARAMETERS: * ip - inode of the file. * cp - cbuf of the file page. * * RETURN VALUES: * 0 - success * -EIO - i/o error. * -ENOSPC - insufficient disk resources. */ int extRecord(struct inode *ip, xad_t * xp) { int rc; if (isReadOnly(ip)) { jfs_error(ip->i_sb, "read-only filesystem\n"); return -EIO; } txBeginAnon(ip->i_sb); mutex_lock(&JFS_IP(ip)->commit_mutex); /* update the extent */ rc = xtUpdate(0, ip, xp); mutex_unlock(&JFS_IP(ip)->commit_mutex); return rc; } /* * NAME: extBalloc() * * FUNCTION: allocate disk blocks to form an extent. * * initially, we will try to allocate disk blocks for the * requested size (nblocks). if this fails (nblocks * contiguous free blocks not available), we'll try to allocate * a smaller number of blocks (producing a smaller extent), with * this smaller number of blocks consisting of the requested * number of blocks rounded down to the next smaller power of 2 * number (i.e. 16 -> 8). we'll continue to round down and * retry the allocation until the number of blocks to allocate * is smaller than the number of blocks per page. * * PARAMETERS: * ip - the inode of the file. * hint - disk block number to be used as an allocation hint. * *nblocks - pointer to an s64 value. on entry, this value specifies * the desired number of block to be allocated. on successful * exit, this value is set to the number of blocks actually * allocated. * blkno - pointer to a block address that is filled in on successful * return with the starting block number of the newly * allocated block range. * * RETURN VALUES: * 0 - success * -EIO - i/o error. * -ENOSPC - insufficient disk resources. */ static int extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) { struct jfs_inode_info *ji = JFS_IP(ip); struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); s64 nb, nblks, daddr, max; int rc, nbperpage = sbi->nbperpage; struct bmap *bmp = sbi->bmap; int ag; /* get the number of blocks to initially attempt to allocate. * we'll first try the number of blocks requested unless this * number is greater than the maximum number of contiguous free * blocks in the map. in that case, we'll start off with the * maximum free. */ /* give up if no space left */ if (bmp->db_maxfreebud == -1) return -ENOSPC; max = (s64) 1 << bmp->db_maxfreebud; if (*nblocks >= max && *nblocks > nbperpage) nb = nblks = (max > nbperpage) ? max : nbperpage; else nb = nblks = *nblocks; /* try to allocate blocks */ while ((rc = dbAlloc(ip, hint, nb, &daddr)) != 0) { /* if something other than an out of space error, * stop and return this error. */ if (rc != -ENOSPC) return (rc); /* decrease the allocation request size */ nb = min(nblks, extRoundDown(nb)); /* give up if we cannot cover a page */ if (nb < nbperpage) return (rc); } *nblocks = nb; *blkno = daddr; if (S_ISREG(ip->i_mode) && (ji->fileset == FILESYSTEM_I)) { ag = BLKTOAG(daddr, sbi); spin_lock_irq(&ji->ag_lock); if (ji->active_ag == -1) { atomic_inc(&bmp->db_active[ag]); ji->active_ag = ag; } else if (ji->active_ag != ag) { atomic_dec(&bmp->db_active[ji->active_ag]); atomic_inc(&bmp->db_active[ag]); ji->active_ag = ag; } spin_unlock_irq(&ji->ag_lock); } return (0); } /* * NAME: extRoundDown() * * FUNCTION: round down a specified number of blocks to the next * smallest power of 2 number. * * PARAMETERS: * nb - the inode of the file. * * RETURN VALUES: * next smallest power of 2 number. */ static s64 extRoundDown(s64 nb) { int i; u64 m, k; for (i = 0, m = (u64) 1 << 63; i < 64; i++, m >>= 1) { if (m & nb) break; } i = 63 - i; k = (u64) 1 << i; k = ((k - 1) & nb) ? k : k >> 1; return (k); } |
| 4 1 59 59 58 8 5 5 5 5 4 4 26 53 3 3 3 3 108 108 1 79 117 1 118 127 123 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Code for manipulating bucket marks for garbage collection. * * Copyright 2014 Datera, Inc. */ #ifndef _BUCKETS_H #define _BUCKETS_H #include "buckets_types.h" #include "extents.h" #include "sb-members.h" static inline u64 sector_to_bucket(const struct bch_dev *ca, sector_t s) { return div_u64(s, ca->mi.bucket_size); } static inline sector_t bucket_to_sector(const struct bch_dev *ca, size_t b) { return ((sector_t) b) * ca->mi.bucket_size; } static inline sector_t bucket_remainder(const struct bch_dev *ca, sector_t s) { u32 remainder; div_u64_rem(s, ca->mi.bucket_size, &remainder); return remainder; } static inline u64 sector_to_bucket_and_offset(const struct bch_dev *ca, sector_t s, u32 *offset) { return div_u64_rem(s, ca->mi.bucket_size, offset); } #define for_each_bucket(_b, _buckets) \ for (_b = (_buckets)->b + (_buckets)->first_bucket; \ _b < (_buckets)->b + (_buckets)->nbuckets; _b++) static inline void bucket_unlock(struct bucket *b) { BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte); clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock); smp_mb__after_atomic(); wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR); } static inline void bucket_lock(struct bucket *b) { wait_on_bit_lock((void *) &b->lock, BUCKET_LOCK_BITNR, TASK_UNINTERRUPTIBLE); } static inline struct bucket *gc_bucket(struct bch_dev *ca, size_t b) { return bucket_valid(ca, b) ? genradix_ptr(&ca->buckets_gc, b) : NULL; } static inline struct bucket_gens *bucket_gens(struct bch_dev *ca) { return rcu_dereference_check(ca->bucket_gens, lockdep_is_held(&ca->fs->state_lock)); } static inline u8 *bucket_gen(struct bch_dev *ca, size_t b) { struct bucket_gens *gens = bucket_gens(ca); if (b - gens->first_bucket >= gens->nbuckets_minus_first) return NULL; return gens->b + b; } static inline int bucket_gen_get_rcu(struct bch_dev *ca, size_t b) { u8 *gen = bucket_gen(ca, b); return gen ? *gen : -1; } static inline int bucket_gen_get(struct bch_dev *ca, size_t b) { guard(rcu)(); return bucket_gen_get_rcu(ca, b); } static inline size_t PTR_BUCKET_NR(const struct bch_dev *ca, const struct bch_extent_ptr *ptr) { return sector_to_bucket(ca, ptr->offset); } static inline struct bpos PTR_BUCKET_POS(const struct bch_dev *ca, const struct bch_extent_ptr *ptr) { return POS(ptr->dev, PTR_BUCKET_NR(ca, ptr)); } static inline struct bpos PTR_BUCKET_POS_OFFSET(const struct bch_dev *ca, const struct bch_extent_ptr *ptr, u32 *bucket_offset) { return POS(ptr->dev, sector_to_bucket_and_offset(ca, ptr->offset, bucket_offset)); } static inline struct bucket *PTR_GC_BUCKET(struct bch_dev *ca, const struct bch_extent_ptr *ptr) { return gc_bucket(ca, PTR_BUCKET_NR(ca, ptr)); } static inline enum bch_data_type ptr_data_type(const struct bkey *k, const struct bch_extent_ptr *ptr) { if (bkey_is_btree_ptr(k)) return BCH_DATA_btree; return ptr->cached ? BCH_DATA_cached : BCH_DATA_user; } static inline s64 ptr_disk_sectors(s64 sectors, struct extent_ptr_decoded p) { EBUG_ON(sectors < 0); return crc_is_compressed(p.crc) ? DIV_ROUND_UP_ULL(sectors * p.crc.compressed_size, p.crc.uncompressed_size) : sectors; } static inline int gen_cmp(u8 a, u8 b) { return (s8) (a - b); } static inline int gen_after(u8 a, u8 b) { return max(0, gen_cmp(a, b)); } static inline int dev_ptr_stale_rcu(struct bch_dev *ca, const struct bch_extent_ptr *ptr) { int gen = bucket_gen_get_rcu(ca, PTR_BUCKET_NR(ca, ptr)); return gen < 0 ? gen : gen_after(gen, ptr->gen); } /** * dev_ptr_stale() - check if a pointer points into a bucket that has been * invalidated. */ static inline int dev_ptr_stale(struct bch_dev *ca, const struct bch_extent_ptr *ptr) { guard(rcu)(); return dev_ptr_stale_rcu(ca, ptr); } /* Device usage: */ void bch2_dev_usage_read_fast(struct bch_dev *, struct bch_dev_usage *); static inline struct bch_dev_usage bch2_dev_usage_read(struct bch_dev *ca) { struct bch_dev_usage ret; bch2_dev_usage_read_fast(ca, &ret); return ret; } void bch2_dev_usage_full_read_fast(struct bch_dev *, struct bch_dev_usage_full *); static inline struct bch_dev_usage_full bch2_dev_usage_full_read(struct bch_dev *ca) { struct bch_dev_usage_full ret; bch2_dev_usage_full_read_fast(ca, &ret); return ret; } void bch2_dev_usage_to_text(struct printbuf *, struct bch_dev *, struct bch_dev_usage_full *); static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum bch_watermark watermark) { s64 reserved = 0; switch (watermark) { case BCH_WATERMARK_NR: BUG(); case BCH_WATERMARK_stripe: reserved += ca->mi.nbuckets >> 6; fallthrough; case BCH_WATERMARK_normal: reserved += ca->mi.nbuckets >> 6; fallthrough; case BCH_WATERMARK_copygc: reserved += ca->nr_btree_reserve; fallthrough; case BCH_WATERMARK_btree: reserved += ca->nr_btree_reserve; fallthrough; case BCH_WATERMARK_btree_copygc: case BCH_WATERMARK_reclaim: case BCH_WATERMARK_interior_updates: break; } return reserved; } static inline u64 dev_buckets_free(struct bch_dev *ca, struct bch_dev_usage usage, enum bch_watermark watermark) { return max_t(s64, 0, usage.buckets[BCH_DATA_free]- ca->nr_open_buckets - bch2_dev_buckets_reserved(ca, watermark)); } static inline u64 __dev_buckets_available(struct bch_dev *ca, struct bch_dev_usage usage, enum bch_watermark watermark) { return max_t(s64, 0, usage.buckets[BCH_DATA_free] + usage.buckets[BCH_DATA_cached] + usage.buckets[BCH_DATA_need_gc_gens] + usage.buckets[BCH_DATA_need_discard] - ca->nr_open_buckets - bch2_dev_buckets_reserved(ca, watermark)); } static inline u64 dev_buckets_available(struct bch_dev *ca, enum bch_watermark watermark) { return __dev_buckets_available(ca, bch2_dev_usage_read(ca), watermark); } /* Filesystem usage: */ struct bch_fs_usage_short bch2_fs_usage_read_short(struct bch_fs *); int bch2_bucket_ref_update(struct btree_trans *, struct bch_dev *, struct bkey_s_c, const struct bch_extent_ptr *, s64, enum bch_data_type, u8, u8, u32 *); int bch2_check_fix_ptrs(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, enum btree_iter_update_trigger_flags); int bch2_trigger_extent(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_s, enum btree_iter_update_trigger_flags); #define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\ ({ \ int ret = 0; \ \ if (_old.k->type) \ ret = _fn(_trans, _btree_id, _level, _old, _flags & ~BTREE_TRIGGER_insert); \ if (!ret && _new.k->type) \ ret = _fn(_trans, _btree_id, _level, _new.s_c, _flags & ~BTREE_TRIGGER_overwrite);\ ret; \ }) void bch2_trans_account_disk_usage_change(struct btree_trans *); int bch2_trans_mark_metadata_bucket(struct btree_trans *, struct bch_dev *, u64, enum bch_data_type, unsigned, enum btree_iter_update_trigger_flags); int bch2_trans_mark_dev_sb(struct bch_fs *, struct bch_dev *, enum btree_iter_update_trigger_flags); int bch2_trans_mark_dev_sbs_flags(struct bch_fs *, enum btree_iter_update_trigger_flags); int bch2_trans_mark_dev_sbs(struct bch_fs *); bool bch2_is_superblock_bucket(struct bch_dev *, u64); static inline const char *bch2_data_type_str(enum bch_data_type type) { return type < BCH_DATA_NR ? __bch2_data_types[type] : "(invalid data type)"; } /* disk reservations: */ static inline void bch2_disk_reservation_put(struct bch_fs *c, struct disk_reservation *res) { if (res->sectors) { this_cpu_sub(*c->online_reserved, res->sectors); res->sectors = 0; } } enum bch_reservation_flags { BCH_DISK_RESERVATION_NOFAIL = 1 << 0, BCH_DISK_RESERVATION_PARTIAL = 1 << 1, }; int __bch2_disk_reservation_add(struct bch_fs *, struct disk_reservation *, u64, enum bch_reservation_flags); static inline int bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res, u64 sectors, enum bch_reservation_flags flags) { #ifdef __KERNEL__ u64 old, new; old = this_cpu_read(c->pcpu->sectors_available); do { if (sectors > old) return __bch2_disk_reservation_add(c, res, sectors, flags); new = old - sectors; } while (!this_cpu_try_cmpxchg(c->pcpu->sectors_available, &old, new)); this_cpu_add(*c->online_reserved, sectors); res->sectors += sectors; return 0; #else return __bch2_disk_reservation_add(c, res, sectors, flags); #endif } static inline struct disk_reservation bch2_disk_reservation_init(struct bch_fs *c, unsigned nr_replicas) { return (struct disk_reservation) { .sectors = 0, #if 0 /* not used yet: */ .gen = c->capacity_gen, #endif .nr_replicas = nr_replicas, }; } static inline int bch2_disk_reservation_get(struct bch_fs *c, struct disk_reservation *res, u64 sectors, unsigned nr_replicas, int flags) { *res = bch2_disk_reservation_init(c, nr_replicas); return bch2_disk_reservation_add(c, res, sectors * nr_replicas, flags); } #define RESERVE_FACTOR 6 static inline u64 avail_factor(u64 r) { return div_u64(r << RESERVE_FACTOR, (1 << RESERVE_FACTOR) + 1); } void bch2_buckets_nouse_free(struct bch_fs *); int bch2_buckets_nouse_alloc(struct bch_fs *); int bch2_dev_buckets_resize(struct bch_fs *, struct bch_dev *, u64); void bch2_dev_buckets_free(struct bch_dev *); int bch2_dev_buckets_alloc(struct bch_fs *, struct bch_dev *); #endif /* _BUCKETS_H */ |
| 966 7 922 6 4 9 1 16 1 1 43 21 16 17 6 7 16 16 16 16 10 10 10 4 3 2 8 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> #include <linux/nodemask.h> struct ctl_table; struct user_struct; struct mmu_gather; struct node; void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long start, unsigned long end, struct folio *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; void hugetlb_bootmem_alloc(void); bool hugetlb_bootmem_allocated(void); extern nodemask_t hugetlb_bootmem_nodes; void hugetlb_bootmem_set_nodes(void); /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); void fixup_hugetlb_reservations(struct vm_area_struct *vma); void hugetlb_split(struct vm_area_struct *vma, unsigned long addr); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { return -EINVAL; } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { BUG(); } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void folio_putback_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) { } static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {} #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, HPG_cma, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) HPAGEFLAG(Cma, cma) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; char name[HSTATE_NAME_LEN]; }; struct cma; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; unsigned long flags; struct cma *cma; }; #define HUGE_BOOTMEM_HVO 0x0001 #define HUGE_BOOTMEM_ZONES_VALID 0x0002 #define HUGE_BOOTMEM_CMA 0x0004 bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m); int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return huge_page_order(h) > MAX_PAGE_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif #ifndef arch_has_huge_bootmem_alloc /* * Some architectures do their own bootmem allocation, so they can't use * early CMA allocation. */ static inline bool arch_has_huge_bootmem_alloc(void) { return false; } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h)) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { gfp_t gfp = __GFP_COMP | __GFP_NOWARN; gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { const unsigned long size = huge_page_size(h); VM_WARN_ON(size == PAGE_SIZE); /* * hugetlb must use the exact same PT locks as core-mm page table * walkers would. When modifying a PTE table, hugetlb must take the * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD * PT lock etc. * * The expectation is that any hugetlb folio smaller than a PMD is * always mapped into a single PTE table and that any hugetlb folio * smaller than a PUD (but at least as big as a PMD) is always mapped * into a single PMD table. * * If that does not hold for an architecture, then that architecture * must disable split PT locks such that all *_lockptr() functions * will give us the same result: the per-MM PT lock. * * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() * and core-mm would use pmd_lockptr(). However, in such configurations * split PMD locks are disabled -- they don't make sense on a single * PGDIR page table -- and the end result is the same. */ if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ return ptep_lockptr(mm, pte); } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { unsigned long psize = huge_page_size(hstate_vma(vma)); return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); static inline unsigned long huge_page_mask_align(struct file *file) { return PAGE_MASK & ~huge_page_mask(hstate_file(file)); } #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline unsigned long huge_page_mask_align(struct file *file) { return 0; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { return -ENOMEM; } static inline int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline void wait_for_freed_hugetlb_folios(void) { } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) { return NULL; } static inline struct folio * alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } static inline void hugetlb_bootmem_alloc(void) { } static inline bool hugetlb_bootmem_allocated(void) { return false; } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); #else static inline __init void hugetlb_cma_reserve(int order) { } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 958 27 2471 87 25 112 | 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 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/node.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/preferred/etc */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); extern int mempolicy_set_node_perf(unsigned int node, struct access_coordinate *coords); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 1530 2349 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM exceptions #if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(exceptions, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code), TP_STRUCT__entry( __field( unsigned long, address ) __field( unsigned long, ip ) __field( unsigned long, error_code ) ), TP_fast_assign( __entry->address = address; __entry->ip = instruction_pointer(regs); __entry->error_code = error_code; ), TP_printk("address=%ps ip=%ps error_code=0x%lx", (void *)__entry->address, (void *)__entry->ip, __entry->error_code) ); DEFINE_EVENT(exceptions, page_fault_user, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code)); DEFINE_EVENT(exceptions, page_fault_kernel, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code)); #endif /* _TRACE_PAGE_FAULT_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1657 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Block data types and constants. Directly include this file only to * break include dependency loop. */ #ifndef __LINUX_BLK_TYPES_H #define __LINUX_BLK_TYPES_H #include <linux/types.h> #include <linux/bvec.h> #include <linux/device.h> #include <linux/ktime.h> #include <linux/rw_hint.h> struct bio_set; struct bio; struct bio_integrity_payload; struct page; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; /* * The basic unit of block I/O is a sector. It is used in a number of contexts * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 * bytes. Variables of type sector_t represent an offset or size that is a * multiple of 512 bytes. Hence these two constants. */ #ifndef SECTOR_SHIFT #define SECTOR_SHIFT 9 #endif #ifndef SECTOR_SIZE #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif #define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) #define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) #define SECTOR_MASK (PAGE_SECTORS - 1) struct block_device { sector_t bd_start_sect; sector_t bd_nr_sectors; struct gendisk * bd_disk; struct request_queue * bd_queue; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; atomic_t __bd_flags; // partition number + flags #define BD_PARTNO 255 // lower 8 bits; assign-once #define BD_READ_ONLY (1u<<8) // read-only policy #define BD_WRITE_HOLDER (1u<<9) #define BD_HAS_SUBMIT_BIO (1u<<10) #define BD_RO_WARNED (1u<<11) #ifdef CONFIG_FAIL_MAKE_REQUEST #define BD_MAKE_IT_FAIL (1u<<12) #endif dev_t bd_dev; struct address_space *bd_mapping; /* page cache */ atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ void * bd_claiming; void * bd_holder; const struct blk_holder_ops *bd_holder_ops; struct mutex bd_holder_lock; int bd_holders; struct kobject *bd_holder_dir; atomic_t bd_fsfreeze_count; /* number of freeze requests */ struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */ struct partition_meta_info *bd_meta_info; int bd_writers; #ifdef CONFIG_SECURITY void *bd_security; #endif /* * keep this out-of-line as it's both big and not needed in the fast * path */ struct device bd_device; } __randomize_layout; #define bdev_whole(_bdev) \ ((_bdev)->bd_disk->part0) #define dev_to_bdev(device) \ container_of((device), struct block_device, bd_device) #define bdev_kobj(_bdev) \ (&((_bdev)->bd_device.kobj)) /* * Block error status values. See block/blk-core:blk_errors for the details. */ typedef u8 __bitwise blk_status_t; typedef u16 blk_short_t; #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) #define BLK_STS_NOSPC ((__force blk_status_t)3) #define BLK_STS_TRANSPORT ((__force blk_status_t)4) #define BLK_STS_TARGET ((__force blk_status_t)5) #define BLK_STS_RESV_CONFLICT ((__force blk_status_t)6) #define BLK_STS_MEDIUM ((__force blk_status_t)7) #define BLK_STS_PROTECTION ((__force blk_status_t)8) #define BLK_STS_RESOURCE ((__force blk_status_t)9) #define BLK_STS_IOERR ((__force blk_status_t)10) /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) /* * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set * and the bio would block (cf bio_wouldblock_error()) */ #define BLK_STS_AGAIN ((__force blk_status_t)12) /* * BLK_STS_DEV_RESOURCE is returned from the driver to the block layer if * device related resources are unavailable, but the driver can guarantee * that the queue will be rerun in the future once resources become * available again. This is typically the case for device specific * resources that are consumed for IO. If the driver fails allocating these * resources, we know that inflight (or pending) IO will free these * resource upon completion. * * This is different from BLK_STS_RESOURCE in that it explicitly references * a device specific resource. For resources of wider scope, allocation * failure can happen without having pending IO. This means that we can't * rely on request completions freeing these resources, as IO may not be in * flight. Examples of that are kernel memory allocations, DMA mappings, or * any other system wide resources. */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ #define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently active. The same command should be successful if resubmitted * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_OFFLINE is returned from the driver when the target device is offline * or is being taken offline. This could help differentiate the case where a * device is intentionally being shut down from a real I/O error. */ #define BLK_STS_OFFLINE ((__force blk_status_t)16) /* * BLK_STS_DURATION_LIMIT is returned from the driver when the target device * aborted the command because it exceeded one of its Command Duration Limits. */ #define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) /* * Invalid size or alignment. */ #define BLK_STS_INVAL ((__force blk_status_t)19) /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with * * Description: * This classifies block error status into non-retryable errors and ones * that may be successful if retried on a failover path. * * Return: * %false - retrying failover path will not help * %true - may succeed if retried */ static inline bool blk_path_error(blk_status_t error) { switch (error) { case BLK_STS_NOTSUPP: case BLK_STS_NOSPC: case BLK_STS_TARGET: case BLK_STS_RESV_CONFLICT: case BLK_STS_MEDIUM: case BLK_STS_PROTECTION: return false; } /* Anything else could be a path failure, so should be retried */ return true; } struct bio_issue { u64 value; }; typedef __u32 __bitwise blk_opf_t; typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; blk_opf_t bi_opf; /* bottom bits REQ_OP, top bits * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; enum rw_hint bi_write_hint; u8 bi_write_stream; blk_status_t bi_status; atomic_t __bi_remaining; struct bvec_iter bi_iter; union { /* for polled bios: */ blk_qc_t bi_cookie; /* for plugged zoned writes only: */ unsigned int __bi_nr_segments; }; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP /* * Represents the association of the css and request_queue for the bio. * If a bio goes direct to device, it will not have a blkg as it will * not have a request_queue associated with it. The reference is put * on release of the bio. */ struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #ifdef CONFIG_BLK_CGROUP_IOCOST u64 bi_iocost_cost; #endif #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *bi_crypt_context; #endif #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif unsigned short bi_vcnt; /* how many bio_vec's */ /* * Everything starting with bi_max_vecs will be preserved by bio_reset() */ unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ atomic_t __bi_cnt; /* pin count */ struct bio_vec *bi_io_vec; /* the actual vec list */ struct bio_set *bi_pool; /* * We can inline a number of vecs at the end of the bio, to avoid * double allocations for a small number of bio_vecs. This member * MUST obviously be kept at the very end of the bio. */ struct bio_vec bi_inline_vecs[]; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) #define BIO_MAX_SECTORS (UINT_MAX >> SECTOR_SHIFT) /* * bio flags */ enum { BIO_PAGE_PINNED, /* Unpin pages in bio_release_pages() */ BIO_CLONED, /* doesn't own data */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ BIO_BPS_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ /* * This bio has completed bps throttling at the single tg granularity, * which is different from BIO_BPS_THROTTLED. When the bio is enqueued * into the sq->queued of the upper tg, or is about to be dispatched, * this flag needs to be cleared. Since blk-throttle and rq_qos are not * on the same hierarchical level, reuse the value. */ BIO_TG_BPS_THROTTLED = BIO_QOS_THROTTLED, BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */ BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */ BIO_FLAG_LAST }; typedef __u32 __bitwise blk_mq_req_flags_t; #define REQ_OP_BITS 8 #define REQ_OP_MASK (__force blk_opf_t)((1 << REQ_OP_BITS) - 1) #define REQ_FLAG_BITS 24 /** * enum req_op - Operations common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. * * The least significant bit of the operation number indicates the data * transfer direction: * * - if the least significant bit is set transfers are TO the device * - if the least significant bit is not set transfers are FROM the device * * If a operation does not transfer data the least significant bit has no * meaning. */ enum req_op { /* read sectors from the device */ REQ_OP_READ = (__force blk_opf_t)0, /* write sectors to the device */ REQ_OP_WRITE = (__force blk_opf_t)1, /* flush the volatile write cache */ REQ_OP_FLUSH = (__force blk_opf_t)2, /* discard sectors */ REQ_OP_DISCARD = (__force blk_opf_t)3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = (__force blk_opf_t)5, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = (__force blk_opf_t)7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, /* Open a zone */ REQ_OP_ZONE_OPEN = (__force blk_opf_t)10, /* Close a zone */ REQ_OP_ZONE_CLOSE = (__force blk_opf_t)11, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = (__force blk_opf_t)12, /* reset a zone write pointer */ REQ_OP_ZONE_RESET = (__force blk_opf_t)13, /* reset all the zone present on the device */ REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)15, /* Driver private requests */ REQ_OP_DRV_IN = (__force blk_opf_t)34, REQ_OP_DRV_OUT = (__force blk_opf_t)35, REQ_OP_LAST = (__force blk_opf_t)36, }; /* Keep cmd_flag_name[] in sync with the definitions below */ enum req_flag_bits { __REQ_FAILFAST_DEV = /* no driver retries of device errors */ REQ_OP_BITS, __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ __REQ_NOMERGE, /* don't touch this for merging */ __REQ_IDLE, /* anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ __REQ_POLLED, /* caller polls for completion using bio_poll */ __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ __REQ_FS_PRIVATE, /* for file system (submitter) use */ __REQ_ATOMIC, /* for atomic write operations */ /* * Command specific flags, keep last: */ /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ __REQ_NR_BITS, /* stops here */ }; #define REQ_FAILFAST_DEV \ (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT \ (__force blk_opf_t)(1ULL << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER \ (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (__force blk_opf_t)(1ULL << __REQ_SYNC) #define REQ_META (__force blk_opf_t)(1ULL << __REQ_META) #define REQ_PRIO (__force blk_opf_t)(1ULL << __REQ_PRIO) #define REQ_NOMERGE (__force blk_opf_t)(1ULL << __REQ_NOMERGE) #define REQ_IDLE (__force blk_opf_t)(1ULL << __REQ_IDLE) #define REQ_INTEGRITY (__force blk_opf_t)(1ULL << __REQ_INTEGRITY) #define REQ_FUA (__force blk_opf_t)(1ULL << __REQ_FUA) #define REQ_PREFLUSH (__force blk_opf_t)(1ULL << __REQ_PREFLUSH) #define REQ_RAHEAD (__force blk_opf_t)(1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (__force blk_opf_t)(1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (__force blk_opf_t)(1ULL << __REQ_NOWAIT) #define REQ_POLLED (__force blk_opf_t)(1ULL << __REQ_POLLED) #define REQ_ALLOC_CACHE (__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE) #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) #define REQ_ATOMIC (__force blk_opf_t)(1ULL << __REQ_ATOMIC) #define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, STAT_FLUSH, NR_STAT_GROUPS }; static inline enum req_op bio_op(const struct bio *bio) { return bio->bi_opf & REQ_OP_MASK; } static inline bool op_is_write(blk_opf_t op) { return !!(op & (__force blk_opf_t)1); } /* * Check if the bio or request is one that needs special treatment in the * flush state machine. */ static inline bool op_is_flush(blk_opf_t op) { return op & (REQ_FUA | REQ_PREFLUSH); } /* * Reads are always treated as synchronous, as are requests with the FUA or * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. */ static inline bool op_is_sync(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } static inline bool op_is_discard(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } /* * Check if a bio or request operation is a zone management operation, with * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case * due to its different handling in the block layer and device response in * case of command failure. */ static inline bool op_is_zone_mgmt(enum req_op op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: return true; default: return false; } } static inline int op_stat_group(enum req_op op) { if (op_is_discard(op)) return STAT_DISCARD; return op_is_write(op); } struct blk_rq_stat { u64 mean; u64 min; u64 max; u32 nr_samples; u64 batch; }; #endif /* __LINUX_BLK_TYPES_H */ |
| 4480 4495 4492 9629 9618 4499 4491 4474 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. * * A context holding the printk_cpu_sync must not spin waiting for * another CPU. For legacy printing, it could be the console_lock * or the port lock. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi() || is_printk_cpu_sync_owner()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 8656 3028 8429 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fault-inject.h> #include <linux/debugfs.h> #include <linux/error-injection.h> #include <linux/mm.h> static struct { struct fault_attr attr; bool ignore_gfp_highmem; bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_reclaim = true, .ignore_gfp_highmem = true, .min_order = 1, }; static int __init setup_fail_page_alloc(char *str) { return setup_fault_attr(&fail_page_alloc.attr, str); } __setup("fail_page_alloc=", setup_fail_page_alloc); bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { int flags = 0; if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; if (fail_page_alloc.ignore_gfp_reclaim && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) flags |= FAULT_NOWARN; return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_page_alloc_debugfs(void) { umode_t mode = S_IFREG | 0600; struct dentry *dir; dir = fault_create_debugfs_attr("fail_page_alloc", NULL, &fail_page_alloc.attr); debugfs_create_bool("ignore-gfp-wait", mode, dir, &fail_page_alloc.ignore_gfp_reclaim); debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem); debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); return 0; } late_initcall(fail_page_alloc_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ |
| 8 8 4 6 6 1 1 1 1 2 1 1 1 1 2 2 2 2 2 2 6 1 4 4 15 5 8 1 1 14 4 4 4 4 4 4 5 5 1 4 11 4 9 14 14 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 2005-2006 Ian Kent <raven@themaw.net> */ #include <linux/seq_file.h> #include <linux/pagemap.h> #include "autofs_i.h" struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi) { struct autofs_info *ino; ino = kzalloc(sizeof(*ino), GFP_KERNEL); if (ino) { INIT_LIST_HEAD(&ino->active); INIT_LIST_HEAD(&ino->expiring); ino->last_used = jiffies; ino->sbi = sbi; ino->exp_timeout = -1; ino->count = 1; } return ino; } void autofs_clean_ino(struct autofs_info *ino) { ino->uid = GLOBAL_ROOT_UID; ino->gid = GLOBAL_ROOT_GID; ino->exp_timeout = -1; ino->last_used = jiffies; } void autofs_free_ino(struct autofs_info *ino) { kfree_rcu(ino, rcu); } void autofs_kill_sb(struct super_block *sb) { struct autofs_sb_info *sbi = autofs_sbi(sb); /* * In the event of a failure in get_sb_nodev the superblock * info is not present so nothing else has been setup, so * just call kill_anon_super when we are called from * deactivate_super. */ if (sbi) { /* Free wait queues, close pipe */ autofs_catatonic_mode(sbi); put_pid(sbi->oz_pgrp); } pr_debug("shutting down\n"); kill_litter_super(sb); if (sbi) kfree_rcu(sbi, rcu); } static int autofs_show_options(struct seq_file *m, struct dentry *root) { struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct inode *root_inode = d_inode(root->d_sb->s_root); if (!sbi) return 0; seq_printf(m, ",fd=%d", sbi->pipefd); if (!uid_eq(root_inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, root_inode->i_uid)); if (!gid_eq(root_inode->i_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, root_inode->i_gid)); seq_printf(m, ",pgrp=%d", pid_vnr(sbi->oz_pgrp)); seq_printf(m, ",timeout=%lu", sbi->exp_timeout/HZ); seq_printf(m, ",minproto=%d", sbi->min_proto); seq_printf(m, ",maxproto=%d", sbi->max_proto); if (autofs_type_offset(sbi->type)) seq_puts(m, ",offset"); else if (autofs_type_direct(sbi->type)) seq_puts(m, ",direct"); else seq_puts(m, ",indirect"); if (sbi->flags & AUTOFS_SBI_STRICTEXPIRE) seq_puts(m, ",strictexpire"); if (sbi->flags & AUTOFS_SBI_IGNORE) seq_puts(m, ",ignore"); #ifdef CONFIG_CHECKPOINT_RESTORE if (sbi->pipe) seq_printf(m, ",pipe_ino=%ld", file_inode(sbi->pipe)->i_ino); else seq_puts(m, ",pipe_ino=-1"); #endif return 0; } static void autofs_evict_inode(struct inode *inode) { clear_inode(inode); kfree(inode->i_private); } static const struct super_operations autofs_sops = { .statfs = simple_statfs, .show_options = autofs_show_options, .evict_inode = autofs_evict_inode, }; enum { Opt_direct, Opt_fd, Opt_gid, Opt_ignore, Opt_indirect, Opt_maxproto, Opt_minproto, Opt_offset, Opt_pgrp, Opt_strictexpire, Opt_uid, }; const struct fs_parameter_spec autofs_param_specs[] = { fsparam_flag ("direct", Opt_direct), fsparam_fd ("fd", Opt_fd), fsparam_gid ("gid", Opt_gid), fsparam_flag ("ignore", Opt_ignore), fsparam_flag ("indirect", Opt_indirect), fsparam_u32 ("maxproto", Opt_maxproto), fsparam_u32 ("minproto", Opt_minproto), fsparam_flag ("offset", Opt_offset), fsparam_u32 ("pgrp", Opt_pgrp), fsparam_flag ("strictexpire", Opt_strictexpire), fsparam_uid ("uid", Opt_uid), {} }; struct autofs_fs_context { kuid_t uid; kgid_t gid; int pgrp; bool pgrp_set; }; /* * Open the fd. We do it here rather than in get_tree so that it's done in the * context of the system call that passed the data and not the one that * triggered the superblock creation, lest the fd gets reassigned. */ static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi, struct fs_parameter *param, struct fs_parse_result *result) { struct file *pipe; int ret; if (param->type == fs_value_is_file) { /* came through the new api */ pipe = param->file; param->file = NULL; } else { pipe = fget(result->uint_32); } if (!pipe) { errorf(fc, "could not open pipe file descriptor"); return -EBADF; } ret = autofs_check_pipe(pipe); if (ret < 0) { errorf(fc, "Invalid/unusable pipe"); fput(pipe); return -EBADF; } autofs_set_packet_pipe_flags(pipe); if (sbi->pipe) fput(sbi->pipe); sbi->pipefd = result->uint_32; sbi->pipe = pipe; return 0; } static int autofs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct autofs_fs_context *ctx = fc->fs_private; struct autofs_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, autofs_param_specs, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_fd: return autofs_parse_fd(fc, sbi, param, &result); case Opt_uid: ctx->uid = result.uid; break; case Opt_gid: ctx->gid = result.gid; break; case Opt_pgrp: ctx->pgrp = result.uint_32; ctx->pgrp_set = true; break; case Opt_minproto: sbi->min_proto = result.uint_32; break; case Opt_maxproto: sbi->max_proto = result.uint_32; break; case Opt_indirect: set_autofs_type_indirect(&sbi->type); break; case Opt_direct: set_autofs_type_direct(&sbi->type); break; case Opt_offset: set_autofs_type_offset(&sbi->type); break; case Opt_strictexpire: sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; break; case Opt_ignore: sbi->flags |= AUTOFS_SBI_IGNORE; } return 0; } static struct autofs_sb_info *autofs_alloc_sbi(void) { struct autofs_sb_info *sbi; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return NULL; sbi->magic = AUTOFS_SBI_MAGIC; sbi->flags = AUTOFS_SBI_CATATONIC; sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; sbi->pipefd = -1; set_autofs_type_indirect(&sbi->type); mutex_init(&sbi->wq_mutex); mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); spin_lock_init(&sbi->lookup_lock); INIT_LIST_HEAD(&sbi->active_list); INIT_LIST_HEAD(&sbi->expiring_list); return sbi; } static int autofs_validate_protocol(struct fs_context *fc) { struct autofs_sb_info *sbi = fc->s_fs_info; /* Test versions first */ if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) { errorf(fc, "kernel does not match daemon version " "daemon (%d, %d) kernel (%d, %d)\n", sbi->min_proto, sbi->max_proto, AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION); return -EINVAL; } /* Establish highest kernel protocol version */ if (sbi->max_proto > AUTOFS_MAX_PROTO_VERSION) sbi->version = AUTOFS_MAX_PROTO_VERSION; else sbi->version = sbi->max_proto; switch (sbi->version) { case 4: sbi->sub_version = 7; break; case 5: sbi->sub_version = AUTOFS_PROTO_SUBVERSION; break; default: sbi->sub_version = 0; } return 0; } static int autofs_fill_super(struct super_block *s, struct fs_context *fc) { struct autofs_fs_context *ctx = fc->fs_private; struct autofs_sb_info *sbi = s->s_fs_info; struct inode *root_inode; struct autofs_info *ino; pr_debug("starting up, sbi = %p\n", sbi); sbi->sb = s; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = AUTOFS_SUPER_MAGIC; s->s_op = &autofs_sops; s->s_d_op = &autofs_dentry_operations; s->s_time_gran = 1; /* * Get the root inode and dentry, but defer checking for errors. */ ino = autofs_new_ino(sbi); if (!ino) return -ENOMEM; root_inode = autofs_get_inode(s, S_IFDIR | 0755); if (!root_inode) return -ENOMEM; root_inode->i_uid = ctx->uid; root_inode->i_gid = ctx->gid; root_inode->i_fop = &autofs_root_operations; root_inode->i_op = &autofs_dir_inode_operations; s->s_root = d_make_root(root_inode); if (unlikely(!s->s_root)) { autofs_free_ino(ino); return -ENOMEM; } s->s_root->d_fsdata = ino; if (ctx->pgrp_set) { sbi->oz_pgrp = find_get_pid(ctx->pgrp); if (!sbi->oz_pgrp) return invalf(fc, "Could not find process group %d", ctx->pgrp); } else sbi->oz_pgrp = get_task_pid(current, PIDTYPE_PGID); if (autofs_type_trigger(sbi->type)) /* s->s_root won't be contended so there's little to * be gained by not taking the d_lock when setting * d_flags, even when a lot mounts are being done. */ managed_dentry_set_managed(s->s_root); pr_debug("pipe fd = %d, pgrp = %u\n", sbi->pipefd, pid_nr(sbi->oz_pgrp)); sbi->flags &= ~AUTOFS_SBI_CATATONIC; return 0; } /* * Validate the parameters and then request a superblock. */ static int autofs_get_tree(struct fs_context *fc) { struct autofs_sb_info *sbi = fc->s_fs_info; int ret; ret = autofs_validate_protocol(fc); if (ret) return ret; if (sbi->pipefd < 0) return invalf(fc, "No control pipe specified"); return get_tree_nodev(fc, autofs_fill_super); } static void autofs_free_fc(struct fs_context *fc) { struct autofs_fs_context *ctx = fc->fs_private; struct autofs_sb_info *sbi = fc->s_fs_info; if (sbi) { if (sbi->pipe) fput(sbi->pipe); kfree(sbi); } kfree(ctx); } static const struct fs_context_operations autofs_context_ops = { .free = autofs_free_fc, .parse_param = autofs_parse_param, .get_tree = autofs_get_tree, }; /* * Set up the filesystem mount context. */ int autofs_init_fs_context(struct fs_context *fc) { struct autofs_fs_context *ctx; struct autofs_sb_info *sbi; ctx = kzalloc(sizeof(struct autofs_fs_context), GFP_KERNEL); if (!ctx) goto nomem; ctx->uid = current_uid(); ctx->gid = current_gid(); sbi = autofs_alloc_sbi(); if (!sbi) goto nomem_ctx; fc->fs_private = ctx; fc->s_fs_info = sbi; fc->ops = &autofs_context_ops; return 0; nomem_ctx: kfree(ctx); nomem: return -ENOMEM; } struct inode *autofs_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (inode == NULL) return NULL; inode->i_mode = mode; if (sb->s_root) { inode->i_uid = d_inode(sb->s_root)->i_uid; inode->i_gid = d_inode(sb->s_root)->i_gid; } simple_inode_init_ts(inode); inode->i_ino = get_next_ino(); if (S_ISDIR(mode)) { set_nlink(inode, 2); inode->i_op = &autofs_dir_inode_operations; inode->i_fop = &autofs_dir_operations; } else if (S_ISLNK(mode)) { inode->i_op = &autofs_symlink_inode_operations; } else WARN_ON(1); return inode; } |
| 34 287 269 17 169 125 44 317 302 17 358 303 56 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/bitmap.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) */ #include <linux/buffer_head.h> #include "ext4.h" unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { return numchars * BITS_PER_BYTE - memweight(bitmap, numchars); } int ext4_inode_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz; if (!ext4_has_feature_metadata_csum(sb)) return 1; sz = EXT4_INODES_PER_GROUP(sb) >> 3; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); calculated = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz); if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) { hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi); provided |= (hi << 16); } else calculated &= 0xFFFF; return provided == calculated; } void ext4_inode_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz; if (!ext4_has_feature_metadata_csum(sb)) return; sz = EXT4_INODES_PER_GROUP(sb) >> 3; csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz); gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16); } int ext4_block_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; if (!ext4_has_feature_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); calculated = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz); if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) { hi = le16_to_cpu(gdp->bg_block_bitmap_csum_hi); provided |= (hi << 16); } else calculated &= 0xFFFF; return provided == calculated; } void ext4_block_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh) { int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); if (!ext4_has_feature_metadata_csum(sb)) return; csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)bh->b_data, sz); gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16); } |
| 15 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching interface * * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: * * Documentation/filesystems/caching/netfs-api.rst * * for a description of the network filesystem interface declared here. */ #ifndef _LINUX_FSCACHE_H #define _LINUX_FSCACHE_H #include <linux/fs.h> #include <linux/netfs.h> #include <linux/writeback.h> #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) #define __fscache_available (1) #define fscache_available() (1) #define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) #define fscache_resources_valid(cres) ((cres)->cache_priv) #define fscache_cookie_enabled(cookie) (cookie && !test_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) #else #define __fscache_available (0) #define fscache_available() (0) #define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) #define fscache_resources_valid(cres) (false) #define fscache_cookie_enabled(cookie) (0) #endif struct fscache_cookie; #define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ #define FSCACHE_ADV_WANT_CACHE_SIZE 0x04 /* Retrieve cache size at runtime */ #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ enum fscache_want_state { FSCACHE_WANT_PARAMS, FSCACHE_WANT_WRITE, FSCACHE_WANT_READ, }; /* * Data object state. */ enum fscache_cookie_state { FSCACHE_COOKIE_STATE_QUIESCENT, /* The cookie is uncached */ FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ FSCACHE_COOKIE_STATE_INVALIDATING, /* The cache is being invalidated */ FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ #define FSCACHE_COOKIE_STATE__NR (FSCACHE_COOKIE_STATE_DROPPED + 1) } __attribute__((mode(byte))); /* * Volume representation cookie. */ struct fscache_volume { refcount_t ref; atomic_t n_cookies; /* Number of data cookies in volume */ atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; unsigned int key_hash; /* Hash of key string */ u8 *key; /* Volume ID, eg. "afs@example.com@1234" */ struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ struct hlist_bl_node hash_link; /* Link in hash table */ struct work_struct work; struct fscache_cache *cache; /* The cache in which this resides */ void *cache_priv; /* Cache private data */ spinlock_t lock; unsigned long flags; #define FSCACHE_VOLUME_RELINQUISHED 0 /* Volume is being cleaned up */ #define FSCACHE_VOLUME_INVALIDATE 1 /* Volume was invalidated */ #define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ #define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ #define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ u8 coherency_len; /* Length of the coherency data */ u8 coherency[]; /* Coherency data */ }; /* * Data file representation cookie. * - a file will only appear in one cache * - a request to cache a file may or may not be honoured, subject to * constraints such as disk space * - indices are created on disk just-in-time */ struct fscache_cookie { refcount_t ref; atomic_t n_active; /* number of active users of cookie */ atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; unsigned int inval_counter; /* Number of invalidations made */ spinlock_t lock; struct fscache_volume *volume; /* Parent volume of this file. */ void *cache_priv; /* Cache-side representation */ struct hlist_bl_node hash_link; /* Link in hash table */ struct list_head proc_link; /* Link in proc list */ struct list_head commit_link; /* Link in commit queue */ struct work_struct work; /* Commit/relinq/withdraw work */ loff_t object_size; /* Size of the netfs object */ unsigned long unused_at; /* Time at which unused (jiffies) */ unsigned long flags; #define FSCACHE_COOKIE_RELINQUISHED 0 /* T if cookie has been relinquished */ #define FSCACHE_COOKIE_RETIRED 1 /* T if this cookie has retired on relinq */ #define FSCACHE_COOKIE_IS_CACHING 2 /* T if this cookie is cached */ #define FSCACHE_COOKIE_NO_DATA_TO_READ 3 /* T if this cookie has nothing to read */ #define FSCACHE_COOKIE_NEEDS_UPDATE 4 /* T if attrs have been updated */ #define FSCACHE_COOKIE_HAS_BEEN_CACHED 5 /* T if cookie needs withdraw-on-relinq */ #define FSCACHE_COOKIE_DISABLED 6 /* T if cookie has been disabled */ #define FSCACHE_COOKIE_LOCAL_WRITE 7 /* T if cookie has been modified locally */ #define FSCACHE_COOKIE_NO_ACCESS_WAKE 8 /* T if no wake when n_accesses goes 0 */ #define FSCACHE_COOKIE_DO_RELINQUISH 9 /* T if this cookie needs relinquishment */ #define FSCACHE_COOKIE_DO_WITHDRAW 10 /* T if this cookie needs withdrawing */ #define FSCACHE_COOKIE_DO_LRU_DISCARD 11 /* T if this cookie needs LRU discard */ #define FSCACHE_COOKIE_DO_PREP_TO_WRITE 12 /* T if cookie needs write preparation */ #define FSCACHE_COOKIE_HAVE_DATA 13 /* T if this cookie has data stored */ #define FSCACHE_COOKIE_IS_HASHED 14 /* T if this cookie is hashed */ #define FSCACHE_COOKIE_DO_INVALIDATE 15 /* T if cookie needs invalidation */ enum fscache_cookie_state state; u8 advice; /* FSCACHE_ADV_* */ u8 key_len; /* Length of index key */ u8 aux_len; /* Length of auxiliary data */ u32 key_hash; /* Hash of volume, key, len */ union { void *key; /* Index key */ u8 inline_key[16]; /* - If the key is short enough */ }; union { void *aux; /* Auxiliary data */ u8 inline_aux[8]; /* - If the aux data is short enough */ }; }; /* * slow-path functions for when there is actually caching available, and the * netfs does actually have a valid token * - these are not to be called directly * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ extern struct fscache_volume *__fscache_acquire_volume(const char *, const char *, const void *, size_t); extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); extern struct fscache_cookie *__fscache_acquire_cookie( struct fscache_volume *, u8, const void *, size_t, const void *, size_t, loff_t); extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); void __fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, bool using_pgpriv2, bool cond); extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** * fscache_acquire_volume - Register a volume as desiring caching services * @volume_key: An identification string for the volume * @cache_name: The name of the cache to use (or NULL for the default) * @coherency_data: Piece of arbitrary coherency data to check (or NULL) * @coherency_len: The size of the coherency data * * Register a volume as desiring caching services if they're available. The * caller must provide an identifier for the volume and may also indicate which * cache it should be in. If a preexisting volume entry is found in the cache, * the coherency data must match otherwise the entry will be invalidated. * * Returns a cookie pointer on success, -ENOMEM if out of memory or -EBUSY if a * cache volume of that name is already acquired. Note that "NULL" is a valid * cookie pointer and can be returned if caching is refused. */ static inline struct fscache_volume *fscache_acquire_volume(const char *volume_key, const char *cache_name, const void *coherency_data, size_t coherency_len) { if (!fscache_available()) return NULL; return __fscache_acquire_volume(volume_key, cache_name, coherency_data, coherency_len); } /** * fscache_relinquish_volume - Cease caching a volume * @volume: The volume cookie * @coherency_data: Piece of arbitrary coherency data to set (or NULL) * @invalidate: True if the volume should be invalidated * * Indicate that a filesystem no longer desires caching services for a volume. * The caller must have relinquished all file cookies prior to calling this. * The stored coherency data is updated. */ static inline void fscache_relinquish_volume(struct fscache_volume *volume, const void *coherency_data, bool invalidate) { if (fscache_volume_valid(volume)) __fscache_relinquish_volume(volume, coherency_data, invalidate); } /** * fscache_acquire_cookie - Acquire a cookie to represent a cache object * @volume: The volume in which to locate/create this cookie * @advice: Advice flags (FSCACHE_COOKIE_ADV_*) * @index_key: The index key for this cookie * @index_key_len: Size of the index key * @aux_data: The auxiliary data for the cookie (may be NULL) * @aux_data_len: Size of the auxiliary data buffer * @object_size: The initial size of object * * Acquire a cookie to represent a data file within the given cache volume. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, u8 advice, const void *index_key, size_t index_key_len, const void *aux_data, size_t aux_data_len, loff_t object_size) { if (!fscache_volume_valid(volume)) return NULL; return __fscache_acquire_cookie(volume, advice, index_key, index_key_len, aux_data, aux_data_len, object_size); } /** * fscache_use_cookie - Request usage of cookie attached to an object * @cookie: The cookie representing the cache object * @will_modify: If cache is expected to be modified locally * * Request usage of the cookie attached to an object. The caller should tell * the cache if the object's contents are about to be modified locally and then * the cache can apply the policy that has been set to handle this case. */ static inline void fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify) { if (fscache_cookie_valid(cookie)) __fscache_use_cookie(cookie, will_modify); } /** * fscache_unuse_cookie - Cease usage of cookie attached to an object * @cookie: The cookie representing the cache object * @aux_data: Updated auxiliary data (or NULL) * @object_size: Revised size of the object (or NULL) * * Cease usage of the cookie attached to an object. When the users count * reaches zero then the cookie relinquishment will be permitted to proceed. */ static inline void fscache_unuse_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size) { if (fscache_cookie_valid(cookie)) __fscache_unuse_cookie(cookie, aux_data, object_size); } /** * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding * it * @cookie: The cookie being returned * @retire: True if the cache object the cookie represents is to be discarded * * This function returns a cookie to the cache, forcibly discarding the * associated cache object if retire is set to true. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) { if (fscache_cookie_valid(cookie)) __fscache_relinquish_cookie(cookie, retire); } /* * Find the auxiliary data on a cookie. */ static inline void *fscache_get_aux(struct fscache_cookie *cookie) { if (cookie->aux_len <= sizeof(cookie->inline_aux)) return cookie->inline_aux; else return cookie->aux; } /* * Update the auxiliary data on a cookie. */ static inline void fscache_update_aux(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size) { void *p = fscache_get_aux(cookie); if (aux_data && p) memcpy(p, aux_data, cookie->aux_len); if (object_size) cookie->object_size = *object_size; } #ifdef CONFIG_FSCACHE_STATS extern atomic_t fscache_n_updates; #endif static inline void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size) { #ifdef CONFIG_FSCACHE_STATS atomic_inc(&fscache_n_updates); #endif fscache_update_aux(cookie, aux_data, object_size); smp_wmb(); set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } /** * fscache_update_cookie - Request that a cache object be updated * @cookie: The cookie representing the cache object * @aux_data: The updated auxiliary data for the cookie (may be NULL) * @object_size: The current size of the object (may be NULL) * * Request an update of the index data for the cache object associated with the * cookie. The auxiliary data on the cookie will be updated first if @aux_data * is set and the object size will be updated and the object possibly trimmed * if @object_size is set. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size) { if (fscache_cookie_enabled(cookie)) __fscache_update_cookie(cookie, aux_data, object_size); } /** * fscache_resize_cookie - Request that a cache object be resized * @cookie: The cookie representing the cache object * @new_size: The new size of the object (may be NULL) * * Request that the size of an object be changed. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) { if (fscache_cookie_enabled(cookie)) __fscache_resize_cookie(cookie, new_size); } /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object * @aux_data: The updated auxiliary data for the cookie (may be NULL) * @size: The revised size of the object. * @flags: Invalidation flags (FSCACHE_INVAL_*) * * Notify the cache that an object is needs to be invalidated and that it * should abort any retrievals or stores it is doing on the cache. This * increments inval_counter on the cookie which can be used by the caller to * reconsider I/O requests as they complete. * * If @flags has FSCACHE_INVAL_DIO_WRITE set, this indicates that this is due * to a direct I/O write and will cause caching to be disabled on this cookie * until it is completely unused. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline void fscache_invalidate(struct fscache_cookie *cookie, const void *aux_data, loff_t size, unsigned int flags) { if (fscache_cookie_enabled(cookie)) __fscache_invalidate(cookie, aux_data, size, flags); } /** * fscache_operation_valid - Return true if operations resources are usable * @cres: The resources to check. * * Returns a pointer to the operations table if usable or NULL if not. */ static inline const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_resources *cres) { return fscache_resources_valid(cres) ? cres->ops : NULL; } /** * fscache_begin_read_operation - Begin a read operation for the netfs lib * @cres: The cache resources for the read being performed * @cookie: The cookie representing the cache object * * Begin a read operation on behalf of the netfs helper library. @cres * indicates the cache resources to which the operation state should be * attached; @cookie indicates the cache object that will be accessed. * * @cres->inval_counter is set from @cookie->inval_counter for comparison at * the end of the operation. This allows invalidation during the operation to * be detected by the caller. * * Returns: * * 0 - Success * * -ENOBUFS - No caching available * * Other error code from the cache, such as -ENOMEM. */ static inline int fscache_begin_read_operation(struct netfs_cache_resources *cres, struct fscache_cookie *cookie) { if (fscache_cookie_enabled(cookie)) return __fscache_begin_read_operation(cres, cookie); return -ENOBUFS; } /** * fscache_end_operation - End the read operation for the netfs lib * @cres: The cache resources for the read operation * * Clean up the resources at the end of the read request. */ static inline void fscache_end_operation(struct netfs_cache_resources *cres) { const struct netfs_cache_ops *ops = fscache_operation_valid(cres); if (ops) ops->end_operation(cres); } /** * fscache_read - Start a read from the cache. * @cres: The cache resources to use * @start_pos: The beginning file offset in the cache file * @iter: The buffer to fill - and also the length * @read_hole: How to handle a hole in the data. * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func * * Start a read from the cache. @cres indicates the cache object to read from * and must be obtained by a call to fscache_begin_operation() beforehand. * * The data is read into the iterator, @iter, and that also indicates the size * of the operation. @start_pos is the start position in the file, though if * @seek_data is set appropriately, the cache can use SEEK_DATA to find the * next piece of data, writing zeros for the hole into the iterator. * * Upon termination of the operation, @term_func will be called and supplied * with @term_func_priv plus the amount of data written, if successful, or the * error code otherwise. * * @read_hole indicates how a partially populated region in the cache should be * handled. It can be one of a number of settings: * * NETFS_READ_HOLE_IGNORE - Just try to read (may return a short read). * * NETFS_READ_HOLE_FAIL - Give ENODATA if we encounter a hole. */ static inline int fscache_read(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv) { const struct netfs_cache_ops *ops = fscache_operation_valid(cres); return ops->read(cres, start_pos, iter, read_hole, term_func, term_func_priv); } /** * fscache_begin_write_operation - Begin a write operation for the netfs lib * @cres: The cache resources for the write being performed * @cookie: The cookie representing the cache object * * Begin a write operation on behalf of the netfs helper library. @cres * indicates the cache resources to which the operation state should be * attached; @cookie indicates the cache object that will be accessed. * * @cres->inval_counter is set from @cookie->inval_counter for comparison at * the end of the operation. This allows invalidation during the operation to * be detected by the caller. * * Returns: * * 0 - Success * * -ENOBUFS - No caching available * * Other error code from the cache, such as -ENOMEM. */ static inline int fscache_begin_write_operation(struct netfs_cache_resources *cres, struct fscache_cookie *cookie) { if (fscache_cookie_enabled(cookie)) return __fscache_begin_write_operation(cres, cookie); return -ENOBUFS; } /** * fscache_write - Start a write to the cache. * @cres: The cache resources to use * @start_pos: The beginning file offset in the cache file * @iter: The data to write - and also the length * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func * * Start a write to the cache. @cres indicates the cache object to write to and * must be obtained by a call to fscache_begin_operation() beforehand. * * The data to be written is obtained from the iterator, @iter, and that also * indicates the size of the operation. @start_pos is the start position in * the file. * * Upon termination of the operation, @term_func will be called and supplied * with @term_func_priv plus the amount of data written, if successful, or the * error code otherwise. */ static inline int fscache_write(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, netfs_io_terminated_t term_func, void *term_func_priv) { const struct netfs_cache_ops *ops = fscache_operation_valid(cres); return ops->write(cres, start_pos, iter, term_func, term_func_priv); } /** * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to unlock * @caching: If PG_fscache has been set * * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's * waiting. */ static inline void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) { if (caching) __fscache_clear_page_bits(mapping, start, len); } /** * fscache_write_to_cache - Save a write to the cache and clear PG_fscache * @cookie: The cookie representing the cache object * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to write back * @i_size: The new size of the inode * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func * @using_pgpriv2: If we're using PG_private_2 to mark in-progress write * @caching: If we actually want to do the caching * * Helper function for a netfs to write dirty data from an inode into the cache * object that's backing it. * * @start and @len describe the range of the data. This does not need to be * page-aligned, but to satisfy DIO requirements, the cache may expand it up to * the page boundaries on either end. All the pages covering the range must be * marked with PG_fscache. * * If given, @term_func will be called upon completion and supplied with * @term_func_priv. Note that if @using_pgpriv2 is set, the PG_private_2 flags * will have been cleared by this point, so the netfs must retain its own pin * on the mapping. */ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, bool using_pgpriv2, bool caching) { if (caching) __fscache_write_to_cache(cookie, mapping, start, len, i_size, term_func, term_func_priv, using_pgpriv2, caching); else if (term_func) term_func(term_func_priv, -ENOBUFS); } /** * fscache_note_page_release - Note that a netfs page got released * @cookie: The cookie corresponding to the file * * Note that a page that has been copied to the cache has been released. This * means that future reads will need to look in the cache to see if it's there. */ static inline void fscache_note_page_release(struct fscache_cookie *cookie) { /* If we've written data to the cache (HAVE_DATA) and there wasn't any * data in the cache when we started (NO_DATA_TO_READ), it may no * longer be true that we can skip reading from the cache - so clear * the flag that causes reads to be skipped. */ if (cookie && test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); } #endif /* _LINUX_FSCACHE_H */ |
| 20 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H #include <linux/cgroup.h> #include <linux/kernfs.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/fs_parser.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; extern void __init enable_debug_cgroup(void); /* * cgroup_path() takes a spin lock. It is good practice not to take * spin locks within trace point handlers, as they are mostly hidden * from normal view. As cgroup_path() can take the kernfs_rename_lock * spin lock, it is best to not call that function from the trace event * handler. * * Note: trace_cgroup_##type##_enabled() is a static branch that will only * be set when the trace event is enabled. */ #define TRACE_CGROUP_PATH(type, cgrp, ...) \ do { \ if (trace_cgroup_##type##_enabled()) { \ unsigned long flags; \ spin_lock_irqsave(&trace_cgroup_path_lock, \ flags); \ cgroup_path(cgrp, trace_cgroup_path, \ TRACE_CGROUP_PATH_LEN); \ trace_cgroup_##type(cgrp, trace_cgroup_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_cgroup_path_lock, \ flags); \ } \ } while (0) /* * The cgroup filesystem superblock creation/mount context. */ struct cgroup_fs_context { struct kernfs_fs_context kfc; struct cgroup_root *root; struct cgroup_namespace *ns; unsigned int flags; /* CGRP_ROOT_* flags */ /* cgroup1 bits */ bool cpuset_clone_children; bool none; /* User explicitly requested empty subsystem */ bool all_ss; /* Seen 'all' option */ u16 subsys_mask; /* Selected subsystems */ char *name; /* Hierarchy name */ char *release_agent; /* Path for release notifications */ }; static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; return container_of(kfc, struct cgroup_fs_context, kfc); } struct cgroup_pidlist; struct cgroup_file_ctx { struct cgroup_namespace *ns; struct { void *trigger; } psi; struct { bool started; struct css_task_iter iter; } procs; struct { struct cgroup_pidlist *pidlist; } procs1; struct cgroup_of_peak peak; }; /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* used to track tasks and csets during migration */ struct cgroup_taskset { /* the src and dst cset list running through cset->mg_node */ struct list_head src_csets; struct list_head dst_csets; /* the number of tasks in the set */ int nr_tasks; /* the subsys currently being processed */ int ssid; /* * Fields for cgroup_taskset_*() iteration. * * Before migration is committed, the target migration tasks are on * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of * the csets on ->dst_csets. ->csets point to either ->src_csets * or ->dst_csets depending on whether migration is committed. * * ->cur_csets and ->cur_task point to the current task position * during iteration. */ struct list_head *csets; struct css_set *cur_cset; struct task_struct *cur_task; }; /* migration context also tracks preloading */ struct cgroup_mgctx { /* * Preloaded source and destination csets. Used to guarantee * atomic success or failure on actual migration. */ struct list_head preloaded_src_csets; struct list_head preloaded_dst_csets; /* tasks and csets to migrate */ struct cgroup_taskset tset; /* subsystems affected by migration */ u16 ss_mask; }; #define CGROUP_TASKSET_INIT(tset) \ { \ .src_csets = LIST_HEAD_INIT(tset.src_csets), \ .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ .csets = &tset.src_csets, \ } #define CGROUP_MGCTX_INIT(name) \ { \ LIST_HEAD_INIT(name.preloaded_src_csets), \ LIST_HEAD_INIT(name.preloaded_dst_csets), \ CGROUP_TASKSET_INIT(name.tset), \ } #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; extern bool cgrp_dfl_visible; /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry_rcu((root), &cgroup_roots, root_list, \ lockdep_is_held(&cgroup_mutex)) /** * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end */ #define for_each_subsys(ss, ssid) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return !(cgrp->self.flags & CSS_ONLINE); } static inline bool notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } void put_css_set_locked(struct css_set *cset); static inline void put_css_set(struct css_set *cset) { unsigned long flags; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (refcount_dec_not_one(&cset->refcount)) return; spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); spin_unlock_irqrestore(&css_set_lock, flags); } /* * refcounted get/put for css_set objects */ static inline void get_css_set(struct css_set *cset) { refcount_inc(&cset->refcount); } bool cgroup_ssid_enabled(int ssid); bool cgroup_on_dfl(const struct cgroup *cgrp); struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root); struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); void cgroup_kn_unlock(struct kernfs_node *kn); int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); void cgroup_favor_dynmods(struct cgroup_root *root, bool favor); void cgroup_free_root(struct cgroup_root *root); void init_cgroup_root(struct cgroup_fs_context *ctx); int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); int cgroup_do_get_tree(struct fs_context *fc); int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx); int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx); int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); void cgroup_attach_lock(bool lock_threadgroup); void cgroup_attach_unlock(bool lock_threadgroup); struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *locked) __acquires(&cgroup_threadgroup_rwsem); void cgroup_procs_write_finish(struct task_struct *task, bool locked) __releases(&cgroup_threadgroup_rwsem); void cgroup_lock_and_drain_offline(struct cgroup *cgrp); int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); int cgroup_rmdir(struct kernfs_node *kn); int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root); int __cgroup_task_count(const struct cgroup *cgrp); int cgroup_task_count(const struct cgroup *cgrp); /* * rstat.c */ int css_rstat_init(struct cgroup_subsys_state *css); void css_rstat_exit(struct cgroup_subsys_state *css); int ss_rstat_init(struct cgroup_subsys *ss); void cgroup_base_stat_cputime_show(struct seq_file *seq); /* * namespace.c */ extern const struct proc_ns_operations cgroupns_operations; /* * cgroup-v1.c */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; extern const struct fs_parameter_spec cgroup1_fs_parameters[]; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); void cgroup1_check_for_release(struct cgroup *cgrp); int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); int cgroup1_get_tree(struct fs_context *fc); int cgroup1_reconfigure(struct fs_context *ctx); #endif /* __CGROUP_INTERNAL_H */ |
| 752 847 395 390 4 245 245 61 60 10 10 129 130 775 307 649 339 69 282 352 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/fast_commit.c * * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com> * * Ext4 fast commits routines. */ #include "ext4.h" #include "ext4_jbd2.h" #include "ext4_extents.h" #include "mballoc.h" #include <linux/lockdep.h> /* * Ext4 Fast Commits * ----------------- * * Ext4 fast commits implement fine grained journalling for Ext4. * * Fast commits are organized as a log of tag-length-value (TLV) structs. (See * struct ext4_fc_tl). Each TLV contains some delta that is replayed TLV by * TLV during the recovery phase. For the scenarios for which we currently * don't have replay code, fast commit falls back to full commits. * Fast commits record delta in one of the following three categories. * * (A) Directory entry updates: * * - EXT4_FC_TAG_UNLINK - records directory entry unlink * - EXT4_FC_TAG_LINK - records directory entry link * - EXT4_FC_TAG_CREAT - records inode and directory entry creation * * (B) File specific data range updates: * * - EXT4_FC_TAG_ADD_RANGE - records addition of new blocks to an inode * - EXT4_FC_TAG_DEL_RANGE - records deletion of blocks from an inode * * (C) Inode metadata (mtime / ctime etc): * * - EXT4_FC_TAG_INODE - record the inode that should be replayed * during recovery. Note that iblocks field is * not replayed and instead derived during * replay. * Commit Operation * ---------------- * With fast commits, we maintain all the directory entry operations in the * order in which they are issued in an in-memory queue. This queue is flushed * to disk during the commit operation. We also maintain a list of inodes * that need to be committed during a fast commit in another in memory queue of * inodes. During the commit operation, we commit in the following order: * * [1] Prepare all the inodes to write out their data by setting * "EXT4_STATE_FC_FLUSHING_DATA". This ensures that inode cannot be * deleted while it is being flushed. * [2] Flush data buffers to disk and clear "EXT4_STATE_FC_FLUSHING_DATA" * state. * [3] Lock the journal by calling jbd2_journal_lock_updates. This ensures that * all the exsiting handles finish and no new handles can start. * [4] Mark all the fast commit eligible inodes as undergoing fast commit * by setting "EXT4_STATE_FC_COMMITTING" state. * [5] Unlock the journal by calling jbd2_journal_unlock_updates. This allows * starting of new handles. If new handles try to start an update on * any of the inodes that are being committed, ext4_fc_track_inode() * will block until those inodes have finished the fast commit. * [6] Commit all the directory entry updates in the fast commit space. * [7] Commit all the changed inodes in the fast commit space and clear * "EXT4_STATE_FC_COMMITTING" for these inodes. * [8] Write tail tag (this tag ensures the atomicity, please read the following * section for more details). * * All the inode updates must be enclosed within jbd2_jounrnal_start() * and jbd2_journal_stop() similar to JBD2 journaling. * * Fast Commit Ineligibility * ------------------------- * * Not all operations are supported by fast commits today (e.g extended * attributes). Fast commit ineligibility is marked by calling * ext4_fc_mark_ineligible(): This makes next fast commit operation to fall back * to full commit. * * Atomicity of commits * -------------------- * In order to guarantee atomicity during the commit operation, fast commit * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail * tag contains CRC of the contents and TID of the transaction after which * this fast commit should be applied. Recovery code replays fast commit * logs only if there's at least 1 valid tail present. For every fast commit * operation, there is 1 tail. This means, we may end up with multiple tails * in the fast commit space. Here's an example: * * - Create a new file A and remove existing file B * - fsync() * - Append contents to file A * - Truncate file A * - fsync() * * The fast commit space at the end of above operations would look like this: * [HEAD] [CREAT A] [UNLINK B] [TAIL] [ADD_RANGE A] [DEL_RANGE A] [TAIL] * |<--- Fast Commit 1 --->|<--- Fast Commit 2 ---->| * * Replay code should thus check for all the valid tails in the FC area. * * Fast Commit Replay Idempotence * ------------------------------ * * Fast commits tags are idempotent in nature provided the recovery code follows * certain rules. The guiding principle that the commit path follows while * committing is that it stores the result of a particular operation instead of * storing the procedure. * * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a' * was associated with inode 10. During fast commit, instead of storing this * operation as a procedure "rename a to b", we store the resulting file system * state as a "series" of outcomes: * * - Link dirent b to inode 10 * - Unlink dirent a * - Inode <10> with valid refcount * * Now when recovery code runs, it needs "enforce" this state on the file * system. This is what guarantees idempotence of fast commit replay. * * Let's take an example of a procedure that is not idempotent and see how fast * commits make it idempotent. Consider following sequence of operations: * * rm A; mv B A; read A * (x) (y) (z) * * (x), (y) and (z) are the points at which we can crash. If we store this * sequence of operations as is then the replay is not idempotent. Let's say * while in replay, we crash at (z). During the second replay, file A (which was * actually created as a result of "mv B A" operation) would get deleted. Thus, * file named A would be absent when we try to read A. So, this sequence of * operations is not idempotent. However, as mentioned above, instead of storing * the procedure fast commits store the outcome of each procedure. Thus the fast * commit log for above procedure would be as follows: * * (Let's assume dirent A was linked to inode 10 and dirent B was linked to * inode 11 before the replay) * * [Unlink A] [Link A to inode 11] [Unlink B] [Inode 11] * (w) (x) (y) (z) * * If we crash at (z), we will have file A linked to inode 11. During the second * replay, we will remove file A (inode 11). But we will create it back and make * it point to inode 11. We won't find B, so we'll just skip that step. At this * point, the refcount for inode 11 is not reliable, but that gets fixed by the * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled * similarly. Thus, by converting a non-idempotent procedure into a series of * idempotent outcomes, fast commits ensured idempotence during the replay. * * Locking * ------- * sbi->s_fc_lock protects the fast commit inodes queue and the fast commit * dentry queue. ei->i_fc_lock protects the fast commit related info in a given * inode. Most of the code avoids acquiring both the locks, but if one must do * that then sbi->s_fc_lock must be acquired before ei->i_fc_lock. * * TODOs * ----- * * 0) Fast commit replay path hardening: Fast commit replay code should use * journal handles to make sure all the updates it does during the replay * path are atomic. With that if we crash during fast commit replay, after * trying to do recovery again, we will find a file system where fast commit * area is invalid (because new full commit would be found). In order to deal * with that, fast commit replay code should ensure that the "FC_REPLAY" * superblock state is persisted before starting the replay, so that after * the crash, fast commit recovery code can look at that flag and perform * fast commit recovery even if that area is invalidated by later full * commits. * * 1) Handle more ineligible cases. * * 2) Change ext4_fc_commit() to lookup logical to physical mapping using extent * status tree. This would get rid of the need to call ext4_fc_track_inode() * before acquiring i_data_sem. To do that we would need to ensure that * modified extents from the extent status tree are not evicted from memory. */ #include <trace/events/ext4.h> static struct kmem_cache *ext4_fc_dentry_cachep; static void ext4_end_buffer_io_sync(struct buffer_head *bh, int uptodate) { BUFFER_TRACE(bh, ""); if (uptodate) { ext4_debug("%s: Block %lld up-to-date", __func__, bh->b_blocknr); set_buffer_uptodate(bh); } else { ext4_debug("%s: Block %lld not up-to-date", __func__, bh->b_blocknr); clear_buffer_uptodate(bh); } unlock_buffer(bh); } static inline void ext4_fc_reset_inode(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); ei->i_fc_lblk_start = 0; ei->i_fc_lblk_len = 0; } void ext4_fc_init_inode(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_fc_reset_inode(inode); ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING); INIT_LIST_HEAD(&ei->i_fc_list); INIT_LIST_HEAD(&ei->i_fc_dilist); init_waitqueue_head(&ei->i_fc_wait); } static bool ext4_fc_disabled(struct super_block *sb) { return (!test_opt2(sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)); } /* * Remove inode from fast commit list. If the inode is being committed * we wait until inode commit is done. */ void ext4_fc_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_fc_dentry_update *fc_dentry; wait_queue_head_t *wq; if (ext4_fc_disabled(inode->i_sb)) return; mutex_lock(&sbi->s_fc_lock); if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) { mutex_unlock(&sbi->s_fc_lock); return; } /* * Since ext4_fc_del is called from ext4_evict_inode while having a * handle open, there is no need for us to wait here even if a fast * commit is going on. That is because, if this inode is being * committed, ext4_mark_inode_dirty would have waited for inode commit * operation to finish before we come here. So, by the time we come * here, inode's EXT4_STATE_FC_COMMITTING would have been cleared. So, * we shouldn't see EXT4_STATE_FC_COMMITTING to be set on this inode * here. * * We may come here without any handles open in the "no_delete" case of * ext4_evict_inode as well. However, if that happens, we first mark the * file system as fast commit ineligible anyway. So, even in that case, * it is okay to remove the inode from the fc list. */ WARN_ON(ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING) && !ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)); while (ext4_test_inode_state(inode, EXT4_STATE_FC_FLUSHING_DATA)) { #if (BITS_PER_LONG < 64) DEFINE_WAIT_BIT(wait, &ei->i_state_flags, EXT4_STATE_FC_FLUSHING_DATA); wq = bit_waitqueue(&ei->i_state_flags, EXT4_STATE_FC_FLUSHING_DATA); #else DEFINE_WAIT_BIT(wait, &ei->i_flags, EXT4_STATE_FC_FLUSHING_DATA); wq = bit_waitqueue(&ei->i_flags, EXT4_STATE_FC_FLUSHING_DATA); #endif prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (ext4_test_inode_state(inode, EXT4_STATE_FC_FLUSHING_DATA)) { mutex_unlock(&sbi->s_fc_lock); schedule(); mutex_lock(&sbi->s_fc_lock); } finish_wait(wq, &wait.wq_entry); } list_del_init(&ei->i_fc_list); /* * Since this inode is getting removed, let's also remove all FC * dentry create references, since it is not needed to log it anyways. */ if (list_empty(&ei->i_fc_dilist)) { mutex_unlock(&sbi->s_fc_lock); return; } fc_dentry = list_first_entry(&ei->i_fc_dilist, struct ext4_fc_dentry_update, fcd_dilist); WARN_ON(fc_dentry->fcd_op != EXT4_FC_TAG_CREAT); list_del_init(&fc_dentry->fcd_list); list_del_init(&fc_dentry->fcd_dilist); WARN_ON(!list_empty(&ei->i_fc_dilist)); mutex_unlock(&sbi->s_fc_lock); release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); } /* * Mark file system as fast commit ineligible, and record latest * ineligible transaction tid. This means until the recorded * transaction, commit operation would result in a full jbd2 commit. */ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle) { struct ext4_sb_info *sbi = EXT4_SB(sb); tid_t tid; bool has_transaction = true; bool is_ineligible; if (ext4_fc_disabled(sb)) return; if (handle && !IS_ERR(handle)) tid = handle->h_transaction->t_tid; else { read_lock(&sbi->s_journal->j_state_lock); if (sbi->s_journal->j_running_transaction) tid = sbi->s_journal->j_running_transaction->t_tid; else has_transaction = false; read_unlock(&sbi->s_journal->j_state_lock); } mutex_lock(&sbi->s_fc_lock); is_ineligible = ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); if (has_transaction && (!is_ineligible || tid_gt(tid, sbi->s_fc_ineligible_tid))) sbi->s_fc_ineligible_tid = tid; ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); mutex_unlock(&sbi->s_fc_lock); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } /* * Generic fast commit tracking function. If this is the first time this we are * called after a full commit, we initialize fast commit fields and then call * __fc_track_fn() with update = 0. If we have already been called after a full * commit, we pass update = 1. Based on that, the track function can determine * if it needs to track a field for the first time or if it needs to just * update the previously tracked value. * * If enqueue is set, this function enqueues the inode in fast commit list. */ static int ext4_fc_track_template( handle_t *handle, struct inode *inode, int (*__fc_track_fn)(handle_t *handle, struct inode *, void *, bool), void *args, int enqueue) { bool update = false; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); tid_t tid = 0; int ret; tid = handle->h_transaction->t_tid; spin_lock(&ei->i_fc_lock); if (tid == ei->i_sync_tid) { update = true; } else { ext4_fc_reset_inode(inode); ei->i_sync_tid = tid; } ret = __fc_track_fn(handle, inode, args, update); spin_unlock(&ei->i_fc_lock); if (!enqueue) return ret; mutex_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); mutex_unlock(&sbi->s_fc_lock); return ret; } struct __track_dentry_update_args { struct dentry *dentry; int op; }; /* __track_fn for directory entry updates. Called with ei->i_fc_lock. */ static int __track_dentry_update(handle_t *handle, struct inode *inode, void *arg, bool update) { struct ext4_fc_dentry_update *node; struct ext4_inode_info *ei = EXT4_I(inode); struct __track_dentry_update_args *dentry_update = (struct __track_dentry_update_args *)arg; struct dentry *dentry = dentry_update->dentry; struct inode *dir = dentry->d_parent->d_inode; struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); spin_unlock(&ei->i_fc_lock); if (IS_ENCRYPTED(dir)) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_ENCRYPTED_FILENAME, handle); spin_lock(&ei->i_fc_lock); return -EOPNOTSUPP; } node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); spin_lock(&ei->i_fc_lock); return -ENOMEM; } node->fcd_op = dentry_update->op; node->fcd_parent = dir->i_ino; node->fcd_ino = inode->i_ino; take_dentry_name_snapshot(&node->fcd_name, dentry); INIT_LIST_HEAD(&node->fcd_dilist); INIT_LIST_HEAD(&node->fcd_list); mutex_lock(&sbi->s_fc_lock); if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]); /* * This helps us keep a track of all fc_dentry updates which is part of * this ext4 inode. So in case the inode is getting unlinked, before * even we get a chance to fsync, we could remove all fc_dentry * references while evicting the inode in ext4_fc_del(). * Also with this, we don't need to loop over all the inodes in * sbi->s_fc_q to get the corresponding inode in * ext4_fc_commit_dentry_updates(). */ if (dentry_update->op == EXT4_FC_TAG_CREAT) { WARN_ON(!list_empty(&ei->i_fc_dilist)); list_add_tail(&node->fcd_dilist, &ei->i_fc_dilist); } mutex_unlock(&sbi->s_fc_lock); spin_lock(&ei->i_fc_lock); return 0; } void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_UNLINK; ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_unlink(handle, inode, dentry, ret); } void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (ext4_fc_disabled(inode->i_sb)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; __ext4_fc_track_unlink(handle, inode, dentry); } void __ext4_fc_track_link(handle_t *handle, struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_LINK; ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_link(handle, inode, dentry, ret); } void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (ext4_fc_disabled(inode->i_sb)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; __ext4_fc_track_link(handle, inode, dentry); } void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_CREAT; ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_create(handle, inode, dentry, ret); } void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (ext4_fc_disabled(inode->i_sb)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; __ext4_fc_track_create(handle, inode, dentry); } /* __track_fn for inode tracking */ static int __track_inode(handle_t *handle, struct inode *inode, void *arg, bool update) { if (update) return -EEXIST; EXT4_I(inode)->i_fc_lblk_len = 0; return 0; } void ext4_fc_track_inode(handle_t *handle, struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); wait_queue_head_t *wq; int ret; if (S_ISDIR(inode->i_mode)) return; if (ext4_fc_disabled(inode->i_sb)) return; if (ext4_should_journal_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_INODE_JOURNAL_DATA, handle); return; } if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; /* * If we come here, we may sleep while waiting for the inode to * commit. We shouldn't be holding i_data_sem when we go to sleep since * the commit path needs to grab the lock while committing the inode. */ lockdep_assert_not_held(&ei->i_data_sem); while (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { #if (BITS_PER_LONG < 64) DEFINE_WAIT_BIT(wait, &ei->i_state_flags, EXT4_STATE_FC_COMMITTING); wq = bit_waitqueue(&ei->i_state_flags, EXT4_STATE_FC_COMMITTING); #else DEFINE_WAIT_BIT(wait, &ei->i_flags, EXT4_STATE_FC_COMMITTING); wq = bit_waitqueue(&ei->i_flags, EXT4_STATE_FC_COMMITTING); #endif prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) schedule(); finish_wait(wq, &wait.wq_entry); } /* * From this point on, this inode will not be committed either * by fast or full commit as long as the handle is open. */ ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1); trace_ext4_fc_track_inode(handle, inode, ret); } struct __track_range_args { ext4_lblk_t start, end; }; /* __track_fn for tracking data updates */ static int __track_range(handle_t *handle, struct inode *inode, void *arg, bool update) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_lblk_t oldstart; struct __track_range_args *__arg = (struct __track_range_args *)arg; if (inode->i_ino < EXT4_FIRST_INO(inode->i_sb)) { ext4_debug("Special inode %ld being modified\n", inode->i_ino); return -ECANCELED; } oldstart = ei->i_fc_lblk_start; if (update && ei->i_fc_lblk_len > 0) { ei->i_fc_lblk_start = min(ei->i_fc_lblk_start, __arg->start); ei->i_fc_lblk_len = max(oldstart + ei->i_fc_lblk_len - 1, __arg->end) - ei->i_fc_lblk_start + 1; } else { ei->i_fc_lblk_start = __arg->start; ei->i_fc_lblk_len = __arg->end - __arg->start + 1; } return 0; } void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct __track_range_args args; int ret; if (S_ISDIR(inode->i_mode)) return; if (ext4_fc_disabled(inode->i_sb)) return; if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) return; if (ext4_has_inline_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); return; } args.start = start; args.end = end; ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1); trace_ext4_fc_track_range(handle, inode, start, end, ret); } static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { blk_opf_t write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; /* Add REQ_FUA | REQ_PREFLUSH only its tail */ if (test_opt(sb, BARRIER) && is_tail) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); set_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = ext4_end_buffer_io_sync; submit_bh(REQ_OP_WRITE | write_flags, bh); EXT4_SB(sb)->s_fc_bh = NULL; } /* Ext4 commit path routines */ /* * Allocate len bytes on a fast commit buffer. * * During the commit time this function is used to manage fast commit * block space. We don't split a fast commit log onto different * blocks. So this function makes sure that if there's not enough space * on the current block, the remaining space in the current block is * marked as unused by adding EXT4_FC_TAG_PAD tag. In that case, * new block is from jbd2 and CRC is updated to reflect the padding * we added. */ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) { struct ext4_fc_tl tl; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh; int bsize = sbi->s_journal->j_blocksize; int ret, off = sbi->s_fc_bytes % bsize; int remaining; u8 *dst; /* * If 'len' is too long to fit in any block alongside a PAD tlv, then we * cannot fulfill the request. */ if (len > bsize - EXT4_FC_TAG_BASE_LEN) return NULL; if (!sbi->s_fc_bh) { ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) return NULL; sbi->s_fc_bh = bh; } dst = sbi->s_fc_bh->b_data + off; /* * Allocate the bytes in the current block if we can do so while still * leaving enough space for a PAD tlv. */ remaining = bsize - EXT4_FC_TAG_BASE_LEN - off; if (len <= remaining) { sbi->s_fc_bytes += len; return dst; } /* * Else, terminate the current block with a PAD tlv, then allocate a new * block and allocate the bytes at the start of that new block. */ tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_PAD); tl.fc_len = cpu_to_le16(remaining); memcpy(dst, &tl, EXT4_FC_TAG_BASE_LEN); memset(dst + EXT4_FC_TAG_BASE_LEN, 0, remaining); *crc = ext4_chksum(*crc, sbi->s_fc_bh->b_data, bsize); ext4_fc_submit_bh(sb, false); ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) return NULL; sbi->s_fc_bh = bh; sbi->s_fc_bytes += bsize - off + len; return sbi->s_fc_bh->b_data; } /* * Complete a fast commit by writing tail tag. * * Writing tail tag marks the end of a fast commit. In order to guarantee * atomicity, after writing tail tag, even if there's space remaining * in the block, next commit shouldn't use it. That's why tail tag * has the length as that of the remaining space on the block. */ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_tl tl; struct ext4_fc_tail tail; int off, bsize = sbi->s_journal->j_blocksize; u8 *dst; /* * ext4_fc_reserve_space takes care of allocating an extra block if * there's no enough space on this block for accommodating this tail. */ dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(tail), &crc); if (!dst) return -ENOSPC; off = sbi->s_fc_bytes % bsize; tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_TAIL); tl.fc_len = cpu_to_le16(bsize - off + sizeof(struct ext4_fc_tail)); sbi->s_fc_bytes = round_up(sbi->s_fc_bytes, bsize); memcpy(dst, &tl, EXT4_FC_TAG_BASE_LEN); dst += EXT4_FC_TAG_BASE_LEN; tail.fc_tid = cpu_to_le32(sbi->s_journal->j_running_transaction->t_tid); memcpy(dst, &tail.fc_tid, sizeof(tail.fc_tid)); dst += sizeof(tail.fc_tid); crc = ext4_chksum(crc, sbi->s_fc_bh->b_data, dst - (u8 *)sbi->s_fc_bh->b_data); tail.fc_crc = cpu_to_le32(crc); memcpy(dst, &tail.fc_crc, sizeof(tail.fc_crc)); dst += sizeof(tail.fc_crc); memset(dst, 0, bsize - off); /* Don't leak uninitialized memory. */ ext4_fc_submit_bh(sb, true); return 0; } /* * Adds tag, length, value and updates CRC. Returns true if tlv was added. * Returns false if there's not enough space. */ static bool ext4_fc_add_tlv(struct super_block *sb, u16 tag, u16 len, u8 *val, u32 *crc) { struct ext4_fc_tl tl; u8 *dst; dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + len, crc); if (!dst) return false; tl.fc_tag = cpu_to_le16(tag); tl.fc_len = cpu_to_le16(len); memcpy(dst, &tl, EXT4_FC_TAG_BASE_LEN); memcpy(dst + EXT4_FC_TAG_BASE_LEN, val, len); return true; } /* Same as above, but adds dentry tlv. */ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, struct ext4_fc_dentry_update *fc_dentry) { struct ext4_fc_dentry_info fcd; struct ext4_fc_tl tl; int dlen = fc_dentry->fcd_name.name.len; u8 *dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc); if (!dst) return false; fcd.fc_parent_ino = cpu_to_le32(fc_dentry->fcd_parent); fcd.fc_ino = cpu_to_le32(fc_dentry->fcd_ino); tl.fc_tag = cpu_to_le16(fc_dentry->fcd_op); tl.fc_len = cpu_to_le16(sizeof(fcd) + dlen); memcpy(dst, &tl, EXT4_FC_TAG_BASE_LEN); dst += EXT4_FC_TAG_BASE_LEN; memcpy(dst, &fcd, sizeof(fcd)); dst += sizeof(fcd); memcpy(dst, fc_dentry->fcd_name.name.name, dlen); return true; } /* * Writes inode in the fast commit space under TLV with tag @tag. * Returns 0 on success, error on failure. */ static int ext4_fc_write_inode(struct inode *inode, u32 *crc) { struct ext4_inode_info *ei = EXT4_I(inode); int inode_len = EXT4_GOOD_OLD_INODE_SIZE; int ret; struct ext4_iloc iloc; struct ext4_fc_inode fc_inode; struct ext4_fc_tl tl; u8 *dst; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) inode_len = EXT4_INODE_SIZE(inode->i_sb); else if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) inode_len += ei->i_extra_isize; fc_inode.fc_ino = cpu_to_le32(inode->i_ino); tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE); tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino)); ret = -ECANCELED; dst = ext4_fc_reserve_space(inode->i_sb, EXT4_FC_TAG_BASE_LEN + inode_len + sizeof(fc_inode.fc_ino), crc); if (!dst) goto err; memcpy(dst, &tl, EXT4_FC_TAG_BASE_LEN); dst += EXT4_FC_TAG_BASE_LEN; memcpy(dst, &fc_inode, sizeof(fc_inode)); dst += sizeof(fc_inode); memcpy(dst, (u8 *)ext4_raw_inode(&iloc), inode_len); ret = 0; err: brelse(iloc.bh); return ret; } /* * Writes updated data ranges for the inode in question. Updates CRC. * Returns 0 on success, error otherwise. */ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) { ext4_lblk_t old_blk_size, cur_lblk_off, new_blk_size; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_map_blocks map; struct ext4_fc_add_range fc_ext; struct ext4_fc_del_range lrange; struct ext4_extent *ex; int ret; spin_lock(&ei->i_fc_lock); if (ei->i_fc_lblk_len == 0) { spin_unlock(&ei->i_fc_lock); return 0; } old_blk_size = ei->i_fc_lblk_start; new_blk_size = ei->i_fc_lblk_start + ei->i_fc_lblk_len - 1; ei->i_fc_lblk_len = 0; spin_unlock(&ei->i_fc_lock); cur_lblk_off = old_blk_size; ext4_debug("will try writing %d to %d for inode %ld\n", cur_lblk_off, new_blk_size, inode->i_ino); while (cur_lblk_off <= new_blk_size) { map.m_lblk = cur_lblk_off; map.m_len = new_blk_size - cur_lblk_off + 1; ret = ext4_map_blocks(NULL, inode, &map, EXT4_GET_BLOCKS_IO_SUBMIT | EXT4_EX_NOCACHE); if (ret < 0) return -ECANCELED; if (map.m_len == 0) { cur_lblk_off++; continue; } if (ret == 0) { lrange.fc_ino = cpu_to_le32(inode->i_ino); lrange.fc_lblk = cpu_to_le32(map.m_lblk); lrange.fc_len = cpu_to_le32(map.m_len); if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_DEL_RANGE, sizeof(lrange), (u8 *)&lrange, crc)) return -ENOSPC; } else { unsigned int max = (map.m_flags & EXT4_MAP_UNWRITTEN) ? EXT_UNWRITTEN_MAX_LEN : EXT_INIT_MAX_LEN; /* Limit the number of blocks in one extent */ map.m_len = min(max, map.m_len); fc_ext.fc_ino = cpu_to_le32(inode->i_ino); ex = (struct ext4_extent *)&fc_ext.fc_ex; ex->ee_block = cpu_to_le32(map.m_lblk); ex->ee_len = cpu_to_le16(map.m_len); ext4_ext_store_pblock(ex, map.m_pblk); if (map.m_flags & EXT4_MAP_UNWRITTEN) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_ADD_RANGE, sizeof(fc_ext), (u8 *)&fc_ext, crc)) return -ENOSPC; } cur_lblk_off += map.m_len; } return 0; } /* Flushes data of all the inodes in the commit queue. */ static int ext4_fc_flush_data(journal_t *journal) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; int ret = 0; list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ret = jbd2_submit_inode_data(journal, ei->jinode); if (ret) return ret; } list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ret = jbd2_wait_inode_data(journal, ei->jinode); if (ret) return ret; } return 0; } /* Commit all the directory entry updates */ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n; struct inode *inode; struct ext4_inode_info *ei; int ret; if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) return 0; list_for_each_entry_safe(fc_dentry, fc_dentry_n, &sbi->s_fc_dentry_q[FC_Q_MAIN], fcd_list) { if (fc_dentry->fcd_op != EXT4_FC_TAG_CREAT) { if (!ext4_fc_add_dentry_tlv(sb, crc, fc_dentry)) return -ENOSPC; continue; } /* * With fcd_dilist we need not loop in sbi->s_fc_q to get the * corresponding inode. Also, the corresponding inode could have been * deleted, in which case, we don't need to do anything. */ if (list_empty(&fc_dentry->fcd_dilist)) continue; ei = list_first_entry(&fc_dentry->fcd_dilist, struct ext4_inode_info, i_fc_dilist); inode = &ei->vfs_inode; WARN_ON(inode->i_ino != fc_dentry->fcd_ino); /* * We first write the inode and then the create dirent. This * allows the recovery code to create an unnamed inode first * and then link it to a directory entry. This allows us * to use namei.c routines almost as is and simplifies * the recovery code. */ ret = ext4_fc_write_inode(inode, crc); if (ret) return ret; ret = ext4_fc_write_inode_data(inode, crc); if (ret) return ret; if (!ext4_fc_add_dentry_tlv(sb, crc, fc_dentry)) return -ENOSPC; } return 0; } static int ext4_fc_perform_commit(journal_t *journal) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *iter; struct ext4_fc_head head; struct inode *inode; struct blk_plug plug; int ret = 0; u32 crc = 0; /* * Step 1: Mark all inodes on s_fc_q[MAIN] with * EXT4_STATE_FC_FLUSHING_DATA. This prevents these inodes from being * freed until the data flush is over. */ mutex_lock(&sbi->s_fc_lock); list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&iter->vfs_inode, EXT4_STATE_FC_FLUSHING_DATA); } mutex_unlock(&sbi->s_fc_lock); /* Step 2: Flush data for all the eligible inodes. */ ret = ext4_fc_flush_data(journal); /* * Step 3: Clear EXT4_STATE_FC_FLUSHING_DATA flag, before returning * any error from step 2. This ensures that waiters waiting on * EXT4_STATE_FC_FLUSHING_DATA can resume. */ mutex_lock(&sbi->s_fc_lock); list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_clear_inode_state(&iter->vfs_inode, EXT4_STATE_FC_FLUSHING_DATA); #if (BITS_PER_LONG < 64) wake_up_bit(&iter->i_state_flags, EXT4_STATE_FC_FLUSHING_DATA); #else wake_up_bit(&iter->i_flags, EXT4_STATE_FC_FLUSHING_DATA); #endif } /* * Make sure clearing of EXT4_STATE_FC_FLUSHING_DATA is visible before * the waiter checks the bit. Pairs with implicit barrier in * prepare_to_wait() in ext4_fc_del(). */ smp_mb(); mutex_unlock(&sbi->s_fc_lock); /* * If we encountered error in Step 2, return it now after clearing * EXT4_STATE_FC_FLUSHING_DATA bit. */ if (ret) return ret; /* Step 4: Mark all inodes as being committed. */ jbd2_journal_lock_updates(journal); /* * The journal is now locked. No more handles can start and all the * previous handles are now drained. We now mark the inodes on the * commit queue as being committed. */ mutex_lock(&sbi->s_fc_lock); list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&iter->vfs_inode, EXT4_STATE_FC_COMMITTING); } mutex_unlock(&sbi->s_fc_lock); jbd2_journal_unlock_updates(journal); /* * Step 5: If file system device is different from journal device, * issue a cache flush before we start writing fast commit blocks. */ if (journal->j_fs_dev != journal->j_dev) blkdev_issue_flush(journal->j_fs_dev); blk_start_plug(&plug); /* Step 6: Write fast commit blocks to disk. */ if (sbi->s_fc_bytes == 0) { /* * Step 6.1: Add a head tag only if this is the first fast * commit in this TID. */ head.fc_features = cpu_to_le32(EXT4_FC_SUPPORTED_FEATURES); head.fc_tid = cpu_to_le32( sbi->s_journal->j_running_transaction->t_tid); if (!ext4_fc_add_tlv(sb, EXT4_FC_TAG_HEAD, sizeof(head), (u8 *)&head, &crc)) { ret = -ENOSPC; goto out; } } /* Step 6.2: Now write all the dentry updates. */ mutex_lock(&sbi->s_fc_lock); ret = ext4_fc_commit_dentry_updates(journal, &crc); if (ret) goto out; /* Step 6.3: Now write all the changed inodes to disk. */ list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { inode = &iter->vfs_inode; if (!ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) continue; ret = ext4_fc_write_inode_data(inode, &crc); if (ret) goto out; ret = ext4_fc_write_inode(inode, &crc); if (ret) goto out; } /* Step 6.4: Finally write tail tag to conclude this fast commit. */ ret = ext4_fc_write_tail(sb, crc); out: mutex_unlock(&sbi->s_fc_lock); blk_finish_plug(&plug); return ret; } static void ext4_fc_update_stats(struct super_block *sb, int status, u64 commit_time, int nblks, tid_t commit_tid) { struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats; ext4_debug("Fast commit ended with status = %d for tid %u", status, commit_tid); if (status == EXT4_FC_STATUS_OK) { stats->fc_num_commits++; stats->fc_numblks += nblks; if (likely(stats->s_fc_avg_commit_time)) stats->s_fc_avg_commit_time = (commit_time + stats->s_fc_avg_commit_time * 3) / 4; else stats->s_fc_avg_commit_time = commit_time; } else if (status == EXT4_FC_STATUS_FAILED || status == EXT4_FC_STATUS_INELIGIBLE) { if (status == EXT4_FC_STATUS_FAILED) stats->fc_failed_commits++; stats->fc_ineligible_commits++; } else { stats->fc_skipped_commits++; } trace_ext4_fc_commit_stop(sb, nblks, status, commit_tid); } /* * The main commit entry point. Performs a fast commit for transaction * commit_tid if needed. If it's not possible to perform a fast commit * due to various reasons, we fall back to full commit. Returns 0 * on success, error otherwise. */ int ext4_fc_commit(journal_t *journal, tid_t commit_tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int nblks = 0, ret, bsize = journal->j_blocksize; int subtid = atomic_read(&sbi->s_fc_subtid); int status = EXT4_FC_STATUS_OK, fc_bufs_before = 0; ktime_t start_time, commit_time; int old_ioprio, journal_ioprio; if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return jbd2_complete_transaction(journal, commit_tid); trace_ext4_fc_commit_start(sb, commit_tid); start_time = ktime_get(); old_ioprio = get_current_ioprio(); restart_fc: ret = jbd2_fc_begin_commit(journal, commit_tid); if (ret == -EALREADY) { /* There was an ongoing commit, check if we need to restart */ if (atomic_read(&sbi->s_fc_subtid) <= subtid && tid_gt(commit_tid, journal->j_commit_sequence)) goto restart_fc; ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0, commit_tid); return 0; } else if (ret) { /* * Commit couldn't start. Just update stats and perform a * full commit. */ ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0, commit_tid); return jbd2_complete_transaction(journal, commit_tid); } /* * After establishing journal barrier via jbd2_fc_begin_commit(), check * if we are fast commit ineligible. */ if (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE)) { status = EXT4_FC_STATUS_INELIGIBLE; goto fallback; } /* * Now that we know that this thread is going to do a fast commit, * elevate the priority to match that of the journal thread. */ if (journal->j_task->io_context) journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; else journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO; set_task_ioprio(current, journal_ioprio); fc_bufs_before = (sbi->s_fc_bytes + bsize - 1) / bsize; ret = ext4_fc_perform_commit(journal); if (ret < 0) { status = EXT4_FC_STATUS_FAILED; goto fallback; } nblks = (sbi->s_fc_bytes + bsize - 1) / bsize - fc_bufs_before; ret = jbd2_fc_wait_bufs(journal, nblks); if (ret < 0) { status = EXT4_FC_STATUS_FAILED; goto fallback; } atomic_inc(&sbi->s_fc_subtid); ret = jbd2_fc_end_commit(journal); set_task_ioprio(current, old_ioprio); /* * weight the commit time higher than the average time so we * don't react too strongly to vast changes in the commit time */ commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); ext4_fc_update_stats(sb, status, commit_time, nblks, commit_tid); return ret; fallback: set_task_ioprio(current, old_ioprio); ret = jbd2_fc_end_commit_fallback(journal); ext4_fc_update_stats(sb, status, 0, 0, commit_tid); return ret; } /* * Fast commit cleanup routine. This is called after every fast commit and * full commit. full is true if we are called after a full commit. */ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; struct ext4_fc_dentry_update *fc_dentry; if (full && sbi->s_fc_bh) sbi->s_fc_bh = NULL; trace_ext4_fc_cleanup(journal, full, tid); jbd2_fc_release_bufs(journal); mutex_lock(&sbi->s_fc_lock); while (!list_empty(&sbi->s_fc_q[FC_Q_MAIN])) { ei = list_first_entry(&sbi->s_fc_q[FC_Q_MAIN], struct ext4_inode_info, i_fc_list); list_del_init(&ei->i_fc_list); ext4_clear_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); if (tid_geq(tid, ei->i_sync_tid)) { ext4_fc_reset_inode(&ei->vfs_inode); } else if (full) { /* * We are called after a full commit, inode has been * modified while the commit was running. Re-enqueue * the inode into STAGING, which will then be splice * back into MAIN. This cannot happen during * fastcommit because the journal is locked all the * time in that case (and tid doesn't increase so * tid check above isn't reliable). */ list_add_tail(&ei->i_fc_list, &sbi->s_fc_q[FC_Q_STAGING]); } /* * Make sure clearing of EXT4_STATE_FC_COMMITTING is * visible before we send the wakeup. Pairs with implicit * barrier in prepare_to_wait() in ext4_fc_track_inode(). */ smp_mb(); #if (BITS_PER_LONG < 64) wake_up_bit(&ei->i_state_flags, EXT4_STATE_FC_COMMITTING); #else wake_up_bit(&ei->i_flags, EXT4_STATE_FC_COMMITTING); #endif } while (!list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) { fc_dentry = list_first_entry(&sbi->s_fc_dentry_q[FC_Q_MAIN], struct ext4_fc_dentry_update, fcd_list); list_del_init(&fc_dentry->fcd_list); list_del_init(&fc_dentry->fcd_dilist); release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); } list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING], &sbi->s_fc_dentry_q[FC_Q_MAIN]); list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_MAIN]); if (tid_geq(tid, sbi->s_fc_ineligible_tid)) { sbi->s_fc_ineligible_tid = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); } if (full) sbi->s_fc_bytes = 0; mutex_unlock(&sbi->s_fc_lock); trace_ext4_fc_stats(sb); } /* Ext4 Replay Path Routines */ /* Helper struct for dentry replay routines */ struct dentry_info_args { int parent_ino, dname_len, ino, inode_len; char *dname; }; /* Same as struct ext4_fc_tl, but uses native endianness fields */ struct ext4_fc_tl_mem { u16 fc_tag; u16 fc_len; }; static inline void tl_to_darg(struct dentry_info_args *darg, struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_dentry_info fcd; memcpy(&fcd, val, sizeof(fcd)); darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino); darg->ino = le32_to_cpu(fcd.fc_ino); darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname); darg->dname_len = tl->fc_len - sizeof(struct ext4_fc_dentry_info); } static inline void ext4_fc_get_tl(struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_tl tl_disk; memcpy(&tl_disk, val, EXT4_FC_TAG_BASE_LEN); tl->fc_len = le16_to_cpu(tl_disk.fc_len); tl->fc_tag = le16_to_cpu(tl_disk.fc_tag); } /* Unlink replay function */ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct inode *inode, *old_parent; struct qstr entry; struct dentry_info_args darg; int ret = 0; tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino, darg.parent_ino, darg.dname_len); entry.name = darg.dname; entry.len = darg.dname_len; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(old_parent)) { ext4_debug("Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; } ret = __ext4_unlink(old_parent, &entry, inode, NULL); /* -ENOENT ok coz it might not exist anymore. */ if (ret == -ENOENT) ret = 0; iput(old_parent); iput(inode); return ret; } static int ext4_fc_replay_link_internal(struct super_block *sb, struct dentry_info_args *darg, struct inode *inode) { struct inode *dir = NULL; struct dentry *dentry_dir = NULL, *dentry_inode = NULL; struct qstr qstr_dname = QSTR_INIT(darg->dname, darg->dname_len); int ret = 0; dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { ext4_debug("Dir with inode %d not found.", darg->parent_ino); dir = NULL; goto out; } dentry_dir = d_obtain_alias(dir); if (IS_ERR(dentry_dir)) { ext4_debug("Failed to obtain dentry"); dentry_dir = NULL; goto out; } dentry_inode = d_alloc(dentry_dir, &qstr_dname); if (!dentry_inode) { ext4_debug("Inode dentry not created."); ret = -ENOMEM; goto out; } ret = __ext4_link(dir, inode, dentry_inode); /* * It's possible that link already existed since data blocks * for the dir in question got persisted before we crashed OR * we replayed this tag and crashed before the entire replay * could complete. */ if (ret && ret != -EEXIST) { ext4_debug("Failed to link\n"); goto out; } ret = 0; out: if (dentry_dir) { d_drop(dentry_dir); dput(dentry_dir); } else if (dir) { iput(dir); } if (dentry_inode) { d_drop(dentry_inode); dput(dentry_inode); } return ret; } /* Link replay function */ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct inode *inode; struct dentry_info_args darg; int ret = 0; tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino, darg.parent_ino, darg.dname_len); inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); return 0; } ret = ext4_fc_replay_link_internal(sb, &darg, inode); iput(inode); return ret; } /* * Record all the modified inodes during replay. We use this later to setup * block bitmaps correctly. */ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino) { struct ext4_fc_replay_state *state; int i; state = &EXT4_SB(sb)->s_fc_replay_state; for (i = 0; i < state->fc_modified_inodes_used; i++) if (state->fc_modified_inodes[i] == ino) return 0; if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) { int *fc_modified_inodes; fc_modified_inodes = krealloc(state->fc_modified_inodes, sizeof(int) * (state->fc_modified_inodes_size + EXT4_FC_REPLAY_REALLOC_INCREMENT), GFP_KERNEL); if (!fc_modified_inodes) return -ENOMEM; state->fc_modified_inodes = fc_modified_inodes; state->fc_modified_inodes_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; } state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino; return 0; } /* * Inode replay function */ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_inode fc_inode; struct ext4_inode *raw_inode; struct ext4_inode *raw_fc_inode; struct inode *inode = NULL; struct ext4_iloc iloc; int inode_len, ino, ret, tag = tl->fc_tag; struct ext4_extent_header *eh; size_t off_gen = offsetof(struct ext4_inode, i_generation); memcpy(&fc_inode, val, sizeof(fc_inode)); ino = le32_to_cpu(fc_inode.fc_ino); trace_ext4_fc_replay(sb, tag, ino, 0, 0); inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (!IS_ERR(inode)) { ext4_ext_clear_bb(inode); iput(inode); } inode = NULL; ret = ext4_fc_record_modified_inode(sb, ino); if (ret) goto out; raw_fc_inode = (struct ext4_inode *) (val + offsetof(struct ext4_fc_inode, fc_raw_inode)); ret = ext4_get_fc_inode_loc(sb, ino, &iloc); if (ret) goto out; inode_len = tl->fc_len - sizeof(struct ext4_fc_inode); raw_inode = ext4_raw_inode(&iloc); memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); memcpy((u8 *)raw_inode + off_gen, (u8 *)raw_fc_inode + off_gen, inode_len - off_gen); if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) { eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]); if (eh->eh_magic != EXT4_EXT_MAGIC) { memset(eh, 0, sizeof(*eh)); eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16( (sizeof(raw_inode->i_block) - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent)); } } else if (le32_to_cpu(raw_inode->i_flags) & EXT4_INLINE_DATA_FL) { memcpy(raw_inode->i_block, raw_fc_inode->i_block, sizeof(raw_inode->i_block)); } /* Immediately update the inode on disk. */ ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); if (ret) goto out; ret = sync_dirty_buffer(iloc.bh); if (ret) goto out; ret = ext4_mark_inode_used(sb, ino); if (ret) goto out; /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); return -EFSCORRUPTED; } /* * Our allocator could have made different decisions than before * crashing. This should be fixed but until then, we calculate * the number of blocks the inode. */ if (!ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) ext4_ext_replay_set_iblocks(inode); inode->i_generation = le32_to_cpu(ext4_raw_inode(&iloc)->i_generation); ext4_reset_inode_seed(inode); ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode)); ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); sync_dirty_buffer(iloc.bh); brelse(iloc.bh); out: iput(inode); if (!ret) blkdev_issue_flush(sb->s_bdev); return 0; } /* * Dentry create replay function. * * EXT4_FC_TAG_CREAT is preceded by EXT4_FC_TAG_INODE_FULL. Which means, the * inode for which we are trying to create a dentry here, should already have * been replayed before we start here. */ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { int ret = 0; struct inode *inode = NULL; struct inode *dir = NULL; struct dentry_info_args darg; tl_to_darg(&darg, tl, val); trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino, darg.parent_ino, darg.dname_len); /* This takes care of update group descriptor and other metadata */ ret = ext4_mark_inode_used(sb, darg.ino); if (ret) goto out; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; goto out; } if (S_ISDIR(inode->i_mode)) { /* * If we are creating a directory, we need to make sure that the * dot and dot dot dirents are setup properly. */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { ext4_debug("Dir %d not found.", darg.ino); goto out; } ret = ext4_init_new_dir(NULL, dir, inode); iput(dir); if (ret) { ret = 0; goto out; } } ret = ext4_fc_replay_link_internal(sb, &darg, inode); if (ret) goto out; set_nlink(inode, 1); ext4_mark_inode_dirty(NULL, inode); out: iput(inode); return ret; } /* * Record physical disk regions which are in use as per fast commit area, * and used by inodes during replay phase. Our simple replay phase * allocator excludes these regions from allocation. */ int ext4_fc_record_regions(struct super_block *sb, int ino, ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay) { struct ext4_fc_replay_state *state; struct ext4_fc_alloc_region *region; state = &EXT4_SB(sb)->s_fc_replay_state; /* * during replay phase, the fc_regions_valid may not same as * fc_regions_used, update it when do new additions. */ if (replay && state->fc_regions_used != state->fc_regions_valid) state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { struct ext4_fc_alloc_region *fc_regions; fc_regions = krealloc(state->fc_regions, sizeof(struct ext4_fc_alloc_region) * (state->fc_regions_size + EXT4_FC_REPLAY_REALLOC_INCREMENT), GFP_KERNEL); if (!fc_regions) return -ENOMEM; state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; state->fc_regions = fc_regions; } region = &state->fc_regions[state->fc_regions_used++]; region->ino = ino; region->lblk = lblk; region->pblk = pblk; region->len = len; if (replay) state->fc_regions_valid++; return 0; } /* Replay add range tag */ static int ext4_fc_replay_add_range(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct ext4_fc_add_range fc_add_ex; struct ext4_extent newex, *ex; struct inode *inode; ext4_lblk_t start, cur; int remaining, len; ext4_fsblk_t start_pblk; struct ext4_map_blocks map; struct ext4_ext_path *path = NULL; int ret; memcpy(&fc_add_ex, val, sizeof(fc_add_ex)); ex = (struct ext4_extent *)&fc_add_ex.fc_ex; trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE, le32_to_cpu(fc_add_ex.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_get_actual_len(ex)); inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); if (ret) goto out; start = le32_to_cpu(ex->ee_block); start_pblk = ext4_ext_pblock(ex); len = ext4_ext_get_actual_len(ex); cur = start; remaining = len; ext4_debug("ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n", start, start_pblk, len, ext4_ext_is_unwritten(ex), inode->i_ino); while (remaining > 0) { map.m_lblk = cur; map.m_len = remaining; map.m_pblk = 0; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) goto out; if (ret == 0) { /* Range is not mapped */ path = ext4_find_extent(inode, cur, path, 0); if (IS_ERR(path)) goto out; memset(&newex, 0, sizeof(newex)); newex.ee_block = cpu_to_le32(cur); ext4_ext_store_pblock( &newex, start_pblk + cur - start); newex.ee_len = cpu_to_le16(map.m_len); if (ext4_ext_is_unwritten(ex)) ext4_ext_mark_unwritten(&newex); down_write(&EXT4_I(inode)->i_data_sem); path = ext4_ext_insert_extent(NULL, inode, path, &newex, 0); up_write((&EXT4_I(inode)->i_data_sem)); if (IS_ERR(path)) goto out; goto next; } if (start_pblk + cur - start != map.m_pblk) { /* * Logical to physical mapping changed. This can happen * if this range was removed and then reallocated to * map to new physical blocks during a fast commit. */ ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), start_pblk + cur - start); if (ret) goto out; /* * Mark the old blocks as free since they aren't used * anymore. We maintain an array of all the modified * inodes. In case these blocks are still used at either * a different logical range in the same inode or in * some different inode, we will mark them as allocated * at the end of the FC replay using our array of * modified inodes. */ ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); goto next; } /* Range is mapped and needs a state change */ ext4_debug("Converting from %ld to %d %lld", map.m_flags & EXT4_MAP_UNWRITTEN, ext4_ext_is_unwritten(ex), map.m_pblk); ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), map.m_pblk); if (ret) goto out; /* * We may have split the extent tree while toggling the state. * Try to shrink the extent tree now. */ ext4_ext_replay_shrink_inode(inode, start + len); next: cur += map.m_len; remaining -= map.m_len; } ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); out: ext4_free_ext_path(path); iput(inode); return 0; } /* Replay DEL_RANGE tag */ static int ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl_mem *tl, u8 *val) { struct inode *inode; struct ext4_fc_del_range lrange; struct ext4_map_blocks map; ext4_lblk_t cur, remaining; int ret; memcpy(&lrange, val, sizeof(lrange)); cur = le32_to_cpu(lrange.fc_lblk); remaining = le32_to_cpu(lrange.fc_len); trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE, le32_to_cpu(lrange.fc_ino), cur, remaining); inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode %d not found", le32_to_cpu(lrange.fc_ino)); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); if (ret) goto out; ext4_debug("DEL_RANGE, inode %ld, lblk %d, len %d\n", inode->i_ino, le32_to_cpu(lrange.fc_lblk), le32_to_cpu(lrange.fc_len)); while (remaining > 0) { map.m_lblk = cur; map.m_len = remaining; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) goto out; if (ret > 0) { remaining -= ret; cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); } else { remaining -= map.m_len; cur += map.m_len; } } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_remove_space(inode, le32_to_cpu(lrange.fc_lblk), le32_to_cpu(lrange.fc_lblk) + le32_to_cpu(lrange.fc_len) - 1); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out; ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); ext4_mark_inode_dirty(NULL, inode); out: iput(inode); return 0; } static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) { struct ext4_fc_replay_state *state; struct inode *inode; struct ext4_ext_path *path = NULL; struct ext4_map_blocks map; int i, ret, j; ext4_lblk_t cur, end; state = &EXT4_SB(sb)->s_fc_replay_state; for (i = 0; i < state->fc_modified_inodes_used; i++) { inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode %d not found.", state->fc_modified_inodes[i]); continue; } cur = 0; end = EXT_MAX_BLOCKS; if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) { iput(inode); continue; } while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, path, 0); if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, true); } else { path = NULL; } cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, true); } else { cur = cur + (map.m_len ? map.m_len : 1); } } iput(inode); } ext4_free_ext_path(path); } /* * Check if block is in excluded regions for block allocation. The simple * allocator that runs during replay phase is calls this function to see * if it is okay to use a block. */ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk) { int i; struct ext4_fc_replay_state *state; state = &EXT4_SB(sb)->s_fc_replay_state; for (i = 0; i < state->fc_regions_valid; i++) { if (state->fc_regions[i].ino == 0 || state->fc_regions[i].len == 0) continue; if (in_range(blk, state->fc_regions[i].pblk, state->fc_regions[i].len)) return true; } return false; } /* Cleanup function called after replay */ void ext4_fc_replay_cleanup(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); sbi->s_mount_state &= ~EXT4_FC_REPLAY; kfree(sbi->s_fc_replay_state.fc_regions); kfree(sbi->s_fc_replay_state.fc_modified_inodes); } static bool ext4_fc_value_len_isvalid(struct ext4_sb_info *sbi, int tag, int len) { switch (tag) { case EXT4_FC_TAG_ADD_RANGE: return len == sizeof(struct ext4_fc_add_range); case EXT4_FC_TAG_DEL_RANGE: return len == sizeof(struct ext4_fc_del_range); case EXT4_FC_TAG_CREAT: case EXT4_FC_TAG_LINK: case EXT4_FC_TAG_UNLINK: len -= sizeof(struct ext4_fc_dentry_info); return len >= 1 && len <= EXT4_NAME_LEN; case EXT4_FC_TAG_INODE: len -= sizeof(struct ext4_fc_inode); return len >= EXT4_GOOD_OLD_INODE_SIZE && len <= sbi->s_inode_size; case EXT4_FC_TAG_PAD: return true; /* padding can have any length */ case EXT4_FC_TAG_TAIL: return len >= sizeof(struct ext4_fc_tail); case EXT4_FC_TAG_HEAD: return len == sizeof(struct ext4_fc_head); } return false; } /* * Recovery Scan phase handler * * This function is called during the scan phase and is responsible * for doing following things: * - Make sure the fast commit area has valid tags for replay * - Count number of tags that need to be replayed by the replay handler * - Verify CRC * - Create a list of excluded blocks for allocation during replay phase * * This function returns JBD2_FC_REPLAY_CONTINUE to indicate that SCAN is * incomplete and JBD2 should send more blocks. It returns JBD2_FC_REPLAY_STOP * to indicate that scan has finished and JBD2 can now start replay phase. * It returns a negative error to indicate that there was an error. At the end * of a successful scan phase, sbi->s_fc_replay_state.fc_replay_num_tags is set * to indicate the number of tags that need to replayed during the replay phase. */ static int ext4_fc_replay_scan(journal_t *journal, struct buffer_head *bh, int off, tid_t expected_tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_replay_state *state; int ret = JBD2_FC_REPLAY_CONTINUE; struct ext4_fc_add_range ext; struct ext4_fc_tl_mem tl; struct ext4_fc_tail tail; __u8 *start, *end, *cur, *val; struct ext4_fc_head head; struct ext4_extent *ex; state = &sbi->s_fc_replay_state; start = (u8 *)bh->b_data; end = start + journal->j_blocksize; if (state->fc_replay_expected_off == 0) { state->fc_cur_tag = 0; state->fc_replay_num_tags = 0; state->fc_crc = 0; state->fc_regions = NULL; state->fc_regions_valid = state->fc_regions_used = state->fc_regions_size = 0; /* Check if we can stop early */ if (le16_to_cpu(((struct ext4_fc_tl *)start)->fc_tag) != EXT4_FC_TAG_HEAD) return 0; } if (off != state->fc_replay_expected_off) { ret = -EFSCORRUPTED; goto out_err; } state->fc_replay_expected_off++; for (cur = start; cur <= end - EXT4_FC_TAG_BASE_LEN; cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) { ext4_fc_get_tl(&tl, cur); val = cur + EXT4_FC_TAG_BASE_LEN; if (tl.fc_len > end - val || !ext4_fc_value_len_isvalid(sbi, tl.fc_tag, tl.fc_len)) { ret = state->fc_replay_num_tags ? JBD2_FC_REPLAY_STOP : -ECANCELED; goto out_err; } ext4_debug("Scan phase, tag:%s, blk %lld\n", tag2str(tl.fc_tag), bh->b_blocknr); switch (tl.fc_tag) { case EXT4_FC_TAG_ADD_RANGE: memcpy(&ext, val, sizeof(ext)); ex = (struct ext4_extent *)&ext.fc_ex; ret = ext4_fc_record_regions(sb, le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_get_actual_len(ex), 0); if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE; fallthrough; case EXT4_FC_TAG_DEL_RANGE: case EXT4_FC_TAG_LINK: case EXT4_FC_TAG_UNLINK: case EXT4_FC_TAG_CREAT: case EXT4_FC_TAG_INODE: case EXT4_FC_TAG_PAD: state->fc_cur_tag++; state->fc_crc = ext4_chksum(state->fc_crc, cur, EXT4_FC_TAG_BASE_LEN + tl.fc_len); break; case EXT4_FC_TAG_TAIL: state->fc_cur_tag++; memcpy(&tail, val, sizeof(tail)); state->fc_crc = ext4_chksum(state->fc_crc, cur, EXT4_FC_TAG_BASE_LEN + offsetof(struct ext4_fc_tail, fc_crc)); if (le32_to_cpu(tail.fc_tid) == expected_tid && le32_to_cpu(tail.fc_crc) == state->fc_crc) { state->fc_replay_num_tags = state->fc_cur_tag; state->fc_regions_valid = state->fc_regions_used; } else { ret = state->fc_replay_num_tags ? JBD2_FC_REPLAY_STOP : -EFSBADCRC; } state->fc_crc = 0; break; case EXT4_FC_TAG_HEAD: memcpy(&head, val, sizeof(head)); if (le32_to_cpu(head.fc_features) & ~EXT4_FC_SUPPORTED_FEATURES) { ret = -EOPNOTSUPP; break; } if (le32_to_cpu(head.fc_tid) != expected_tid) { ret = JBD2_FC_REPLAY_STOP; break; } state->fc_cur_tag++; state->fc_crc = ext4_chksum(state->fc_crc, cur, EXT4_FC_TAG_BASE_LEN + tl.fc_len); break; default: ret = state->fc_replay_num_tags ? JBD2_FC_REPLAY_STOP : -ECANCELED; } if (ret < 0 || ret == JBD2_FC_REPLAY_STOP) break; } out_err: trace_ext4_fc_replay_scan(sb, ret, off); return ret; } /* * Main recovery path entry point. * The meaning of return codes is similar as above. */ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_tl_mem tl; __u8 *start, *end, *cur, *val; int ret = JBD2_FC_REPLAY_CONTINUE; struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state; struct ext4_fc_tail tail; if (pass == PASS_SCAN) { state->fc_current_pass = PASS_SCAN; return ext4_fc_replay_scan(journal, bh, off, expected_tid); } if (state->fc_current_pass != pass) { state->fc_current_pass = pass; sbi->s_mount_state |= EXT4_FC_REPLAY; } if (!sbi->s_fc_replay_state.fc_replay_num_tags) { ext4_debug("Replay stops\n"); ext4_fc_set_bitmaps_and_counters(sb); return 0; } #ifdef CONFIG_EXT4_DEBUG if (sbi->s_fc_debug_max_replay && off >= sbi->s_fc_debug_max_replay) { pr_warn("Dropping fc block %d because max_replay set\n", off); return JBD2_FC_REPLAY_STOP; } #endif start = (u8 *)bh->b_data; end = start + journal->j_blocksize; for (cur = start; cur <= end - EXT4_FC_TAG_BASE_LEN; cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) { ext4_fc_get_tl(&tl, cur); val = cur + EXT4_FC_TAG_BASE_LEN; if (state->fc_replay_num_tags == 0) { ret = JBD2_FC_REPLAY_STOP; ext4_fc_set_bitmaps_and_counters(sb); break; } ext4_debug("Replay phase, tag:%s\n", tag2str(tl.fc_tag)); state->fc_replay_num_tags--; switch (tl.fc_tag) { case EXT4_FC_TAG_LINK: ret = ext4_fc_replay_link(sb, &tl, val); break; case EXT4_FC_TAG_UNLINK: ret = ext4_fc_replay_unlink(sb, &tl, val); break; case EXT4_FC_TAG_ADD_RANGE: ret = ext4_fc_replay_add_range(sb, &tl, val); break; case EXT4_FC_TAG_CREAT: ret = ext4_fc_replay_create(sb, &tl, val); break; case EXT4_FC_TAG_DEL_RANGE: ret = ext4_fc_replay_del_range(sb, &tl, val); break; case EXT4_FC_TAG_INODE: ret = ext4_fc_replay_inode(sb, &tl, val); break; case EXT4_FC_TAG_PAD: trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0, tl.fc_len, 0); break; case EXT4_FC_TAG_TAIL: trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0, tl.fc_len, 0); memcpy(&tail, val, sizeof(tail)); WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid); break; case EXT4_FC_TAG_HEAD: break; default: trace_ext4_fc_replay(sb, tl.fc_tag, 0, tl.fc_len, 0); ret = -ECANCELED; break; } if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE; } return ret; } void ext4_fc_init(struct super_block *sb, journal_t *journal) { /* * We set replay callback even if fast commit disabled because we may * could still have fast commit blocks that need to be replayed even if * fast commit has now been turned off. */ journal->j_fc_replay_callback = ext4_fc_replay; if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return; journal->j_fc_cleanup_callback = ext4_fc_cleanup; } static const char * const fc_ineligible_reasons[] = { [EXT4_FC_REASON_XATTR] = "Extended attributes changed", [EXT4_FC_REASON_CROSS_RENAME] = "Cross rename", [EXT4_FC_REASON_JOURNAL_FLAG_CHANGE] = "Journal flag changed", [EXT4_FC_REASON_NOMEM] = "Insufficient memory", [EXT4_FC_REASON_SWAP_BOOT] = "Swap boot", [EXT4_FC_REASON_RESIZE] = "Resize", [EXT4_FC_REASON_RENAME_DIR] = "Dir renamed", [EXT4_FC_REASON_FALLOC_RANGE] = "Falloc range op", [EXT4_FC_REASON_INODE_JOURNAL_DATA] = "Data journalling", [EXT4_FC_REASON_ENCRYPTED_FILENAME] = "Encrypted filename", }; int ext4_fc_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *)seq->private); struct ext4_fc_stats *stats = &sbi->s_fc_stats; int i; if (v != SEQ_START_TOKEN) return 0; seq_printf(seq, "fc stats:\n%ld commits\n%ld ineligible\n%ld numblks\n%lluus avg_commit_time\n", stats->fc_num_commits, stats->fc_ineligible_commits, stats->fc_numblks, div_u64(stats->s_fc_avg_commit_time, 1000)); seq_puts(seq, "Ineligible reasons:\n"); for (i = 0; i < EXT4_FC_REASON_MAX; i++) seq_printf(seq, "\"%s\":\t%d\n", fc_ineligible_reasons[i], stats->fc_ineligible_reason_count[i]); return 0; } int __init ext4_fc_init_dentry_cache(void) { ext4_fc_dentry_cachep = KMEM_CACHE(ext4_fc_dentry_update, SLAB_RECLAIM_ACCOUNT); if (ext4_fc_dentry_cachep == NULL) return -ENOMEM; return 0; } void ext4_fc_destroy_dentry_cache(void) { kmem_cache_destroy(ext4_fc_dentry_cachep); } |
| 8914 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_INTERNAL_H #define __X86_KERNEL_FPU_INTERNAL_H extern struct fpstate init_fpstate; /* CPU feature check wrappers */ static __always_inline __pure bool use_xsave(void) { return cpu_feature_enabled(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return cpu_feature_enabled(X86_FEATURE_FXSR); } #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; }) #endif /* Used in init.c */ extern void fpstate_init_user(struct fpstate *fpstate); extern void fpstate_reset(struct fpu *fpu); #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 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 | // SPDX-License-Identifier: GPL-2.0 /* * hrtimers - High-resolution kernel timers * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes * * Started by: Thomas Gleixner and Ingo Molnar */ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> #include <linux/hrtimer_types.h> #include <linux/init.h> #include <linux/list.h> #include <linux/percpu-defs.h> #include <linux/rbtree.h> #include <linux/timer.h> /* * Mode arguments of xxx_hrtimer functions: * * HRTIMER_MODE_ABS - Time value is absolute * HRTIMER_MODE_REL - Time value is relative to now * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered * when starting the timer) * HRTIMER_MODE_SOFT - Timer callback function will be executed in * soft irq context * HRTIMER_MODE_HARD - Timer callback function will be executed in * hard irq context even on PREEMPT_RT. */ enum hrtimer_mode { HRTIMER_MODE_ABS = 0x00, HRTIMER_MODE_REL = 0x01, HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, HRTIMER_MODE_HARD = 0x08, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, }; /* * Values to track state of the timer * * Possible states: * * 0x00 inactive * 0x01 enqueued into rbtree * * The callback state is not part of the timer->state because clearing it would * mean touching the timer after the callback, this makes it impossible to free * the timer from the callback function. * * Therefore we track the callback state in: * * timer->base->cpu_base->running == timer * * On SMP it is possible to have a "callback function running and enqueued" * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 /** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up * * task is set to NULL, when the timer expires. */ struct hrtimer_sleeper { struct hrtimer timer; struct task_struct *task; }; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { timer->node.expires = tv64; timer->_softexpires = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { return timer->node.expires; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) { return ktime_to_ns(timer->node.expires); } static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { return ktime_sub(timer->node.expires, timer->base->get_time()); } static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) { return timer->base->get_time(); } static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? timer->base->cpu_base->hres_active : 0; } #ifdef CONFIG_HIGH_RES_TIMERS struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); extern unsigned int hrtimer_resolution; #else #define hrtimer_resolution (unsigned int)LOW_RES_NSEC #endif static inline ktime_t __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) { ktime_t rem = ktime_sub(timer->node.expires, now); /* * Adjust relative timers for the extra we added in * hrtimer_start_range_ns() to prevent short timeouts. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) rem -= hrtimer_resolution; return rem; } static inline ktime_t hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) { return __hrtimer_expires_remaining_adjusted(timer, timer->base->get_time()); } #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); extern void timerfd_resume(void); #else static inline void timerfd_clock_was_set(void) { } static inline void timerfd_resume(void) { } #endif DECLARE_PER_CPU(struct tick_device, tick_cpu_device); #ifdef CONFIG_PREEMPT_RT void hrtimer_cancel_wait_running(const struct hrtimer *timer); #else static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) { cpu_relax(); } #endif static inline enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) { return HRTIMER_NORESTART; } /* Exported timer functions: */ /* Initialize timers: */ extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { hrtimer_start_range_ns(timer, tim, 0, mode); } extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); hrtimer_start_range_ns(timer, soft, delta, mode); } void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode); static inline void hrtimer_restart(struct hrtimer *timer) { hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read */ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { return __hrtimer_get_remaining(timer, false); } extern u64 hrtimer_get_next_event(void); extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); /** * hrtimer_is_queued - check, whether the timer is on one of the queues * @timer: Timer to check * * Returns: True if the timer is queued, false otherwise * * The function can be used lockless, but it gives only a current snapshot. */ static inline bool hrtimer_is_queued(struct hrtimer *timer) { /* The READ_ONCE pairs with the update functions of timer->state */ return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* * Helper function to check, whether the timer is running the callback * function */ static inline int hrtimer_callback_running(struct hrtimer *timer) { return timer->base->running == timer; } /** * hrtimer_update_function - Update the timer's callback function * @timer: Timer to update * @function: New callback function * * Only safe to call if the timer is not enqueued. Can be called in the callback function if the * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED). */ static inline void hrtimer_update_function(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *)) { #ifdef CONFIG_PROVE_LOCKING guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); if (WARN_ON_ONCE(hrtimer_is_queued(timer))) return; if (WARN_ON_ONCE(!function)) return; #endif ACCESS_PRIVATE(timer, function) = function; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /** * hrtimer_forward_now() - forward the timer expiry so it expires after now * @timer: hrtimer to forward * @interval: the interval to forward * * It is a variant of hrtimer_forward(). The timer will expire after the current * time of the hrtimer clock base. See hrtimer_forward() for details. */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { return hrtimer_forward(timer, timer->base->get_time(), interval); } /* Precise sleep: */ extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); /* Show pending timers: */ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); int hrtimers_cpu_starting(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else #define hrtimers_cpu_dying NULL #endif #endif |
| 157 157 157 34 3 37 37 151 152 152 123 4 24 115 96 19 150 32 129 150 118 18 100 1 2 1 96 4 118 114 4 6 6 2 4 4 4 127 93 76 23 1 53 128 127 1 61 61 61 61 195 195 43 21 55 2 6 6 6 6 44 21 61 78 78 77 71 1 72 71 75 75 2 74 47 2 7 46 1 53 53 1 21 76 76 74 1 52 74 74 2 74 75 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * localalloc.c * * Node local data allocation * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/bitops.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "blockcheck.h" #include "dlmglue.h" #include "inode.h" #include "journal.h" #include "localalloc.h" #include "suballoc.h" #include "super.h" #include "sysfile.h" #include "ocfs2_trace.h" #include "buffer_head_io.h" #define OCFS2_LOCAL_ALLOC(dinode) (&((dinode)->id2.i_lab)) static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc); static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, struct ocfs2_dinode *alloc, u32 *numbits, struct ocfs2_alloc_reservation *resv); static void ocfs2_clear_local_alloc(struct ocfs2_dinode *alloc); static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_dinode *alloc, struct inode *main_bm_inode, struct buffer_head *main_bm_bh); static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb, struct ocfs2_alloc_context **ac, struct inode **bitmap_inode, struct buffer_head **bitmap_bh); static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac); static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, struct inode *local_alloc_inode); /* * ocfs2_la_default_mb() - determine a default size, in megabytes of * the local alloc. * * Generally, we'd like to pick as large a local alloc as * possible. Performance on large workloads tends to scale * proportionally to la size. In addition to that, the reservations * code functions more efficiently as it can reserve more windows for * write. * * Some things work against us when trying to choose a large local alloc: * * - We need to ensure our sizing is picked to leave enough space in * group descriptors for other allocations (such as block groups, * etc). Picking default sizes which are a multiple of 4 could help * - block groups are allocated in 2mb and 4mb chunks. * * - Likewise, we don't want to starve other nodes of bits on small * file systems. This can easily be taken care of by limiting our * default to a reasonable size (256M) on larger cluster sizes. * * - Some file systems can't support very large sizes - 4k and 8k in * particular are limited to less than 128 and 256 megabytes respectively. * * The following reference table shows group descriptor and local * alloc maximums at various cluster sizes (4k blocksize) * * csize: 4K group: 126M la: 121M * csize: 8K group: 252M la: 243M * csize: 16K group: 504M la: 486M * csize: 32K group: 1008M la: 972M * csize: 64K group: 2016M la: 1944M * csize: 128K group: 4032M la: 3888M * csize: 256K group: 8064M la: 7776M * csize: 512K group: 16128M la: 15552M * csize: 1024K group: 32256M la: 31104M */ #define OCFS2_LA_MAX_DEFAULT_MB 256 #define OCFS2_LA_OLD_DEFAULT 8 unsigned int ocfs2_la_default_mb(struct ocfs2_super *osb) { unsigned int la_mb; unsigned int gd_mb; unsigned int la_max_mb; unsigned int megs_per_slot; struct super_block *sb = osb->sb; gd_mb = ocfs2_clusters_to_megabytes(osb->sb, 8 * ocfs2_group_bitmap_size(sb, 0, osb->s_feature_incompat)); /* * This takes care of files systems with very small group * descriptors - 512 byte blocksize at cluster sizes lower * than 16K and also 1k blocksize with 4k cluster size. */ if ((sb->s_blocksize == 512 && osb->s_clustersize <= 8192) || (sb->s_blocksize == 1024 && osb->s_clustersize == 4096)) return OCFS2_LA_OLD_DEFAULT; /* * Leave enough room for some block groups and make the final * value we work from a multiple of 4. */ gd_mb -= 16; gd_mb &= 0xFFFFFFFB; la_mb = gd_mb; /* * Keep window sizes down to a reasonable default */ if (la_mb > OCFS2_LA_MAX_DEFAULT_MB) { /* * Some clustersize / blocksize combinations will have * given us a larger than OCFS2_LA_MAX_DEFAULT_MB * default size, but get poor distribution when * limited to exactly 256 megabytes. * * As an example, 16K clustersize at 4K blocksize * gives us a cluster group size of 504M. Paring the * local alloc size down to 256 however, would give us * only one window and around 200MB left in the * cluster group. Instead, find the first size below * 256 which would give us an even distribution. * * Larger cluster group sizes actually work out pretty * well when pared to 256, so we don't have to do this * for any group that fits more than two * OCFS2_LA_MAX_DEFAULT_MB windows. */ if (gd_mb > (2 * OCFS2_LA_MAX_DEFAULT_MB)) la_mb = 256; else { unsigned int gd_mult = gd_mb; while (gd_mult > 256) gd_mult = gd_mult >> 1; la_mb = gd_mult; } } megs_per_slot = osb->osb_clusters_at_boot / osb->max_slots; megs_per_slot = ocfs2_clusters_to_megabytes(osb->sb, megs_per_slot); /* Too many nodes, too few disk clusters. */ if (megs_per_slot < la_mb) la_mb = megs_per_slot; /* We can't store more bits than we can in a block. */ la_max_mb = ocfs2_clusters_to_megabytes(osb->sb, ocfs2_local_alloc_size(sb) * 8); if (la_mb > la_max_mb) la_mb = la_max_mb; return la_mb; } void ocfs2_la_set_sizes(struct ocfs2_super *osb, int requested_mb) { struct super_block *sb = osb->sb; unsigned int la_default_mb = ocfs2_la_default_mb(osb); unsigned int la_max_mb; la_max_mb = ocfs2_clusters_to_megabytes(sb, ocfs2_local_alloc_size(sb) * 8); trace_ocfs2_la_set_sizes(requested_mb, la_max_mb, la_default_mb); if (requested_mb == -1) { /* No user request - use defaults */ osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, la_default_mb); } else if (requested_mb > la_max_mb) { /* Request is too big, we give the maximum available */ osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, la_max_mb); } else { osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, requested_mb); } osb->local_alloc_bits = osb->local_alloc_default_bits; } static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb) { return (osb->local_alloc_state == OCFS2_LA_THROTTLED || osb->local_alloc_state == OCFS2_LA_ENABLED); } void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb, unsigned int num_clusters) { if (num_clusters >= osb->local_alloc_default_bits) { spin_lock(&osb->osb_lock); if (osb->local_alloc_state == OCFS2_LA_DISABLED || osb->local_alloc_state == OCFS2_LA_THROTTLED) { cancel_delayed_work(&osb->la_enable_wq); osb->local_alloc_state = OCFS2_LA_ENABLED; } spin_unlock(&osb->osb_lock); } } void ocfs2_la_enable_worker(struct work_struct *work) { struct ocfs2_super *osb = container_of(work, struct ocfs2_super, la_enable_wq.work); spin_lock(&osb->osb_lock); osb->local_alloc_state = OCFS2_LA_ENABLED; spin_unlock(&osb->osb_lock); } /* * Tell us whether a given allocation should use the local alloc * file. Otherwise, it has to go to the main bitmap. * * This function does semi-dirty reads of local alloc size and state! * This is ok however, as the values are re-checked once under mutex. */ int ocfs2_alloc_should_use_local(struct ocfs2_super *osb, u64 bits) { int ret = 0; int la_bits; spin_lock(&osb->osb_lock); la_bits = osb->local_alloc_bits; if (!ocfs2_la_state_enabled(osb)) goto bail; /* la_bits should be at least twice the size (in clusters) of * a new block group. We want to be sure block group * allocations go through the local alloc, so allow an * allocation to take up to half the bitmap. */ if (bits > (la_bits / 2)) goto bail; ret = 1; bail: trace_ocfs2_alloc_should_use_local( (unsigned long long)bits, osb->local_alloc_state, la_bits, ret); spin_unlock(&osb->osb_lock); return ret; } int ocfs2_load_local_alloc(struct ocfs2_super *osb) { int status = 0; struct ocfs2_dinode *alloc = NULL; struct buffer_head *alloc_bh = NULL; u32 num_used; struct inode *inode = NULL; struct ocfs2_local_alloc *la; if (osb->local_alloc_bits == 0) goto bail; if (osb->local_alloc_bits >= osb->bitmap_cpg) { mlog(ML_NOTICE, "Requested local alloc window %d is larger " "than max possible %u. Using defaults.\n", osb->local_alloc_bits, (osb->bitmap_cpg - 1)); osb->local_alloc_bits = ocfs2_megabytes_to_clusters(osb->sb, ocfs2_la_default_mb(osb)); } /* read the alloc off disk */ inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, osb->slot_num); if (!inode) { status = -EINVAL; mlog_errno(status); goto bail; } status = ocfs2_read_inode_block_full(inode, &alloc_bh, OCFS2_BH_IGNORE_CACHE); if (status < 0) { mlog_errno(status); goto bail; } alloc = (struct ocfs2_dinode *) alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); if (!(le32_to_cpu(alloc->i_flags) & (OCFS2_LOCAL_ALLOC_FL|OCFS2_BITMAP_FL))) { mlog(ML_ERROR, "Invalid local alloc inode, %llu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); status = -EINVAL; goto bail; } if ((la->la_size == 0) || (le16_to_cpu(la->la_size) > ocfs2_local_alloc_size(inode->i_sb))) { mlog(ML_ERROR, "Local alloc size is invalid (la_size = %u)\n", le16_to_cpu(la->la_size)); status = -EINVAL; goto bail; } /* do a little verification. */ num_used = ocfs2_local_alloc_count_bits(alloc); /* hopefully the local alloc has always been recovered before * we load it. */ if (num_used || alloc->id1.bitmap1.i_used || alloc->id1.bitmap1.i_total || la->la_bm_off) { mlog(ML_ERROR, "inconsistent detected, clean journal with" " unrecovered local alloc, please run fsck.ocfs2!\n" "found = %u, set = %u, taken = %u, off = %u\n", num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), le32_to_cpu(alloc->id1.bitmap1.i_total), le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off)); status = -EINVAL; goto bail; } osb->local_alloc_bh = alloc_bh; osb->local_alloc_state = OCFS2_LA_ENABLED; bail: if (status < 0) brelse(alloc_bh); iput(inode); trace_ocfs2_load_local_alloc(osb->local_alloc_bits); if (status) mlog_errno(status); return status; } /* * return any unused bits to the bitmap and write out a clean * local_alloc. * * local_alloc_bh is optional. If not passed, we will simply use the * one off osb. If you do pass it however, be warned that it *will* be * returned brelse'd and NULL'd out.*/ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) { int status; handle_t *handle; struct inode *local_alloc_inode = NULL; struct buffer_head *bh = NULL; struct buffer_head *main_bm_bh = NULL; struct inode *main_bm_inode = NULL; struct ocfs2_dinode *alloc_copy = NULL; struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); if (osb->ocfs2_wq) flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; local_alloc_inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, osb->slot_num); if (!local_alloc_inode) { status = -ENOENT; mlog_errno(status); goto out; } osb->local_alloc_state = OCFS2_LA_DISABLED; ocfs2_resmap_uninit(&osb->osb_la_resmap); main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); if (!main_bm_inode) { status = -EINVAL; mlog_errno(status); goto out; } inode_lock(main_bm_inode); status = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1); if (status < 0) { mlog_errno(status); goto out_mutex; } /* WINDOW_MOVE_CREDITS is a bit heavy... */ handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS); if (IS_ERR(handle)) { mlog_errno(PTR_ERR(handle)); handle = NULL; goto out_unlock; } bh = osb->local_alloc_bh; alloc = (struct ocfs2_dinode *) bh->b_data; alloc_copy = kmemdup(alloc, bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; goto out_commit; } status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_commit; } ocfs2_clear_local_alloc(alloc); ocfs2_journal_dirty(handle, bh); brelse(bh); osb->local_alloc_bh = NULL; osb->local_alloc_state = OCFS2_LA_UNUSED; status = ocfs2_sync_local_to_main(osb, handle, alloc_copy, main_bm_inode, main_bm_bh); if (status < 0) mlog_errno(status); out_commit: ocfs2_commit_trans(osb, handle); out_unlock: brelse(main_bm_bh); ocfs2_inode_unlock(main_bm_inode, 1); out_mutex: inode_unlock(main_bm_inode); iput(main_bm_inode); out: iput(local_alloc_inode); kfree(alloc_copy); } /* * We want to free the bitmap bits outside of any recovery context as * we'll need a cluster lock to do so, but we must clear the local * alloc before giving up the recovered nodes journal. To solve this, * we kmalloc a copy of the local alloc before it's change for the * caller to process with ocfs2_complete_local_alloc_recovery */ int ocfs2_begin_local_alloc_recovery(struct ocfs2_super *osb, int slot_num, struct ocfs2_dinode **alloc_copy) { int status = 0; struct buffer_head *alloc_bh = NULL; struct inode *inode = NULL; struct ocfs2_dinode *alloc; trace_ocfs2_begin_local_alloc_recovery(slot_num); *alloc_copy = NULL; inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, slot_num); if (!inode) { status = -EINVAL; mlog_errno(status); goto bail; } inode_lock(inode); status = ocfs2_read_inode_block_full(inode, &alloc_bh, OCFS2_BH_IGNORE_CACHE); if (status < 0) { mlog_errno(status); goto bail; } *alloc_copy = kmalloc(alloc_bh->b_size, GFP_KERNEL); if (!(*alloc_copy)) { status = -ENOMEM; goto bail; } memcpy((*alloc_copy), alloc_bh->b_data, alloc_bh->b_size); alloc = (struct ocfs2_dinode *) alloc_bh->b_data; ocfs2_clear_local_alloc(alloc); ocfs2_compute_meta_ecc(osb->sb, alloc_bh->b_data, &alloc->i_check); status = ocfs2_write_block(osb, alloc_bh, INODE_CACHE(inode)); if (status < 0) mlog_errno(status); bail: if (status < 0) { kfree(*alloc_copy); *alloc_copy = NULL; } brelse(alloc_bh); if (inode) { inode_unlock(inode); iput(inode); } if (status) mlog_errno(status); return status; } /* * Step 2: By now, we've completed the journal recovery, we've stamped * a clean local alloc on disk and dropped the node out of the * recovery map. Dlm locks will no longer stall, so lets clear out the * main bitmap. */ int ocfs2_complete_local_alloc_recovery(struct ocfs2_super *osb, struct ocfs2_dinode *alloc) { int status; handle_t *handle; struct buffer_head *main_bm_bh = NULL; struct inode *main_bm_inode; main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); if (!main_bm_inode) { status = -EINVAL; mlog_errno(status); goto out; } inode_lock(main_bm_inode); status = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1); if (status < 0) { mlog_errno(status); goto out_mutex; } handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto out_unlock; } /* we want the bitmap change to be recorded on disk asap */ handle->h_sync = 1; status = ocfs2_sync_local_to_main(osb, handle, alloc, main_bm_inode, main_bm_bh); if (status < 0) mlog_errno(status); ocfs2_commit_trans(osb, handle); out_unlock: ocfs2_inode_unlock(main_bm_inode, 1); out_mutex: inode_unlock(main_bm_inode); brelse(main_bm_bh); iput(main_bm_inode); out: if (!status) ocfs2_init_steal_slots(osb); if (status) mlog_errno(status); return status; } /* * make sure we've got at least bits_wanted contiguous bits in the * local alloc. You lose them when you drop i_rwsem. * * We will add ourselves to the transaction passed in, but may start * our own in order to shift windows. */ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, u32 bits_wanted, struct ocfs2_alloc_context *ac) { int status; struct ocfs2_dinode *alloc; struct inode *local_alloc_inode; unsigned int free_bits; BUG_ON(!ac); local_alloc_inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, osb->slot_num); if (!local_alloc_inode) { status = -ENOENT; mlog_errno(status); goto bail; } inode_lock(local_alloc_inode); /* * We must double check state and allocator bits because * another process may have changed them while holding i_rwsem. */ spin_lock(&osb->osb_lock); if (!ocfs2_la_state_enabled(osb) || (bits_wanted > osb->local_alloc_bits)) { spin_unlock(&osb->osb_lock); status = -ENOSPC; goto bail; } spin_unlock(&osb->osb_lock); alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; #ifdef CONFIG_OCFS2_DEBUG_FS if (le32_to_cpu(alloc->id1.bitmap1.i_used) != ocfs2_local_alloc_count_bits(alloc)) { status = ocfs2_error(osb->sb, "local alloc inode %llu says it has %u used bits, but a count shows %u\n", (unsigned long long)le64_to_cpu(alloc->i_blkno), le32_to_cpu(alloc->id1.bitmap1.i_used), ocfs2_local_alloc_count_bits(alloc)); goto bail; } #endif free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) - le32_to_cpu(alloc->id1.bitmap1.i_used); if (bits_wanted > free_bits) { /* uhoh, window change time. */ status = ocfs2_local_alloc_slide_window(osb, local_alloc_inode); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } /* * Under certain conditions, the window slide code * might have reduced the number of bits available or * disabled the local alloc entirely. Re-check * here and return -ENOSPC if necessary. */ status = -ENOSPC; if (!ocfs2_la_state_enabled(osb)) goto bail; free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) - le32_to_cpu(alloc->id1.bitmap1.i_used); if (bits_wanted > free_bits) goto bail; } ac->ac_inode = local_alloc_inode; /* We should never use localalloc from another slot */ ac->ac_alloc_slot = osb->slot_num; ac->ac_which = OCFS2_AC_USE_LOCAL; get_bh(osb->local_alloc_bh); ac->ac_bh = osb->local_alloc_bh; status = 0; bail: if (status < 0 && local_alloc_inode) { inode_unlock(local_alloc_inode); iput(local_alloc_inode); } trace_ocfs2_reserve_local_alloc_bits( (unsigned long long)ac->ac_max_block, bits_wanted, osb->slot_num, status); if (status) mlog_errno(status); return status; } int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac, u32 bits_wanted, u32 *bit_off, u32 *num_bits) { int status, start; struct inode *local_alloc_inode; void *bitmap; struct ocfs2_dinode *alloc; struct ocfs2_local_alloc *la; BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL); local_alloc_inode = ac->ac_inode; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); start = ocfs2_local_alloc_find_clear_bits(osb, alloc, &bits_wanted, ac->ac_resv); if (start == -1) { /* TODO: Shouldn't we just BUG here? */ status = -ENOSPC; mlog_errno(status); goto bail; } bitmap = la->la_bitmap; *bit_off = le32_to_cpu(la->la_bm_off) + start; *num_bits = bits_wanted; status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), osb->local_alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } ocfs2_resmap_claimed_bits(&osb->osb_la_resmap, ac->ac_resv, start, bits_wanted); while(bits_wanted--) ocfs2_set_bit(start++, bitmap); le32_add_cpu(&alloc->id1.bitmap1.i_used, *num_bits); ocfs2_journal_dirty(handle, osb->local_alloc_bh); bail: if (status) mlog_errno(status); return status; } int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac, u32 bit_off, u32 num_bits) { int status, start; u32 clear_bits; struct inode *local_alloc_inode; void *bitmap; struct ocfs2_dinode *alloc; struct ocfs2_local_alloc *la; BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL); local_alloc_inode = ac->ac_inode; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); bitmap = la->la_bitmap; start = bit_off - le32_to_cpu(la->la_bm_off); clear_bits = num_bits; status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), osb->local_alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } while (clear_bits--) ocfs2_clear_bit(start++, bitmap); le32_add_cpu(&alloc->id1.bitmap1.i_used, -num_bits); ocfs2_journal_dirty(handle, osb->local_alloc_bh); bail: return status; } static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc) { u32 count; struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); count = memweight(la->la_bitmap, le16_to_cpu(la->la_size)); trace_ocfs2_local_alloc_count_bits(count); return count; } static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, struct ocfs2_dinode *alloc, u32 *numbits, struct ocfs2_alloc_reservation *resv) { int numfound = 0, bitoff, left, startoff; int local_resv = 0; struct ocfs2_alloc_reservation r; void *bitmap = NULL; struct ocfs2_reservation_map *resmap = &osb->osb_la_resmap; if (!alloc->id1.bitmap1.i_total) { bitoff = -1; goto bail; } if (!resv) { local_resv = 1; ocfs2_resv_init_once(&r); ocfs2_resv_set_type(&r, OCFS2_RESV_FLAG_TMP); resv = &r; } numfound = *numbits; if (ocfs2_resmap_resv_bits(resmap, resv, &bitoff, &numfound) == 0) { if (numfound < *numbits) *numbits = numfound; goto bail; } /* * Code error. While reservations are enabled, local * allocation should _always_ go through them. */ BUG_ON(osb->osb_resv_level != 0); /* * Reservations are disabled. Handle this the old way. */ bitmap = OCFS2_LOCAL_ALLOC(alloc)->la_bitmap; numfound = bitoff = startoff = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) < left) { /* Ok, we found a zero bit... is it contig. or do we * start over?*/ if (bitoff == startoff) { /* we found a zero */ numfound++; startoff++; } else { /* got a zero after some ones */ numfound = 1; startoff = bitoff+1; } /* we got everything we needed */ if (numfound == *numbits) { /* mlog(0, "Found it all!\n"); */ break; } } trace_ocfs2_local_alloc_find_clear_bits_search_bitmap(bitoff, numfound); if (numfound == *numbits) bitoff = startoff - numfound; else bitoff = -1; bail: if (local_resv) ocfs2_resv_discard(resmap, resv); trace_ocfs2_local_alloc_find_clear_bits(*numbits, le32_to_cpu(alloc->id1.bitmap1.i_total), bitoff, numfound); return bitoff; } static void ocfs2_clear_local_alloc(struct ocfs2_dinode *alloc) { struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); int i; alloc->id1.bitmap1.i_total = 0; alloc->id1.bitmap1.i_used = 0; la->la_bm_off = 0; for(i = 0; i < le16_to_cpu(la->la_size); i++) la->la_bitmap[i] = 0; } #if 0 /* turn this on and uncomment below to aid debugging window shifts. */ static void ocfs2_verify_zero_bits(unsigned long *bitmap, unsigned int start, unsigned int count) { unsigned int tmp = count; while(tmp--) { if (ocfs2_test_bit(start + tmp, bitmap)) { printk("ocfs2_verify_zero_bits: start = %u, count = " "%u\n", start, count); printk("ocfs2_verify_zero_bits: bit %u is set!", start + tmp); BUG(); } } } #endif /* * sync the local alloc to main bitmap. * * assumes you've already locked the main bitmap -- the bitmap inode * passed is used for caching. */ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_dinode *alloc, struct inode *main_bm_inode, struct buffer_head *main_bm_bh) { int status = 0; int bit_off, left, count, start; u64 la_start_blk; u64 blkno; void *bitmap; struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); trace_ocfs2_sync_local_to_main( le32_to_cpu(alloc->id1.bitmap1.i_total), le32_to_cpu(alloc->id1.bitmap1.i_used)); if (!alloc->id1.bitmap1.i_total) { goto bail; } if (le32_to_cpu(alloc->id1.bitmap1.i_used) == le32_to_cpu(alloc->id1.bitmap1.i_total)) { goto bail; } la_start_blk = ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(la->la_bm_off)); bitmap = la->la_bitmap; start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); while (1) { bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; } if (count) { blkno = la_start_blk + ocfs2_clusters_to_blocks(osb->sb, start - count); trace_ocfs2_sync_local_to_main_free( count, start - count, (unsigned long long)la_start_blk, (unsigned long long)blkno); status = ocfs2_release_clusters(handle, main_bm_inode, main_bm_bh, blkno, count); if (status < 0) { mlog_errno(status); goto bail; } } if (bit_off >= left) break; count = 1; start = bit_off + 1; } bail: if (status) mlog_errno(status); return status; } enum ocfs2_la_event { OCFS2_LA_EVENT_SLIDE, /* Normal window slide. */ OCFS2_LA_EVENT_FRAGMENTED, /* The global bitmap has * enough bits theoretically * free, but a contiguous * allocation could not be * found. */ OCFS2_LA_EVENT_ENOSPC, /* Global bitmap doesn't have * enough bits free to satisfy * our request. */ }; #define OCFS2_LA_ENABLE_INTERVAL (30 * HZ) /* * Given an event, calculate the size of our next local alloc window. * * This should always be called under i_rwsem of the local alloc inode * so that local alloc disabling doesn't race with processes trying to * use the allocator. * * Returns the state which the local alloc was left in. This value can * be ignored by some paths. */ static int ocfs2_recalc_la_window(struct ocfs2_super *osb, enum ocfs2_la_event event) { unsigned int bits; int state; spin_lock(&osb->osb_lock); if (osb->local_alloc_state == OCFS2_LA_DISABLED) { WARN_ON_ONCE(osb->local_alloc_state == OCFS2_LA_DISABLED); goto out_unlock; } /* * ENOSPC and fragmentation are treated similarly for now. */ if (event == OCFS2_LA_EVENT_ENOSPC || event == OCFS2_LA_EVENT_FRAGMENTED) { /* * We ran out of contiguous space in the primary * bitmap. Drastically reduce the number of bits used * by local alloc until we have to disable it. */ bits = osb->local_alloc_bits >> 1; if (bits > ocfs2_megabytes_to_clusters(osb->sb, 1)) { /* * By setting state to THROTTLED, we'll keep * the number of local alloc bits used down * until an event occurs which would give us * reason to assume the bitmap situation might * have changed. */ osb->local_alloc_state = OCFS2_LA_THROTTLED; osb->local_alloc_bits = bits; } else { osb->local_alloc_state = OCFS2_LA_DISABLED; } queue_delayed_work(osb->ocfs2_wq, &osb->la_enable_wq, OCFS2_LA_ENABLE_INTERVAL); goto out_unlock; } /* * Don't increase the size of the local alloc window until we * know we might be able to fulfill the request. Otherwise, we * risk bouncing around the global bitmap during periods of * low space. */ if (osb->local_alloc_state != OCFS2_LA_THROTTLED) osb->local_alloc_bits = osb->local_alloc_default_bits; out_unlock: state = osb->local_alloc_state; spin_unlock(&osb->osb_lock); return state; } static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb, struct ocfs2_alloc_context **ac, struct inode **bitmap_inode, struct buffer_head **bitmap_bh) { int status; *ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL); if (!(*ac)) { status = -ENOMEM; mlog_errno(status); goto bail; } retry_enospc: (*ac)->ac_bits_wanted = osb->local_alloc_bits; status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac); if (status == -ENOSPC) { if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_ENOSPC) == OCFS2_LA_DISABLED) goto bail; ocfs2_free_ac_resource(*ac); memset(*ac, 0, sizeof(struct ocfs2_alloc_context)); goto retry_enospc; } if (status < 0) { mlog_errno(status); goto bail; } *bitmap_inode = (*ac)->ac_inode; igrab(*bitmap_inode); *bitmap_bh = (*ac)->ac_bh; get_bh(*bitmap_bh); status = 0; bail: if ((status < 0) && *ac) { ocfs2_free_alloc_context(*ac); *ac = NULL; } if (status) mlog_errno(status); return status; } /* * pass it the bitmap lock in lock_bh if you have it. */ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac) { int status = 0; u32 cluster_off, cluster_count; struct ocfs2_dinode *alloc = NULL; struct ocfs2_local_alloc *la; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); trace_ocfs2_local_alloc_new_window( le32_to_cpu(alloc->id1.bitmap1.i_total), osb->local_alloc_bits); /* Instruct the allocation code to try the most recently used * cluster group. We'll re-record the group used this pass * below. */ ac->ac_last_group = osb->la_last_gd; /* we used the generic suballoc reserve function, but we set * everything up nicely, so there's no reason why we can't use * the more specific cluster api to claim bits. */ status = ocfs2_claim_clusters(handle, ac, osb->local_alloc_bits, &cluster_off, &cluster_count); if (status == -ENOSPC) { retry_enospc: /* * Note: We could also try syncing the journal here to * allow use of any free bits which the current * transaction can't give us access to. --Mark */ if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_FRAGMENTED) == OCFS2_LA_DISABLED) goto bail; ac->ac_bits_wanted = osb->local_alloc_bits; status = ocfs2_claim_clusters(handle, ac, osb->local_alloc_bits, &cluster_off, &cluster_count); if (status == -ENOSPC) goto retry_enospc; /* * We only shrunk the *minimum* number of in our * request - it's entirely possible that the allocator * might give us more than we asked for. */ if (status == 0) { spin_lock(&osb->osb_lock); osb->local_alloc_bits = cluster_count; spin_unlock(&osb->osb_lock); } } if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } osb->la_last_gd = ac->ac_last_group; la->la_bm_off = cpu_to_le32(cluster_off); alloc->id1.bitmap1.i_total = cpu_to_le32(cluster_count); /* just in case... In the future when we find space ourselves, * we don't have to get all contiguous -- but we'll have to * set all previously used bits in bitmap and update * la_bits_set before setting the bits in the main bitmap. */ alloc->id1.bitmap1.i_used = 0; memset(OCFS2_LOCAL_ALLOC(alloc)->la_bitmap, 0, le16_to_cpu(la->la_size)); ocfs2_resmap_restart(&osb->osb_la_resmap, cluster_count, OCFS2_LOCAL_ALLOC(alloc)->la_bitmap); trace_ocfs2_local_alloc_new_window_result( le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off), le32_to_cpu(alloc->id1.bitmap1.i_total)); bail: if (status) mlog_errno(status); return status; } /* Note that we do *NOT* lock the local alloc inode here as * it's been locked already for us. */ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, struct inode *local_alloc_inode) { int status = 0; struct buffer_head *main_bm_bh = NULL; struct inode *main_bm_inode = NULL; handle_t *handle = NULL; struct ocfs2_dinode *alloc; struct ocfs2_dinode *alloc_copy = NULL; struct ocfs2_alloc_context *ac = NULL; ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_SLIDE); /* This will lock the main bitmap for us. */ status = ocfs2_local_alloc_reserve_for_window(osb, &ac, &main_bm_inode, &main_bm_bh); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto bail; } alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; /* We want to clear the local alloc before doing anything * else, so that if we error later during this operation, * local alloc shutdown won't try to double free main bitmap * bits. Make a copy so the sync function knows which bits to * free. */ alloc_copy = kmemdup(alloc, osb->local_alloc_bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; mlog_errno(status); goto bail; } status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), osb->local_alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } ocfs2_clear_local_alloc(alloc); ocfs2_journal_dirty(handle, osb->local_alloc_bh); status = ocfs2_sync_local_to_main(osb, handle, alloc_copy, main_bm_inode, main_bm_bh); if (status < 0) { mlog_errno(status); goto bail; } status = ocfs2_local_alloc_new_window(osb, handle, ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } atomic_inc(&osb->alloc_stats.moves); bail: if (handle) ocfs2_commit_trans(osb, handle); brelse(main_bm_bh); iput(main_bm_inode); kfree(alloc_copy); if (ac) ocfs2_free_alloc_context(ac); if (status) mlog_errno(status); return status; } |
| 21 15 21 18 | 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 | /* * linux/fs/nls/nls_cp860.c * * Charset cp860 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e3, 0x00e0, 0x00c1, 0x00e7, 0x00ea, 0x00ca, 0x00e8, 0x00cd, 0x00d4, 0x00ec, 0x00c3, 0x00c2, /* 0x90*/ 0x00c9, 0x00c0, 0x00c8, 0x00f4, 0x00f5, 0x00f2, 0x00da, 0x00f9, 0x00cc, 0x00d5, 0x00dc, 0x00a2, 0x00a3, 0x00d9, 0x20a7, 0x00d3, /* 0xa0*/ 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba, 0x00bf, 0x00d2, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229, /* 0xf0*/ 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0xad, 0x9b, 0x9c, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0xa6, 0xae, 0xaa, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0x00, 0x00, 0xe6, 0x00, 0xfa, /* 0xb0-0xb7 */ 0x00, 0x00, 0xa7, 0xaf, 0xac, 0xab, 0x00, 0xa8, /* 0xb8-0xbf */ 0x91, 0x86, 0x8f, 0x8e, 0x00, 0x00, 0x00, 0x80, /* 0xc0-0xc7 */ 0x92, 0x90, 0x89, 0x00, 0x98, 0x8b, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0xa5, 0xa9, 0x9f, 0x8c, 0x99, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x9d, 0x96, 0x00, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x85, 0xa0, 0x83, 0x84, 0x00, 0x00, 0x00, 0x87, /* 0xe0-0xe7 */ 0x8a, 0x82, 0x88, 0x00, 0x8d, 0xa1, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0xa4, 0x95, 0xa2, 0x93, 0x94, 0x00, 0xf6, /* 0xf0-0xf7 */ 0x00, 0x97, 0xa3, 0x00, 0x81, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0xe2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0xe9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0xe4, 0x00, 0x00, 0xe8, 0x00, /* 0xa0-0xa7 */ 0x00, 0xea, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0xe0, 0x00, 0x00, 0xeb, 0xee, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xe3, 0x00, 0x00, 0xe5, 0xe7, 0x00, 0xed, 0x00, /* 0xc0-0xc7 */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x9e, /* 0xa0-0xa7 */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0xec, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0xef, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0xf0, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0xf4, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x84, 0x85, 0xa0, 0x87, /* 0x80-0x87 */ 0x88, 0x88, 0x8a, 0xa1, 0x93, 0x8d, 0x84, 0x83, /* 0x88-0x8f */ 0x82, 0x85, 0x8a, 0x93, 0x94, 0x95, 0xa3, 0x97, /* 0x90-0x97 */ 0x8d, 0x94, 0x81, 0x9b, 0x9c, 0x97, 0x9e, 0xa2, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa4, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0x95, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0x00, 0xe3, 0xe5, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xed, 0x00, 0x00, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0x8f, 0x8e, 0x91, 0x86, 0x80, /* 0x80-0x87 */ 0x89, 0x89, 0x92, 0x8b, 0x8c, 0x98, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x8c, 0x99, 0xa9, 0x96, 0x9d, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0x86, 0x8b, 0x9f, 0x96, 0xa5, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0xe4, 0x00, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0x00, 0xec, 0xe8, 0x00, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp860", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp860(void) { return register_nls(&table); } static void __exit exit_nls_cp860(void) { unregister_nls(&table); } module_init(init_nls_cp860) module_exit(exit_nls_cp860) MODULE_DESCRIPTION("NLS Codepage 860 (Portuguese)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 3 3 2 2 2 2 1 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Linaro Ltd */ #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/poll.h> #include <linux/skbuff.h> #include <linux/uaccess.h> #include "qrtr.h" struct qrtr_tun { struct qrtr_endpoint ep; struct sk_buff_head queue; wait_queue_head_t readq; }; static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) { struct qrtr_tun *tun = container_of(ep, struct qrtr_tun, ep); skb_queue_tail(&tun->queue, skb); /* wake up any blocking processes, waiting for new data */ wake_up_interruptible(&tun->readq); return 0; } static int qrtr_tun_open(struct inode *inode, struct file *filp) { struct qrtr_tun *tun; int ret; tun = kzalloc(sizeof(*tun), GFP_KERNEL); if (!tun) return -ENOMEM; skb_queue_head_init(&tun->queue); init_waitqueue_head(&tun->readq); tun->ep.xmit = qrtr_tun_send; filp->private_data = tun; ret = qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); if (ret) goto out; return 0; out: filp->private_data = NULL; kfree(tun); return ret; } static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *filp = iocb->ki_filp; struct qrtr_tun *tun = filp->private_data; struct sk_buff *skb; int count; while (!(skb = skb_dequeue(&tun->queue))) { if (filp->f_flags & O_NONBLOCK) return -EAGAIN; /* Wait until we get data or the endpoint goes away */ if (wait_event_interruptible(tun->readq, !skb_queue_empty(&tun->queue))) return -ERESTARTSYS; } count = min_t(size_t, iov_iter_count(to), skb->len); if (copy_to_iter(skb->data, count, to) != count) count = -EFAULT; kfree_skb(skb); return count; } static ssize_t qrtr_tun_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct qrtr_tun *tun = filp->private_data; size_t len = iov_iter_count(from); ssize_t ret; void *kbuf; if (!len) return -EINVAL; if (len > KMALLOC_MAX_SIZE) return -ENOMEM; kbuf = kzalloc(len, GFP_KERNEL); if (!kbuf) return -ENOMEM; if (!copy_from_iter_full(kbuf, len, from)) { kfree(kbuf); return -EFAULT; } ret = qrtr_endpoint_post(&tun->ep, kbuf, len); kfree(kbuf); return ret < 0 ? ret : len; } static __poll_t qrtr_tun_poll(struct file *filp, poll_table *wait) { struct qrtr_tun *tun = filp->private_data; __poll_t mask = 0; poll_wait(filp, &tun->readq, wait); if (!skb_queue_empty(&tun->queue)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } static int qrtr_tun_release(struct inode *inode, struct file *filp) { struct qrtr_tun *tun = filp->private_data; qrtr_endpoint_unregister(&tun->ep); /* Discard all SKBs */ skb_queue_purge(&tun->queue); kfree(tun); return 0; } static const struct file_operations qrtr_tun_ops = { .owner = THIS_MODULE, .open = qrtr_tun_open, .poll = qrtr_tun_poll, .read_iter = qrtr_tun_read_iter, .write_iter = qrtr_tun_write_iter, .release = qrtr_tun_release, }; static struct miscdevice qrtr_tun_miscdev = { MISC_DYNAMIC_MINOR, "qrtr-tun", &qrtr_tun_ops, }; static int __init qrtr_tun_init(void) { int ret; ret = misc_register(&qrtr_tun_miscdev); if (ret) pr_err("failed to register Qualcomm IPC Router tun device\n"); return ret; } static void __exit qrtr_tun_exit(void) { misc_deregister(&qrtr_tun_miscdev); } module_init(qrtr_tun_init); module_exit(qrtr_tun_exit); MODULE_DESCRIPTION("Qualcomm IPC Router TUN device"); MODULE_LICENSE("GPL v2"); |
| 4 4 1 2 1 1 2 5 3 3 1 1 1 9 1 1 6 2 3 2 2 2 10 1 1 4 4 8 1 2 5 2 3 4 3 6 3 3 2 2 4 4 1 3 1 12 1 2 4 4 4 7 11 7 6 2 10 7 4 4 7 7 4 1 2 1 8 8 1 1 1 2 1 1 1 1 1 1 1 1 1 14 1 1 1 1 9 9 241 239 1 1 1 13 1 3 1 9 1 1 6 1 1 4 1 1 1 4 1 8 10 10 3 14 22 1 4 1 1 1 14 6 7 1 9 1 5 1 8 1 5 3 8 1 6 1 4 1 11 1 3 1 8 1 14 241 2 2 239 235 1 27 1 1 1 1 254 1 31 3 245 245 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Code related to the io_uring_register() syscall * * Copyright (C) 2023 Jens Axboe */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/refcount.h> #include <linux/bits.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/io_uring_types.h> #include "io_uring.h" #include "opdef.h" #include "tctx.h" #include "rsrc.h" #include "sqpoll.h" #include "register.h" #include "cancel.h" #include "kbuf.h" #include "napi.h" #include "eventfd.h" #include "msg_ring.h" #include "memmap.h" #include "zcrx.h" #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { struct io_uring_probe *p; size_t size; int i, ret; if (nr_args > IORING_OP_LAST) nr_args = IORING_OP_LAST; size = struct_size(p, ops, nr_args); p = kzalloc(size, GFP_KERNEL); if (!p) return -ENOMEM; ret = -EFAULT; if (copy_from_user(p, arg, size)) goto out; ret = -EINVAL; if (memchr_inv(p, 0, size)) goto out; p->last_op = IORING_OP_LAST - 1; for (i = 0; i < nr_args; i++) { p->ops[i].op = i; if (io_uring_op_supported(i)) p->ops[i].flags = IO_URING_OP_SUPPORTED; } p->ops_len = i; ret = 0; if (copy_to_user(arg, p, size)) ret = -EFAULT; out: kfree(p); return ret; } int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { const struct cred *creds; creds = xa_erase(&ctx->personalities, id); if (creds) { put_cred(creds); return 0; } return -EINVAL; } static int io_register_personality(struct io_ring_ctx *ctx) { const struct cred *creds; u32 id; int ret; creds = get_current_cred(); ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); if (ret < 0) { put_cred(creds); return ret; } return id; } static __cold int io_parse_restrictions(void __user *arg, unsigned int nr_args, struct io_restriction *restrictions) { struct io_uring_restriction *res; size_t size; int i, ret; if (!arg || nr_args > IORING_MAX_RESTRICTIONS) return -EINVAL; size = array_size(nr_args, sizeof(*res)); if (size == SIZE_MAX) return -EOVERFLOW; res = memdup_user(arg, size); if (IS_ERR(res)) return PTR_ERR(res); ret = -EINVAL; for (i = 0; i < nr_args; i++) { switch (res[i].opcode) { case IORING_RESTRICTION_REGISTER_OP: if (res[i].register_op >= IORING_REGISTER_LAST) goto err; __set_bit(res[i].register_op, restrictions->register_op); break; case IORING_RESTRICTION_SQE_OP: if (res[i].sqe_op >= IORING_OP_LAST) goto err; __set_bit(res[i].sqe_op, restrictions->sqe_op); break; case IORING_RESTRICTION_SQE_FLAGS_ALLOWED: restrictions->sqe_flags_allowed = res[i].sqe_flags; break; case IORING_RESTRICTION_SQE_FLAGS_REQUIRED: restrictions->sqe_flags_required = res[i].sqe_flags; break; default: goto err; } } ret = 0; err: kfree(res); return ret; } static __cold int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, unsigned int nr_args) { int ret; /* Restrictions allowed only if rings started disabled */ if (!(ctx->flags & IORING_SETUP_R_DISABLED)) return -EBADFD; /* We allow only a single restrictions registration */ if (ctx->restrictions.registered) return -EBUSY; ret = io_parse_restrictions(arg, nr_args, &ctx->restrictions); /* Reset all restrictions if an error happened */ if (ret != 0) memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); else ctx->restrictions.registered = true; return ret; } static int io_register_enable_rings(struct io_ring_ctx *ctx) { if (!(ctx->flags & IORING_SETUP_R_DISABLED)) return -EBADFD; if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) { WRITE_ONCE(ctx->submitter_task, get_task_struct(current)); /* * Lazy activation attempts would fail if it was polled before * submitter_task is set. */ if (wq_has_sleeper(&ctx->poll_wq)) io_activate_pollwq(ctx); } if (ctx->restrictions.registered) ctx->restricted = 1; ctx->flags &= ~IORING_SETUP_R_DISABLED; if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); return 0; } static __cold int __io_register_iowq_aff(struct io_ring_ctx *ctx, cpumask_var_t new_mask) { int ret; if (!(ctx->flags & IORING_SETUP_SQPOLL)) { ret = io_wq_cpu_affinity(current->io_uring, new_mask); } else { mutex_unlock(&ctx->uring_lock); ret = io_sqpoll_wq_cpu_affinity(ctx, new_mask); mutex_lock(&ctx->uring_lock); } return ret; } static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, unsigned len) { cpumask_var_t new_mask; int ret; if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) return -ENOMEM; cpumask_clear(new_mask); if (len > cpumask_size()) len = cpumask_size(); #ifdef CONFIG_COMPAT if (in_compat_syscall()) ret = compat_get_bitmap(cpumask_bits(new_mask), (const compat_ulong_t __user *)arg, len * 8 /* CHAR_BIT */); else #endif ret = copy_from_user(new_mask, arg, len); if (ret) { free_cpumask_var(new_mask); return -EFAULT; } ret = __io_register_iowq_aff(ctx, new_mask); free_cpumask_var(new_mask); return ret; } static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx) { return __io_register_iowq_aff(ctx, NULL); } static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, void __user *arg) __must_hold(&ctx->uring_lock) { struct io_tctx_node *node; struct io_uring_task *tctx = NULL; struct io_sq_data *sqd = NULL; __u32 new_count[2]; int i, ret; if (copy_from_user(new_count, arg, sizeof(new_count))) return -EFAULT; for (i = 0; i < ARRAY_SIZE(new_count); i++) if (new_count[i] > INT_MAX) return -EINVAL; if (ctx->flags & IORING_SETUP_SQPOLL) { sqd = ctx->sq_data; if (sqd) { struct task_struct *tsk; /* * Observe the correct sqd->lock -> ctx->uring_lock * ordering. Fine to drop uring_lock here, we hold * a ref to the ctx. */ refcount_inc(&sqd->refs); mutex_unlock(&ctx->uring_lock); mutex_lock(&sqd->lock); mutex_lock(&ctx->uring_lock); tsk = sqpoll_task_locked(sqd); if (tsk) tctx = tsk->io_uring; } } else { tctx = current->io_uring; } BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); for (i = 0; i < ARRAY_SIZE(new_count); i++) if (new_count[i]) ctx->iowq_limits[i] = new_count[i]; ctx->iowq_limits_set = true; if (tctx && tctx->io_wq) { ret = io_wq_max_workers(tctx->io_wq, new_count); if (ret) goto err; } else { memset(new_count, 0, sizeof(new_count)); } if (sqd) { mutex_unlock(&ctx->uring_lock); mutex_unlock(&sqd->lock); io_put_sq_data(sqd); mutex_lock(&ctx->uring_lock); } if (copy_to_user(arg, new_count, sizeof(new_count))) return -EFAULT; /* that's it for SQPOLL, only the SQPOLL task creates requests */ if (sqd) return 0; /* now propagate the restriction to all registered users */ list_for_each_entry(node, &ctx->tctx_list, ctx_node) { tctx = node->task->io_uring; if (WARN_ON_ONCE(!tctx->io_wq)) continue; for (i = 0; i < ARRAY_SIZE(new_count); i++) new_count[i] = ctx->iowq_limits[i]; /* ignore errors, it always returns zero anyway */ (void)io_wq_max_workers(tctx->io_wq, new_count); } return 0; err: if (sqd) { mutex_unlock(&ctx->uring_lock); mutex_unlock(&sqd->lock); io_put_sq_data(sqd); mutex_lock(&ctx->uring_lock); } return ret; } static int io_register_clock(struct io_ring_ctx *ctx, struct io_uring_clock_register __user *arg) { struct io_uring_clock_register reg; if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (memchr_inv(®.__resv, 0, sizeof(reg.__resv))) return -EINVAL; switch (reg.clockid) { case CLOCK_MONOTONIC: ctx->clock_offset = 0; break; case CLOCK_BOOTTIME: ctx->clock_offset = TK_OFFS_BOOT; break; default: return -EINVAL; } ctx->clockid = reg.clockid; return 0; } /* * State to maintain until we can swap. Both new and old state, used for * either mapping or freeing. */ struct io_ring_ctx_rings { struct io_rings *rings; struct io_uring_sqe *sq_sqes; struct io_mapped_region sq_region; struct io_mapped_region ring_region; }; static void io_register_free_rings(struct io_ring_ctx *ctx, struct io_uring_params *p, struct io_ring_ctx_rings *r) { io_free_region(ctx, &r->sq_region); io_free_region(ctx, &r->ring_region); } #define swap_old(ctx, o, n, field) \ do { \ (o).field = (ctx)->field; \ (ctx)->field = (n).field; \ } while (0) #define RESIZE_FLAGS (IORING_SETUP_CQSIZE | IORING_SETUP_CLAMP) #define COPY_FLAGS (IORING_SETUP_NO_SQARRAY | IORING_SETUP_SQE128 | \ IORING_SETUP_CQE32 | IORING_SETUP_NO_MMAP) static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_region_desc rd; struct io_ring_ctx_rings o = { }, n = { }, *to_free = NULL; size_t size, sq_array_offset; unsigned i, tail, old_head; struct io_uring_params p; int ret; /* for single issuer, must be owner resizing */ if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && current != ctx->submitter_task) return -EEXIST; /* limited to DEFER_TASKRUN for now */ if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) return -EINVAL; if (copy_from_user(&p, arg, sizeof(p))) return -EFAULT; if (p.flags & ~RESIZE_FLAGS) return -EINVAL; /* properties that are always inherited */ p.flags |= (ctx->flags & COPY_FLAGS); ret = io_uring_fill_params(p.sq_entries, &p); if (unlikely(ret)) return ret; /* nothing to do, but copy params back */ if (p.sq_entries == ctx->sq_entries && p.cq_entries == ctx->cq_entries) { if (copy_to_user(arg, &p, sizeof(p))) return -EFAULT; return 0; } size = rings_size(p.flags, p.sq_entries, p.cq_entries, &sq_array_offset); if (size == SIZE_MAX) return -EOVERFLOW; memset(&rd, 0, sizeof(rd)); rd.size = PAGE_ALIGN(size); if (p.flags & IORING_SETUP_NO_MMAP) { rd.user_addr = p.cq_off.user_addr; rd.flags |= IORING_MEM_REGION_TYPE_USER; } ret = io_create_region_mmap_safe(ctx, &n.ring_region, &rd, IORING_OFF_CQ_RING); if (ret) { io_register_free_rings(ctx, &p, &n); return ret; } n.rings = io_region_get_ptr(&n.ring_region); /* * At this point n.rings is shared with userspace, just like o.rings * is as well. While we don't expect userspace to modify it while * a resize is in progress, and it's most likely that userspace will * shoot itself in the foot if it does, we can't always assume good * intent... Use read/write once helpers from here on to indicate the * shared nature of it. */ WRITE_ONCE(n.rings->sq_ring_mask, p.sq_entries - 1); WRITE_ONCE(n.rings->cq_ring_mask, p.cq_entries - 1); WRITE_ONCE(n.rings->sq_ring_entries, p.sq_entries); WRITE_ONCE(n.rings->cq_ring_entries, p.cq_entries); if (copy_to_user(arg, &p, sizeof(p))) { io_register_free_rings(ctx, &p, &n); return -EFAULT; } if (p.flags & IORING_SETUP_SQE128) size = array_size(2 * sizeof(struct io_uring_sqe), p.sq_entries); else size = array_size(sizeof(struct io_uring_sqe), p.sq_entries); if (size == SIZE_MAX) { io_register_free_rings(ctx, &p, &n); return -EOVERFLOW; } memset(&rd, 0, sizeof(rd)); rd.size = PAGE_ALIGN(size); if (p.flags & IORING_SETUP_NO_MMAP) { rd.user_addr = p.sq_off.user_addr; rd.flags |= IORING_MEM_REGION_TYPE_USER; } ret = io_create_region_mmap_safe(ctx, &n.sq_region, &rd, IORING_OFF_SQES); if (ret) { io_register_free_rings(ctx, &p, &n); return ret; } n.sq_sqes = io_region_get_ptr(&n.sq_region); /* * If using SQPOLL, park the thread */ if (ctx->sq_data) { mutex_unlock(&ctx->uring_lock); io_sq_thread_park(ctx->sq_data); mutex_lock(&ctx->uring_lock); } /* * We'll do the swap. Grab the ctx->mmap_lock, which will exclude * any new mmap's on the ring fd. Clear out existing mappings to prevent * mmap from seeing them, as we'll unmap them. Any attempt to mmap * existing rings beyond this point will fail. Not that it could proceed * at this point anyway, as the io_uring mmap side needs go grab the * ctx->mmap_lock as well. Likewise, hold the completion lock over the * duration of the actual swap. */ mutex_lock(&ctx->mmap_lock); spin_lock(&ctx->completion_lock); o.rings = ctx->rings; ctx->rings = NULL; o.sq_sqes = ctx->sq_sqes; ctx->sq_sqes = NULL; /* * Now copy SQ and CQ entries, if any. If either of the destination * rings can't hold what is already there, then fail the operation. */ tail = READ_ONCE(o.rings->sq.tail); old_head = READ_ONCE(o.rings->sq.head); if (tail - old_head > p.sq_entries) goto overflow; for (i = old_head; i < tail; i++) { unsigned src_head = i & (ctx->sq_entries - 1); unsigned dst_head = i & (p.sq_entries - 1); n.sq_sqes[dst_head] = o.sq_sqes[src_head]; } WRITE_ONCE(n.rings->sq.head, old_head); WRITE_ONCE(n.rings->sq.tail, tail); tail = READ_ONCE(o.rings->cq.tail); old_head = READ_ONCE(o.rings->cq.head); if (tail - old_head > p.cq_entries) { overflow: /* restore old rings, and return -EOVERFLOW via cleanup path */ ctx->rings = o.rings; ctx->sq_sqes = o.sq_sqes; to_free = &n; ret = -EOVERFLOW; goto out; } for (i = old_head; i < tail; i++) { unsigned src_head = i & (ctx->cq_entries - 1); unsigned dst_head = i & (p.cq_entries - 1); n.rings->cqes[dst_head] = o.rings->cqes[src_head]; } WRITE_ONCE(n.rings->cq.head, old_head); WRITE_ONCE(n.rings->cq.tail, tail); /* invalidate cached cqe refill */ ctx->cqe_cached = ctx->cqe_sentinel = NULL; WRITE_ONCE(n.rings->sq_dropped, READ_ONCE(o.rings->sq_dropped)); atomic_set(&n.rings->sq_flags, atomic_read(&o.rings->sq_flags)); WRITE_ONCE(n.rings->cq_flags, READ_ONCE(o.rings->cq_flags)); WRITE_ONCE(n.rings->cq_overflow, READ_ONCE(o.rings->cq_overflow)); /* all done, store old pointers and assign new ones */ if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) ctx->sq_array = (u32 *)((char *)n.rings + sq_array_offset); ctx->sq_entries = p.sq_entries; ctx->cq_entries = p.cq_entries; ctx->rings = n.rings; ctx->sq_sqes = n.sq_sqes; swap_old(ctx, o, n, ring_region); swap_old(ctx, o, n, sq_region); to_free = &o; ret = 0; out: spin_unlock(&ctx->completion_lock); mutex_unlock(&ctx->mmap_lock); io_register_free_rings(ctx, &p, to_free); if (ctx->sq_data) io_sq_thread_unpark(ctx->sq_data); return ret; } static int io_register_mem_region(struct io_ring_ctx *ctx, void __user *uarg) { struct io_uring_mem_region_reg __user *reg_uptr = uarg; struct io_uring_mem_region_reg reg; struct io_uring_region_desc __user *rd_uptr; struct io_uring_region_desc rd; int ret; if (io_region_is_set(&ctx->param_region)) return -EBUSY; if (copy_from_user(®, reg_uptr, sizeof(reg))) return -EFAULT; rd_uptr = u64_to_user_ptr(reg.region_uptr); if (copy_from_user(&rd, rd_uptr, sizeof(rd))) return -EFAULT; if (memchr_inv(®.__resv, 0, sizeof(reg.__resv))) return -EINVAL; if (reg.flags & ~IORING_MEM_REGION_REG_WAIT_ARG) return -EINVAL; /* * This ensures there are no waiters. Waiters are unlocked and it's * hard to synchronise with them, especially if we need to initialise * the region. */ if ((reg.flags & IORING_MEM_REGION_REG_WAIT_ARG) && !(ctx->flags & IORING_SETUP_R_DISABLED)) return -EINVAL; ret = io_create_region_mmap_safe(ctx, &ctx->param_region, &rd, IORING_MAP_OFF_PARAM_REGION); if (ret) return ret; if (copy_to_user(rd_uptr, &rd, sizeof(rd))) { io_free_region(ctx, &ctx->param_region); return -EFAULT; } if (reg.flags & IORING_MEM_REGION_REG_WAIT_ARG) { ctx->cq_wait_arg = io_region_get_ptr(&ctx->param_region); ctx->cq_wait_size = rd.size; } return 0; } static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) __acquires(ctx->uring_lock) { int ret; /* * We don't quiesce the refs for register anymore and so it can't be * dying as we're holding a file ref here. */ if (WARN_ON_ONCE(percpu_ref_is_dying(&ctx->refs))) return -ENXIO; if (ctx->submitter_task && ctx->submitter_task != current) return -EEXIST; if (ctx->restricted) { opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); if (!test_bit(opcode, ctx->restrictions.register_op)) return -EACCES; } switch (opcode) { case IORING_REGISTER_BUFFERS: ret = -EFAULT; if (!arg) break; ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_BUFFERS: ret = -EINVAL; if (arg || nr_args) break; ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: ret = -EFAULT; if (!arg) break; ret = io_sqe_files_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_FILES: ret = -EINVAL; if (arg || nr_args) break; ret = io_sqe_files_unregister(ctx); break; case IORING_REGISTER_FILES_UPDATE: ret = io_register_files_update(ctx, arg, nr_args); break; case IORING_REGISTER_EVENTFD: ret = -EINVAL; if (nr_args != 1) break; ret = io_eventfd_register(ctx, arg, 0); break; case IORING_REGISTER_EVENTFD_ASYNC: ret = -EINVAL; if (nr_args != 1) break; ret = io_eventfd_register(ctx, arg, 1); break; case IORING_UNREGISTER_EVENTFD: ret = -EINVAL; if (arg || nr_args) break; ret = io_eventfd_unregister(ctx); break; case IORING_REGISTER_PROBE: ret = -EINVAL; if (!arg || nr_args > 256) break; ret = io_probe(ctx, arg, nr_args); break; case IORING_REGISTER_PERSONALITY: ret = -EINVAL; if (arg || nr_args) break; ret = io_register_personality(ctx); break; case IORING_UNREGISTER_PERSONALITY: ret = -EINVAL; if (arg) break; ret = io_unregister_personality(ctx, nr_args); break; case IORING_REGISTER_ENABLE_RINGS: ret = -EINVAL; if (arg || nr_args) break; ret = io_register_enable_rings(ctx); break; case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; case IORING_REGISTER_FILES2: ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); break; case IORING_REGISTER_FILES_UPDATE2: ret = io_register_rsrc_update(ctx, arg, nr_args, IORING_RSRC_FILE); break; case IORING_REGISTER_BUFFERS2: ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; case IORING_REGISTER_BUFFERS_UPDATE: ret = io_register_rsrc_update(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; case IORING_REGISTER_IOWQ_AFF: ret = -EINVAL; if (!arg || !nr_args) break; ret = io_register_iowq_aff(ctx, arg, nr_args); break; case IORING_UNREGISTER_IOWQ_AFF: ret = -EINVAL; if (arg || nr_args) break; ret = io_unregister_iowq_aff(ctx); break; case IORING_REGISTER_IOWQ_MAX_WORKERS: ret = -EINVAL; if (!arg || nr_args != 2) break; ret = io_register_iowq_max_workers(ctx, arg); break; case IORING_REGISTER_RING_FDS: ret = io_ringfd_register(ctx, arg, nr_args); break; case IORING_UNREGISTER_RING_FDS: ret = io_ringfd_unregister(ctx, arg, nr_args); break; case IORING_REGISTER_PBUF_RING: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_pbuf_ring(ctx, arg); break; case IORING_UNREGISTER_PBUF_RING: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_unregister_pbuf_ring(ctx, arg); break; case IORING_REGISTER_SYNC_CANCEL: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_sync_cancel(ctx, arg); break; case IORING_REGISTER_FILE_ALLOC_RANGE: ret = -EINVAL; if (!arg || nr_args) break; ret = io_register_file_alloc_range(ctx, arg); break; case IORING_REGISTER_PBUF_STATUS: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_pbuf_status(ctx, arg); break; case IORING_REGISTER_NAPI: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_napi(ctx, arg); break; case IORING_UNREGISTER_NAPI: ret = -EINVAL; if (nr_args != 1) break; ret = io_unregister_napi(ctx, arg); break; case IORING_REGISTER_CLOCK: ret = -EINVAL; if (!arg || nr_args) break; ret = io_register_clock(ctx, arg); break; case IORING_REGISTER_CLONE_BUFFERS: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_clone_buffers(ctx, arg); break; case IORING_REGISTER_ZCRX_IFQ: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_zcrx_ifq(ctx, arg); break; case IORING_REGISTER_RESIZE_RINGS: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_resize_rings(ctx, arg); break; case IORING_REGISTER_MEM_REGION: ret = -EINVAL; if (!arg || nr_args != 1) break; ret = io_register_mem_region(ctx, arg); break; default: ret = -EINVAL; break; } return ret; } /* * Given an 'fd' value, return the ctx associated with if. If 'registered' is * true, then the registered index is used. Otherwise, the normal fd table. * Caller must call fput() on the returned file, unless it's an ERR_PTR. */ struct file *io_uring_register_get_file(unsigned int fd, bool registered) { struct file *file; if (registered) { /* * Ring fd has been registered via IORING_REGISTER_RING_FDS, we * need only dereference our task private array to find it. */ struct io_uring_task *tctx = current->io_uring; if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX)) return ERR_PTR(-EINVAL); fd = array_index_nospec(fd, IO_RINGFD_REG_MAX); file = tctx->registered_rings[fd]; if (file) get_file(file); } else { file = fget(fd); } if (unlikely(!file)) return ERR_PTR(-EBADF); if (io_is_uring_fops(file)) return file; fput(file); return ERR_PTR(-EOPNOTSUPP); } /* * "blind" registration opcodes are ones where there's no ring given, and * hence the source fd must be -1. */ static int io_uring_register_blind(unsigned int opcode, void __user *arg, unsigned int nr_args) { switch (opcode) { case IORING_REGISTER_SEND_MSG_RING: { struct io_uring_sqe sqe; if (!arg || nr_args != 1) return -EINVAL; if (copy_from_user(&sqe, arg, sizeof(sqe))) return -EFAULT; /* no flags supported */ if (sqe.flags) return -EINVAL; if (sqe.opcode == IORING_OP_MSG_RING) return io_uring_sync_msg_ring(&sqe); } } return -EINVAL; } SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, void __user *, arg, unsigned int, nr_args) { struct io_ring_ctx *ctx; long ret = -EBADF; struct file *file; bool use_registered_ring; use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING); opcode &= ~IORING_REGISTER_USE_REGISTERED_RING; if (opcode >= IORING_REGISTER_LAST) return -EINVAL; if (fd == -1) return io_uring_register_blind(opcode, arg, nr_args); file = io_uring_register_get_file(fd, use_registered_ring); if (IS_ERR(file)) return PTR_ERR(file); ctx = file->private_data; mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr, ctx->buf_table.nr, ret); mutex_unlock(&ctx->uring_lock); fput(file); return ret; } |
| 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211_hwsim - software simulator of 802.11 radio(s) for mac80211 * Copyright (c) 2008, Jouni Malinen <j@w1.fi> * Copyright (c) 2011, Javier Lopez <jlopex@gmail.com> * Copyright (c) 2016 - 2017 Intel Deutschland GmbH * Copyright (C) 2018 - 2025 Intel Corporation */ /* * TODO: * - Add TSF sync and fix IBSS beacon transmission by adding * competition for "air time" at TBTT * - RX filtering based on filter configuration (data->rx_filter) */ #include <linux/list.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/mac80211.h> #include <net/ieee80211_radiotap.h> #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> #include <linux/platform_device.h> #include <linux/debugfs.h> #include <linux/module.h> #include <linux/ktime.h> #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/rhashtable.h> #include <linux/nospec.h> #include <linux/virtio.h> #include <linux/virtio_ids.h> #include <linux/virtio_config.h> #include "mac80211_hwsim.h" #define WARN_QUEUE 100 #define MAX_QUEUE 200 MODULE_AUTHOR("Jouni Malinen"); MODULE_DESCRIPTION("Software simulator of 802.11 radio(s) for mac80211"); MODULE_LICENSE("GPL"); static int radios = 2; module_param(radios, int, 0444); MODULE_PARM_DESC(radios, "Number of simulated radios"); static int channels = 1; module_param(channels, int, 0444); MODULE_PARM_DESC(channels, "Number of concurrent channels"); static bool paged_rx = false; module_param(paged_rx, bool, 0644); MODULE_PARM_DESC(paged_rx, "Use paged SKBs for RX instead of linear ones"); static bool rctbl = false; module_param(rctbl, bool, 0444); MODULE_PARM_DESC(rctbl, "Handle rate control table"); static bool support_p2p_device = true; module_param(support_p2p_device, bool, 0444); MODULE_PARM_DESC(support_p2p_device, "Support P2P-Device interface type"); static bool mlo; module_param(mlo, bool, 0444); MODULE_PARM_DESC(mlo, "Support MLO"); static bool multi_radio; module_param(multi_radio, bool, 0444); MODULE_PARM_DESC(multi_radio, "Support Multiple Radios per wiphy"); /** * enum hwsim_regtest - the type of regulatory tests we offer * * @HWSIM_REGTEST_DISABLED: No regulatory tests are performed, * this is the default value. * @HWSIM_REGTEST_DRIVER_REG_FOLLOW: Used for testing the driver regulatory * hint, only one driver regulatory hint will be sent as such the * secondary radios are expected to follow. * @HWSIM_REGTEST_DRIVER_REG_ALL: Used for testing the driver regulatory * request with all radios reporting the same regulatory domain. * @HWSIM_REGTEST_DIFF_COUNTRY: Used for testing the drivers calling * different regulatory domains requests. Expected behaviour is for * an intersection to occur but each device will still use their * respective regulatory requested domains. Subsequent radios will * use the resulting intersection. * @HWSIM_REGTEST_WORLD_ROAM: Used for testing the world roaming. We accomplish * this by using a custom beacon-capable regulatory domain for the first * radio. All other device world roam. * @HWSIM_REGTEST_CUSTOM_WORLD: Used for testing the custom world regulatory * domain requests. All radios will adhere to this custom world regulatory * domain. * @HWSIM_REGTEST_CUSTOM_WORLD_2: Used for testing 2 custom world regulatory * domain requests. The first radio will adhere to the first custom world * regulatory domain, the second one to the second custom world regulatory * domain. All other devices will world roam. * @HWSIM_REGTEST_STRICT_FOLLOW: Used for testing strict regulatory domain * settings, only the first radio will send a regulatory domain request * and use strict settings. The rest of the radios are expected to follow. * @HWSIM_REGTEST_STRICT_ALL: Used for testing strict regulatory domain * settings. All radios will adhere to this. * @HWSIM_REGTEST_STRICT_AND_DRIVER_REG: Used for testing strict regulatory * domain settings, combined with secondary driver regulatory domain * settings. The first radio will get a strict regulatory domain setting * using the first driver regulatory request and the second radio will use * non-strict settings using the second driver regulatory request. All * other devices should follow the intersection created between the * first two. * @HWSIM_REGTEST_ALL: Used for testing every possible mix. You will need * at least 6 radios for a complete test. We will test in this order: * 1 - driver custom world regulatory domain * 2 - second custom world regulatory domain * 3 - first driver regulatory domain request * 4 - second driver regulatory domain request * 5 - strict regulatory domain settings using the third driver regulatory * domain request * 6 and on - should follow the intersection of the 3rd, 4rth and 5th radio * regulatory requests. * * These are the different values you can use for the regtest * module parameter. This is useful to help test world roaming * and the driver regulatory_hint() call and combinations of these. * If you want to do specific alpha2 regulatory domain tests simply * use the userspace regulatory request as that will be respected as * well without the need of this module parameter. This is designed * only for testing the driver regulatory request, world roaming * and all possible combinations. */ enum hwsim_regtest { HWSIM_REGTEST_DISABLED = 0, HWSIM_REGTEST_DRIVER_REG_FOLLOW = 1, HWSIM_REGTEST_DRIVER_REG_ALL = 2, HWSIM_REGTEST_DIFF_COUNTRY = 3, HWSIM_REGTEST_WORLD_ROAM = 4, HWSIM_REGTEST_CUSTOM_WORLD = 5, HWSIM_REGTEST_CUSTOM_WORLD_2 = 6, HWSIM_REGTEST_STRICT_FOLLOW = 7, HWSIM_REGTEST_STRICT_ALL = 8, HWSIM_REGTEST_STRICT_AND_DRIVER_REG = 9, HWSIM_REGTEST_ALL = 10, }; /* Set to one of the HWSIM_REGTEST_* values above */ static int regtest = HWSIM_REGTEST_DISABLED; module_param(regtest, int, 0444); MODULE_PARM_DESC(regtest, "The type of regulatory test we want to run"); static const char *hwsim_alpha2s[] = { "FI", "AL", "US", "DE", "JP", "AL", }; static const struct ieee80211_regdomain hwsim_world_regdom_custom_01 = { .n_reg_rules = 5, .alpha2 = "99", .reg_rules = { REG_RULE(2412-10, 2462+10, 40, 0, 20, 0), REG_RULE(2484-10, 2484+10, 40, 0, 20, 0), REG_RULE(5150-10, 5240+10, 40, 0, 30, 0), REG_RULE(5745-10, 5825+10, 40, 0, 30, 0), REG_RULE(5855-10, 5925+10, 40, 0, 33, 0), } }; static const struct ieee80211_regdomain hwsim_world_regdom_custom_02 = { .n_reg_rules = 3, .alpha2 = "99", .reg_rules = { REG_RULE(2412-10, 2462+10, 40, 0, 20, 0), REG_RULE(5725-10, 5850+10, 40, 0, 30, NL80211_RRF_NO_IR), REG_RULE(5855-10, 5925+10, 40, 0, 33, 0), } }; static const struct ieee80211_regdomain hwsim_world_regdom_custom_03 = { .n_reg_rules = 6, .alpha2 = "99", .reg_rules = { REG_RULE(2412 - 10, 2462 + 10, 40, 0, 20, 0), REG_RULE(2484 - 10, 2484 + 10, 40, 0, 20, 0), REG_RULE(5150 - 10, 5240 + 10, 40, 0, 30, 0), REG_RULE(5745 - 10, 5825 + 10, 40, 0, 30, 0), REG_RULE(5855 - 10, 5925 + 10, 40, 0, 33, 0), REG_RULE(5955 - 10, 7125 + 10, 320, 0, 33, 0), } }; static const struct ieee80211_regdomain hwsim_world_regdom_custom_04 = { .n_reg_rules = 6, .alpha2 = "99", .reg_rules = { REG_RULE(2412 - 10, 2462 + 10, 40, 0, 20, 0), REG_RULE(2484 - 10, 2484 + 10, 40, 0, 20, 0), REG_RULE(5150 - 10, 5240 + 10, 80, 0, 30, NL80211_RRF_AUTO_BW), REG_RULE(5260 - 10, 5320 + 10, 80, 0, 30, NL80211_RRF_DFS_CONCURRENT | NL80211_RRF_DFS | NL80211_RRF_AUTO_BW), REG_RULE(5500 - 10, 5720 + 10, 160, 0, 30, NL80211_RRF_DFS_CONCURRENT | NL80211_RRF_DFS), REG_RULE(5745 - 10, 5825 + 10, 80, 0, 30, 0), REG_RULE(5855 - 10, 5925 + 10, 80, 0, 33, 0), } }; static const struct ieee80211_regdomain *hwsim_world_regdom_custom[] = { &hwsim_world_regdom_custom_01, &hwsim_world_regdom_custom_02, &hwsim_world_regdom_custom_03, &hwsim_world_regdom_custom_04, }; struct hwsim_vif_priv { u32 magic; u32 skip_beacons[IEEE80211_MLD_MAX_NUM_LINKS]; u8 bssid[ETH_ALEN]; bool assoc; bool bcn_en; u16 aid; }; #define HWSIM_VIF_MAGIC 0x69537748 static inline void hwsim_check_magic(struct ieee80211_vif *vif) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; WARN(vp->magic != HWSIM_VIF_MAGIC, "Invalid VIF (%p) magic %#x, %pM, %d/%d\n", vif, vp->magic, vif->addr, vif->type, vif->p2p); } static inline void hwsim_set_magic(struct ieee80211_vif *vif) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; vp->magic = HWSIM_VIF_MAGIC; } static inline void hwsim_clear_magic(struct ieee80211_vif *vif) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; vp->magic = 0; } struct hwsim_sta_priv { u32 magic; unsigned int last_link; u16 active_links_rx; }; #define HWSIM_STA_MAGIC 0x6d537749 static inline void hwsim_check_sta_magic(struct ieee80211_sta *sta) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; WARN_ON(sp->magic != HWSIM_STA_MAGIC); } static inline void hwsim_set_sta_magic(struct ieee80211_sta *sta) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; sp->magic = HWSIM_STA_MAGIC; } static inline void hwsim_clear_sta_magic(struct ieee80211_sta *sta) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; sp->magic = 0; } struct hwsim_chanctx_priv { u32 magic; }; #define HWSIM_CHANCTX_MAGIC 0x6d53774a static inline void hwsim_check_chanctx_magic(struct ieee80211_chanctx_conf *c) { struct hwsim_chanctx_priv *cp = (void *)c->drv_priv; WARN_ON(cp->magic != HWSIM_CHANCTX_MAGIC); } static inline void hwsim_set_chanctx_magic(struct ieee80211_chanctx_conf *c) { struct hwsim_chanctx_priv *cp = (void *)c->drv_priv; cp->magic = HWSIM_CHANCTX_MAGIC; } static inline void hwsim_clear_chanctx_magic(struct ieee80211_chanctx_conf *c) { struct hwsim_chanctx_priv *cp = (void *)c->drv_priv; cp->magic = 0; } static unsigned int hwsim_net_id; static DEFINE_IDA(hwsim_netgroup_ida); struct hwsim_net { int netgroup; u32 wmediumd; }; static inline int hwsim_net_get_netgroup(struct net *net) { struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id); return hwsim_net->netgroup; } static inline int hwsim_net_set_netgroup(struct net *net) { struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id); hwsim_net->netgroup = ida_alloc(&hwsim_netgroup_ida, GFP_KERNEL); return hwsim_net->netgroup >= 0 ? 0 : -ENOMEM; } static inline u32 hwsim_net_get_wmediumd(struct net *net) { struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id); return hwsim_net->wmediumd; } static inline void hwsim_net_set_wmediumd(struct net *net, u32 portid) { struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id); hwsim_net->wmediumd = portid; } static struct class *hwsim_class; static struct net_device *hwsim_mon; /* global monitor netdev */ #define CHAN2G(_freq) { \ .band = NL80211_BAND_2GHZ, \ .center_freq = (_freq), \ .hw_value = (_freq), \ } #define CHAN5G(_freq) { \ .band = NL80211_BAND_5GHZ, \ .center_freq = (_freq), \ .hw_value = (_freq), \ } #define CHAN6G(_freq) { \ .band = NL80211_BAND_6GHZ, \ .center_freq = (_freq), \ .hw_value = (_freq), \ } static const struct ieee80211_channel hwsim_channels_2ghz[] = { CHAN2G(2412), /* Channel 1 */ CHAN2G(2417), /* Channel 2 */ CHAN2G(2422), /* Channel 3 */ CHAN2G(2427), /* Channel 4 */ CHAN2G(2432), /* Channel 5 */ CHAN2G(2437), /* Channel 6 */ CHAN2G(2442), /* Channel 7 */ CHAN2G(2447), /* Channel 8 */ CHAN2G(2452), /* Channel 9 */ CHAN2G(2457), /* Channel 10 */ CHAN2G(2462), /* Channel 11 */ CHAN2G(2467), /* Channel 12 */ CHAN2G(2472), /* Channel 13 */ CHAN2G(2484), /* Channel 14 */ }; static const struct ieee80211_channel hwsim_channels_5ghz[] = { CHAN5G(5180), /* Channel 36 */ CHAN5G(5200), /* Channel 40 */ CHAN5G(5220), /* Channel 44 */ CHAN5G(5240), /* Channel 48 */ CHAN5G(5260), /* Channel 52 */ CHAN5G(5280), /* Channel 56 */ CHAN5G(5300), /* Channel 60 */ CHAN5G(5320), /* Channel 64 */ CHAN5G(5500), /* Channel 100 */ CHAN5G(5520), /* Channel 104 */ CHAN5G(5540), /* Channel 108 */ CHAN5G(5560), /* Channel 112 */ CHAN5G(5580), /* Channel 116 */ CHAN5G(5600), /* Channel 120 */ CHAN5G(5620), /* Channel 124 */ CHAN5G(5640), /* Channel 128 */ CHAN5G(5660), /* Channel 132 */ CHAN5G(5680), /* Channel 136 */ CHAN5G(5700), /* Channel 140 */ CHAN5G(5745), /* Channel 149 */ CHAN5G(5765), /* Channel 153 */ CHAN5G(5785), /* Channel 157 */ CHAN5G(5805), /* Channel 161 */ CHAN5G(5825), /* Channel 165 */ CHAN5G(5845), /* Channel 169 */ CHAN5G(5855), /* Channel 171 */ CHAN5G(5860), /* Channel 172 */ CHAN5G(5865), /* Channel 173 */ CHAN5G(5870), /* Channel 174 */ CHAN5G(5875), /* Channel 175 */ CHAN5G(5880), /* Channel 176 */ CHAN5G(5885), /* Channel 177 */ CHAN5G(5890), /* Channel 178 */ CHAN5G(5895), /* Channel 179 */ CHAN5G(5900), /* Channel 180 */ CHAN5G(5905), /* Channel 181 */ CHAN5G(5910), /* Channel 182 */ CHAN5G(5915), /* Channel 183 */ CHAN5G(5920), /* Channel 184 */ CHAN5G(5925), /* Channel 185 */ }; static const struct ieee80211_channel hwsim_channels_6ghz[] = { CHAN6G(5955), /* Channel 1 */ CHAN6G(5975), /* Channel 5 */ CHAN6G(5995), /* Channel 9 */ CHAN6G(6015), /* Channel 13 */ CHAN6G(6035), /* Channel 17 */ CHAN6G(6055), /* Channel 21 */ CHAN6G(6075), /* Channel 25 */ CHAN6G(6095), /* Channel 29 */ CHAN6G(6115), /* Channel 33 */ CHAN6G(6135), /* Channel 37 */ CHAN6G(6155), /* Channel 41 */ CHAN6G(6175), /* Channel 45 */ CHAN6G(6195), /* Channel 49 */ CHAN6G(6215), /* Channel 53 */ CHAN6G(6235), /* Channel 57 */ CHAN6G(6255), /* Channel 61 */ CHAN6G(6275), /* Channel 65 */ CHAN6G(6295), /* Channel 69 */ CHAN6G(6315), /* Channel 73 */ CHAN6G(6335), /* Channel 77 */ CHAN6G(6355), /* Channel 81 */ CHAN6G(6375), /* Channel 85 */ CHAN6G(6395), /* Channel 89 */ CHAN6G(6415), /* Channel 93 */ CHAN6G(6435), /* Channel 97 */ CHAN6G(6455), /* Channel 181 */ CHAN6G(6475), /* Channel 105 */ CHAN6G(6495), /* Channel 109 */ CHAN6G(6515), /* Channel 113 */ CHAN6G(6535), /* Channel 117 */ CHAN6G(6555), /* Channel 121 */ CHAN6G(6575), /* Channel 125 */ CHAN6G(6595), /* Channel 129 */ CHAN6G(6615), /* Channel 133 */ CHAN6G(6635), /* Channel 137 */ CHAN6G(6655), /* Channel 141 */ CHAN6G(6675), /* Channel 145 */ CHAN6G(6695), /* Channel 149 */ CHAN6G(6715), /* Channel 153 */ CHAN6G(6735), /* Channel 157 */ CHAN6G(6755), /* Channel 161 */ CHAN6G(6775), /* Channel 165 */ CHAN6G(6795), /* Channel 169 */ CHAN6G(6815), /* Channel 173 */ CHAN6G(6835), /* Channel 177 */ CHAN6G(6855), /* Channel 181 */ CHAN6G(6875), /* Channel 185 */ CHAN6G(6895), /* Channel 189 */ CHAN6G(6915), /* Channel 193 */ CHAN6G(6935), /* Channel 197 */ CHAN6G(6955), /* Channel 201 */ CHAN6G(6975), /* Channel 205 */ CHAN6G(6995), /* Channel 209 */ CHAN6G(7015), /* Channel 213 */ CHAN6G(7035), /* Channel 217 */ CHAN6G(7055), /* Channel 221 */ CHAN6G(7075), /* Channel 225 */ CHAN6G(7095), /* Channel 229 */ CHAN6G(7115), /* Channel 233 */ }; #define NUM_S1G_CHANS_US 51 static struct ieee80211_channel hwsim_channels_s1g[NUM_S1G_CHANS_US]; static const struct ieee80211_sta_s1g_cap hwsim_s1g_cap = { .s1g = true, .cap = { S1G_CAP0_SGI_1MHZ | S1G_CAP0_SGI_2MHZ, 0, 0, S1G_CAP3_MAX_MPDU_LEN, 0, S1G_CAP5_AMPDU, 0, S1G_CAP7_DUP_1MHZ, S1G_CAP8_TWT_RESPOND | S1G_CAP8_TWT_REQUEST, 0}, .nss_mcs = { 0xfc | 1, /* MCS 7 for 1 SS */ /* RX Highest Supported Long GI Data Rate 0:7 */ 0, /* RX Highest Supported Long GI Data Rate 0:7 */ /* TX S1G MCS Map 0:6 */ 0xfa, /* TX S1G MCS Map :7 */ /* TX Highest Supported Long GI Data Rate 0:6 */ 0x80, /* TX Highest Supported Long GI Data Rate 7:8 */ /* Rx Single spatial stream and S1G-MCS Map for 1MHz */ /* Tx Single spatial stream and S1G-MCS Map for 1MHz */ 0 }, }; static void hwsim_init_s1g_channels(struct ieee80211_channel *chans) { int ch, freq; for (ch = 0; ch < NUM_S1G_CHANS_US; ch++) { freq = 902000 + (ch + 1) * 500; chans[ch].band = NL80211_BAND_S1GHZ; chans[ch].center_freq = KHZ_TO_MHZ(freq); chans[ch].freq_offset = freq % 1000; chans[ch].hw_value = ch + 1; } } static const struct ieee80211_rate hwsim_rates[] = { { .bitrate = 10 }, { .bitrate = 20, .flags = IEEE80211_RATE_SHORT_PREAMBLE }, { .bitrate = 55, .flags = IEEE80211_RATE_SHORT_PREAMBLE }, { .bitrate = 110, .flags = IEEE80211_RATE_SHORT_PREAMBLE }, { .bitrate = 60 }, { .bitrate = 90 }, { .bitrate = 120 }, { .bitrate = 180 }, { .bitrate = 240 }, { .bitrate = 360 }, { .bitrate = 480 }, { .bitrate = 540 } }; #define DEFAULT_RX_RSSI -50 static const u32 hwsim_ciphers[] = { WLAN_CIPHER_SUITE_WEP40, WLAN_CIPHER_SUITE_WEP104, WLAN_CIPHER_SUITE_TKIP, WLAN_CIPHER_SUITE_CCMP, WLAN_CIPHER_SUITE_CCMP_256, WLAN_CIPHER_SUITE_GCMP, WLAN_CIPHER_SUITE_GCMP_256, WLAN_CIPHER_SUITE_AES_CMAC, WLAN_CIPHER_SUITE_BIP_CMAC_256, WLAN_CIPHER_SUITE_BIP_GMAC_128, WLAN_CIPHER_SUITE_BIP_GMAC_256, }; #define OUI_QCA 0x001374 #define QCA_NL80211_SUBCMD_TEST 1 enum qca_nl80211_vendor_subcmds { QCA_WLAN_VENDOR_ATTR_TEST = 8, QCA_WLAN_VENDOR_ATTR_MAX = QCA_WLAN_VENDOR_ATTR_TEST }; static const struct nla_policy hwsim_vendor_test_policy[QCA_WLAN_VENDOR_ATTR_MAX + 1] = { [QCA_WLAN_VENDOR_ATTR_MAX] = { .type = NLA_U32 }, }; static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy, struct wireless_dev *wdev, const void *data, int data_len) { struct sk_buff *skb; struct nlattr *tb[QCA_WLAN_VENDOR_ATTR_MAX + 1]; int err; u32 val; err = nla_parse_deprecated(tb, QCA_WLAN_VENDOR_ATTR_MAX, data, data_len, hwsim_vendor_test_policy, NULL); if (err) return err; if (!tb[QCA_WLAN_VENDOR_ATTR_TEST]) return -EINVAL; val = nla_get_u32(tb[QCA_WLAN_VENDOR_ATTR_TEST]); wiphy_dbg(wiphy, "%s: test=%u\n", __func__, val); /* Send a vendor event as a test. Note that this would not normally be * done within a command handler, but rather, based on some other * trigger. For simplicity, this command is used to trigger the event * here. * * event_idx = 0 (index in mac80211_hwsim_vendor_commands) */ skb = cfg80211_vendor_event_alloc(wiphy, wdev, 100, 0, GFP_KERNEL); if (skb) { /* skb_put() or nla_put() will fill up data within * NL80211_ATTR_VENDOR_DATA. */ /* Add vendor data */ nla_put_u32(skb, QCA_WLAN_VENDOR_ATTR_TEST, val + 1); /* Send the event - this will call nla_nest_end() */ cfg80211_vendor_event(skb, GFP_KERNEL); } /* Send a response to the command */ skb = cfg80211_vendor_cmd_alloc_reply_skb(wiphy, 10); if (!skb) return -ENOMEM; /* skb_put() or nla_put() will fill up data within * NL80211_ATTR_VENDOR_DATA */ nla_put_u32(skb, QCA_WLAN_VENDOR_ATTR_TEST, val + 2); return cfg80211_vendor_cmd_reply(skb); } static struct wiphy_vendor_command mac80211_hwsim_vendor_commands[] = { { .info = { .vendor_id = OUI_QCA, .subcmd = QCA_NL80211_SUBCMD_TEST }, .flags = WIPHY_VENDOR_CMD_NEED_NETDEV, .doit = mac80211_hwsim_vendor_cmd_test, .policy = hwsim_vendor_test_policy, .maxattr = QCA_WLAN_VENDOR_ATTR_MAX, } }; /* Advertise support vendor specific events */ static const struct nl80211_vendor_cmd_info mac80211_hwsim_vendor_events[] = { { .vendor_id = OUI_QCA, .subcmd = 1 }, }; static DEFINE_SPINLOCK(hwsim_radio_lock); static LIST_HEAD(hwsim_radios); static struct rhashtable hwsim_radios_rht; static int hwsim_radio_idx; static int hwsim_radios_generation = 1; static struct platform_driver mac80211_hwsim_driver = { .driver = { .name = "mac80211_hwsim", }, }; struct mac80211_hwsim_link_data { u32 link_id; u64 beacon_int /* beacon interval in us */; struct hrtimer beacon_timer; }; struct mac80211_hwsim_data { struct list_head list; struct rhash_head rht; struct ieee80211_hw *hw; struct device *dev; struct ieee80211_supported_band bands[NUM_NL80211_BANDS]; struct ieee80211_channel channels_2ghz[ARRAY_SIZE(hwsim_channels_2ghz)]; struct ieee80211_channel channels_5ghz[ARRAY_SIZE(hwsim_channels_5ghz)]; struct ieee80211_channel channels_6ghz[ARRAY_SIZE(hwsim_channels_6ghz)]; struct ieee80211_channel channels_s1g[ARRAY_SIZE(hwsim_channels_s1g)]; struct ieee80211_rate rates[ARRAY_SIZE(hwsim_rates)]; struct ieee80211_iface_combination if_combination; struct ieee80211_iface_limit if_limits[3]; int n_if_limits; struct ieee80211_iface_combination if_combination_radio; struct wiphy_radio_freq_range radio_range[NUM_NL80211_BANDS]; struct wiphy_radio radio[NUM_NL80211_BANDS]; u32 ciphers[ARRAY_SIZE(hwsim_ciphers)]; struct mac_address addresses[2]; int channels, idx; bool use_chanctx; bool destroy_on_close; u32 portid; char alpha2[2]; const struct ieee80211_regdomain *regd; struct ieee80211_channel *tmp_chan; struct ieee80211_channel *roc_chan; u32 roc_duration; struct delayed_work roc_start; struct delayed_work roc_done; struct delayed_work hw_scan; struct cfg80211_scan_request *hw_scan_request; struct ieee80211_vif *hw_scan_vif; int scan_chan_idx; u8 scan_addr[ETH_ALEN]; struct { struct ieee80211_channel *channel; unsigned long next_start, start, end; } survey_data[ARRAY_SIZE(hwsim_channels_2ghz) + ARRAY_SIZE(hwsim_channels_5ghz) + ARRAY_SIZE(hwsim_channels_6ghz)]; struct ieee80211_channel *channel; enum nl80211_chan_width bw; unsigned int rx_filter; bool started, idle, scanning; struct mutex mutex; enum ps_mode { PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL } ps; bool ps_poll_pending; struct dentry *debugfs; atomic_t pending_cookie; struct sk_buff_head pending; /* packets pending */ /* * Only radios in the same group can communicate together (the * channel has to match too). Each bit represents a group. A * radio can be in more than one group. */ u64 group; /* group shared by radios created in the same netns */ int netgroup; /* wmediumd portid responsible for netgroup of this radio */ u32 wmediumd; /* difference between this hw's clock and the real clock, in usecs */ s64 tsf_offset; s64 bcn_delta; /* absolute beacon transmission time. Used to cover up "tx" delay. */ u64 abs_bcn_ts; /* Stats */ u64 tx_pkts; u64 rx_pkts; u64 tx_bytes; u64 rx_bytes; u64 tx_dropped; u64 tx_failed; /* RSSI in rx status of the receiver */ int rx_rssi; /* only used when pmsr capability is supplied */ struct cfg80211_pmsr_capabilities pmsr_capa; struct cfg80211_pmsr_request *pmsr_request; struct wireless_dev *pmsr_request_wdev; struct mac80211_hwsim_link_data link_data[IEEE80211_MLD_MAX_NUM_LINKS]; }; static const struct rhashtable_params hwsim_rht_params = { .nelem_hint = 2, .automatic_shrinking = true, .key_len = ETH_ALEN, .key_offset = offsetof(struct mac80211_hwsim_data, addresses[1]), .head_offset = offsetof(struct mac80211_hwsim_data, rht), }; struct hwsim_radiotap_hdr { struct ieee80211_radiotap_header_fixed hdr; __le64 rt_tsft; u8 rt_flags; u8 rt_rate; __le16 rt_channel; __le16 rt_chbitmask; } __packed; struct hwsim_radiotap_ack_hdr { struct ieee80211_radiotap_header_fixed hdr; u8 rt_flags; u8 pad; __le16 rt_channel; __le16 rt_chbitmask; } __packed; static struct mac80211_hwsim_data *get_hwsim_data_ref_from_addr(const u8 *addr) { return rhashtable_lookup_fast(&hwsim_radios_rht, addr, hwsim_rht_params); } /* MAC80211_HWSIM netlink family */ static struct genl_family hwsim_genl_family; enum hwsim_multicast_groups { HWSIM_MCGRP_CONFIG, }; static const struct genl_multicast_group hwsim_mcgrps[] = { [HWSIM_MCGRP_CONFIG] = { .name = "config", }, }; /* MAC80211_HWSIM netlink policy */ static const struct nla_policy hwsim_rate_info_policy[HWSIM_RATE_INFO_ATTR_MAX + 1] = { [HWSIM_RATE_INFO_ATTR_FLAGS] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_MCS] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_LEGACY] = { .type = NLA_U16 }, [HWSIM_RATE_INFO_ATTR_NSS] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_BW] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_HE_GI] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_HE_DCM] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_HE_RU_ALLOC] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_N_BOUNDED_CH] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_EHT_GI] = { .type = NLA_U8 }, [HWSIM_RATE_INFO_ATTR_EHT_RU_ALLOC] = { .type = NLA_U8 }, }; static const struct nla_policy hwsim_ftm_result_policy[NL80211_PMSR_FTM_RESP_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_RESP_ATTR_BURST_INDEX] = { .type = NLA_U16 }, [NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_RESP_ATTR_BURST_DURATION] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_RESP_ATTR_FTMS_PER_BURST] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_RESP_ATTR_RSSI_AVG] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_RESP_ATTR_RSSI_SPREAD] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_RESP_ATTR_TX_RATE] = NLA_POLICY_NESTED(hwsim_rate_info_policy), [NL80211_PMSR_FTM_RESP_ATTR_RX_RATE] = NLA_POLICY_NESTED(hwsim_rate_info_policy), [NL80211_PMSR_FTM_RESP_ATTR_RTT_AVG] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_RESP_ATTR_RTT_VARIANCE] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_RESP_ATTR_RTT_SPREAD] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_RESP_ATTR_DIST_AVG] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_RESP_ATTR_DIST_VARIANCE] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_RESP_ATTR_DIST_SPREAD] = { .type = NLA_U64 }, [NL80211_PMSR_FTM_RESP_ATTR_LCI] = { .type = NLA_STRING }, [NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC] = { .type = NLA_STRING }, }; static const struct nla_policy hwsim_pmsr_resp_type_policy[NL80211_PMSR_TYPE_MAX + 1] = { [NL80211_PMSR_TYPE_FTM] = NLA_POLICY_NESTED(hwsim_ftm_result_policy), }; static const struct nla_policy hwsim_pmsr_resp_policy[NL80211_PMSR_RESP_ATTR_MAX + 1] = { [NL80211_PMSR_RESP_ATTR_STATUS] = { .type = NLA_U32 }, [NL80211_PMSR_RESP_ATTR_HOST_TIME] = { .type = NLA_U64 }, [NL80211_PMSR_RESP_ATTR_AP_TSF] = { .type = NLA_U64 }, [NL80211_PMSR_RESP_ATTR_FINAL] = { .type = NLA_FLAG }, [NL80211_PMSR_RESP_ATTR_DATA] = NLA_POLICY_NESTED(hwsim_pmsr_resp_type_policy), }; static const struct nla_policy hwsim_pmsr_peer_result_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { [NL80211_PMSR_PEER_ATTR_ADDR] = NLA_POLICY_ETH_ADDR_COMPAT, [NL80211_PMSR_PEER_ATTR_CHAN] = { .type = NLA_REJECT }, [NL80211_PMSR_PEER_ATTR_REQ] = { .type = NLA_REJECT }, [NL80211_PMSR_PEER_ATTR_RESP] = NLA_POLICY_NESTED(hwsim_pmsr_resp_policy), }; static const struct nla_policy hwsim_pmsr_peers_result_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_MAX_PEERS] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_REPORT_AP_TSF] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_PEERS] = NLA_POLICY_NESTED_ARRAY(hwsim_pmsr_peer_result_policy), }; static const struct nla_policy hwsim_ftm_capa_policy[NL80211_PMSR_FTM_CAPA_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_CAPA_ATTR_ASAP] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_CAPA_ATTR_NON_ASAP] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_CAPA_ATTR_REQ_LCI] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_CAPA_ATTR_REQ_CIVICLOC] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_CAPA_ATTR_PREAMBLES] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_CAPA_ATTR_BANDWIDTHS] = { .type = NLA_U32 }, [NL80211_PMSR_FTM_CAPA_ATTR_MAX_BURSTS_EXPONENT] = NLA_POLICY_MAX(NLA_U8, 15), [NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST] = NLA_POLICY_MAX(NLA_U8, 31), [NL80211_PMSR_FTM_CAPA_ATTR_TRIGGER_BASED] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED] = { .type = NLA_FLAG }, }; static const struct nla_policy hwsim_pmsr_capa_type_policy[NL80211_PMSR_TYPE_MAX + 1] = { [NL80211_PMSR_TYPE_FTM] = NLA_POLICY_NESTED(hwsim_ftm_capa_policy), }; static const struct nla_policy hwsim_pmsr_capa_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_MAX_PEERS] = { .type = NLA_U32 }, [NL80211_PMSR_ATTR_REPORT_AP_TSF] = { .type = NLA_FLAG }, [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_FLAG }, [NL80211_PMSR_ATTR_TYPE_CAPA] = NLA_POLICY_NESTED(hwsim_pmsr_capa_type_policy), [NL80211_PMSR_ATTR_PEERS] = { .type = NLA_REJECT }, // only for request. }; static const struct nla_policy hwsim_genl_policy[HWSIM_ATTR_MAX + 1] = { [HWSIM_ATTR_ADDR_RECEIVER] = NLA_POLICY_ETH_ADDR_COMPAT, [HWSIM_ATTR_ADDR_TRANSMITTER] = NLA_POLICY_ETH_ADDR_COMPAT, [HWSIM_ATTR_FRAME] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, [HWSIM_ATTR_FLAGS] = { .type = NLA_U32 }, [HWSIM_ATTR_RX_RATE] = { .type = NLA_U32 }, [HWSIM_ATTR_SIGNAL] = { .type = NLA_U32 }, [HWSIM_ATTR_TX_INFO] = { .type = NLA_BINARY, .len = IEEE80211_TX_MAX_RATES * sizeof(struct hwsim_tx_rate)}, [HWSIM_ATTR_COOKIE] = { .type = NLA_U64 }, [HWSIM_ATTR_CHANNELS] = { .type = NLA_U32 }, [HWSIM_ATTR_RADIO_ID] = { .type = NLA_U32 }, [HWSIM_ATTR_REG_HINT_ALPHA2] = { .type = NLA_STRING, .len = 2 }, [HWSIM_ATTR_REG_CUSTOM_REG] = { .type = NLA_U32 }, [HWSIM_ATTR_REG_STRICT_REG] = { .type = NLA_FLAG }, [HWSIM_ATTR_SUPPORT_P2P_DEVICE] = { .type = NLA_FLAG }, [HWSIM_ATTR_USE_CHANCTX] = { .type = NLA_FLAG }, [HWSIM_ATTR_DESTROY_RADIO_ON_CLOSE] = { .type = NLA_FLAG }, [HWSIM_ATTR_RADIO_NAME] = { .type = NLA_STRING }, [HWSIM_ATTR_NO_VIF] = { .type = NLA_FLAG }, [HWSIM_ATTR_FREQ] = { .type = NLA_U32 }, [HWSIM_ATTR_TX_INFO_FLAGS] = { .type = NLA_BINARY }, [HWSIM_ATTR_PERM_ADDR] = NLA_POLICY_ETH_ADDR_COMPAT, [HWSIM_ATTR_IFTYPE_SUPPORT] = { .type = NLA_U32 }, [HWSIM_ATTR_CIPHER_SUPPORT] = { .type = NLA_BINARY }, [HWSIM_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, [HWSIM_ATTR_PMSR_SUPPORT] = NLA_POLICY_NESTED(hwsim_pmsr_capa_policy), [HWSIM_ATTR_PMSR_RESULT] = NLA_POLICY_NESTED(hwsim_pmsr_peers_result_policy), [HWSIM_ATTR_MULTI_RADIO] = { .type = NLA_FLAG }, }; #if IS_REACHABLE(CONFIG_VIRTIO) /* MAC80211_HWSIM virtio queues */ static struct virtqueue *hwsim_vqs[HWSIM_NUM_VQS]; static bool hwsim_virtio_enabled; static DEFINE_SPINLOCK(hwsim_virtio_lock); static void hwsim_virtio_rx_work(struct work_struct *work); static DECLARE_WORK(hwsim_virtio_rx, hwsim_virtio_rx_work); static int hwsim_tx_virtio(struct mac80211_hwsim_data *data, struct sk_buff *skb) { struct scatterlist sg[1]; unsigned long flags; int err; spin_lock_irqsave(&hwsim_virtio_lock, flags); if (!hwsim_virtio_enabled) { err = -ENODEV; goto out_free; } sg_init_one(sg, skb->head, skb_end_offset(skb)); err = virtqueue_add_outbuf(hwsim_vqs[HWSIM_VQ_TX], sg, 1, skb, GFP_ATOMIC); if (err) goto out_free; virtqueue_kick(hwsim_vqs[HWSIM_VQ_TX]); spin_unlock_irqrestore(&hwsim_virtio_lock, flags); return 0; out_free: spin_unlock_irqrestore(&hwsim_virtio_lock, flags); nlmsg_free(skb); return err; } #else /* cause a linker error if this ends up being needed */ extern int hwsim_tx_virtio(struct mac80211_hwsim_data *data, struct sk_buff *skb); #define hwsim_virtio_enabled false #endif static int hwsim_get_chanwidth(enum nl80211_chan_width bw) { switch (bw) { case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: return 20; case NL80211_CHAN_WIDTH_40: return 40; case NL80211_CHAN_WIDTH_80: return 80; case NL80211_CHAN_WIDTH_80P80: case NL80211_CHAN_WIDTH_160: return 160; case NL80211_CHAN_WIDTH_320: return 320; case NL80211_CHAN_WIDTH_5: return 5; case NL80211_CHAN_WIDTH_10: return 10; case NL80211_CHAN_WIDTH_1: return 1; case NL80211_CHAN_WIDTH_2: return 2; case NL80211_CHAN_WIDTH_4: return 4; case NL80211_CHAN_WIDTH_8: return 8; case NL80211_CHAN_WIDTH_16: return 16; } return INT_MAX; } static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, struct sk_buff *skb, struct ieee80211_channel *chan); /* sysfs attributes */ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *data = dat; struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct sk_buff *skb; struct ieee80211_pspoll *pspoll; if (!vp->assoc) return; wiphy_dbg(data->hw->wiphy, "%s: send PS-Poll to %pM for aid %d\n", __func__, vp->bssid, vp->aid); skb = dev_alloc_skb(sizeof(*pspoll)); if (!skb) return; pspoll = skb_put(skb, sizeof(*pspoll)); pspoll->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL | IEEE80211_FCTL_PM); pspoll->aid = cpu_to_le16(0xc000 | vp->aid); memcpy(pspoll->bssid, vp->bssid, ETH_ALEN); memcpy(pspoll->ta, mac, ETH_ALEN); rcu_read_lock(); mac80211_hwsim_tx_frame(data->hw, skb, rcu_dereference(vif->bss_conf.chanctx_conf)->def.chan); rcu_read_unlock(); } static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, struct ieee80211_vif *vif, int ps) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct sk_buff *skb; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *cb; if (!vp->assoc) return; wiphy_dbg(data->hw->wiphy, "%s: send data::nullfunc to %pM ps=%d\n", __func__, vp->bssid, ps); skb = dev_alloc_skb(sizeof(*hdr)); if (!skb) return; hdr = skb_put(skb, sizeof(*hdr) - ETH_ALEN); hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | IEEE80211_FCTL_TODS | (ps ? IEEE80211_FCTL_PM : 0)); hdr->duration_id = cpu_to_le16(0); memcpy(hdr->addr1, vp->bssid, ETH_ALEN); memcpy(hdr->addr2, mac, ETH_ALEN); memcpy(hdr->addr3, vp->bssid, ETH_ALEN); cb = IEEE80211_SKB_CB(skb); cb->control.rates[0].count = 1; cb->control.rates[1].idx = -1; rcu_read_lock(); mac80211_hwsim_tx_frame(data->hw, skb, rcu_dereference(vif->bss_conf.chanctx_conf)->def.chan); rcu_read_unlock(); } static void hwsim_send_nullfunc_ps(void *dat, u8 *mac, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *data = dat; hwsim_send_nullfunc(data, mac, vif, 1); } static void hwsim_send_nullfunc_no_ps(void *dat, u8 *mac, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *data = dat; hwsim_send_nullfunc(data, mac, vif, 0); } static int hwsim_fops_ps_read(void *dat, u64 *val) { struct mac80211_hwsim_data *data = dat; *val = data->ps; return 0; } static int hwsim_fops_ps_write(void *dat, u64 val) { struct mac80211_hwsim_data *data = dat; enum ps_mode old_ps; if (val != PS_DISABLED && val != PS_ENABLED && val != PS_AUTO_POLL && val != PS_MANUAL_POLL) return -EINVAL; if (val == PS_MANUAL_POLL) { if (data->ps != PS_ENABLED) return -EINVAL; local_bh_disable(); ieee80211_iterate_active_interfaces_atomic( data->hw, IEEE80211_IFACE_ITER_NORMAL, hwsim_send_ps_poll, data); local_bh_enable(); return 0; } old_ps = data->ps; data->ps = val; local_bh_disable(); if (old_ps == PS_DISABLED && val != PS_DISABLED) { ieee80211_iterate_active_interfaces_atomic( data->hw, IEEE80211_IFACE_ITER_NORMAL, hwsim_send_nullfunc_ps, data); } else if (old_ps != PS_DISABLED && val == PS_DISABLED) { ieee80211_iterate_active_interfaces_atomic( data->hw, IEEE80211_IFACE_ITER_NORMAL, hwsim_send_nullfunc_no_ps, data); } local_bh_enable(); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(hwsim_fops_ps, hwsim_fops_ps_read, hwsim_fops_ps_write, "%llu\n"); static int hwsim_write_simulate_radar(void *dat, u64 val) { struct mac80211_hwsim_data *data = dat; ieee80211_radar_detected(data->hw, NULL); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(hwsim_simulate_radar, NULL, hwsim_write_simulate_radar, "%llu\n"); static int hwsim_fops_group_read(void *dat, u64 *val) { struct mac80211_hwsim_data *data = dat; *val = data->group; return 0; } static int hwsim_fops_group_write(void *dat, u64 val) { struct mac80211_hwsim_data *data = dat; data->group = val; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(hwsim_fops_group, hwsim_fops_group_read, hwsim_fops_group_write, "%llx\n"); static int hwsim_fops_rx_rssi_read(void *dat, u64 *val) { struct mac80211_hwsim_data *data = dat; *val = data->rx_rssi; return 0; } static int hwsim_fops_rx_rssi_write(void *dat, u64 val) { struct mac80211_hwsim_data *data = dat; int rssi = (int)val; if (rssi >= 0 || rssi < -100) return -EINVAL; data->rx_rssi = rssi; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(hwsim_fops_rx_rssi, hwsim_fops_rx_rssi_read, hwsim_fops_rx_rssi_write, "%lld\n"); static netdev_tx_t hwsim_mon_xmit(struct sk_buff *skb, struct net_device *dev) { /* TODO: allow packet injection */ dev_kfree_skb(skb); return NETDEV_TX_OK; } static inline u64 mac80211_hwsim_get_tsf_raw(void) { return ktime_to_us(ktime_get_real()); } static __le64 __mac80211_hwsim_get_tsf(struct mac80211_hwsim_data *data) { u64 now = mac80211_hwsim_get_tsf_raw(); return cpu_to_le64(now + data->tsf_offset); } static u64 mac80211_hwsim_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *data = hw->priv; return le64_to_cpu(__mac80211_hwsim_get_tsf(data)); } static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 tsf) { struct mac80211_hwsim_data *data = hw->priv; u64 now = mac80211_hwsim_get_tsf(hw, vif); /* MLD not supported here */ u32 bcn_int = data->link_data[0].beacon_int; u64 delta = abs(tsf - now); struct ieee80211_bss_conf *conf; conf = link_conf_dereference_protected(vif, data->link_data[0].link_id); if (conf && !conf->enable_beacon) return; /* adjust after beaconing with new timestamp at old TBTT */ if (tsf > now) { data->tsf_offset += delta; data->bcn_delta = do_div(delta, bcn_int); } else { data->tsf_offset -= delta; data->bcn_delta = -(s64)do_div(delta, bcn_int); } } static void mac80211_hwsim_monitor_rx(struct ieee80211_hw *hw, struct sk_buff *tx_skb, struct ieee80211_channel *chan) { struct mac80211_hwsim_data *data = hw->priv; struct sk_buff *skb; struct hwsim_radiotap_hdr *hdr; u16 flags, bitrate; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_skb); struct ieee80211_rate *txrate = ieee80211_get_tx_rate(hw, info); if (!txrate) bitrate = 0; else bitrate = txrate->bitrate; if (!netif_running(hwsim_mon)) return; skb = skb_copy_expand(tx_skb, sizeof(*hdr), 0, GFP_ATOMIC); if (skb == NULL) return; hdr = skb_push(skb, sizeof(*hdr)); hdr->hdr.it_version = PKTHDR_RADIOTAP_VERSION; hdr->hdr.it_pad = 0; hdr->hdr.it_len = cpu_to_le16(sizeof(*hdr)); hdr->hdr.it_present = cpu_to_le32((1 << IEEE80211_RADIOTAP_FLAGS) | (1 << IEEE80211_RADIOTAP_RATE) | (1 << IEEE80211_RADIOTAP_TSFT) | (1 << IEEE80211_RADIOTAP_CHANNEL)); hdr->rt_tsft = __mac80211_hwsim_get_tsf(data); hdr->rt_flags = 0; hdr->rt_rate = bitrate / 5; hdr->rt_channel = cpu_to_le16(chan->center_freq); flags = IEEE80211_CHAN_2GHZ; if (txrate && txrate->flags & IEEE80211_RATE_ERP_G) flags |= IEEE80211_CHAN_OFDM; else flags |= IEEE80211_CHAN_CCK; hdr->rt_chbitmask = cpu_to_le16(flags); skb->dev = hwsim_mon; skb_reset_mac_header(skb); skb->ip_summed = CHECKSUM_UNNECESSARY; skb->pkt_type = PACKET_OTHERHOST; skb->protocol = htons(ETH_P_802_2); memset(skb->cb, 0, sizeof(skb->cb)); netif_rx(skb); } static void mac80211_hwsim_monitor_ack(struct ieee80211_channel *chan, const u8 *addr) { struct sk_buff *skb; struct hwsim_radiotap_ack_hdr *hdr; u16 flags; struct ieee80211_hdr *hdr11; if (!netif_running(hwsim_mon)) return; skb = dev_alloc_skb(100); if (skb == NULL) return; hdr = skb_put(skb, sizeof(*hdr)); hdr->hdr.it_version = PKTHDR_RADIOTAP_VERSION; hdr->hdr.it_pad = 0; hdr->hdr.it_len = cpu_to_le16(sizeof(*hdr)); hdr->hdr.it_present = cpu_to_le32((1 << IEEE80211_RADIOTAP_FLAGS) | (1 << IEEE80211_RADIOTAP_CHANNEL)); hdr->rt_flags = 0; hdr->pad = 0; hdr->rt_channel = cpu_to_le16(chan->center_freq); flags = IEEE80211_CHAN_2GHZ; hdr->rt_chbitmask = cpu_to_le16(flags); hdr11 = skb_put(skb, 10); hdr11->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK); hdr11->duration_id = cpu_to_le16(0); memcpy(hdr11->addr1, addr, ETH_ALEN); skb->dev = hwsim_mon; skb_reset_mac_header(skb); skb->ip_summed = CHECKSUM_UNNECESSARY; skb->pkt_type = PACKET_OTHERHOST; skb->protocol = htons(ETH_P_802_2); memset(skb->cb, 0, sizeof(skb->cb)); netif_rx(skb); } struct mac80211_hwsim_addr_match_data { u8 addr[ETH_ALEN]; bool ret; }; static void mac80211_hwsim_addr_iter(void *data, u8 *mac, struct ieee80211_vif *vif) { int i; struct mac80211_hwsim_addr_match_data *md = data; if (memcmp(mac, md->addr, ETH_ALEN) == 0) { md->ret = true; return; } /* Match the link address */ for (i = 0; i < ARRAY_SIZE(vif->link_conf); i++) { struct ieee80211_bss_conf *conf; conf = rcu_dereference(vif->link_conf[i]); if (!conf) continue; if (memcmp(conf->addr, md->addr, ETH_ALEN) == 0) { md->ret = true; return; } } } static bool mac80211_hwsim_addr_match(struct mac80211_hwsim_data *data, const u8 *addr) { struct mac80211_hwsim_addr_match_data md = { .ret = false, }; if (data->scanning && memcmp(addr, data->scan_addr, ETH_ALEN) == 0) return true; memcpy(md.addr, addr, ETH_ALEN); ieee80211_iterate_active_interfaces_atomic(data->hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_addr_iter, &md); return md.ret; } static bool hwsim_ps_rx_ok(struct mac80211_hwsim_data *data, struct sk_buff *skb) { switch (data->ps) { case PS_DISABLED: return true; case PS_ENABLED: return false; case PS_AUTO_POLL: /* TODO: accept (some) Beacons by default and other frames only * if pending PS-Poll has been sent */ return true; case PS_MANUAL_POLL: /* Allow unicast frames to own address if there is a pending * PS-Poll */ if (data->ps_poll_pending && mac80211_hwsim_addr_match(data, skb->data + 4)) { data->ps_poll_pending = false; return true; } return false; } return true; } static int hwsim_unicast_netgroup(struct mac80211_hwsim_data *data, struct sk_buff *skb, int portid) { struct net *net; bool found = false; int res = -ENOENT; rcu_read_lock(); for_each_net_rcu(net) { if (data->netgroup == hwsim_net_get_netgroup(net)) { res = genlmsg_unicast(net, skb, portid); found = true; break; } } rcu_read_unlock(); if (!found) nlmsg_free(skb); return res; } static void mac80211_hwsim_config_mac_nl(struct ieee80211_hw *hw, const u8 *addr, bool add) { struct mac80211_hwsim_data *data = hw->priv; u32 _portid = READ_ONCE(data->wmediumd); struct sk_buff *skb; void *msg_head; WARN_ON(!is_valid_ether_addr(addr)); if (!_portid && !hwsim_virtio_enabled) return; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, add ? HWSIM_CMD_ADD_MAC_ADDR : HWSIM_CMD_DEL_MAC_ADDR); if (!msg_head) { pr_debug("mac80211_hwsim: problem with msg_head\n"); goto nla_put_failure; } if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, data->addresses[1].addr)) goto nla_put_failure; if (nla_put(skb, HWSIM_ATTR_ADDR_RECEIVER, ETH_ALEN, addr)) goto nla_put_failure; genlmsg_end(skb, msg_head); if (hwsim_virtio_enabled) hwsim_tx_virtio(data, skb); else hwsim_unicast_netgroup(data, skb, _portid); return; nla_put_failure: nlmsg_free(skb); } static inline u16 trans_tx_rate_flags_ieee2hwsim(struct ieee80211_tx_rate *rate) { u16 result = 0; if (rate->flags & IEEE80211_TX_RC_USE_RTS_CTS) result |= MAC80211_HWSIM_TX_RC_USE_RTS_CTS; if (rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT) result |= MAC80211_HWSIM_TX_RC_USE_CTS_PROTECT; if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE) result |= MAC80211_HWSIM_TX_RC_USE_SHORT_PREAMBLE; if (rate->flags & IEEE80211_TX_RC_MCS) result |= MAC80211_HWSIM_TX_RC_MCS; if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD) result |= MAC80211_HWSIM_TX_RC_GREEN_FIELD; if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) result |= MAC80211_HWSIM_TX_RC_40_MHZ_WIDTH; if (rate->flags & IEEE80211_TX_RC_DUP_DATA) result |= MAC80211_HWSIM_TX_RC_DUP_DATA; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) result |= MAC80211_HWSIM_TX_RC_SHORT_GI; if (rate->flags & IEEE80211_TX_RC_VHT_MCS) result |= MAC80211_HWSIM_TX_RC_VHT_MCS; if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) result |= MAC80211_HWSIM_TX_RC_80_MHZ_WIDTH; if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) result |= MAC80211_HWSIM_TX_RC_160_MHZ_WIDTH; return result; } static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, struct sk_buff *my_skb, int dst_portid, struct ieee80211_channel *channel) { struct sk_buff *skb; struct mac80211_hwsim_data *data = hw->priv; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) my_skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(my_skb); void *msg_head; unsigned int hwsim_flags = 0; int i; struct hwsim_tx_rate tx_attempts[IEEE80211_TX_MAX_RATES]; struct hwsim_tx_rate_flag tx_attempts_flags[IEEE80211_TX_MAX_RATES]; uintptr_t cookie; if (data->ps != PS_DISABLED) hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PM); /* If the queue contains MAX_QUEUE skb's drop some */ if (skb_queue_len(&data->pending) >= MAX_QUEUE) { /* Dropping until WARN_QUEUE level */ while (skb_queue_len(&data->pending) >= WARN_QUEUE) { ieee80211_free_txskb(hw, skb_dequeue(&data->pending)); data->tx_dropped++; } } skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (skb == NULL) goto nla_put_failure; msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_FRAME); if (msg_head == NULL) { pr_debug("mac80211_hwsim: problem with msg_head\n"); goto nla_put_failure; } if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, data->addresses[1].addr)) goto nla_put_failure; /* We get the skb->data */ if (nla_put(skb, HWSIM_ATTR_FRAME, my_skb->len, my_skb->data)) goto nla_put_failure; /* We get the flags for this transmission, and we translate them to wmediumd flags */ if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) hwsim_flags |= HWSIM_TX_CTL_REQ_TX_STATUS; if (info->flags & IEEE80211_TX_CTL_NO_ACK) hwsim_flags |= HWSIM_TX_CTL_NO_ACK; if (nla_put_u32(skb, HWSIM_ATTR_FLAGS, hwsim_flags)) goto nla_put_failure; if (nla_put_u32(skb, HWSIM_ATTR_FREQ, channel->center_freq)) goto nla_put_failure; /* We get the tx control (rate and retries) info*/ for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { tx_attempts[i].idx = info->status.rates[i].idx; tx_attempts_flags[i].idx = info->status.rates[i].idx; tx_attempts[i].count = info->status.rates[i].count; tx_attempts_flags[i].flags = trans_tx_rate_flags_ieee2hwsim( &info->status.rates[i]); } if (nla_put(skb, HWSIM_ATTR_TX_INFO, sizeof(struct hwsim_tx_rate)*IEEE80211_TX_MAX_RATES, tx_attempts)) goto nla_put_failure; if (nla_put(skb, HWSIM_ATTR_TX_INFO_FLAGS, sizeof(struct hwsim_tx_rate_flag) * IEEE80211_TX_MAX_RATES, tx_attempts_flags)) goto nla_put_failure; /* We create a cookie to identify this skb */ cookie = atomic_inc_return(&data->pending_cookie); info->rate_driver_data[0] = (void *)cookie; if (nla_put_u64_64bit(skb, HWSIM_ATTR_COOKIE, cookie, HWSIM_ATTR_PAD)) goto nla_put_failure; genlmsg_end(skb, msg_head); if (hwsim_virtio_enabled) { if (hwsim_tx_virtio(data, skb)) goto err_free_txskb; } else { if (hwsim_unicast_netgroup(data, skb, dst_portid)) goto err_free_txskb; } /* Enqueue the packet */ skb_queue_tail(&data->pending, my_skb); data->tx_pkts++; data->tx_bytes += my_skb->len; return; nla_put_failure: nlmsg_free(skb); err_free_txskb: pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); ieee80211_free_txskb(hw, my_skb); data->tx_failed++; } static bool hwsim_chans_compat(struct ieee80211_channel *c1, struct ieee80211_channel *c2) { if (!c1 || !c2) return false; return c1->center_freq == c2->center_freq; } struct tx_iter_data { struct ieee80211_channel *channel; bool receive; }; static void mac80211_hwsim_tx_iter(void *_data, u8 *addr, struct ieee80211_vif *vif) { struct tx_iter_data *data = _data; int i; for (i = 0; i < ARRAY_SIZE(vif->link_conf); i++) { struct ieee80211_bss_conf *conf; struct ieee80211_chanctx_conf *chanctx; conf = rcu_dereference(vif->link_conf[i]); if (!conf) continue; chanctx = rcu_dereference(conf->chanctx_conf); if (!chanctx) continue; if (!hwsim_chans_compat(data->channel, chanctx->def.chan)) continue; data->receive = true; return; } } static void mac80211_hwsim_add_vendor_rtap(struct sk_buff *skb) { /* * To enable this code, #define the HWSIM_RADIOTAP_OUI, * e.g. like this: * #define HWSIM_RADIOTAP_OUI "\x02\x00\x00" * (but you should use a valid OUI, not that) * * If anyone wants to 'donate' a radiotap OUI/subns code * please send a patch removing this #ifdef and changing * the values accordingly. */ #ifdef HWSIM_RADIOTAP_OUI struct ieee80211_radiotap_vendor_tlv *rtap; static const char vendor_data[8] = "ABCDEFGH"; // Make sure no padding is needed BUILD_BUG_ON(sizeof(vendor_data) % 4); /* this is last radiotap info before the mac header, so * skb_reset_mac_header for mac8022 to know the end of * the radiotap TLV/beginning of the 802.11 header */ skb_reset_mac_header(skb); /* * Note that this code requires the headroom in the SKB * that was allocated earlier. */ rtap = skb_push(skb, sizeof(*rtap) + sizeof(vendor_data)); rtap->len = cpu_to_le16(sizeof(*rtap) - sizeof(struct ieee80211_radiotap_tlv) + sizeof(vendor_data)); rtap->type = cpu_to_le16(IEEE80211_RADIOTAP_VENDOR_NAMESPACE); rtap->content.oui[0] = HWSIM_RADIOTAP_OUI[0]; rtap->content.oui[1] = HWSIM_RADIOTAP_OUI[1]; rtap->content.oui[2] = HWSIM_RADIOTAP_OUI[2]; rtap->content.oui_subtype = 127; /* clear reserved field */ rtap->content.reserved = 0; rtap->content.vendor_type = 0; memcpy(rtap->content.data, vendor_data, sizeof(vendor_data)); IEEE80211_SKB_RXCB(skb)->flag |= RX_FLAG_RADIOTAP_TLV_AT_END; #endif } static void mac80211_hwsim_rx(struct mac80211_hwsim_data *data, struct ieee80211_rx_status *rx_status, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (void *)skb->data; if (!ieee80211_has_morefrags(hdr->frame_control) && !is_multicast_ether_addr(hdr->addr1) && (ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_data(hdr->frame_control))) { struct ieee80211_sta *sta; unsigned int link_id; rcu_read_lock(); sta = ieee80211_find_sta_by_link_addrs(data->hw, hdr->addr2, hdr->addr1, &link_id); if (sta) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; if (ieee80211_has_pm(hdr->frame_control)) sp->active_links_rx &= ~BIT(link_id); else sp->active_links_rx |= BIT(link_id); rx_status->link_valid = true; rx_status->link_id = link_id; } rcu_read_unlock(); } memcpy(IEEE80211_SKB_RXCB(skb), rx_status, sizeof(*rx_status)); mac80211_hwsim_add_vendor_rtap(skb); data->rx_pkts++; data->rx_bytes += skb->len; ieee80211_rx_irqsafe(data->hw, skb); } static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw, struct sk_buff *skb, struct ieee80211_channel *chan) { struct mac80211_hwsim_data *data = hw->priv, *data2; bool ack = false; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_rx_status rx_status; u64 now; memset(&rx_status, 0, sizeof(rx_status)); rx_status.flag |= RX_FLAG_MACTIME_START; rx_status.freq = chan->center_freq; rx_status.freq_offset = chan->freq_offset ? 1 : 0; rx_status.band = chan->band; if (info->control.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) { rx_status.rate_idx = ieee80211_rate_get_vht_mcs(&info->control.rates[0]); rx_status.nss = ieee80211_rate_get_vht_nss(&info->control.rates[0]); rx_status.encoding = RX_ENC_VHT; } else { rx_status.rate_idx = info->control.rates[0].idx; if (info->control.rates[0].flags & IEEE80211_TX_RC_MCS) rx_status.encoding = RX_ENC_HT; } if (info->control.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH) rx_status.bw = RATE_INFO_BW_40; else if (info->control.rates[0].flags & IEEE80211_TX_RC_80_MHZ_WIDTH) rx_status.bw = RATE_INFO_BW_80; else if (info->control.rates[0].flags & IEEE80211_TX_RC_160_MHZ_WIDTH) rx_status.bw = RATE_INFO_BW_160; else rx_status.bw = RATE_INFO_BW_20; if (info->control.rates[0].flags & IEEE80211_TX_RC_SHORT_GI) rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI; /* TODO: simulate optional packet loss */ rx_status.signal = data->rx_rssi; if (info->control.vif) rx_status.signal += info->control.vif->bss_conf.txpower; if (data->ps != PS_DISABLED) hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PM); /* release the skb's source info */ skb_orphan(skb); skb_dst_drop(skb); skb->mark = 0; skb_ext_reset(skb); nf_reset_ct(skb); /* * Get absolute mactime here so all HWs RX at the "same time", and * absolute TX time for beacon mactime so the timestamp matches. * Giving beacons a different mactime than non-beacons looks messy, but * it helps the Toffset be exact and a ~10us mactime discrepancy * probably doesn't really matter. */ if (ieee80211_is_beacon(hdr->frame_control) || ieee80211_is_probe_resp(hdr->frame_control)) { rx_status.boottime_ns = ktime_get_boottime_ns(); now = data->abs_bcn_ts; } else { now = mac80211_hwsim_get_tsf_raw(); } /* Copy skb to all enabled radios that are on the current frequency */ spin_lock(&hwsim_radio_lock); list_for_each_entry(data2, &hwsim_radios, list) { struct sk_buff *nskb; struct tx_iter_data tx_iter_data = { .receive = false, .channel = chan, }; if (data == data2) continue; if (!data2->started || (data2->idle && !data2->tmp_chan) || !hwsim_ps_rx_ok(data2, skb)) continue; if (!(data->group & data2->group)) continue; if (data->netgroup != data2->netgroup) continue; if (!hwsim_chans_compat(chan, data2->tmp_chan) && !hwsim_chans_compat(chan, data2->channel)) { ieee80211_iterate_active_interfaces_atomic( data2->hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_tx_iter, &tx_iter_data); if (!tx_iter_data.receive) continue; } /* * reserve some space for our vendor and the normal * radiotap header, since we're copying anyway */ if (skb->len < PAGE_SIZE && paged_rx) { struct page *page = alloc_page(GFP_ATOMIC); if (!page) continue; nskb = dev_alloc_skb(128); if (!nskb) { __free_page(page); continue; } memcpy(page_address(page), skb->data, skb->len); skb_add_rx_frag(nskb, 0, page, 0, skb->len, skb->len); } else { nskb = skb_copy(skb, GFP_ATOMIC); if (!nskb) continue; } if (mac80211_hwsim_addr_match(data2, hdr->addr1)) ack = true; rx_status.mactime = now + data2->tsf_offset; mac80211_hwsim_rx(data2, &rx_status, nskb); } spin_unlock(&hwsim_radio_lock); return ack; } static struct ieee80211_bss_conf * mac80211_hwsim_select_tx_link(struct mac80211_hwsim_data *data, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_hdr *hdr, struct ieee80211_link_sta **link_sta) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; int i; if (!ieee80211_vif_is_mld(vif)) return &vif->bss_conf; WARN_ON(is_multicast_ether_addr(hdr->addr1)); if (WARN_ON_ONCE(!sta || !sta->valid_links)) return &vif->bss_conf; for (i = 0; i < ARRAY_SIZE(vif->link_conf); i++) { struct ieee80211_bss_conf *bss_conf; unsigned int link_id; /* round-robin the available link IDs */ link_id = (sp->last_link + i + 1) % ARRAY_SIZE(vif->link_conf); if (!(vif->active_links & BIT(link_id))) continue; if (!(sp->active_links_rx & BIT(link_id))) continue; *link_sta = rcu_dereference(sta->link[link_id]); if (!*link_sta) continue; bss_conf = rcu_dereference(vif->link_conf[link_id]); if (WARN_ON_ONCE(!bss_conf)) continue; /* can happen while switching links */ if (!rcu_access_pointer(bss_conf->chanctx_conf)) continue; sp->last_link = link_id; return bss_conf; } return NULL; } static void mac80211_hwsim_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb) { struct mac80211_hwsim_data *data = hw->priv; struct ieee80211_tx_info *txi = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_channel *channel; bool ack; enum nl80211_chan_width confbw = NL80211_CHAN_WIDTH_20_NOHT; u32 _portid, i; if (WARN_ON(skb->len < 10)) { /* Should not happen; just a sanity check for addr1 use */ ieee80211_free_txskb(hw, skb); return; } if (!data->use_chanctx) { channel = data->channel; confbw = data->bw; } else if (txi->hw_queue == 4) { channel = data->tmp_chan; } else { u8 link = u32_get_bits(IEEE80211_SKB_CB(skb)->control.flags, IEEE80211_TX_CTRL_MLO_LINK); struct ieee80211_vif *vif = txi->control.vif; struct ieee80211_link_sta *link_sta = NULL; struct ieee80211_sta *sta = control->sta; struct ieee80211_bss_conf *bss_conf; if (link != IEEE80211_LINK_UNSPECIFIED) { bss_conf = rcu_dereference(txi->control.vif->link_conf[link]); if (sta) link_sta = rcu_dereference(sta->link[link]); } else { bss_conf = mac80211_hwsim_select_tx_link(data, vif, sta, hdr, &link_sta); } if (unlikely(!bss_conf)) { /* if it's an MLO STA, it might have deactivated all * links temporarily - but we don't handle real PS in * this code yet, so just drop the frame in that case */ WARN(link != IEEE80211_LINK_UNSPECIFIED || !sta || !sta->mlo, "link:%d, sta:%pM, sta->mlo:%d\n", link, sta ? sta->addr : NULL, sta ? sta->mlo : -1); ieee80211_free_txskb(hw, skb); return; } /* Do address translations only between shared links. It is * possible that while an non-AP MLD station and an AP MLD * station have shared links, the frame is intended to be sent * on a link which is not shared (for example when sending a * probe response). */ if (sta && sta->mlo && link_sta) { /* address translation to link addresses on TX */ ether_addr_copy(hdr->addr1, link_sta->addr); ether_addr_copy(hdr->addr2, bss_conf->addr); /* translate A3 only if it's the BSSID */ if (!ieee80211_has_tods(hdr->frame_control) && !ieee80211_has_fromds(hdr->frame_control)) { if (ether_addr_equal(hdr->addr3, sta->addr)) ether_addr_copy(hdr->addr3, link_sta->addr); else if (ether_addr_equal(hdr->addr3, vif->addr)) ether_addr_copy(hdr->addr3, bss_conf->addr); } /* no need to look at A4, if present it's SA */ } chanctx_conf = rcu_dereference(bss_conf->chanctx_conf); if (chanctx_conf) { channel = chanctx_conf->def.chan; confbw = chanctx_conf->def.width; } else { channel = NULL; } } if (WARN(!channel, "TX w/o channel - queue = %d\n", txi->hw_queue)) { ieee80211_free_txskb(hw, skb); return; } if (data->idle && !data->tmp_chan) { wiphy_dbg(hw->wiphy, "Trying to TX when idle - reject\n"); ieee80211_free_txskb(hw, skb); return; } if (txi->control.vif) hwsim_check_magic(txi->control.vif); if (control->sta) hwsim_check_sta_magic(control->sta); if (ieee80211_hw_check(hw, SUPPORTS_RC_TABLE)) ieee80211_get_tx_rates(txi->control.vif, control->sta, skb, txi->control.rates, ARRAY_SIZE(txi->control.rates)); for (i = 0; i < ARRAY_SIZE(txi->control.rates); i++) { u16 rflags = txi->control.rates[i].flags; /* initialize to data->bw for 5/10 MHz handling */ enum nl80211_chan_width bw = data->bw; if (txi->control.rates[i].idx == -1) break; if (rflags & IEEE80211_TX_RC_40_MHZ_WIDTH) bw = NL80211_CHAN_WIDTH_40; else if (rflags & IEEE80211_TX_RC_80_MHZ_WIDTH) bw = NL80211_CHAN_WIDTH_80; else if (rflags & IEEE80211_TX_RC_160_MHZ_WIDTH) bw = NL80211_CHAN_WIDTH_160; if (WARN_ON(hwsim_get_chanwidth(bw) > hwsim_get_chanwidth(confbw))) return; } if (skb->len >= 24 + 8 && ieee80211_is_probe_resp(hdr->frame_control)) { /* fake header transmission time */ struct ieee80211_mgmt *mgmt; struct ieee80211_rate *txrate; /* TODO: get MCS */ int bitrate = 100; u64 ts; mgmt = (struct ieee80211_mgmt *)skb->data; txrate = ieee80211_get_tx_rate(hw, txi); if (txrate) bitrate = txrate->bitrate; ts = mac80211_hwsim_get_tsf_raw(); mgmt->u.probe_resp.timestamp = cpu_to_le64(ts + data->tsf_offset + 24 * 8 * 10 / bitrate); } mac80211_hwsim_monitor_rx(hw, skb, channel); /* wmediumd mode check */ _portid = READ_ONCE(data->wmediumd); if (_portid || hwsim_virtio_enabled) return mac80211_hwsim_tx_frame_nl(hw, skb, _portid, channel); /* NO wmediumd detected, perfect medium simulation */ data->tx_pkts++; data->tx_bytes += skb->len; ack = mac80211_hwsim_tx_frame_no_nl(hw, skb, channel); if (ack && skb->len >= 16) mac80211_hwsim_monitor_ack(channel, hdr->addr2); ieee80211_tx_info_clear_status(txi); /* frame was transmitted at most favorable rate at first attempt */ txi->control.rates[0].count = 1; txi->control.rates[1].idx = -1; if (!(txi->flags & IEEE80211_TX_CTL_NO_ACK) && ack) txi->flags |= IEEE80211_TX_STAT_ACK; ieee80211_tx_status_irqsafe(hw, skb); } static int mac80211_hwsim_start(struct ieee80211_hw *hw) { struct mac80211_hwsim_data *data = hw->priv; wiphy_dbg(hw->wiphy, "%s\n", __func__); data->started = true; return 0; } static void mac80211_hwsim_stop(struct ieee80211_hw *hw, bool suspend) { struct mac80211_hwsim_data *data = hw->priv; int i; data->started = false; for (i = 0; i < ARRAY_SIZE(data->link_data); i++) hrtimer_cancel(&data->link_data[i].beacon_timer); while (!skb_queue_empty(&data->pending)) ieee80211_free_txskb(hw, skb_dequeue(&data->pending)); wiphy_dbg(hw->wiphy, "%s\n", __func__); } static int mac80211_hwsim_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", __func__, ieee80211_vif_type_p2p(vif), vif->addr); hwsim_set_magic(vif); if (vif->type != NL80211_IFTYPE_MONITOR) mac80211_hwsim_config_mac_nl(hw, vif->addr, true); vif->cab_queue = 0; vif->hw_queue[IEEE80211_AC_VO] = 0; vif->hw_queue[IEEE80211_AC_VI] = 1; vif->hw_queue[IEEE80211_AC_BE] = 2; vif->hw_queue[IEEE80211_AC_BK] = 3; return 0; } #ifdef CONFIG_MAC80211_DEBUGFS static void mac80211_hwsim_link_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct dentry *dir) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; debugfs_create_u32("skip_beacons", 0600, dir, &vp->skip_beacons[link_conf->link_id]); } #endif static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum nl80211_iftype newtype, bool newp2p) { newtype = ieee80211_iftype_p2p(newtype, newp2p); wiphy_dbg(hw->wiphy, "%s (old type=%d, new type=%d, mac_addr=%pM)\n", __func__, ieee80211_vif_type_p2p(vif), newtype, vif->addr); hwsim_check_magic(vif); /* * interface may change from non-AP to AP in * which case this needs to be set up again */ vif->cab_queue = 0; return 0; } static void mac80211_hwsim_remove_interface( struct ieee80211_hw *hw, struct ieee80211_vif *vif) { wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", __func__, ieee80211_vif_type_p2p(vif), vif->addr); hwsim_check_magic(vif); hwsim_clear_magic(vif); if (vif->type != NL80211_IFTYPE_MONITOR) mac80211_hwsim_config_mac_nl(hw, vif->addr, false); } static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, struct sk_buff *skb, struct ieee80211_channel *chan) { struct mac80211_hwsim_data *data = hw->priv; u32 _portid = READ_ONCE(data->wmediumd); if (ieee80211_hw_check(hw, SUPPORTS_RC_TABLE)) { struct ieee80211_tx_info *txi = IEEE80211_SKB_CB(skb); ieee80211_get_tx_rates(txi->control.vif, NULL, skb, txi->control.rates, ARRAY_SIZE(txi->control.rates)); } mac80211_hwsim_monitor_rx(hw, skb, chan); if (_portid || hwsim_virtio_enabled) return mac80211_hwsim_tx_frame_nl(hw, skb, _portid, chan); data->tx_pkts++; data->tx_bytes += skb->len; mac80211_hwsim_tx_frame_no_nl(hw, skb, chan); dev_kfree_skb(skb); } static void __mac80211_hwsim_beacon_tx(struct ieee80211_bss_conf *link_conf, struct mac80211_hwsim_data *data, struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct sk_buff *skb) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct ieee80211_tx_info *info; struct ieee80211_rate *txrate; struct ieee80211_mgmt *mgmt; /* TODO: get MCS */ int bitrate = 100; if (vp->skip_beacons[link_conf->link_id]) { vp->skip_beacons[link_conf->link_id]--; dev_kfree_skb(skb); return; } info = IEEE80211_SKB_CB(skb); if (ieee80211_hw_check(hw, SUPPORTS_RC_TABLE)) ieee80211_get_tx_rates(vif, NULL, skb, info->control.rates, ARRAY_SIZE(info->control.rates)); txrate = ieee80211_get_tx_rate(hw, info); if (txrate) bitrate = txrate->bitrate; mgmt = (struct ieee80211_mgmt *) skb->data; /* fake header transmission time */ data->abs_bcn_ts = mac80211_hwsim_get_tsf_raw(); if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { struct ieee80211_ext *ext = (void *) mgmt; ext->u.s1g_beacon.timestamp = cpu_to_le32(data->abs_bcn_ts + data->tsf_offset + 10 * 8 * 10 / bitrate); } else { mgmt->u.beacon.timestamp = cpu_to_le64(data->abs_bcn_ts + data->tsf_offset + 24 * 8 * 10 / bitrate); } mac80211_hwsim_tx_frame(hw, skb, rcu_dereference(link_conf->chanctx_conf)->def.chan); } static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac, struct ieee80211_vif *vif) { struct mac80211_hwsim_link_data *link_data = arg; u32 link_id = link_data->link_id; struct ieee80211_bss_conf *link_conf, *tx_bss_conf; struct mac80211_hwsim_data *data = container_of(link_data, struct mac80211_hwsim_data, link_data[link_id]); struct ieee80211_hw *hw = data->hw; struct sk_buff *skb; hwsim_check_magic(vif); link_conf = rcu_dereference(vif->link_conf[link_id]); if (!link_conf) return; if (vif->type != NL80211_IFTYPE_AP && vif->type != NL80211_IFTYPE_MESH_POINT && vif->type != NL80211_IFTYPE_ADHOC && vif->type != NL80211_IFTYPE_OCB) return; tx_bss_conf = rcu_access_pointer(link_conf->tx_bss_conf); if (tx_bss_conf && tx_bss_conf != link_conf) return; if (link_conf->ema_ap) { struct ieee80211_ema_beacons *ema; u8 i = 0; ema = ieee80211_beacon_get_template_ema_list(hw, vif, link_id); if (!ema || !ema->cnt) return; for (i = 0; i < ema->cnt; i++) { __mac80211_hwsim_beacon_tx(link_conf, data, hw, vif, ema->bcn[i].skb); ema->bcn[i].skb = NULL; /* Already freed */ } ieee80211_beacon_free_ema_list(ema); } else { skb = ieee80211_beacon_get(hw, vif, link_id); if (!skb) return; __mac80211_hwsim_beacon_tx(link_conf, data, hw, vif, skb); } while ((skb = ieee80211_get_buffered_bc(hw, vif)) != NULL) { mac80211_hwsim_tx_frame(hw, skb, rcu_dereference(link_conf->chanctx_conf)->def.chan); } if (link_conf->csa_active && ieee80211_beacon_cntdwn_is_complete(vif, link_id)) ieee80211_csa_finish(vif, link_id); if (link_conf->color_change_active && ieee80211_beacon_cntdwn_is_complete(vif, link_id)) ieee80211_color_change_finish(vif, link_id); } static enum hrtimer_restart mac80211_hwsim_beacon(struct hrtimer *timer) { struct mac80211_hwsim_link_data *link_data = container_of(timer, struct mac80211_hwsim_link_data, beacon_timer); struct mac80211_hwsim_data *data = container_of(link_data, struct mac80211_hwsim_data, link_data[link_data->link_id]); struct ieee80211_hw *hw = data->hw; u64 bcn_int = link_data->beacon_int; if (!data->started) return HRTIMER_NORESTART; ieee80211_iterate_active_interfaces_atomic( hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_beacon_tx, link_data); /* beacon at new TBTT + beacon interval */ if (data->bcn_delta) { bcn_int -= data->bcn_delta; data->bcn_delta = 0; } hrtimer_forward_now(&link_data->beacon_timer, ns_to_ktime(bcn_int * NSEC_PER_USEC)); return HRTIMER_RESTART; } static const char * const hwsim_chanwidths[] = { [NL80211_CHAN_WIDTH_5] = "ht5", [NL80211_CHAN_WIDTH_10] = "ht10", [NL80211_CHAN_WIDTH_20_NOHT] = "noht", [NL80211_CHAN_WIDTH_20] = "ht20", [NL80211_CHAN_WIDTH_40] = "ht40", [NL80211_CHAN_WIDTH_80] = "vht80", [NL80211_CHAN_WIDTH_80P80] = "vht80p80", [NL80211_CHAN_WIDTH_160] = "vht160", [NL80211_CHAN_WIDTH_1] = "1MHz", [NL80211_CHAN_WIDTH_2] = "2MHz", [NL80211_CHAN_WIDTH_4] = "4MHz", [NL80211_CHAN_WIDTH_8] = "8MHz", [NL80211_CHAN_WIDTH_16] = "16MHz", [NL80211_CHAN_WIDTH_320] = "eht320", }; static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed) { struct mac80211_hwsim_data *data = hw->priv; struct ieee80211_conf *conf = &hw->conf; static const char *smps_modes[IEEE80211_SMPS_NUM_MODES] = { [IEEE80211_SMPS_AUTOMATIC] = "auto", [IEEE80211_SMPS_OFF] = "off", [IEEE80211_SMPS_STATIC] = "static", [IEEE80211_SMPS_DYNAMIC] = "dynamic", }; int idx; if (conf->chandef.chan) wiphy_dbg(hw->wiphy, "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n", __func__, conf->chandef.chan->center_freq, conf->chandef.center_freq1, conf->chandef.center_freq2, hwsim_chanwidths[conf->chandef.width], !!(conf->flags & IEEE80211_CONF_IDLE), !!(conf->flags & IEEE80211_CONF_PS), smps_modes[conf->smps_mode]); else wiphy_dbg(hw->wiphy, "%s (freq=0 idle=%d ps=%d smps=%s)\n", __func__, !!(conf->flags & IEEE80211_CONF_IDLE), !!(conf->flags & IEEE80211_CONF_PS), smps_modes[conf->smps_mode]); data->idle = !!(conf->flags & IEEE80211_CONF_IDLE); WARN_ON(conf->chandef.chan && data->use_chanctx); mutex_lock(&data->mutex); if (data->scanning && conf->chandef.chan) { for (idx = 0; idx < ARRAY_SIZE(data->survey_data); idx++) { if (data->survey_data[idx].channel == data->channel) { data->survey_data[idx].start = data->survey_data[idx].next_start; data->survey_data[idx].end = jiffies; break; } } data->channel = conf->chandef.chan; data->bw = conf->chandef.width; for (idx = 0; idx < ARRAY_SIZE(data->survey_data); idx++) { if (data->survey_data[idx].channel && data->survey_data[idx].channel != data->channel) continue; data->survey_data[idx].channel = data->channel; data->survey_data[idx].next_start = jiffies; break; } } else { data->channel = conf->chandef.chan; data->bw = conf->chandef.width; } mutex_unlock(&data->mutex); for (idx = 0; idx < ARRAY_SIZE(data->link_data); idx++) { struct mac80211_hwsim_link_data *link_data = &data->link_data[idx]; if (!data->started || !link_data->beacon_int) { hrtimer_cancel(&link_data->beacon_timer); } else if (!hrtimer_active(&link_data->beacon_timer)) { u64 tsf = mac80211_hwsim_get_tsf(hw, NULL); u32 bcn_int = link_data->beacon_int; u64 until_tbtt = bcn_int - do_div(tsf, bcn_int); hrtimer_start(&link_data->beacon_timer, ns_to_ktime(until_tbtt * NSEC_PER_USEC), HRTIMER_MODE_REL_SOFT); } } return 0; } static void mac80211_hwsim_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags, unsigned int *total_flags,u64 multicast) { struct mac80211_hwsim_data *data = hw->priv; wiphy_dbg(hw->wiphy, "%s\n", __func__); data->rx_filter = 0; if (*total_flags & FIF_ALLMULTI) data->rx_filter |= FIF_ALLMULTI; if (*total_flags & FIF_MCAST_ACTION) data->rx_filter |= FIF_MCAST_ACTION; *total_flags = data->rx_filter; } static void mac80211_hwsim_bcn_en_iter(void *data, u8 *mac, struct ieee80211_vif *vif) { unsigned int *count = data; struct hwsim_vif_priv *vp = (void *)vif->drv_priv; if (vp->bcn_en) (*count)++; } static void mac80211_hwsim_vif_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 changed) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; hwsim_check_magic(vif); wiphy_dbg(hw->wiphy, "%s(changed=0x%llx vif->addr=%pM)\n", __func__, changed, vif->addr); if (changed & BSS_CHANGED_ASSOC) { wiphy_dbg(hw->wiphy, " ASSOC: assoc=%d aid=%d\n", vif->cfg.assoc, vif->cfg.aid); vp->assoc = vif->cfg.assoc; vp->aid = vif->cfg.aid; } if (vif->type == NL80211_IFTYPE_STATION && changed & (BSS_CHANGED_MLD_VALID_LINKS | BSS_CHANGED_MLD_TTLM)) { u16 usable_links = ieee80211_vif_usable_links(vif); if (vif->active_links != usable_links) ieee80211_set_active_links_async(vif, usable_links); } } static void mac80211_hwsim_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u64 changed) { struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct mac80211_hwsim_data *data = hw->priv; unsigned int link_id = info->link_id; struct mac80211_hwsim_link_data *link_data = &data->link_data[link_id]; hwsim_check_magic(vif); wiphy_dbg(hw->wiphy, "%s(changed=0x%llx vif->addr=%pM, link id %u)\n", __func__, (unsigned long long)changed, vif->addr, link_id); if (changed & BSS_CHANGED_BSSID) { wiphy_dbg(hw->wiphy, "%s: BSSID changed: %pM\n", __func__, info->bssid); memcpy(vp->bssid, info->bssid, ETH_ALEN); } if (changed & BSS_CHANGED_BEACON_ENABLED) { wiphy_dbg(hw->wiphy, " BCN EN: %d (BI=%u)\n", info->enable_beacon, info->beacon_int); vp->bcn_en = info->enable_beacon; if (data->started && !hrtimer_active(&link_data->beacon_timer) && info->enable_beacon) { u64 tsf, until_tbtt; u32 bcn_int; link_data->beacon_int = info->beacon_int * 1024; tsf = mac80211_hwsim_get_tsf(hw, vif); bcn_int = link_data->beacon_int; until_tbtt = bcn_int - do_div(tsf, bcn_int); hrtimer_start(&link_data->beacon_timer, ns_to_ktime(until_tbtt * NSEC_PER_USEC), HRTIMER_MODE_REL_SOFT); } else if (!info->enable_beacon) { unsigned int count = 0; ieee80211_iterate_active_interfaces_atomic( data->hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_bcn_en_iter, &count); wiphy_dbg(hw->wiphy, " beaconing vifs remaining: %u", count); if (count == 0) { hrtimer_cancel(&link_data->beacon_timer); link_data->beacon_int = 0; } } } if (changed & BSS_CHANGED_ERP_CTS_PROT) { wiphy_dbg(hw->wiphy, " ERP_CTS_PROT: %d\n", info->use_cts_prot); } if (changed & BSS_CHANGED_ERP_PREAMBLE) { wiphy_dbg(hw->wiphy, " ERP_PREAMBLE: %d\n", info->use_short_preamble); } if (changed & BSS_CHANGED_ERP_SLOT) { wiphy_dbg(hw->wiphy, " ERP_SLOT: %d\n", info->use_short_slot); } if (changed & BSS_CHANGED_HT) { wiphy_dbg(hw->wiphy, " HT: op_mode=0x%x\n", info->ht_operation_mode); } if (changed & BSS_CHANGED_BASIC_RATES) { wiphy_dbg(hw->wiphy, " BASIC_RATES: 0x%llx\n", (unsigned long long) info->basic_rates); } if (changed & BSS_CHANGED_TXPOWER) wiphy_dbg(hw->wiphy, " TX Power: %d dBm\n", info->txpower); } static void mac80211_hwsim_sta_rc_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_link_sta *link_sta, u32 changed) { struct mac80211_hwsim_data *data = hw->priv; struct ieee80211_sta *sta = link_sta->sta; u32 bw = U32_MAX; int link_id; rcu_read_lock(); for (link_id = 0; link_id < ARRAY_SIZE(vif->link_conf); link_id++) { enum nl80211_chan_width confbw = NL80211_CHAN_WIDTH_20_NOHT; struct ieee80211_bss_conf *vif_conf; link_sta = rcu_dereference(sta->link[link_id]); if (!link_sta) continue; switch (link_sta->bandwidth) { #define C(_bw) case IEEE80211_STA_RX_BW_##_bw: bw = _bw; break C(20); C(40); C(80); C(160); C(320); #undef C } if (!data->use_chanctx) { confbw = data->bw; } else { struct ieee80211_chanctx_conf *chanctx_conf; vif_conf = rcu_dereference(vif->link_conf[link_id]); if (WARN_ON(!vif_conf)) continue; chanctx_conf = rcu_dereference(vif_conf->chanctx_conf); if (!WARN_ON(!chanctx_conf)) confbw = chanctx_conf->def.width; } WARN(bw > hwsim_get_chanwidth(confbw), "intf %pM [link=%d]: bad STA %pM bandwidth %d MHz (%d) > channel config %d MHz (%d)\n", vif->addr, link_id, sta->addr, bw, sta->deflink.bandwidth, hwsim_get_chanwidth(data->bw), data->bw); } rcu_read_unlock(); } static int mac80211_hwsim_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; hwsim_check_magic(vif); hwsim_set_sta_magic(sta); mac80211_hwsim_sta_rc_update(hw, vif, &sta->deflink, 0); if (sta->valid_links) { WARN(hweight16(sta->valid_links) > 1, "expect to add STA with single link, have 0x%x\n", sta->valid_links); sp->active_links_rx = sta->valid_links; } return 0; } static int mac80211_hwsim_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { hwsim_check_magic(vif); hwsim_clear_sta_magic(sta); return 0; } static int mac80211_hwsim_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, enum ieee80211_sta_state new_state) { if (new_state == IEEE80211_STA_NOTEXIST) return mac80211_hwsim_sta_remove(hw, vif, sta); if (old_state == IEEE80211_STA_NOTEXIST) return mac80211_hwsim_sta_add(hw, vif, sta); /* * in an MLO connection, when client is authorized * (AP station marked as such), enable all links */ if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION && new_state == IEEE80211_STA_AUTHORIZED && !sta->tdls) ieee80211_set_active_links_async(vif, ieee80211_vif_usable_links(vif)); return 0; } static void mac80211_hwsim_sta_notify(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd cmd, struct ieee80211_sta *sta) { hwsim_check_magic(vif); switch (cmd) { case STA_NOTIFY_SLEEP: case STA_NOTIFY_AWAKE: /* TODO: make good use of these flags */ break; default: WARN(1, "Invalid sta notify: %d\n", cmd); break; } } static int mac80211_hwsim_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set) { hwsim_check_sta_magic(sta); return 0; } static int mac80211_hwsim_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, u16 queue, const struct ieee80211_tx_queue_params *params) { wiphy_dbg(hw->wiphy, "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n", __func__, queue, params->txop, params->cw_min, params->cw_max, params->aifs); return 0; } static int mac80211_hwsim_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey) { struct mac80211_hwsim_data *hwsim = hw->priv; if (idx < 0 || idx >= ARRAY_SIZE(hwsim->survey_data)) return -ENOENT; mutex_lock(&hwsim->mutex); survey->channel = hwsim->survey_data[idx].channel; if (!survey->channel) { mutex_unlock(&hwsim->mutex); return -ENOENT; } /* * Magically conjured dummy values --- this is only ok for simulated hardware. * * A real driver which cannot determine real values noise MUST NOT * report any, especially not a magically conjured ones :-) */ survey->filled = SURVEY_INFO_NOISE_DBM | SURVEY_INFO_TIME | SURVEY_INFO_TIME_BUSY; survey->noise = -92; survey->time = jiffies_to_msecs(hwsim->survey_data[idx].end - hwsim->survey_data[idx].start); /* report 12.5% of channel time is used */ survey->time_busy = survey->time/8; mutex_unlock(&hwsim->mutex); return 0; } static enum ieee80211_neg_ttlm_res mac80211_hwsim_can_neg_ttlm(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_neg_ttlm *neg_ttlm) { u32 i; /* For testing purposes, accept if all TIDs are mapped to the same links * set, otherwise reject. */ for (i = 0; i < IEEE80211_TTLM_NUM_TIDS; i++) { if (neg_ttlm->downlink[i] != neg_ttlm->uplink[i] || neg_ttlm->downlink[i] != neg_ttlm->downlink[0]) return NEG_TTLM_RES_REJECT; } return NEG_TTLM_RES_ACCEPT; } #ifdef CONFIG_NL80211_TESTMODE /* * This section contains example code for using netlink * attributes with the testmode command in nl80211. */ /* These enums need to be kept in sync with userspace */ enum hwsim_testmode_attr { __HWSIM_TM_ATTR_INVALID = 0, HWSIM_TM_ATTR_CMD = 1, HWSIM_TM_ATTR_PS = 2, /* keep last */ __HWSIM_TM_ATTR_AFTER_LAST, HWSIM_TM_ATTR_MAX = __HWSIM_TM_ATTR_AFTER_LAST - 1 }; enum hwsim_testmode_cmd { HWSIM_TM_CMD_SET_PS = 0, HWSIM_TM_CMD_GET_PS = 1, HWSIM_TM_CMD_STOP_QUEUES = 2, HWSIM_TM_CMD_WAKE_QUEUES = 3, }; static const struct nla_policy hwsim_testmode_policy[HWSIM_TM_ATTR_MAX + 1] = { [HWSIM_TM_ATTR_CMD] = { .type = NLA_U32 }, [HWSIM_TM_ATTR_PS] = { .type = NLA_U32 }, }; static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len) { struct mac80211_hwsim_data *hwsim = hw->priv; struct nlattr *tb[HWSIM_TM_ATTR_MAX + 1]; struct sk_buff *skb; int err, ps; err = nla_parse_deprecated(tb, HWSIM_TM_ATTR_MAX, data, len, hwsim_testmode_policy, NULL); if (err) return err; if (!tb[HWSIM_TM_ATTR_CMD]) return -EINVAL; switch (nla_get_u32(tb[HWSIM_TM_ATTR_CMD])) { case HWSIM_TM_CMD_SET_PS: if (!tb[HWSIM_TM_ATTR_PS]) return -EINVAL; ps = nla_get_u32(tb[HWSIM_TM_ATTR_PS]); return hwsim_fops_ps_write(hwsim, ps); case HWSIM_TM_CMD_GET_PS: skb = cfg80211_testmode_alloc_reply_skb(hw->wiphy, nla_total_size(sizeof(u32))); if (!skb) return -ENOMEM; if (nla_put_u32(skb, HWSIM_TM_ATTR_PS, hwsim->ps)) goto nla_put_failure; return cfg80211_testmode_reply(skb); case HWSIM_TM_CMD_STOP_QUEUES: ieee80211_stop_queues(hw); return 0; case HWSIM_TM_CMD_WAKE_QUEUES: ieee80211_wake_queues(hw); return 0; default: return -EOPNOTSUPP; } nla_put_failure: kfree_skb(skb); return -ENOBUFS; } #endif static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params) { struct ieee80211_sta *sta = params->sta; enum ieee80211_ampdu_mlme_action action = params->action; u16 tid = params->tid; switch (action) { case IEEE80211_AMPDU_TX_START: return IEEE80211_AMPDU_TX_START_IMMEDIATE; case IEEE80211_AMPDU_TX_STOP_CONT: case IEEE80211_AMPDU_TX_STOP_FLUSH: case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; case IEEE80211_AMPDU_TX_OPERATIONAL: break; case IEEE80211_AMPDU_RX_START: case IEEE80211_AMPDU_RX_STOP: break; default: return -EOPNOTSUPP; } return 0; } static void mac80211_hwsim_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop) { /* Not implemented, queues only on kernel side */ } static void hw_scan_work(struct work_struct *work) { struct mac80211_hwsim_data *hwsim = container_of(work, struct mac80211_hwsim_data, hw_scan.work); struct cfg80211_scan_request *req = hwsim->hw_scan_request; int dwell, i; mutex_lock(&hwsim->mutex); if (hwsim->scan_chan_idx >= req->n_channels) { struct cfg80211_scan_info info = { .aborted = false, }; wiphy_dbg(hwsim->hw->wiphy, "hw scan complete\n"); ieee80211_scan_completed(hwsim->hw, &info); hwsim->hw_scan_request = NULL; hwsim->hw_scan_vif = NULL; hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); mac80211_hwsim_config_mac_nl(hwsim->hw, hwsim->scan_addr, false); return; } wiphy_dbg(hwsim->hw->wiphy, "hw scan %d MHz\n", req->channels[hwsim->scan_chan_idx]->center_freq); hwsim->tmp_chan = req->channels[hwsim->scan_chan_idx]; if (hwsim->tmp_chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR) || !req->n_ssids) { dwell = 120; } else { dwell = 30; /* send probes */ for (i = 0; i < req->n_ssids; i++) { struct sk_buff *probe; struct ieee80211_mgmt *mgmt; probe = ieee80211_probereq_get(hwsim->hw, hwsim->scan_addr, req->ssids[i].ssid, req->ssids[i].ssid_len, req->ie_len); if (!probe) continue; mgmt = (struct ieee80211_mgmt *) probe->data; memcpy(mgmt->da, req->bssid, ETH_ALEN); memcpy(mgmt->bssid, req->bssid, ETH_ALEN); if (req->ie_len) skb_put_data(probe, req->ie, req->ie_len); rcu_read_lock(); if (!ieee80211_tx_prepare_skb(hwsim->hw, hwsim->hw_scan_vif, probe, hwsim->tmp_chan->band, NULL)) { rcu_read_unlock(); kfree_skb(probe); continue; } local_bh_disable(); mac80211_hwsim_tx_frame(hwsim->hw, probe, hwsim->tmp_chan); rcu_read_unlock(); local_bh_enable(); } } ieee80211_queue_delayed_work(hwsim->hw, &hwsim->hw_scan, msecs_to_jiffies(dwell)); hwsim->survey_data[hwsim->scan_chan_idx].channel = hwsim->tmp_chan; hwsim->survey_data[hwsim->scan_chan_idx].start = jiffies; hwsim->survey_data[hwsim->scan_chan_idx].end = jiffies + msecs_to_jiffies(dwell); hwsim->scan_chan_idx++; mutex_unlock(&hwsim->mutex); } static int mac80211_hwsim_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_scan_request *hw_req) { struct mac80211_hwsim_data *hwsim = hw->priv; struct cfg80211_scan_request *req = &hw_req->req; mutex_lock(&hwsim->mutex); if (WARN_ON(hwsim->tmp_chan || hwsim->hw_scan_request)) { mutex_unlock(&hwsim->mutex); return -EBUSY; } hwsim->hw_scan_request = req; hwsim->hw_scan_vif = vif; hwsim->scan_chan_idx = 0; if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) get_random_mask_addr(hwsim->scan_addr, hw_req->req.mac_addr, hw_req->req.mac_addr_mask); else memcpy(hwsim->scan_addr, vif->addr, ETH_ALEN); memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data)); mutex_unlock(&hwsim->mutex); mac80211_hwsim_config_mac_nl(hw, hwsim->scan_addr, true); wiphy_dbg(hw->wiphy, "hwsim hw_scan request\n"); ieee80211_queue_delayed_work(hwsim->hw, &hwsim->hw_scan, 0); return 0; } static void mac80211_hwsim_cancel_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *hwsim = hw->priv; struct cfg80211_scan_info info = { .aborted = true, }; wiphy_dbg(hw->wiphy, "hwsim cancel_hw_scan\n"); cancel_delayed_work_sync(&hwsim->hw_scan); mutex_lock(&hwsim->mutex); ieee80211_scan_completed(hwsim->hw, &info); hwsim->tmp_chan = NULL; hwsim->hw_scan_request = NULL; hwsim->hw_scan_vif = NULL; mutex_unlock(&hwsim->mutex); } static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac_addr) { struct mac80211_hwsim_data *hwsim = hw->priv; mutex_lock(&hwsim->mutex); if (hwsim->scanning) { pr_debug("two hwsim sw_scans detected!\n"); goto out; } pr_debug("hwsim sw_scan request, prepping stuff\n"); memcpy(hwsim->scan_addr, mac_addr, ETH_ALEN); mac80211_hwsim_config_mac_nl(hw, hwsim->scan_addr, true); hwsim->scanning = true; memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data)); out: mutex_unlock(&hwsim->mutex); } static void mac80211_hwsim_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *hwsim = hw->priv; mutex_lock(&hwsim->mutex); pr_debug("hwsim sw_scan_complete\n"); hwsim->scanning = false; mac80211_hwsim_config_mac_nl(hw, hwsim->scan_addr, false); eth_zero_addr(hwsim->scan_addr); mutex_unlock(&hwsim->mutex); } static void hw_roc_start(struct work_struct *work) { struct mac80211_hwsim_data *hwsim = container_of(work, struct mac80211_hwsim_data, roc_start.work); mutex_lock(&hwsim->mutex); wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC begins\n"); hwsim->tmp_chan = hwsim->roc_chan; ieee80211_ready_on_channel(hwsim->hw); ieee80211_queue_delayed_work(hwsim->hw, &hwsim->roc_done, msecs_to_jiffies(hwsim->roc_duration)); mutex_unlock(&hwsim->mutex); } static void hw_roc_done(struct work_struct *work) { struct mac80211_hwsim_data *hwsim = container_of(work, struct mac80211_hwsim_data, roc_done.work); mutex_lock(&hwsim->mutex); ieee80211_remain_on_channel_expired(hwsim->hw); hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC expired\n"); } static int mac80211_hwsim_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel *chan, int duration, enum ieee80211_roc_type type) { struct mac80211_hwsim_data *hwsim = hw->priv; mutex_lock(&hwsim->mutex); if (WARN_ON(hwsim->tmp_chan || hwsim->hw_scan_request)) { mutex_unlock(&hwsim->mutex); return -EBUSY; } hwsim->roc_chan = chan; hwsim->roc_duration = duration; mutex_unlock(&hwsim->mutex); wiphy_dbg(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n", chan->center_freq, duration); ieee80211_queue_delayed_work(hw, &hwsim->roc_start, HZ/50); return 0; } static int mac80211_hwsim_croc(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { struct mac80211_hwsim_data *hwsim = hw->priv; cancel_delayed_work_sync(&hwsim->roc_start); cancel_delayed_work_sync(&hwsim->roc_done); mutex_lock(&hwsim->mutex); hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); wiphy_dbg(hw->wiphy, "hwsim ROC canceled\n"); return 0; } static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { hwsim_set_chanctx_magic(ctx); wiphy_dbg(hw->wiphy, "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", ctx->def.chan->center_freq, ctx->def.width, ctx->def.center_freq1, ctx->def.center_freq2); return 0; } static void mac80211_hwsim_remove_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { wiphy_dbg(hw->wiphy, "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", ctx->def.chan->center_freq, ctx->def.width, ctx->def.center_freq1, ctx->def.center_freq2); hwsim_check_chanctx_magic(ctx); hwsim_clear_chanctx_magic(ctx); } static void mac80211_hwsim_change_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx, u32 changed) { hwsim_check_chanctx_magic(ctx); wiphy_dbg(hw->wiphy, "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", ctx->def.chan->center_freq, ctx->def.width, ctx->def.center_freq1, ctx->def.center_freq2); } static int mac80211_hwsim_assign_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx) { hwsim_check_magic(vif); hwsim_check_chanctx_magic(ctx); /* if we activate a link while already associated wake it up */ if (vif->type == NL80211_IFTYPE_STATION && vif->cfg.assoc) { struct sk_buff *skb; skb = ieee80211_nullfunc_get(hw, vif, link_conf->link_id, true); if (skb) { local_bh_disable(); mac80211_hwsim_tx_frame(hw, skb, ctx->def.chan); local_bh_enable(); } } return 0; } static void mac80211_hwsim_unassign_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx) { hwsim_check_magic(vif); hwsim_check_chanctx_magic(ctx); /* if we deactivate a link while associated suspend it first */ if (vif->type == NL80211_IFTYPE_STATION && vif->cfg.assoc) { struct sk_buff *skb; skb = ieee80211_nullfunc_get(hw, vif, link_conf->link_id, true); if (skb) { struct ieee80211_hdr *hdr = (void *)skb->data; hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PM); local_bh_disable(); mac80211_hwsim_tx_frame(hw, skb, ctx->def.chan); local_bh_enable(); } } } static int mac80211_hwsim_switch_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif_chanctx_switch *vifs, int n_vifs, enum ieee80211_chanctx_switch_mode mode) { int i; if (n_vifs <= 0) return -EINVAL; wiphy_dbg(hw->wiphy, "switch vif channel context mode: %u\n", mode); for (i = 0; i < n_vifs; i++) { hwsim_check_chanctx_magic(vifs[i].old_ctx); wiphy_dbg(hw->wiphy, "switch vif channel context: %d MHz/width: %d/cfreqs:%d/%d MHz -> %d MHz/width: %d/cfreqs:%d/%d MHz\n", vifs[i].old_ctx->def.chan->center_freq, vifs[i].old_ctx->def.width, vifs[i].old_ctx->def.center_freq1, vifs[i].old_ctx->def.center_freq2, vifs[i].new_ctx->def.chan->center_freq, vifs[i].new_ctx->def.width, vifs[i].new_ctx->def.center_freq1, vifs[i].new_ctx->def.center_freq2); switch (mode) { case CHANCTX_SWMODE_REASSIGN_VIF: hwsim_check_chanctx_magic(vifs[i].new_ctx); break; case CHANCTX_SWMODE_SWAP_CONTEXTS: hwsim_set_chanctx_magic(vifs[i].new_ctx); hwsim_clear_chanctx_magic(vifs[i].old_ctx); break; default: WARN(1, "Invalid mode %d\n", mode); } } return 0; } static const char mac80211_hwsim_gstrings_stats[][ETH_GSTRING_LEN] = { "tx_pkts_nic", "tx_bytes_nic", "rx_pkts_nic", "rx_bytes_nic", "d_tx_dropped", "d_tx_failed", "d_ps_mode", "d_group", }; #define MAC80211_HWSIM_SSTATS_LEN ARRAY_SIZE(mac80211_hwsim_gstrings_stats) static void mac80211_hwsim_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) memcpy(data, mac80211_hwsim_gstrings_stats, sizeof(mac80211_hwsim_gstrings_stats)); } static int mac80211_hwsim_get_et_sset_count(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int sset) { if (sset == ETH_SS_STATS) return MAC80211_HWSIM_SSTATS_LEN; return 0; } static void mac80211_hwsim_get_et_stats(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ethtool_stats *stats, u64 *data) { struct mac80211_hwsim_data *ar = hw->priv; int i = 0; data[i++] = ar->tx_pkts; data[i++] = ar->tx_bytes; data[i++] = ar->rx_pkts; data[i++] = ar->rx_bytes; data[i++] = ar->tx_dropped; data[i++] = ar->tx_failed; data[i++] = ar->ps; data[i++] = ar->group; WARN_ON(i != MAC80211_HWSIM_SSTATS_LEN); } static int mac80211_hwsim_tx_last_beacon(struct ieee80211_hw *hw) { return 1; } static int mac80211_hwsim_set_rts_threshold(struct ieee80211_hw *hw, u32 value) { return -EOPNOTSUPP; } static int mac80211_hwsim_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 old_links, u16 new_links, struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]) { unsigned long rem = old_links & ~new_links; unsigned long add = new_links & ~old_links; int i; if (!old_links) rem |= BIT(0); if (!new_links) add |= BIT(0); for_each_set_bit(i, &rem, IEEE80211_MLD_MAX_NUM_LINKS) mac80211_hwsim_config_mac_nl(hw, old[i]->addr, false); for_each_set_bit(i, &add, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_bss_conf *link_conf; link_conf = link_conf_dereference_protected(vif, i); if (WARN_ON(!link_conf)) continue; mac80211_hwsim_config_mac_nl(hw, link_conf->addr, true); } return 0; } static int mac80211_hwsim_change_sta_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u16 old_links, u16 new_links) { struct hwsim_sta_priv *sp = (void *)sta->drv_priv; hwsim_check_sta_magic(sta); if (vif->type == NL80211_IFTYPE_STATION) sp->active_links_rx = new_links; return 0; } static int mac80211_hwsim_send_pmsr_ftm_request_peer(struct sk_buff *msg, struct cfg80211_pmsr_ftm_request_peer *request) { struct nlattr *ftm; if (!request->requested) return -EINVAL; ftm = nla_nest_start(msg, NL80211_PMSR_TYPE_FTM); if (!ftm) return -ENOBUFS; if (nla_put_u32(msg, NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE, request->preamble)) return -ENOBUFS; if (nla_put_u16(msg, NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD, request->burst_period)) return -ENOBUFS; if (request->asap && nla_put_flag(msg, NL80211_PMSR_FTM_REQ_ATTR_ASAP)) return -ENOBUFS; if (request->request_lci && nla_put_flag(msg, NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI)) return -ENOBUFS; if (request->request_civicloc && nla_put_flag(msg, NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC)) return -ENOBUFS; if (request->trigger_based && nla_put_flag(msg, NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED)) return -ENOBUFS; if (request->non_trigger_based && nla_put_flag(msg, NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED)) return -ENOBUFS; if (request->lmr_feedback && nla_put_flag(msg, NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK)) return -ENOBUFS; if (nla_put_u8(msg, NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP, request->num_bursts_exp)) return -ENOBUFS; if (nla_put_u8(msg, NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION, request->burst_duration)) return -ENOBUFS; if (nla_put_u8(msg, NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST, request->ftms_per_burst)) return -ENOBUFS; if (nla_put_u8(msg, NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES, request->ftmr_retries)) return -ENOBUFS; if (nla_put_u8(msg, NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION, request->burst_duration)) return -ENOBUFS; if (nla_put_u8(msg, NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR, request->bss_color)) return -ENOBUFS; nla_nest_end(msg, ftm); return 0; } static int mac80211_hwsim_send_pmsr_request_peer(struct sk_buff *msg, struct cfg80211_pmsr_request_peer *request) { struct nlattr *peer, *chandef, *req, *data; int err; peer = nla_nest_start(msg, NL80211_PMSR_ATTR_PEERS); if (!peer) return -ENOBUFS; if (nla_put(msg, NL80211_PMSR_PEER_ATTR_ADDR, ETH_ALEN, request->addr)) return -ENOBUFS; chandef = nla_nest_start(msg, NL80211_PMSR_PEER_ATTR_CHAN); if (!chandef) return -ENOBUFS; err = nl80211_send_chandef(msg, &request->chandef); if (err) return err; nla_nest_end(msg, chandef); req = nla_nest_start(msg, NL80211_PMSR_PEER_ATTR_REQ); if (!req) return -ENOBUFS; if (request->report_ap_tsf && nla_put_flag(msg, NL80211_PMSR_REQ_ATTR_GET_AP_TSF)) return -ENOBUFS; data = nla_nest_start(msg, NL80211_PMSR_REQ_ATTR_DATA); if (!data) return -ENOBUFS; err = mac80211_hwsim_send_pmsr_ftm_request_peer(msg, &request->ftm); if (err) return err; nla_nest_end(msg, data); nla_nest_end(msg, req); nla_nest_end(msg, peer); return 0; } static int mac80211_hwsim_send_pmsr_request(struct sk_buff *msg, struct cfg80211_pmsr_request *request) { struct nlattr *pmsr; int err; pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS); if (!pmsr) return -ENOBUFS; if (nla_put_u32(msg, NL80211_ATTR_TIMEOUT, request->timeout)) return -ENOBUFS; if (!is_zero_ether_addr(request->mac_addr)) { if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, request->mac_addr)) return -ENOBUFS; if (nla_put(msg, NL80211_ATTR_MAC_MASK, ETH_ALEN, request->mac_addr_mask)) return -ENOBUFS; } for (int i = 0; i < request->n_peers; i++) { err = mac80211_hwsim_send_pmsr_request_peer(msg, &request->peers[i]); if (err) return err; } nla_nest_end(msg, pmsr); return 0; } static int mac80211_hwsim_start_pmsr(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request) { struct mac80211_hwsim_data *data; struct sk_buff *skb = NULL; struct nlattr *pmsr; void *msg_head; u32 _portid; int err = 0; data = hw->priv; _portid = READ_ONCE(data->wmediumd); if (!_portid && !hwsim_virtio_enabled) return -EOPNOTSUPP; mutex_lock(&data->mutex); if (data->pmsr_request) { err = -EBUSY; goto out_free; } skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) { err = -ENOMEM; goto out_free; } msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_START_PMSR); if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, data->addresses[1].addr)) { err = -ENOMEM; goto out_free; } pmsr = nla_nest_start(skb, HWSIM_ATTR_PMSR_REQUEST); if (!pmsr) { err = -ENOMEM; goto out_free; } err = mac80211_hwsim_send_pmsr_request(skb, request); if (err) goto out_free; nla_nest_end(skb, pmsr); genlmsg_end(skb, msg_head); if (hwsim_virtio_enabled) hwsim_tx_virtio(data, skb); else hwsim_unicast_netgroup(data, skb, _portid); data->pmsr_request = request; data->pmsr_request_wdev = ieee80211_vif_to_wdev(vif); out_free: if (err && skb) nlmsg_free(skb); mutex_unlock(&data->mutex); return err; } static void mac80211_hwsim_abort_pmsr(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request) { struct mac80211_hwsim_data *data; struct sk_buff *skb = NULL; struct nlattr *pmsr; void *msg_head; u32 _portid; int err = 0; data = hw->priv; _portid = READ_ONCE(data->wmediumd); if (!_portid && !hwsim_virtio_enabled) return; mutex_lock(&data->mutex); if (data->pmsr_request != request) { err = -EINVAL; goto out; } skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) { err = -ENOMEM; goto out; } msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_ABORT_PMSR); if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, data->addresses[1].addr)) goto out; pmsr = nla_nest_start(skb, HWSIM_ATTR_PMSR_REQUEST); if (!pmsr) { err = -ENOMEM; goto out; } err = mac80211_hwsim_send_pmsr_request(skb, request); if (err) goto out; err = nla_nest_end(skb, pmsr); if (err) goto out; genlmsg_end(skb, msg_head); if (hwsim_virtio_enabled) hwsim_tx_virtio(data, skb); else hwsim_unicast_netgroup(data, skb, _portid); out: if (err && skb) nlmsg_free(skb); mutex_unlock(&data->mutex); } static int mac80211_hwsim_parse_rate_info(struct nlattr *rateattr, struct rate_info *rate_info, struct genl_info *info) { struct nlattr *tb[HWSIM_RATE_INFO_ATTR_MAX + 1]; int ret; ret = nla_parse_nested(tb, HWSIM_RATE_INFO_ATTR_MAX, rateattr, hwsim_rate_info_policy, info->extack); if (ret) return ret; if (tb[HWSIM_RATE_INFO_ATTR_FLAGS]) rate_info->flags = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_FLAGS]); if (tb[HWSIM_RATE_INFO_ATTR_MCS]) rate_info->mcs = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_MCS]); if (tb[HWSIM_RATE_INFO_ATTR_LEGACY]) rate_info->legacy = nla_get_u16(tb[HWSIM_RATE_INFO_ATTR_LEGACY]); if (tb[HWSIM_RATE_INFO_ATTR_NSS]) rate_info->nss = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_NSS]); if (tb[HWSIM_RATE_INFO_ATTR_BW]) rate_info->bw = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_BW]); if (tb[HWSIM_RATE_INFO_ATTR_HE_GI]) rate_info->he_gi = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_HE_GI]); if (tb[HWSIM_RATE_INFO_ATTR_HE_DCM]) rate_info->he_dcm = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_HE_DCM]); if (tb[HWSIM_RATE_INFO_ATTR_HE_RU_ALLOC]) rate_info->he_ru_alloc = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_HE_RU_ALLOC]); if (tb[HWSIM_RATE_INFO_ATTR_N_BOUNDED_CH]) rate_info->n_bonded_ch = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_N_BOUNDED_CH]); if (tb[HWSIM_RATE_INFO_ATTR_EHT_GI]) rate_info->eht_gi = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_EHT_GI]); if (tb[HWSIM_RATE_INFO_ATTR_EHT_RU_ALLOC]) rate_info->eht_ru_alloc = nla_get_u8(tb[HWSIM_RATE_INFO_ATTR_EHT_RU_ALLOC]); return 0; } static int mac80211_hwsim_parse_ftm_result(struct nlattr *ftm, struct cfg80211_pmsr_ftm_result *result, struct genl_info *info) { struct nlattr *tb[NL80211_PMSR_FTM_RESP_ATTR_MAX + 1]; int ret; ret = nla_parse_nested(tb, NL80211_PMSR_FTM_RESP_ATTR_MAX, ftm, hwsim_ftm_result_policy, info->extack); if (ret) return ret; if (tb[NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON]) result->failure_reason = nla_get_u32(tb[NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON]); if (tb[NL80211_PMSR_FTM_RESP_ATTR_BURST_INDEX]) result->burst_index = nla_get_u16(tb[NL80211_PMSR_FTM_RESP_ATTR_BURST_INDEX]); if (tb[NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS]) { result->num_ftmr_attempts_valid = 1; result->num_ftmr_attempts = nla_get_u32(tb[NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES]) { result->num_ftmr_successes_valid = 1; result->num_ftmr_successes = nla_get_u32(tb[NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME]) result->busy_retry_time = nla_get_u8(tb[NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME]); if (tb[NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP]) result->num_bursts_exp = nla_get_u8(tb[NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP]); if (tb[NL80211_PMSR_FTM_RESP_ATTR_BURST_DURATION]) result->burst_duration = nla_get_u8(tb[NL80211_PMSR_FTM_RESP_ATTR_BURST_DURATION]); if (tb[NL80211_PMSR_FTM_RESP_ATTR_FTMS_PER_BURST]) result->ftms_per_burst = nla_get_u8(tb[NL80211_PMSR_FTM_RESP_ATTR_FTMS_PER_BURST]); if (tb[NL80211_PMSR_FTM_RESP_ATTR_RSSI_AVG]) { result->rssi_avg_valid = 1; result->rssi_avg = nla_get_s32(tb[NL80211_PMSR_FTM_RESP_ATTR_RSSI_AVG]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_RSSI_SPREAD]) { result->rssi_spread_valid = 1; result->rssi_spread = nla_get_s32(tb[NL80211_PMSR_FTM_RESP_ATTR_RSSI_SPREAD]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_TX_RATE]) { result->tx_rate_valid = 1; ret = mac80211_hwsim_parse_rate_info(tb[NL80211_PMSR_FTM_RESP_ATTR_TX_RATE], &result->tx_rate, info); if (ret) return ret; } if (tb[NL80211_PMSR_FTM_RESP_ATTR_RX_RATE]) { result->rx_rate_valid = 1; ret = mac80211_hwsim_parse_rate_info(tb[NL80211_PMSR_FTM_RESP_ATTR_RX_RATE], &result->rx_rate, info); if (ret) return ret; } if (tb[NL80211_PMSR_FTM_RESP_ATTR_RTT_AVG]) { result->rtt_avg_valid = 1; result->rtt_avg = nla_get_u64(tb[NL80211_PMSR_FTM_RESP_ATTR_RTT_AVG]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_RTT_VARIANCE]) { result->rtt_variance_valid = 1; result->rtt_variance = nla_get_u64(tb[NL80211_PMSR_FTM_RESP_ATTR_RTT_VARIANCE]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_RTT_SPREAD]) { result->rtt_spread_valid = 1; result->rtt_spread = nla_get_u64(tb[NL80211_PMSR_FTM_RESP_ATTR_RTT_SPREAD]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_DIST_AVG]) { result->dist_avg_valid = 1; result->dist_avg = nla_get_u64(tb[NL80211_PMSR_FTM_RESP_ATTR_DIST_AVG]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_DIST_VARIANCE]) { result->dist_variance_valid = 1; result->dist_variance = nla_get_u64(tb[NL80211_PMSR_FTM_RESP_ATTR_DIST_VARIANCE]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_DIST_SPREAD]) { result->dist_spread_valid = 1; result->dist_spread = nla_get_u64(tb[NL80211_PMSR_FTM_RESP_ATTR_DIST_SPREAD]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_LCI]) { result->lci = nla_data(tb[NL80211_PMSR_FTM_RESP_ATTR_LCI]); result->lci_len = nla_len(tb[NL80211_PMSR_FTM_RESP_ATTR_LCI]); } if (tb[NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC]) { result->civicloc = nla_data(tb[NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC]); result->civicloc_len = nla_len(tb[NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC]); } return 0; } static int mac80211_hwsim_parse_pmsr_resp(struct nlattr *resp, struct cfg80211_pmsr_result *result, struct genl_info *info) { struct nlattr *tb[NL80211_PMSR_RESP_ATTR_MAX + 1]; struct nlattr *pmsr; int rem; int ret; ret = nla_parse_nested(tb, NL80211_PMSR_RESP_ATTR_MAX, resp, hwsim_pmsr_resp_policy, info->extack); if (ret) return ret; if (tb[NL80211_PMSR_RESP_ATTR_STATUS]) result->status = nla_get_u32(tb[NL80211_PMSR_RESP_ATTR_STATUS]); if (tb[NL80211_PMSR_RESP_ATTR_HOST_TIME]) result->host_time = nla_get_u64(tb[NL80211_PMSR_RESP_ATTR_HOST_TIME]); if (tb[NL80211_PMSR_RESP_ATTR_AP_TSF]) { result->ap_tsf_valid = 1; result->ap_tsf = nla_get_u64(tb[NL80211_PMSR_RESP_ATTR_AP_TSF]); } result->final = !!tb[NL80211_PMSR_RESP_ATTR_FINAL]; if (!tb[NL80211_PMSR_RESP_ATTR_DATA]) return 0; nla_for_each_nested(pmsr, tb[NL80211_PMSR_RESP_ATTR_DATA], rem) { switch (nla_type(pmsr)) { case NL80211_PMSR_TYPE_FTM: result->type = NL80211_PMSR_TYPE_FTM; ret = mac80211_hwsim_parse_ftm_result(pmsr, &result->ftm, info); if (ret) return ret; break; default: NL_SET_ERR_MSG_ATTR(info->extack, pmsr, "Unknown pmsr resp type"); return -EINVAL; } } return 0; } static int mac80211_hwsim_parse_pmsr_result(struct nlattr *peer, struct cfg80211_pmsr_result *result, struct genl_info *info) { struct nlattr *tb[NL80211_PMSR_PEER_ATTR_MAX + 1]; int ret; if (!peer) return -EINVAL; ret = nla_parse_nested(tb, NL80211_PMSR_PEER_ATTR_MAX, peer, hwsim_pmsr_peer_result_policy, info->extack); if (ret) return ret; if (tb[NL80211_PMSR_PEER_ATTR_ADDR]) memcpy(result->addr, nla_data(tb[NL80211_PMSR_PEER_ATTR_ADDR]), ETH_ALEN); if (tb[NL80211_PMSR_PEER_ATTR_RESP]) { ret = mac80211_hwsim_parse_pmsr_resp(tb[NL80211_PMSR_PEER_ATTR_RESP], result, info); if (ret) return ret; } return 0; }; static int hwsim_pmsr_report_nl(struct sk_buff *msg, struct genl_info *info) { struct mac80211_hwsim_data *data; struct nlattr *peers, *peer; struct nlattr *reqattr; const u8 *src; int err; int rem; if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER]) return -EINVAL; src = nla_data(info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER]); data = get_hwsim_data_ref_from_addr(src); if (!data) return -EINVAL; mutex_lock(&data->mutex); if (!data->pmsr_request) { err = -EINVAL; goto out; } reqattr = info->attrs[HWSIM_ATTR_PMSR_RESULT]; if (!reqattr) { err = -EINVAL; goto out; } peers = nla_find_nested(reqattr, NL80211_PMSR_ATTR_PEERS); if (!peers) { err = -EINVAL; goto out; } nla_for_each_nested(peer, peers, rem) { struct cfg80211_pmsr_result result = {}; err = mac80211_hwsim_parse_pmsr_result(peer, &result, info); if (err) goto out; cfg80211_pmsr_report(data->pmsr_request_wdev, data->pmsr_request, &result, GFP_KERNEL); } cfg80211_pmsr_complete(data->pmsr_request_wdev, data->pmsr_request, GFP_KERNEL); err = 0; out: data->pmsr_request = NULL; data->pmsr_request_wdev = NULL; mutex_unlock(&data->mutex); return err; } #ifdef CONFIG_MAC80211_DEBUGFS #define HWSIM_DEBUGFS_OPS \ .link_add_debugfs = mac80211_hwsim_link_add_debugfs, #else #define HWSIM_DEBUGFS_OPS #endif #define HWSIM_COMMON_OPS \ .tx = mac80211_hwsim_tx, \ .wake_tx_queue = ieee80211_handle_wake_tx_queue, \ .start = mac80211_hwsim_start, \ .stop = mac80211_hwsim_stop, \ .add_interface = mac80211_hwsim_add_interface, \ .change_interface = mac80211_hwsim_change_interface, \ .remove_interface = mac80211_hwsim_remove_interface, \ .config = mac80211_hwsim_config, \ .configure_filter = mac80211_hwsim_configure_filter, \ .vif_cfg_changed = mac80211_hwsim_vif_info_changed, \ .link_info_changed = mac80211_hwsim_link_info_changed, \ .tx_last_beacon = mac80211_hwsim_tx_last_beacon, \ .sta_notify = mac80211_hwsim_sta_notify, \ .link_sta_rc_update = mac80211_hwsim_sta_rc_update, \ .conf_tx = mac80211_hwsim_conf_tx, \ .get_survey = mac80211_hwsim_get_survey, \ CFG80211_TESTMODE_CMD(mac80211_hwsim_testmode_cmd) \ .ampdu_action = mac80211_hwsim_ampdu_action, \ .flush = mac80211_hwsim_flush, \ .get_et_sset_count = mac80211_hwsim_get_et_sset_count, \ .get_et_stats = mac80211_hwsim_get_et_stats, \ .get_et_strings = mac80211_hwsim_get_et_strings, \ .start_pmsr = mac80211_hwsim_start_pmsr, \ .abort_pmsr = mac80211_hwsim_abort_pmsr, \ HWSIM_DEBUGFS_OPS #define HWSIM_NON_MLO_OPS \ .sta_add = mac80211_hwsim_sta_add, \ .sta_remove = mac80211_hwsim_sta_remove, \ .set_tim = mac80211_hwsim_set_tim, \ .get_tsf = mac80211_hwsim_get_tsf, \ .set_tsf = mac80211_hwsim_set_tsf, static const struct ieee80211_ops mac80211_hwsim_ops = { HWSIM_COMMON_OPS HWSIM_NON_MLO_OPS .sw_scan_start = mac80211_hwsim_sw_scan, .sw_scan_complete = mac80211_hwsim_sw_scan_complete, .add_chanctx = ieee80211_emulate_add_chanctx, .remove_chanctx = ieee80211_emulate_remove_chanctx, .change_chanctx = ieee80211_emulate_change_chanctx, .switch_vif_chanctx = ieee80211_emulate_switch_vif_chanctx, }; #define HWSIM_CHANCTX_OPS \ .hw_scan = mac80211_hwsim_hw_scan, \ .cancel_hw_scan = mac80211_hwsim_cancel_hw_scan, \ .remain_on_channel = mac80211_hwsim_roc, \ .cancel_remain_on_channel = mac80211_hwsim_croc, \ .add_chanctx = mac80211_hwsim_add_chanctx, \ .remove_chanctx = mac80211_hwsim_remove_chanctx, \ .change_chanctx = mac80211_hwsim_change_chanctx, \ .assign_vif_chanctx = mac80211_hwsim_assign_vif_chanctx,\ .unassign_vif_chanctx = mac80211_hwsim_unassign_vif_chanctx, \ .switch_vif_chanctx = mac80211_hwsim_switch_vif_chanctx, static const struct ieee80211_ops mac80211_hwsim_mchan_ops = { HWSIM_COMMON_OPS HWSIM_NON_MLO_OPS HWSIM_CHANCTX_OPS }; static const struct ieee80211_ops mac80211_hwsim_mlo_ops = { HWSIM_COMMON_OPS HWSIM_CHANCTX_OPS .set_rts_threshold = mac80211_hwsim_set_rts_threshold, .change_vif_links = mac80211_hwsim_change_vif_links, .change_sta_links = mac80211_hwsim_change_sta_links, .sta_state = mac80211_hwsim_sta_state, .can_neg_ttlm = mac80211_hwsim_can_neg_ttlm, }; struct hwsim_new_radio_params { unsigned int channels; const char *reg_alpha2; const struct ieee80211_regdomain *regd; bool reg_strict; bool p2p_device; bool use_chanctx; bool multi_radio; bool destroy_on_close; const char *hwname; bool no_vif; const u8 *perm_addr; u32 iftypes; u32 *ciphers; u8 n_ciphers; bool mlo; const struct cfg80211_pmsr_capabilities *pmsr_capa; }; static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb, struct genl_info *info) { if (info) genl_notify(&hwsim_genl_family, mcast_skb, info, HWSIM_MCGRP_CONFIG, GFP_KERNEL); else genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0, HWSIM_MCGRP_CONFIG, GFP_KERNEL); } static int append_radio_msg(struct sk_buff *skb, int id, struct hwsim_new_radio_params *param) { int ret; ret = nla_put_u32(skb, HWSIM_ATTR_RADIO_ID, id); if (ret < 0) return ret; if (param->channels) { ret = nla_put_u32(skb, HWSIM_ATTR_CHANNELS, param->channels); if (ret < 0) return ret; } if (param->reg_alpha2) { ret = nla_put(skb, HWSIM_ATTR_REG_HINT_ALPHA2, 2, param->reg_alpha2); if (ret < 0) return ret; } if (param->regd) { int i; for (i = 0; i < ARRAY_SIZE(hwsim_world_regdom_custom); i++) { if (hwsim_world_regdom_custom[i] != param->regd) continue; ret = nla_put_u32(skb, HWSIM_ATTR_REG_CUSTOM_REG, i); if (ret < 0) return ret; break; } } if (param->reg_strict) { ret = nla_put_flag(skb, HWSIM_ATTR_REG_STRICT_REG); if (ret < 0) return ret; } if (param->p2p_device) { ret = nla_put_flag(skb, HWSIM_ATTR_SUPPORT_P2P_DEVICE); if (ret < 0) return ret; } if (param->use_chanctx) { ret = nla_put_flag(skb, HWSIM_ATTR_USE_CHANCTX); if (ret < 0) return ret; } if (param->multi_radio) { ret = nla_put_flag(skb, HWSIM_ATTR_MULTI_RADIO); if (ret < 0) return ret; } if (param->hwname) { ret = nla_put(skb, HWSIM_ATTR_RADIO_NAME, strlen(param->hwname), param->hwname); if (ret < 0) return ret; } return 0; } static void hwsim_mcast_new_radio(int id, struct genl_info *info, struct hwsim_new_radio_params *param) { struct sk_buff *mcast_skb; void *data; mcast_skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!mcast_skb) return; data = genlmsg_put(mcast_skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_NEW_RADIO); if (!data) goto out_err; if (append_radio_msg(mcast_skb, id, param) < 0) goto out_err; genlmsg_end(mcast_skb, data); hwsim_mcast_config_msg(mcast_skb, info); return; out_err: nlmsg_free(mcast_skb); } static const struct ieee80211_sband_iftype_data sband_capa_2ghz[] = { { .types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_P2P_CLIENT), .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xffff), .tx_mcs_160 = cpu_to_le16(0xffff), .rx_mcs_80p80 = cpu_to_le16(0xffff), .tx_mcs_80p80 = cpu_to_le16(0xffff), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE, .phy_cap_info[3] = IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, .phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, .phy_cap_info[5] = IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, .phy_cap_info[6] = IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK, .phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW, }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* * Since B0, B1, B2 and B3 are not set in * the supported channel width set field in the * HE PHY capabilities information field the * device is a 20MHz only device on 2.4GHz band. */ .only_20mhz = { .rx_tx_mcs7_max_nss = 0x88, .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, { .types_mask = BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_GO), .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xffff), .tx_mcs_160 = cpu_to_le16(0xffff), .rx_mcs_80p80 = cpu_to_le16(0xffff), .tx_mcs_80p80 = cpu_to_le16(0xffff), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE, .phy_cap_info[3] = IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, .phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, .phy_cap_info[5] = IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, .phy_cap_info[6] = IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK, .phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW, }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* * Since B0, B1, B2 and B3 are not set in * the supported channel width set field in the * HE PHY capabilities information field the * device is a 20MHz only device on 2.4GHz band. */ .only_20mhz = { .rx_tx_mcs7_max_nss = 0x88, .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, #ifdef CONFIG_MAC80211_MESH { .types_mask = BIT(NL80211_IFTYPE_MESH_POINT), .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = 0, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xffff), .tx_mcs_160 = cpu_to_le16(0xffff), .rx_mcs_80p80 = cpu_to_le16(0xffff), .tx_mcs_80p80 = cpu_to_le16(0xffff), }, }, }, #endif }; static const struct ieee80211_sband_iftype_data sband_capa_5ghz[] = { { .types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_P2P_CLIENT), .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xfffa), .tx_mcs_160 = cpu_to_le16(0xfffa), .rx_mcs_80p80 = cpu_to_le16(0xfffa), .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE | IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK, .phy_cap_info[1] = IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK | IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK, .phy_cap_info[2] = IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK | IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK, .phy_cap_info[3] = IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, .phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, .phy_cap_info[5] = IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, .phy_cap_info[6] = IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK, .phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ, }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* * As B1 and B2 are set in the supported * channel width set field in the HE PHY * capabilities information field include all * the following MCS/NSS. */ .bw._80 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._160 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, { .types_mask = BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_GO), .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xfffa), .tx_mcs_160 = cpu_to_le16(0xfffa), .rx_mcs_80p80 = cpu_to_le16(0xfffa), .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE | IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK, .phy_cap_info[1] = IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK | IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK, .phy_cap_info[2] = IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK | IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK, .phy_cap_info[3] = IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, .phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, .phy_cap_info[5] = IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, .phy_cap_info[6] = IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK, .phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ, }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* * As B1 and B2 are set in the supported * channel width set field in the HE PHY * capabilities information field include all * the following MCS/NSS. */ .bw._80 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._160 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, #ifdef CONFIG_MAC80211_MESH { /* TODO: should we support other types, e.g., IBSS?*/ .types_mask = BIT(NL80211_IFTYPE_MESH_POINT), .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = 0, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xfffa), .tx_mcs_160 = cpu_to_le16(0xfffa), .rx_mcs_80p80 = cpu_to_le16(0xfffa), .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, }, #endif }; static const struct ieee80211_sband_iftype_data sband_capa_6ghz[] = { { .types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_P2P_CLIENT), .he_6ghz_capa = { .capa = cpu_to_le16(IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START | IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP | IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN | IEEE80211_HE_6GHZ_CAP_SM_PS | IEEE80211_HE_6GHZ_CAP_RD_RESPONDER | IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS | IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS), }, .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xfffa), .tx_mcs_160 = cpu_to_le16(0xfffa), .rx_mcs_80p80 = cpu_to_le16(0xfffa), .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ | IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE | IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK, .phy_cap_info[1] = IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK | IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK | IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK, .phy_cap_info[2] = IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK | IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK | IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK, .phy_cap_info[3] = IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, .phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, .phy_cap_info[5] = IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, .phy_cap_info[6] = IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK | IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP, .phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ, }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* * As B1 and B2 are set in the supported * channel width set field in the HE PHY * capabilities information field and 320MHz in * 6GHz is supported include all the following * MCS/NSS. */ .bw._80 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._160 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._320 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, { .types_mask = BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_GO), .he_6ghz_capa = { .capa = cpu_to_le16(IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START | IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP | IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN | IEEE80211_HE_6GHZ_CAP_SM_PS | IEEE80211_HE_6GHZ_CAP_RD_RESPONDER | IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS | IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS), }, .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xfffa), .tx_mcs_160 = cpu_to_le16(0xfffa), .rx_mcs_80p80 = cpu_to_le16(0xfffa), .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS | IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ | IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ | IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI | IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER | IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE | IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK, .phy_cap_info[1] = IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK | IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK | IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK, .phy_cap_info[2] = IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK | IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK | IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK, .phy_cap_info[3] = IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK | IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK, .phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO | IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP | IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI | IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK, .phy_cap_info[5] = IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP | IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT | IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK | IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK, .phy_cap_info[6] = IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK | IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK | IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP, .phy_cap_info[7] = IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ, }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* * As B1 and B2 are set in the supported * channel width set field in the HE PHY * capabilities information field and 320MHz in * 6GHz is supported include all the following * MCS/NSS. */ .bw._80 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._160 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._320 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, #ifdef CONFIG_MAC80211_MESH { /* TODO: should we support other types, e.g., IBSS?*/ .types_mask = BIT(NL80211_IFTYPE_MESH_POINT), .he_6ghz_capa = { .capa = cpu_to_le16(IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START | IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP | IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN | IEEE80211_HE_6GHZ_CAP_SM_PS | IEEE80211_HE_6GHZ_CAP_RD_RESPONDER | IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS | IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS), }, .he_cap = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = 0, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, .he_mcs_nss_supp = { .rx_mcs_80 = cpu_to_le16(0xfffa), .tx_mcs_80 = cpu_to_le16(0xfffa), .rx_mcs_160 = cpu_to_le16(0xfffa), .tx_mcs_160 = cpu_to_le16(0xfffa), .rx_mcs_80p80 = cpu_to_le16(0xfffa), .tx_mcs_80p80 = cpu_to_le16(0xfffa), }, }, .eht_cap = { .has_eht = true, .eht_cap_elem = { .mac_cap_info[0] = IEEE80211_EHT_MAC_CAP0_OM_CONTROL | IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1, .phy_cap_info[0] = IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ, /* Leave all the other PHY capability bytes * unset, as DCM, beam forming, RU and PPE * threshold information are not supported */ }, /* For all MCS and bandwidth, set 8 NSS for both Tx and * Rx */ .eht_mcs_nss_supp = { /* As B1 and B2 are set in the supported * channel width set field in the HE PHY * capabilities information field and 320MHz in * 6GHz is supported include all the following * MCS/NSS. */ .bw._80 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._160 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, .bw._320 = { .rx_tx_mcs9_max_nss = 0x88, .rx_tx_mcs11_max_nss = 0x88, .rx_tx_mcs13_max_nss = 0x88, }, }, /* PPE threshold information is not supported */ }, }, #endif }; static void mac80211_hwsim_sband_capab(struct ieee80211_supported_band *sband) { switch (sband->band) { case NL80211_BAND_2GHZ: ieee80211_set_sband_iftype_data(sband, sband_capa_2ghz); break; case NL80211_BAND_5GHZ: ieee80211_set_sband_iftype_data(sband, sband_capa_5ghz); break; case NL80211_BAND_6GHZ: ieee80211_set_sband_iftype_data(sband, sband_capa_6ghz); break; default: break; } } #ifdef CONFIG_MAC80211_MESH #define HWSIM_MESH_BIT BIT(NL80211_IFTYPE_MESH_POINT) #else #define HWSIM_MESH_BIT 0 #endif #define HWSIM_DEFAULT_IF_LIMIT \ (BIT(NL80211_IFTYPE_STATION) | \ BIT(NL80211_IFTYPE_P2P_CLIENT) | \ BIT(NL80211_IFTYPE_AP) | \ BIT(NL80211_IFTYPE_P2P_GO) | \ HWSIM_MESH_BIT) #define HWSIM_IFTYPE_SUPPORT_MASK \ (BIT(NL80211_IFTYPE_STATION) | \ BIT(NL80211_IFTYPE_AP) | \ BIT(NL80211_IFTYPE_P2P_CLIENT) | \ BIT(NL80211_IFTYPE_P2P_GO) | \ BIT(NL80211_IFTYPE_ADHOC) | \ BIT(NL80211_IFTYPE_MESH_POINT) | \ BIT(NL80211_IFTYPE_OCB)) static const u8 iftypes_ext_capa_ap[] = { [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING, [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT, [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF | WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB, [8] = WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB, [9] = WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT, }; #define MAC80211_HWSIM_MLD_CAPA_OPS \ FIELD_PREP_CONST(IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP, \ IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME) | \ FIELD_PREP_CONST(IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS, \ IEEE80211_MLD_MAX_NUM_LINKS - 1) static const struct wiphy_iftype_ext_capab mac80211_hwsim_iftypes_ext_capa[] = { { .iftype = NL80211_IFTYPE_AP, .extended_capabilities = iftypes_ext_capa_ap, .extended_capabilities_mask = iftypes_ext_capa_ap, .extended_capabilities_len = sizeof(iftypes_ext_capa_ap), .eml_capabilities = IEEE80211_EML_CAP_EMLSR_SUPP | IEEE80211_EML_CAP_EMLMR_SUPPORT, .mld_capa_and_ops = MAC80211_HWSIM_MLD_CAPA_OPS, }, }; static int mac80211_hwsim_new_radio(struct genl_info *info, struct hwsim_new_radio_params *param) { int err; u8 addr[ETH_ALEN]; struct mac80211_hwsim_data *data; struct ieee80211_hw *hw; enum nl80211_band band; const struct ieee80211_ops *ops = &mac80211_hwsim_ops; struct net *net; int idx, i; int n_limits = 0; int n_bands = 0; if (WARN_ON(param->channels > 1 && !param->use_chanctx)) return -EINVAL; spin_lock_bh(&hwsim_radio_lock); idx = hwsim_radio_idx++; spin_unlock_bh(&hwsim_radio_lock); if (param->mlo) ops = &mac80211_hwsim_mlo_ops; else if (param->use_chanctx) ops = &mac80211_hwsim_mchan_ops; hw = ieee80211_alloc_hw_nm(sizeof(*data), ops, param->hwname); if (!hw) { pr_debug("mac80211_hwsim: ieee80211_alloc_hw failed\n"); err = -ENOMEM; goto failed; } /* ieee80211_alloc_hw_nm may have used a default name */ param->hwname = wiphy_name(hw->wiphy); if (info) net = genl_info_net(info); else net = &init_net; wiphy_net_set(hw->wiphy, net); data = hw->priv; data->hw = hw; data->dev = device_create(hwsim_class, NULL, 0, hw, "hwsim%d", idx); if (IS_ERR(data->dev)) { printk(KERN_DEBUG "mac80211_hwsim: device_create failed (%ld)\n", PTR_ERR(data->dev)); err = -ENOMEM; goto failed_drvdata; } data->dev->driver = &mac80211_hwsim_driver.driver; err = device_bind_driver(data->dev); if (err != 0) { pr_debug("mac80211_hwsim: device_bind_driver failed (%d)\n", err); goto failed_bind; } skb_queue_head_init(&data->pending); SET_IEEE80211_DEV(hw, data->dev); if (!param->perm_addr) { eth_zero_addr(addr); addr[0] = 0x02; addr[3] = idx >> 8; addr[4] = idx; memcpy(data->addresses[0].addr, addr, ETH_ALEN); /* Why need here second address ? */ memcpy(data->addresses[1].addr, addr, ETH_ALEN); data->addresses[1].addr[0] |= 0x40; hw->wiphy->n_addresses = 2; hw->wiphy->addresses = data->addresses; /* possible address clash is checked at hash table insertion */ } else { memcpy(data->addresses[0].addr, param->perm_addr, ETH_ALEN); /* compatibility with automatically generated mac addr */ memcpy(data->addresses[1].addr, param->perm_addr, ETH_ALEN); hw->wiphy->n_addresses = 2; hw->wiphy->addresses = data->addresses; } data->channels = param->channels; data->use_chanctx = param->use_chanctx; data->idx = idx; data->destroy_on_close = param->destroy_on_close; if (info) data->portid = info->snd_portid; /* setup interface limits, only on interface types we support */ if (param->iftypes & BIT(NL80211_IFTYPE_ADHOC)) { data->if_limits[n_limits].max = 1; data->if_limits[n_limits].types = BIT(NL80211_IFTYPE_ADHOC); n_limits++; } if (param->iftypes & HWSIM_DEFAULT_IF_LIMIT) { data->if_limits[n_limits].max = 2048; /* * For this case, we may only support a subset of * HWSIM_DEFAULT_IF_LIMIT, therefore we only want to add the * bits that both param->iftype & HWSIM_DEFAULT_IF_LIMIT have. */ data->if_limits[n_limits].types = HWSIM_DEFAULT_IF_LIMIT & param->iftypes; n_limits++; } if (param->iftypes & BIT(NL80211_IFTYPE_P2P_DEVICE)) { data->if_limits[n_limits].max = 1; data->if_limits[n_limits].types = BIT(NL80211_IFTYPE_P2P_DEVICE); n_limits++; } data->if_combination.radar_detect_widths = BIT(NL80211_CHAN_WIDTH_5) | BIT(NL80211_CHAN_WIDTH_10) | BIT(NL80211_CHAN_WIDTH_20_NOHT) | BIT(NL80211_CHAN_WIDTH_20) | BIT(NL80211_CHAN_WIDTH_40) | BIT(NL80211_CHAN_WIDTH_80) | BIT(NL80211_CHAN_WIDTH_160); if (data->use_chanctx) { hw->wiphy->max_scan_ssids = 255; hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN; hw->wiphy->max_remain_on_channel_duration = 1000; data->if_combination.num_different_channels = data->channels; } else { data->if_combination.num_different_channels = 1; } if (!n_limits) { err = -EINVAL; goto failed_hw; } data->if_combination.max_interfaces = 0; for (i = 0; i < n_limits; i++) data->if_combination.max_interfaces += data->if_limits[i].max; data->if_combination.n_limits = n_limits; data->if_combination.limits = data->if_limits; /* * If we actually were asked to support combinations, * advertise them - if there's only a single thing like * only IBSS then don't advertise it as combinations. */ if (data->if_combination.max_interfaces > 1) { hw->wiphy->iface_combinations = &data->if_combination; hw->wiphy->n_iface_combinations = 1; } if (param->ciphers) { memcpy(data->ciphers, param->ciphers, param->n_ciphers * sizeof(u32)); hw->wiphy->cipher_suites = data->ciphers; hw->wiphy->n_cipher_suites = param->n_ciphers; } hw->wiphy->mbssid_max_interfaces = 8; hw->wiphy->ema_max_profile_periodicity = 3; data->rx_rssi = DEFAULT_RX_RSSI; INIT_DELAYED_WORK(&data->roc_start, hw_roc_start); INIT_DELAYED_WORK(&data->roc_done, hw_roc_done); INIT_DELAYED_WORK(&data->hw_scan, hw_scan_work); hw->queues = 5; hw->offchannel_tx_hw_queue = 4; ieee80211_hw_set(hw, SUPPORT_FAST_XMIT); ieee80211_hw_set(hw, CHANCTX_STA_CSA); ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES); ieee80211_hw_set(hw, QUEUE_CONTROL); ieee80211_hw_set(hw, WANT_MONITOR_VIF); ieee80211_hw_set(hw, AMPDU_AGGREGATION); ieee80211_hw_set(hw, MFP_CAPABLE); ieee80211_hw_set(hw, SIGNAL_DBM); ieee80211_hw_set(hw, SUPPORTS_PS); ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS); ieee80211_hw_set(hw, TDLS_WIDER_BW); ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); ieee80211_hw_set(hw, STRICT); if (param->mlo) { hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO; ieee80211_hw_set(hw, HAS_RATE_CONTROL); ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); ieee80211_hw_set(hw, CONNECTION_MONITOR); ieee80211_hw_set(hw, AP_LINK_PS); hw->wiphy->iftype_ext_capab = mac80211_hwsim_iftypes_ext_capa; hw->wiphy->num_iftype_ext_capab = ARRAY_SIZE(mac80211_hwsim_iftypes_ext_capa); } else { ieee80211_hw_set(hw, HOST_BROADCAST_PS_BUFFERING); ieee80211_hw_set(hw, PS_NULLFUNC_STACK); if (rctbl) ieee80211_hw_set(hw, SUPPORTS_RC_TABLE); } hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT; hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS | WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL | WIPHY_FLAG_AP_UAPSD | WIPHY_FLAG_SUPPORTS_5_10_MHZ | WIPHY_FLAG_HAS_CHANNEL_SWITCH; hw->wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR | NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE | NL80211_FEATURE_STATIC_SMPS | NL80211_FEATURE_DYNAMIC_SMPS | NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_VHT_IBSS); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_BSS_COLOR); hw->wiphy->interface_modes = param->iftypes; /* ask mac80211 to reserve space for magic */ hw->vif_data_size = sizeof(struct hwsim_vif_priv); hw->sta_data_size = sizeof(struct hwsim_sta_priv); hw->chanctx_data_size = sizeof(struct hwsim_chanctx_priv); memcpy(data->channels_2ghz, hwsim_channels_2ghz, sizeof(hwsim_channels_2ghz)); memcpy(data->channels_5ghz, hwsim_channels_5ghz, sizeof(hwsim_channels_5ghz)); memcpy(data->channels_6ghz, hwsim_channels_6ghz, sizeof(hwsim_channels_6ghz)); memcpy(data->channels_s1g, hwsim_channels_s1g, sizeof(hwsim_channels_s1g)); memcpy(data->rates, hwsim_rates, sizeof(hwsim_rates)); for (band = NL80211_BAND_2GHZ; band < NUM_NL80211_BANDS; band++) { struct ieee80211_supported_band *sband = &data->bands[band]; struct wiphy_radio_freq_range *radio_range; const struct ieee80211_channel *c; struct wiphy_radio *radio; sband->band = band; switch (band) { case NL80211_BAND_2GHZ: sband->channels = data->channels_2ghz; sband->n_channels = ARRAY_SIZE(hwsim_channels_2ghz); sband->bitrates = data->rates; sband->n_bitrates = ARRAY_SIZE(hwsim_rates); break; case NL80211_BAND_5GHZ: sband->channels = data->channels_5ghz; sband->n_channels = ARRAY_SIZE(hwsim_channels_5ghz); sband->bitrates = data->rates + 4; sband->n_bitrates = ARRAY_SIZE(hwsim_rates) - 4; sband->vht_cap.vht_supported = true; sband->vht_cap.cap = IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ | IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160 | IEEE80211_VHT_CAP_TXSTBC | IEEE80211_VHT_CAP_RXSTBC_4 | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; sband->vht_cap.vht_mcs.rx_mcs_map = cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | IEEE80211_VHT_MCS_SUPPORT_0_9 << 14); sband->vht_cap.vht_mcs.tx_mcs_map = sband->vht_cap.vht_mcs.rx_mcs_map; break; case NL80211_BAND_6GHZ: sband->channels = data->channels_6ghz; sband->n_channels = ARRAY_SIZE(hwsim_channels_6ghz); sband->bitrates = data->rates + 4; sband->n_bitrates = ARRAY_SIZE(hwsim_rates) - 4; break; case NL80211_BAND_S1GHZ: memcpy(&sband->s1g_cap, &hwsim_s1g_cap, sizeof(sband->s1g_cap)); sband->channels = data->channels_s1g; sband->n_channels = ARRAY_SIZE(hwsim_channels_s1g); break; default: continue; } if (band != NL80211_BAND_6GHZ){ sband->ht_cap.ht_supported = true; sband->ht_cap.cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 | IEEE80211_HT_CAP_GRN_FLD | IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | IEEE80211_HT_CAP_DSSSCCK40; sband->ht_cap.ampdu_factor = 0x3; sband->ht_cap.ampdu_density = 0x6; memset(&sband->ht_cap.mcs, 0, sizeof(sband->ht_cap.mcs)); sband->ht_cap.mcs.rx_mask[0] = 0xff; sband->ht_cap.mcs.rx_mask[1] = 0xff; sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; } mac80211_hwsim_sband_capab(sband); hw->wiphy->bands[band] = sband; if (!param->multi_radio) continue; c = sband->channels; radio_range = &data->radio_range[n_bands]; radio_range->start_freq = ieee80211_channel_to_khz(c) - 10000; c += sband->n_channels - 1; radio_range->end_freq = ieee80211_channel_to_khz(c) + 10000; radio = &data->radio[n_bands++]; radio->freq_range = radio_range; radio->n_freq_range = 1; radio->iface_combinations = &data->if_combination_radio; radio->n_iface_combinations = 1; } if (param->multi_radio) { hw->wiphy->radio = data->radio; hw->wiphy->n_radio = n_bands; memcpy(&data->if_combination_radio, &data->if_combination, sizeof(data->if_combination)); data->if_combination.num_different_channels *= n_bands; } if (data->use_chanctx) data->if_combination.radar_detect_widths = 0; /* By default all radios belong to the first group */ data->group = 1; mutex_init(&data->mutex); data->netgroup = hwsim_net_get_netgroup(net); data->wmediumd = hwsim_net_get_wmediumd(net); /* Enable frame retransmissions for lossy channels */ hw->max_rates = 4; hw->max_rate_tries = 11; hw->wiphy->vendor_commands = mac80211_hwsim_vendor_commands; hw->wiphy->n_vendor_commands = ARRAY_SIZE(mac80211_hwsim_vendor_commands); hw->wiphy->vendor_events = mac80211_hwsim_vendor_events; hw->wiphy->n_vendor_events = ARRAY_SIZE(mac80211_hwsim_vendor_events); if (param->reg_strict) hw->wiphy->regulatory_flags |= REGULATORY_STRICT_REG; if (param->regd) { data->regd = param->regd; hw->wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG; wiphy_apply_custom_regulatory(hw->wiphy, param->regd); /* give the regulatory workqueue a chance to run */ schedule_timeout_interruptible(1); } wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_DFS_CONCURRENT); if (param->no_vif) ieee80211_hw_set(hw, NO_AUTO_VIF); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); for (i = 0; i < ARRAY_SIZE(data->link_data); i++) { hrtimer_setup(&data->link_data[i].beacon_timer, mac80211_hwsim_beacon, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_SOFT); data->link_data[i].link_id = i; } err = ieee80211_register_hw(hw); if (err < 0) { pr_debug("mac80211_hwsim: ieee80211_register_hw failed (%d)\n", err); goto failed_hw; } wiphy_dbg(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr); if (param->reg_alpha2) { data->alpha2[0] = param->reg_alpha2[0]; data->alpha2[1] = param->reg_alpha2[1]; regulatory_hint(hw->wiphy, param->reg_alpha2); } data->debugfs = debugfs_create_dir("hwsim", hw->wiphy->debugfsdir); debugfs_create_file("ps", 0666, data->debugfs, data, &hwsim_fops_ps); debugfs_create_file("group", 0666, data->debugfs, data, &hwsim_fops_group); debugfs_create_file("rx_rssi", 0666, data->debugfs, data, &hwsim_fops_rx_rssi); if (!data->use_chanctx) debugfs_create_file("dfs_simulate_radar", 0222, data->debugfs, data, &hwsim_simulate_radar); if (param->pmsr_capa) { data->pmsr_capa = *param->pmsr_capa; hw->wiphy->pmsr_capa = &data->pmsr_capa; } spin_lock_bh(&hwsim_radio_lock); err = rhashtable_insert_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); if (err < 0) { if (info) { GENL_SET_ERR_MSG(info, "perm addr already present"); NL_SET_BAD_ATTR(info->extack, info->attrs[HWSIM_ATTR_PERM_ADDR]); } spin_unlock_bh(&hwsim_radio_lock); goto failed_final_insert; } list_add_tail(&data->list, &hwsim_radios); hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); hwsim_mcast_new_radio(idx, info, param); return idx; failed_final_insert: debugfs_remove_recursive(data->debugfs); ieee80211_unregister_hw(data->hw); failed_hw: device_release_driver(data->dev); failed_bind: device_unregister(data->dev); failed_drvdata: ieee80211_free_hw(hw); failed: return err; } static void hwsim_mcast_del_radio(int id, const char *hwname, struct genl_info *info) { struct sk_buff *skb; void *data; int ret; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return; data = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_DEL_RADIO); if (!data) goto error; ret = nla_put_u32(skb, HWSIM_ATTR_RADIO_ID, id); if (ret < 0) goto error; ret = nla_put(skb, HWSIM_ATTR_RADIO_NAME, strlen(hwname), hwname); if (ret < 0) goto error; genlmsg_end(skb, data); hwsim_mcast_config_msg(skb, info); return; error: nlmsg_free(skb); } static void mac80211_hwsim_del_radio(struct mac80211_hwsim_data *data, const char *hwname, struct genl_info *info) { hwsim_mcast_del_radio(data->idx, hwname, info); debugfs_remove_recursive(data->debugfs); ieee80211_unregister_hw(data->hw); device_release_driver(data->dev); device_unregister(data->dev); ieee80211_free_hw(data->hw); } static int mac80211_hwsim_get_radio(struct sk_buff *skb, struct mac80211_hwsim_data *data, u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; struct hwsim_new_radio_params param = { }; int res = -EMSGSIZE; hdr = genlmsg_put(skb, portid, seq, &hwsim_genl_family, flags, HWSIM_CMD_GET_RADIO); if (!hdr) return -EMSGSIZE; if (cb) genl_dump_check_consistent(cb, hdr); if (data->alpha2[0] && data->alpha2[1]) param.reg_alpha2 = data->alpha2; param.reg_strict = !!(data->hw->wiphy->regulatory_flags & REGULATORY_STRICT_REG); param.p2p_device = !!(data->hw->wiphy->interface_modes & BIT(NL80211_IFTYPE_P2P_DEVICE)); param.use_chanctx = data->use_chanctx; param.regd = data->regd; param.channels = data->channels; param.hwname = wiphy_name(data->hw->wiphy); param.pmsr_capa = &data->pmsr_capa; res = append_radio_msg(skb, data->idx, ¶m); if (res < 0) goto out_err; genlmsg_end(skb, hdr); return 0; out_err: genlmsg_cancel(skb, hdr); return res; } static void mac80211_hwsim_free(void) { struct mac80211_hwsim_data *data; spin_lock_bh(&hwsim_radio_lock); while ((data = list_first_entry_or_null(&hwsim_radios, struct mac80211_hwsim_data, list))) { list_del(&data->list); spin_unlock_bh(&hwsim_radio_lock); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL); spin_lock_bh(&hwsim_radio_lock); } spin_unlock_bh(&hwsim_radio_lock); class_destroy(hwsim_class); } static const struct net_device_ops hwsim_netdev_ops = { .ndo_start_xmit = hwsim_mon_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; static void hwsim_mon_setup(struct net_device *dev) { u8 addr[ETH_ALEN]; dev->netdev_ops = &hwsim_netdev_ops; dev->needs_free_netdev = true; ether_setup(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->type = ARPHRD_IEEE80211_RADIOTAP; eth_zero_addr(addr); addr[0] = 0x12; eth_hw_addr_set(dev, addr); } static void hwsim_register_wmediumd(struct net *net, u32 portid) { struct mac80211_hwsim_data *data; hwsim_net_set_wmediumd(net, portid); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data, &hwsim_radios, list) { if (data->netgroup == hwsim_net_get_netgroup(net)) data->wmediumd = portid; } spin_unlock_bh(&hwsim_radio_lock); } static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2, struct genl_info *info) { struct ieee80211_hdr *hdr; struct mac80211_hwsim_data *data2; struct ieee80211_tx_info *txi; struct hwsim_tx_rate *tx_attempts; u64 ret_skb_cookie; struct sk_buff *skb, *tmp; const u8 *src; unsigned int hwsim_flags; int i; unsigned long flags; bool found = false; if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER] || !info->attrs[HWSIM_ATTR_FLAGS] || !info->attrs[HWSIM_ATTR_COOKIE] || !info->attrs[HWSIM_ATTR_SIGNAL] || !info->attrs[HWSIM_ATTR_TX_INFO]) goto out; src = (void *)nla_data(info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER]); hwsim_flags = nla_get_u32(info->attrs[HWSIM_ATTR_FLAGS]); ret_skb_cookie = nla_get_u64(info->attrs[HWSIM_ATTR_COOKIE]); data2 = get_hwsim_data_ref_from_addr(src); if (!data2) goto out; if (!hwsim_virtio_enabled) { if (hwsim_net_get_netgroup(genl_info_net(info)) != data2->netgroup) goto out; if (info->snd_portid != data2->wmediumd) goto out; } /* look for the skb matching the cookie passed back from user */ spin_lock_irqsave(&data2->pending.lock, flags); skb_queue_walk_safe(&data2->pending, skb, tmp) { uintptr_t skb_cookie; txi = IEEE80211_SKB_CB(skb); skb_cookie = (uintptr_t)txi->rate_driver_data[0]; if (skb_cookie == ret_skb_cookie) { __skb_unlink(skb, &data2->pending); found = true; break; } } spin_unlock_irqrestore(&data2->pending.lock, flags); /* not found */ if (!found) goto out; /* Tx info received because the frame was broadcasted on user space, so we get all the necessary info: tx attempts and skb control buff */ tx_attempts = (struct hwsim_tx_rate *)nla_data( info->attrs[HWSIM_ATTR_TX_INFO]); /* now send back TX status */ txi = IEEE80211_SKB_CB(skb); ieee80211_tx_info_clear_status(txi); for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { txi->status.rates[i].idx = tx_attempts[i].idx; txi->status.rates[i].count = tx_attempts[i].count; } txi->status.ack_signal = nla_get_u32(info->attrs[HWSIM_ATTR_SIGNAL]); if (!(hwsim_flags & HWSIM_TX_CTL_NO_ACK) && (hwsim_flags & HWSIM_TX_STAT_ACK)) { if (skb->len >= 16) { hdr = (struct ieee80211_hdr *) skb->data; mac80211_hwsim_monitor_ack(data2->channel, hdr->addr2); } txi->flags |= IEEE80211_TX_STAT_ACK; } if (hwsim_flags & HWSIM_TX_CTL_NO_ACK) txi->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED; ieee80211_tx_status_irqsafe(data2->hw, skb); return 0; out: return -EINVAL; } static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, struct genl_info *info) { struct mac80211_hwsim_data *data2; struct ieee80211_rx_status rx_status; struct ieee80211_hdr *hdr; const u8 *dst; int frame_data_len; void *frame_data; struct sk_buff *skb = NULL; struct ieee80211_channel *channel = NULL; if (!info->attrs[HWSIM_ATTR_ADDR_RECEIVER] || !info->attrs[HWSIM_ATTR_FRAME] || !info->attrs[HWSIM_ATTR_RX_RATE] || !info->attrs[HWSIM_ATTR_SIGNAL]) goto out; dst = (void *)nla_data(info->attrs[HWSIM_ATTR_ADDR_RECEIVER]); frame_data_len = nla_len(info->attrs[HWSIM_ATTR_FRAME]); frame_data = (void *)nla_data(info->attrs[HWSIM_ATTR_FRAME]); if (frame_data_len < sizeof(struct ieee80211_hdr_3addr) || frame_data_len > IEEE80211_MAX_DATA_LEN) goto err; /* Allocate new skb here */ skb = alloc_skb(frame_data_len, GFP_KERNEL); if (skb == NULL) goto err; /* Copy the data */ skb_put_data(skb, frame_data, frame_data_len); data2 = get_hwsim_data_ref_from_addr(dst); if (!data2) goto out; if (data2->use_chanctx) { if (data2->tmp_chan) channel = data2->tmp_chan; } else { channel = data2->channel; } if (!hwsim_virtio_enabled) { if (hwsim_net_get_netgroup(genl_info_net(info)) != data2->netgroup) goto out; if (info->snd_portid != data2->wmediumd) goto out; } /* check if radio is configured properly */ if ((data2->idle && !data2->tmp_chan) || !data2->started) goto out; /* A frame is received from user space */ memset(&rx_status, 0, sizeof(rx_status)); if (info->attrs[HWSIM_ATTR_FREQ]) { struct tx_iter_data iter_data = {}; /* throw away off-channel packets, but allow both the temporary * ("hw" scan/remain-on-channel), regular channels and links, * since the internal datapath also allows this */ rx_status.freq = nla_get_u32(info->attrs[HWSIM_ATTR_FREQ]); iter_data.channel = ieee80211_get_channel(data2->hw->wiphy, rx_status.freq); if (!iter_data.channel) goto out; rx_status.band = iter_data.channel->band; mutex_lock(&data2->mutex); if (!hwsim_chans_compat(iter_data.channel, channel)) { ieee80211_iterate_active_interfaces_atomic( data2->hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_tx_iter, &iter_data); if (!iter_data.receive) { mutex_unlock(&data2->mutex); goto out; } } mutex_unlock(&data2->mutex); } else if (!channel) { goto out; } else { rx_status.freq = channel->center_freq; rx_status.band = channel->band; } rx_status.rate_idx = nla_get_u32(info->attrs[HWSIM_ATTR_RX_RATE]); if (rx_status.rate_idx >= data2->hw->wiphy->bands[rx_status.band]->n_bitrates) goto out; rx_status.signal = nla_get_u32(info->attrs[HWSIM_ATTR_SIGNAL]); hdr = (void *)skb->data; if (ieee80211_is_beacon(hdr->frame_control) || ieee80211_is_probe_resp(hdr->frame_control)) rx_status.boottime_ns = ktime_get_boottime_ns(); mac80211_hwsim_rx(data2, &rx_status, skb); return 0; err: pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); out: dev_kfree_skb(skb); return -EINVAL; } static int hwsim_register_received_nl(struct sk_buff *skb_2, struct genl_info *info) { struct net *net = genl_info_net(info); struct mac80211_hwsim_data *data; int chans = 1; spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data, &hwsim_radios, list) chans = max(chans, data->channels); spin_unlock_bh(&hwsim_radio_lock); /* In the future we should revise the userspace API and allow it * to set a flag that it does support multi-channel, then we can * let this pass conditionally on the flag. * For current userspace, prohibit it since it won't work right. */ if (chans > 1) return -EOPNOTSUPP; if (hwsim_net_get_wmediumd(net)) return -EBUSY; hwsim_register_wmediumd(net, info->snd_portid); pr_debug("mac80211_hwsim: received a REGISTER, " "switching to wmediumd mode with pid %d\n", info->snd_portid); return 0; } /* ensures ciphers only include ciphers listed in 'hwsim_ciphers' array */ static bool hwsim_known_ciphers(const u32 *ciphers, int n_ciphers) { int i; for (i = 0; i < n_ciphers; i++) { int j; int found = 0; for (j = 0; j < ARRAY_SIZE(hwsim_ciphers); j++) { if (ciphers[i] == hwsim_ciphers[j]) { found = 1; break; } } if (!found) return false; } return true; } static int parse_ftm_capa(const struct nlattr *ftm_capa, struct cfg80211_pmsr_capabilities *out, struct genl_info *info) { struct nlattr *tb[NL80211_PMSR_FTM_CAPA_ATTR_MAX + 1]; int ret; ret = nla_parse_nested(tb, NL80211_PMSR_FTM_CAPA_ATTR_MAX, ftm_capa, hwsim_ftm_capa_policy, NULL); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, ftm_capa, "malformed FTM capability"); return -EINVAL; } out->ftm.supported = 1; if (tb[NL80211_PMSR_FTM_CAPA_ATTR_PREAMBLES]) out->ftm.preambles = nla_get_u32(tb[NL80211_PMSR_FTM_CAPA_ATTR_PREAMBLES]); if (tb[NL80211_PMSR_FTM_CAPA_ATTR_BANDWIDTHS]) out->ftm.bandwidths = nla_get_u32(tb[NL80211_PMSR_FTM_CAPA_ATTR_BANDWIDTHS]); if (tb[NL80211_PMSR_FTM_CAPA_ATTR_MAX_BURSTS_EXPONENT]) out->ftm.max_bursts_exponent = nla_get_u8(tb[NL80211_PMSR_FTM_CAPA_ATTR_MAX_BURSTS_EXPONENT]); if (tb[NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST]) out->ftm.max_ftms_per_burst = nla_get_u8(tb[NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST]); out->ftm.asap = !!tb[NL80211_PMSR_FTM_CAPA_ATTR_ASAP]; out->ftm.non_asap = !!tb[NL80211_PMSR_FTM_CAPA_ATTR_NON_ASAP]; out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_CAPA_ATTR_REQ_LCI]; out->ftm.request_civicloc = !!tb[NL80211_PMSR_FTM_CAPA_ATTR_REQ_CIVICLOC]; out->ftm.trigger_based = !!tb[NL80211_PMSR_FTM_CAPA_ATTR_TRIGGER_BASED]; out->ftm.non_trigger_based = !!tb[NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED]; return 0; } static int parse_pmsr_capa(const struct nlattr *pmsr_capa, struct cfg80211_pmsr_capabilities *out, struct genl_info *info) { struct nlattr *tb[NL80211_PMSR_ATTR_MAX + 1]; struct nlattr *nla; int size; int ret; ret = nla_parse_nested(tb, NL80211_PMSR_ATTR_MAX, pmsr_capa, hwsim_pmsr_capa_policy, NULL); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, pmsr_capa, "malformed PMSR capability"); return -EINVAL; } if (tb[NL80211_PMSR_ATTR_MAX_PEERS]) out->max_peers = nla_get_u32(tb[NL80211_PMSR_ATTR_MAX_PEERS]); out->report_ap_tsf = !!tb[NL80211_PMSR_ATTR_REPORT_AP_TSF]; out->randomize_mac_addr = !!tb[NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR]; if (!tb[NL80211_PMSR_ATTR_TYPE_CAPA]) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_ATTR_TYPE_CAPA], "malformed PMSR type"); return -EINVAL; } nla_for_each_nested(nla, tb[NL80211_PMSR_ATTR_TYPE_CAPA], size) { switch (nla_type(nla)) { case NL80211_PMSR_TYPE_FTM: parse_ftm_capa(nla, out, info); break; default: NL_SET_ERR_MSG_ATTR(info->extack, nla, "unsupported measurement type"); return -EINVAL; } } return 0; } static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) { struct hwsim_new_radio_params param = { 0 }; const char *hwname = NULL; int ret; param.reg_strict = info->attrs[HWSIM_ATTR_REG_STRICT_REG]; param.p2p_device = info->attrs[HWSIM_ATTR_SUPPORT_P2P_DEVICE]; param.channels = channels; param.destroy_on_close = info->attrs[HWSIM_ATTR_DESTROY_RADIO_ON_CLOSE]; if (info->attrs[HWSIM_ATTR_CHANNELS]) param.channels = nla_get_u32(info->attrs[HWSIM_ATTR_CHANNELS]); if (param.channels < 1) { GENL_SET_ERR_MSG(info, "must have at least one channel"); return -EINVAL; } if (info->attrs[HWSIM_ATTR_NO_VIF]) param.no_vif = true; if (info->attrs[HWSIM_ATTR_USE_CHANCTX]) param.use_chanctx = true; else param.use_chanctx = (param.channels > 1); if (info->attrs[HWSIM_ATTR_MULTI_RADIO]) param.multi_radio = true; if (info->attrs[HWSIM_ATTR_REG_HINT_ALPHA2]) param.reg_alpha2 = nla_data(info->attrs[HWSIM_ATTR_REG_HINT_ALPHA2]); if (info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]) { u32 idx = nla_get_u32(info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]); if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom)) return -EINVAL; idx = array_index_nospec(idx, ARRAY_SIZE(hwsim_world_regdom_custom)); param.regd = hwsim_world_regdom_custom[idx]; } if (info->attrs[HWSIM_ATTR_PERM_ADDR]) { if (!is_valid_ether_addr( nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]))) { GENL_SET_ERR_MSG(info,"MAC is no valid source addr"); NL_SET_BAD_ATTR(info->extack, info->attrs[HWSIM_ATTR_PERM_ADDR]); return -EINVAL; } param.perm_addr = nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]); } if (info->attrs[HWSIM_ATTR_IFTYPE_SUPPORT]) { param.iftypes = nla_get_u32(info->attrs[HWSIM_ATTR_IFTYPE_SUPPORT]); if (param.iftypes & ~HWSIM_IFTYPE_SUPPORT_MASK) { NL_SET_ERR_MSG_ATTR(info->extack, info->attrs[HWSIM_ATTR_IFTYPE_SUPPORT], "cannot support more iftypes than kernel"); return -EINVAL; } } else { param.iftypes = HWSIM_IFTYPE_SUPPORT_MASK; } /* ensure both flag and iftype support is honored */ if (param.p2p_device || param.iftypes & BIT(NL80211_IFTYPE_P2P_DEVICE)) { param.iftypes |= BIT(NL80211_IFTYPE_P2P_DEVICE); param.p2p_device = true; } if (info->attrs[HWSIM_ATTR_CIPHER_SUPPORT]) { u32 len = nla_len(info->attrs[HWSIM_ATTR_CIPHER_SUPPORT]); param.ciphers = nla_data(info->attrs[HWSIM_ATTR_CIPHER_SUPPORT]); if (len % sizeof(u32)) { NL_SET_ERR_MSG_ATTR(info->extack, info->attrs[HWSIM_ATTR_CIPHER_SUPPORT], "bad cipher list length"); return -EINVAL; } param.n_ciphers = len / sizeof(u32); if (param.n_ciphers > ARRAY_SIZE(hwsim_ciphers)) { NL_SET_ERR_MSG_ATTR(info->extack, info->attrs[HWSIM_ATTR_CIPHER_SUPPORT], "too many ciphers specified"); return -EINVAL; } if (!hwsim_known_ciphers(param.ciphers, param.n_ciphers)) { NL_SET_ERR_MSG_ATTR(info->extack, info->attrs[HWSIM_ATTR_CIPHER_SUPPORT], "unsupported ciphers specified"); return -EINVAL; } } param.mlo = info->attrs[HWSIM_ATTR_MLO_SUPPORT]; if (param.mlo || param.multi_radio) param.use_chanctx = true; if (info->attrs[HWSIM_ATTR_RADIO_NAME]) { hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]), nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), GFP_KERNEL); if (!hwname) return -ENOMEM; param.hwname = hwname; } if (info->attrs[HWSIM_ATTR_PMSR_SUPPORT]) { struct cfg80211_pmsr_capabilities *pmsr_capa; pmsr_capa = kmalloc(sizeof(*pmsr_capa), GFP_KERNEL); if (!pmsr_capa) { ret = -ENOMEM; goto out_free; } param.pmsr_capa = pmsr_capa; ret = parse_pmsr_capa(info->attrs[HWSIM_ATTR_PMSR_SUPPORT], pmsr_capa, info); if (ret) goto out_free; } ret = mac80211_hwsim_new_radio(info, ¶m); out_free: kfree(hwname); kfree(param.pmsr_capa); return ret; } static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) { struct mac80211_hwsim_data *data; s64 idx = -1; const char *hwname = NULL; if (info->attrs[HWSIM_ATTR_RADIO_ID]) { idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]); } else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) { hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]), nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), GFP_KERNEL); if (!hwname) return -ENOMEM; } else return -EINVAL; spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data, &hwsim_radios, list) { if (idx >= 0) { if (data->idx != idx) continue; } else { if (!hwname || strcmp(hwname, wiphy_name(data->hw->wiphy))) continue; } if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info))) continue; list_del(&data->list); rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), info); kfree(hwname); return 0; } spin_unlock_bh(&hwsim_radio_lock); kfree(hwname); return -ENODEV; } static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) { struct mac80211_hwsim_data *data; struct sk_buff *skb; int idx, res = -ENODEV; if (!info->attrs[HWSIM_ATTR_RADIO_ID]) return -EINVAL; idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data, &hwsim_radios, list) { if (data->idx != idx) continue; if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info))) continue; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) { res = -ENOMEM; goto out_err; } res = mac80211_hwsim_get_radio(skb, data, info->snd_portid, info->snd_seq, NULL, 0); if (res < 0) { nlmsg_free(skb); goto out_err; } res = genlmsg_reply(skb, info); break; } out_err: spin_unlock_bh(&hwsim_radio_lock); return res; } static int hwsim_dump_radio_nl(struct sk_buff *skb, struct netlink_callback *cb) { int last_idx = cb->args[0] - 1; struct mac80211_hwsim_data *data = NULL; int res = 0; void *hdr; spin_lock_bh(&hwsim_radio_lock); cb->seq = hwsim_radios_generation; if (last_idx >= hwsim_radio_idx-1) goto done; list_for_each_entry(data, &hwsim_radios, list) { if (data->idx <= last_idx) continue; if (!net_eq(wiphy_net(data->hw->wiphy), sock_net(skb->sk))) continue; res = mac80211_hwsim_get_radio(skb, data, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (res < 0) break; last_idx = data->idx; } cb->args[0] = last_idx + 1; /* list changed, but no new element sent, set interrupted flag */ if (skb->len == 0 && cb->prev_seq && cb->seq != cb->prev_seq) { hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &hwsim_genl_family, NLM_F_MULTI, HWSIM_CMD_GET_RADIO); if (hdr) { genl_dump_check_consistent(cb, hdr); genlmsg_end(skb, hdr); } else { res = -EMSGSIZE; } } done: spin_unlock_bh(&hwsim_radio_lock); return res ?: skb->len; } /* Generic Netlink operations array */ static const struct genl_small_ops hwsim_ops[] = { { .cmd = HWSIM_CMD_REGISTER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_register_received_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = HWSIM_CMD_FRAME, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_cloned_frame_received_nl, }, { .cmd = HWSIM_CMD_TX_INFO_FRAME, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_tx_info_frame_received_nl, }, { .cmd = HWSIM_CMD_NEW_RADIO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_new_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = HWSIM_CMD_DEL_RADIO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_del_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = HWSIM_CMD_GET_RADIO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_get_radio_nl, .dumpit = hwsim_dump_radio_nl, }, { .cmd = HWSIM_CMD_REPORT_PMSR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_pmsr_report_nl, }, }; static struct genl_family hwsim_genl_family __ro_after_init = { .name = "MAC80211_HWSIM", .version = 1, .maxattr = HWSIM_ATTR_MAX, .policy = hwsim_genl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = hwsim_ops, .n_small_ops = ARRAY_SIZE(hwsim_ops), .resv_start_op = HWSIM_CMD_REPORT_PMSR + 1, // match with __HWSIM_CMD_MAX .mcgrps = hwsim_mcgrps, .n_mcgrps = ARRAY_SIZE(hwsim_mcgrps), }; static void remove_user_radios(u32 portid) { struct mac80211_hwsim_data *entry, *tmp; LIST_HEAD(list); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry_safe(entry, tmp, &hwsim_radios, list) { if (entry->destroy_on_close && entry->portid == portid) { list_move(&entry->list, &list); rhashtable_remove_fast(&hwsim_radios_rht, &entry->rht, hwsim_rht_params); hwsim_radios_generation++; } } spin_unlock_bh(&hwsim_radio_lock); list_for_each_entry_safe(entry, tmp, &list, list) { list_del(&entry->list); mac80211_hwsim_del_radio(entry, wiphy_name(entry->hw->wiphy), NULL); } } static int mac80211_hwsim_netlink_notify(struct notifier_block *nb, unsigned long state, void *_notify) { struct netlink_notify *notify = _notify; if (state != NETLINK_URELEASE) return NOTIFY_DONE; remove_user_radios(notify->portid); if (notify->portid == hwsim_net_get_wmediumd(notify->net)) { printk(KERN_INFO "mac80211_hwsim: wmediumd released netlink" " socket, switching to perfect channel medium\n"); hwsim_register_wmediumd(notify->net, 0); } return NOTIFY_DONE; } static struct notifier_block hwsim_netlink_notifier = { .notifier_call = mac80211_hwsim_netlink_notify, }; static int __init hwsim_init_netlink(void) { int rc; printk(KERN_INFO "mac80211_hwsim: initializing netlink\n"); rc = genl_register_family(&hwsim_genl_family); if (rc) goto failure; rc = netlink_register_notifier(&hwsim_netlink_notifier); if (rc) { genl_unregister_family(&hwsim_genl_family); goto failure; } return 0; failure: pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); return -EINVAL; } static __net_init int hwsim_init_net(struct net *net) { return hwsim_net_set_netgroup(net); } static void __net_exit hwsim_exit_net(struct net *net) { struct mac80211_hwsim_data *data, *tmp; LIST_HEAD(list); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry_safe(data, tmp, &hwsim_radios, list) { if (!net_eq(wiphy_net(data->hw->wiphy), net)) continue; /* Radios created in init_net are returned to init_net. */ if (data->netgroup == hwsim_net_get_netgroup(&init_net)) continue; list_move(&data->list, &list); rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); hwsim_radios_generation++; } spin_unlock_bh(&hwsim_radio_lock); list_for_each_entry_safe(data, tmp, &list, list) { list_del(&data->list); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL); } ida_free(&hwsim_netgroup_ida, hwsim_net_get_netgroup(net)); } static struct pernet_operations hwsim_net_ops = { .init = hwsim_init_net, .exit = hwsim_exit_net, .id = &hwsim_net_id, .size = sizeof(struct hwsim_net), }; static void hwsim_exit_netlink(void) { /* unregister the notifier */ netlink_unregister_notifier(&hwsim_netlink_notifier); /* unregister the family */ genl_unregister_family(&hwsim_genl_family); } #if IS_REACHABLE(CONFIG_VIRTIO) static void hwsim_virtio_tx_done(struct virtqueue *vq) { unsigned int len; struct sk_buff *skb; unsigned long flags; spin_lock_irqsave(&hwsim_virtio_lock, flags); while ((skb = virtqueue_get_buf(vq, &len))) dev_kfree_skb_irq(skb); spin_unlock_irqrestore(&hwsim_virtio_lock, flags); } static int hwsim_virtio_handle_cmd(struct sk_buff *skb) { struct nlmsghdr *nlh; struct genlmsghdr *gnlh; struct nlattr *tb[HWSIM_ATTR_MAX + 1]; struct genl_info info = {}; int err; nlh = nlmsg_hdr(skb); gnlh = nlmsg_data(nlh); if (skb->len < nlh->nlmsg_len) return -EINVAL; err = genlmsg_parse(nlh, &hwsim_genl_family, tb, HWSIM_ATTR_MAX, hwsim_genl_policy, NULL); if (err) { pr_err_ratelimited("hwsim: genlmsg_parse returned %d\n", err); return err; } info.attrs = tb; switch (gnlh->cmd) { case HWSIM_CMD_FRAME: hwsim_cloned_frame_received_nl(skb, &info); break; case HWSIM_CMD_TX_INFO_FRAME: hwsim_tx_info_frame_received_nl(skb, &info); break; case HWSIM_CMD_REPORT_PMSR: hwsim_pmsr_report_nl(skb, &info); break; default: pr_err_ratelimited("hwsim: invalid cmd: %d\n", gnlh->cmd); return -EPROTO; } return 0; } static void hwsim_virtio_rx_work(struct work_struct *work) { struct virtqueue *vq; unsigned int len; struct sk_buff *skb; struct scatterlist sg[1]; int err; unsigned long flags; spin_lock_irqsave(&hwsim_virtio_lock, flags); if (!hwsim_virtio_enabled) goto out_unlock; skb = virtqueue_get_buf(hwsim_vqs[HWSIM_VQ_RX], &len); if (!skb) goto out_unlock; spin_unlock_irqrestore(&hwsim_virtio_lock, flags); skb->data = skb->head; skb_reset_tail_pointer(skb); skb_put(skb, len); hwsim_virtio_handle_cmd(skb); spin_lock_irqsave(&hwsim_virtio_lock, flags); if (!hwsim_virtio_enabled) { dev_kfree_skb_irq(skb); goto out_unlock; } vq = hwsim_vqs[HWSIM_VQ_RX]; sg_init_one(sg, skb->head, skb_end_offset(skb)); err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_ATOMIC); if (WARN(err, "virtqueue_add_inbuf returned %d\n", err)) dev_kfree_skb_irq(skb); else virtqueue_kick(vq); schedule_work(&hwsim_virtio_rx); out_unlock: spin_unlock_irqrestore(&hwsim_virtio_lock, flags); } static void hwsim_virtio_rx_done(struct virtqueue *vq) { schedule_work(&hwsim_virtio_rx); } static int init_vqs(struct virtio_device *vdev) { struct virtqueue_info vqs_info[HWSIM_NUM_VQS] = { [HWSIM_VQ_TX] = { "tx", hwsim_virtio_tx_done }, [HWSIM_VQ_RX] = { "rx", hwsim_virtio_rx_done }, }; return virtio_find_vqs(vdev, HWSIM_NUM_VQS, hwsim_vqs, vqs_info, NULL); } static int fill_vq(struct virtqueue *vq) { int i, err; struct sk_buff *skb; struct scatterlist sg[1]; for (i = 0; i < virtqueue_get_vring_size(vq); i++) { skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; sg_init_one(sg, skb->head, skb_end_offset(skb)); err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL); if (err) { nlmsg_free(skb); return err; } } virtqueue_kick(vq); return 0; } static void remove_vqs(struct virtio_device *vdev) { int i; virtio_reset_device(vdev); for (i = 0; i < ARRAY_SIZE(hwsim_vqs); i++) { struct virtqueue *vq = hwsim_vqs[i]; struct sk_buff *skb; while ((skb = virtqueue_detach_unused_buf(vq))) nlmsg_free(skb); } vdev->config->del_vqs(vdev); } static int hwsim_virtio_probe(struct virtio_device *vdev) { int err; unsigned long flags; spin_lock_irqsave(&hwsim_virtio_lock, flags); if (hwsim_virtio_enabled) { spin_unlock_irqrestore(&hwsim_virtio_lock, flags); return -EEXIST; } spin_unlock_irqrestore(&hwsim_virtio_lock, flags); err = init_vqs(vdev); if (err) return err; virtio_device_ready(vdev); err = fill_vq(hwsim_vqs[HWSIM_VQ_RX]); if (err) goto out_remove; spin_lock_irqsave(&hwsim_virtio_lock, flags); hwsim_virtio_enabled = true; spin_unlock_irqrestore(&hwsim_virtio_lock, flags); schedule_work(&hwsim_virtio_rx); return 0; out_remove: remove_vqs(vdev); return err; } static void hwsim_virtio_remove(struct virtio_device *vdev) { hwsim_virtio_enabled = false; cancel_work_sync(&hwsim_virtio_rx); remove_vqs(vdev); } /* MAC80211_HWSIM virtio device id table */ static const struct virtio_device_id id_table[] = { { VIRTIO_ID_MAC80211_HWSIM, VIRTIO_DEV_ANY_ID }, { 0 } }; MODULE_DEVICE_TABLE(virtio, id_table); static struct virtio_driver virtio_hwsim = { .driver.name = KBUILD_MODNAME, .id_table = id_table, .probe = hwsim_virtio_probe, .remove = hwsim_virtio_remove, }; static int hwsim_register_virtio_driver(void) { return register_virtio_driver(&virtio_hwsim); } static void hwsim_unregister_virtio_driver(void) { unregister_virtio_driver(&virtio_hwsim); } #else static inline int hwsim_register_virtio_driver(void) { return 0; } static inline void hwsim_unregister_virtio_driver(void) { } #endif static int __init init_mac80211_hwsim(void) { int i, err; if (radios < 0 || radios > 100) return -EINVAL; if (channels < 1) return -EINVAL; err = rhashtable_init(&hwsim_radios_rht, &hwsim_rht_params); if (err) return err; err = register_pernet_device(&hwsim_net_ops); if (err) goto out_free_rht; err = platform_driver_register(&mac80211_hwsim_driver); if (err) goto out_unregister_pernet; err = hwsim_init_netlink(); if (err) goto out_unregister_driver; err = hwsim_register_virtio_driver(); if (err) goto out_exit_netlink; hwsim_class = class_create("mac80211_hwsim"); if (IS_ERR(hwsim_class)) { err = PTR_ERR(hwsim_class); goto out_exit_virtio; } hwsim_init_s1g_channels(hwsim_channels_s1g); for (i = 0; i < radios; i++) { struct hwsim_new_radio_params param = { 0 }; param.channels = channels; switch (regtest) { case HWSIM_REGTEST_DIFF_COUNTRY: if (i < ARRAY_SIZE(hwsim_alpha2s)) param.reg_alpha2 = hwsim_alpha2s[i]; break; case HWSIM_REGTEST_DRIVER_REG_FOLLOW: if (!i) param.reg_alpha2 = hwsim_alpha2s[0]; break; case HWSIM_REGTEST_STRICT_ALL: param.reg_strict = true; fallthrough; case HWSIM_REGTEST_DRIVER_REG_ALL: param.reg_alpha2 = hwsim_alpha2s[0]; break; case HWSIM_REGTEST_WORLD_ROAM: if (i == 0) param.regd = &hwsim_world_regdom_custom_01; break; case HWSIM_REGTEST_CUSTOM_WORLD: param.regd = &hwsim_world_regdom_custom_03; break; case HWSIM_REGTEST_CUSTOM_WORLD_2: if (i == 0) param.regd = &hwsim_world_regdom_custom_03; else if (i == 1) param.regd = &hwsim_world_regdom_custom_02; break; case HWSIM_REGTEST_STRICT_FOLLOW: if (i == 0) { param.reg_strict = true; param.reg_alpha2 = hwsim_alpha2s[0]; } break; case HWSIM_REGTEST_STRICT_AND_DRIVER_REG: if (i == 0) { param.reg_strict = true; param.reg_alpha2 = hwsim_alpha2s[0]; } else if (i == 1) { param.reg_alpha2 = hwsim_alpha2s[1]; } break; case HWSIM_REGTEST_ALL: switch (i) { case 0: param.regd = &hwsim_world_regdom_custom_01; break; case 1: param.regd = &hwsim_world_regdom_custom_02; break; case 2: param.reg_alpha2 = hwsim_alpha2s[0]; break; case 3: param.reg_alpha2 = hwsim_alpha2s[1]; break; case 4: param.reg_strict = true; param.reg_alpha2 = hwsim_alpha2s[2]; break; } break; default: break; } param.p2p_device = support_p2p_device; param.mlo = mlo; param.multi_radio = multi_radio; param.use_chanctx = channels > 1 || mlo || multi_radio; param.iftypes = HWSIM_IFTYPE_SUPPORT_MASK; if (param.p2p_device) param.iftypes |= BIT(NL80211_IFTYPE_P2P_DEVICE); err = mac80211_hwsim_new_radio(NULL, ¶m); if (err < 0) goto out_free_radios; } hwsim_mon = alloc_netdev(0, "hwsim%d", NET_NAME_UNKNOWN, hwsim_mon_setup); if (hwsim_mon == NULL) { err = -ENOMEM; goto out_free_radios; } rtnl_lock(); err = dev_alloc_name(hwsim_mon, hwsim_mon->name); if (err < 0) { rtnl_unlock(); goto out_free_mon; } err = register_netdevice(hwsim_mon); if (err < 0) { rtnl_unlock(); goto out_free_mon; } rtnl_unlock(); return 0; out_free_mon: free_netdev(hwsim_mon); out_free_radios: mac80211_hwsim_free(); out_exit_virtio: hwsim_unregister_virtio_driver(); out_exit_netlink: hwsim_exit_netlink(); out_unregister_driver: platform_driver_unregister(&mac80211_hwsim_driver); out_unregister_pernet: unregister_pernet_device(&hwsim_net_ops); out_free_rht: rhashtable_destroy(&hwsim_radios_rht); return err; } module_init(init_mac80211_hwsim); static void __exit exit_mac80211_hwsim(void) { pr_debug("mac80211_hwsim: unregister radios\n"); hwsim_unregister_virtio_driver(); hwsim_exit_netlink(); mac80211_hwsim_free(); rhashtable_destroy(&hwsim_radios_rht); unregister_netdev(hwsim_mon); platform_driver_unregister(&mac80211_hwsim_driver); unregister_pernet_device(&hwsim_net_ops); } module_exit(exit_mac80211_hwsim); |
| 7 6 6 1368 6 6 6 6 6 6 6 4819 6 6 1359 1 1367 1 6 6 1365 6 7 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 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 | /* 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. * * Definitions for the AF_INET socket handler. * * Version: @(#)sock.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche <flla@stud.uni-sb.de> * * Fixes: * Alan Cox : Volatiles in skbuff pointers. See * skbuff comments. May be overdone, * better to prove they can be removed * than the reverse. * Alan Cox : Added a zapped field for tcp to note * a socket is reset and must stay shut up * Alan Cox : New fields for options * Pauline Middelink : identd support * Alan Cox : Eliminate low level recv/recvfrom * David S. Miller : New socket lookup architecture. * Steve Whitehouse: Default routines for sock_ops * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made * protinfo be just a void pointer, as the * protocol specific parts were moved to * respective headers and ipv4/v6, etc now * use private slabcaches for its socks * Pedro Hortas : New flags field for socket options */ #ifndef _SOCK_H #define _SOCK_H #include <linux/hardirq.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/timer.h> #include <linux/cache.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* struct sk_buff */ #include <linux/mm.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/static_key.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> #include <linux/rbtree.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> #include <linux/indirect_call_wrapper.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/llist.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> #include <uapi/linux/socket.h> /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of * the other protocols. */ /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. */ typedef struct { spinlock_t slock; int owned; wait_queue_head_t wq; /* * We express the mutex-alike socket_lock semantics * to the lock validator by explicitly managing * the slock as a lock variant (in addition to * the slock itself): */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } socket_lock_t; struct sock; struct proto; struct net; typedef __u32 __bitwise __portpair; typedef __u64 __bitwise __addrpair; /** * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @skc_v6_daddr: IPV6 destination address * @skc_v6_rcv_saddr: IPV6 source address * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_listener: connection request listener socket (aka rsk_listener) * [union with @skc_flags] * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) * [union with @skc_incoming_cpu] * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { union { __addrpair skc_addrpair; struct { __be32 skc_daddr; __be32 skc_rcv_saddr; }; }; union { unsigned int skc_hash; __u16 skc_u16hashes[2]; }; /* skc_dport && skc_num must be grouped as well */ union { __portpair skc_portpair; struct { __be16 skc_dport; __u16 skc_num; }; }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse:4; unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; struct hlist_node skc_portaddr_node; }; struct proto *skc_prot; possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; struct in6_addr skc_v6_rcv_saddr; #endif atomic64_t skc_cookie; /* following fields are padding to force * offset(struct sock, sk_refcnt) == 128 on 64bit arches * assuming IPV6 is enabled. We use this padding differently * for different kind of 'sockets' */ union { unsigned long skc_flags; struct sock *skc_listener; /* request_sock */ struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() */ /* private: */ int skc_dontcopy_begin[0]; /* public: */ union { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING unsigned short skc_rx_queue_mapping; #endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; refcount_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; union { u32 skc_rxhash; u32 skc_window_clamp; u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; struct bpf_local_storage; struct sk_filter; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_rx_dst_ifindex: ifindex for @sk_rx_dst * @sk_rx_dst_cookie: cookie for @sk_rx_dst * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags * @sk_write_queue: Packet sending queue * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward * @sk_reserved_mem: space reserved and non-reclaimable for the socket * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_gso_disabled: if set, NETIF_F_GSO_MASK is forbidden. * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, * IPV6_ADDRFORM for instance) * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' * @sk_drops: raw/udp drops counter * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner * @sk_prefer_busy_poll: prefer busypolling over softirq processing * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags * @sk_bpf_cb_flags: used in bpf_setsockopt() * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. * Sockets that can be used under memory reclaim should * set this to false. * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_disconnects: number of disconnect operations performed on this sock * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @sk_scm_recv_flags: all flags used by scm_recv() * @sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS * @sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY * @sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD * @sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS * @sk_scm_unused: unused flags for scm_recv() * @ns_tracker: tracker for netns reference * @sk_user_frags: xarray of pages the user is holding a reference on. * @sk_owner: reference to the real owner of the socket that calls * sock_lock_init_class_and_name(). */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; #define sk_node __sk_common.skc_node #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_portpair __sk_common.skc_portpair #define sk_num __sk_common.skc_num #define sk_dport __sk_common.skc_dport #define sk_addrpair __sk_common.skc_addrpair #define sk_daddr __sk_common.skc_daddr #define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash __cacheline_group_begin(sock_write_rx); atomic_t sk_drops; __s32 sk_peek_off; struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. * Note : rmem_alloc is in this structure to fill a hole * on 64bit arches, not because its logically part of * backlog. */ struct { atomic_t rmem_alloc; int len; struct sk_buff *head; struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc __cacheline_group_end(sock_write_rx); __cacheline_group_begin(sock_read_rx); /* early demux fields */ struct dst_entry __rcu *sk_rx_dst; int sk_rx_dst_ifindex; u32 sk_rx_dst_cookie; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; unsigned int sk_napi_id; u16 sk_busy_poll_budget; u8 sk_prefer_busy_poll; #endif u8 sk_userlocks; int sk_rcvbuf; struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; /* private: */ struct socket_wq *sk_wq_raw; /* public: */ }; void (*sk_data_ready)(struct sock *sk); long sk_rcvtimeo; int sk_rcvlowat; __cacheline_group_end(sock_read_rx); __cacheline_group_begin(sock_read_rxtx); int sk_err; struct socket *sk_socket; struct mem_cgroup *sk_memcg; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif __cacheline_group_end(sock_read_rxtx); __cacheline_group_begin(sock_write_rxtx); socket_lock_t sk_lock; u32 sk_reserved_mem; int sk_forward_alloc; u32 sk_tsflags; __cacheline_group_end(sock_write_rxtx); __cacheline_group_begin(sock_write_tx); int sk_write_pending; atomic_t sk_omem_alloc; int sk_sndbuf; int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; union { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ struct page_frag sk_frag; struct timer_list sk_timer; unsigned long sk_pacing_rate; /* bytes per second */ atomic_t sk_zckey; atomic_t sk_tskey; __cacheline_group_end(sock_write_tx); __cacheline_group_begin(sock_read_tx); unsigned long sk_max_pacing_rate; long sk_sndtimeo; u32 sk_priority; u32 sk_mark; struct dst_entry __rcu *sk_dst_cache; netdev_features_t sk_route_caps; #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); #endif u16 sk_gso_type; u16 sk_gso_max_segs; unsigned int sk_gso_max_size; gfp_t sk_allocation; u32 sk_txhash; u8 sk_pacing_shift; bool sk_use_task_frag; __cacheline_group_end(sock_read_tx); /* * Because of non atomicity rules, all * changes are protected by socket lock. */ u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1; u8 sk_shutdown; u16 sk_type; u16 sk_protocol; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; spinlock_t sk_peer_lock; int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif int sk_disconnects; union { u8 sk_txrehash; u8 sk_scm_recv_flags; struct { u8 sk_scm_credentials : 1, sk_scm_security : 1, sk_scm_pidfd : 1, sk_scm_rights : 1, sk_scm_unused : 4; }; }; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; #define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG)) u8 sk_bpf_cb_flags; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; void (*sk_state_change)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; struct xarray sk_user_frags; #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) struct module *sk_owner; #endif }; struct sock_bh_locked { struct sock *sock; local_lock_t bh_lock; }; enum sk_pacing { SK_PACING_NONE = 0, SK_PACING_NEEDED = 1, SK_PACING_FQ = 2, }; /* flag bits in sk_user_data * * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might * not be suitable for copying when cloning the socket. For instance, * it can point to a reference counted object. sk_user_data bottom * bit is set if pointer must not be copied. * * - SK_USER_DATA_BPF: Mark whether sk_user_data field is * managed/owned by a BPF reuseport array. This bit should be set * when sk_user_data's sk is added to the bpf's reuseport_array. * * - SK_USER_DATA_PSOCK: Mark whether pointer stored in * sk_user_data points to psock type. This bit should be set * when sk_user_data is assigned to a psock object. */ #define SK_USER_DATA_NOCOPY 1UL #define SK_USER_DATA_BPF 2UL #define SK_USER_DATA_PSOCK 4UL #define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\ SK_USER_DATA_PSOCK) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied * @sk: socket */ static inline bool sk_user_data_is_nocopy(const struct sock *sk) { return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); } #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) /** * __locked_read_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits * * The caller must be holding sk->sk_callback_lock. */ static inline void * __locked_read_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference_check(__sk_user_data(sk), lockdep_is_held(&sk->sk_callback_lock)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } /** * __rcu_dereference_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits */ static inline void * __rcu_dereference_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } #define rcu_dereference_sk_user_data(sk) \ __rcu_dereference_sk_user_data_with_flags(sk, 0) #define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ ({ \ uintptr_t __tmp1 = (uintptr_t)(ptr), \ __tmp2 = (uintptr_t)(flags); \ WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \ WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), \ __tmp1 | __tmp2); \ }) #define rcu_assign_sk_user_data(sk, ptr) \ __rcu_assign_sk_user_data_with_flags(sk, ptr, 0) static inline struct net *sock_net(const struct sock *sk) { return read_pnet(&sk->sk_net); } static inline void sock_net_set(struct sock *sk, struct net *net) { write_pnet(&sk->sk_net, net); } /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE * on a socket means that the socket will reuse everybody else's port * without looking at the other's sk_reuse value. */ #define SK_NO_REUSE 0 #define SK_CAN_REUSE 1 #define SK_FORCE_REUSE 2 int sk_set_peek_off(struct sock *sk, int val); static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); } return 0; } static inline void sk_peek_offset_bwd(struct sock *sk, int val) { s32 off = READ_ONCE(sk->sk_peek_off); if (unlikely(off >= 0)) { off = max_t(s32, off - val, 0); WRITE_ONCE(sk->sk_peek_off, off); } } static inline void sk_peek_offset_fwd(struct sock *sk, int val) { sk_peek_offset_bwd(sk, -val); } /* * Hashed lists helper routines */ static inline struct sock *sk_entry(const struct hlist_node *node) { return hlist_entry(node, struct sock, sk_node); } static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); } static inline struct sock *sk_head(const struct hlist_head *head) { return hlist_empty(head) ? NULL : __sk_head(head); } static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); } static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); } static inline struct sock *sk_next(const struct sock *sk) { return hlist_entry_safe(sk->sk_node.next, struct sock, sk_node); } static inline struct sock *sk_nulls_next(const struct sock *sk) { return (!is_a_nulls(sk->sk_nulls_node.next)) ? hlist_nulls_entry(sk->sk_nulls_node.next, struct sock, sk_nulls_node) : NULL; } static inline bool sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } static inline bool sk_hashed(const struct sock *sk) { return !sk_unhashed(sk); } static inline void sk_node_init(struct hlist_node *node) { node->pprev = NULL; } static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); } /* NB: equivalent to hlist_del_init_rcu */ static inline bool __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { __sk_del_node(sk); sk_node_init(&sk->sk_node); return true; } return false; } /* Grab socket reference count. This operation is valid only when sk is ALREADY grabbed f.e. it is found in hash table or a list and the lookup is made under lock preventing hash table modifications. */ static __always_inline void sock_hold(struct sock *sk) { refcount_inc(&sk->sk_refcnt); } /* Ungrab socket in the context, which assumes that socket refcnt cannot hit zero, f.e. it is true in context of any socketcall. */ static __always_inline void __sock_put(struct sock *sk) { refcount_dec(&sk->sk_refcnt); } static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk) { if (sk_hashed(sk)) { hlist_nulls_del_init_rcu(&sk->sk_nulls_node); return true; } return false; } static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); } static inline void sk_add_node(struct sock *sk, struct hlist_head *list) { sock_hold(sk); __sk_add_node(sk, list); } static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&sk->sk_node, list); else hlist_add_head_rcu(&sk->sk_node, list); } static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); hlist_add_tail_rcu(&sk->sk_node, list); } static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); __sk_nulls_add_node_rcu(sk, list); } static inline void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); } static inline void sk_add_bind_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_bind_node, list); } #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) #define sk_for_each_from(__sk) \ hlist_for_each_entry_from(__sk, sk_node) #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) #define sk_for_each_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) #define sk_for_each_bound_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @offset: offset of hlist_node within the struct. * */ #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from * userspace. */ return sk->sk_socket->file->f_cred->user_ns; } /* Sock flags */ enum sock_flags { SOCK_DEAD, SOCK_DONE, SOCK_URGINLINE, SOCK_KEEPOPEN, SOCK_LINGER, SOCK_DESTROY, SOCK_BROADCAST, SOCK_TIMESTAMP, SOCK_ZAPPED, SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG, /* %SO_DEBUG setting */ SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ SOCK_RXQ_OVFL, SOCK_ZEROCOPY, /* buffers from userspace */ SOCK_WIFI_STATUS, /* push wifi status to userspace */ SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS. * Will use last 4 bytes of packet sent from * user-space instead. */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */ SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) /* * The highest bit of sk_tsflags is reserved for kernel-internal * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that * SOF_TIMESTAMPING* values do not reach this reserved area */ #define SOCKCM_FLAG_TS_OPT_ID BIT(31) static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } static inline void sock_set_flag(struct sock *sk, enum sock_flags flag) { __set_bit(flag, &sk->sk_flags); } static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) { __clear_bit(flag, &sk->sk_flags); } static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, int valbool) { if (valbool) sock_set_flag(sk, bit); else sock_reset_flag(sk, bit); } static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); } #ifdef CONFIG_NET DECLARE_STATIC_KEY_FALSE(memalloc_socks_key); static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) { return 0; } static inline void __receive_sock(struct file *file) { } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) { return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1); } static inline void sk_acceptq_added(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } /* Note: If you think the test should be: * return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.") */ static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); } /* * Compute minimal free write space needed to queue new packets. */ static inline int sk_stream_min_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); } static inline void sk_wmem_queued_add(struct sock *sk, int val) { WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } static inline void sk_forward_alloc_add(struct sock *sk, int val) { /* Paired with lockless reads of sk->sk_forward_alloc */ WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val); } void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ skb_dst_force(skb); if (!sk->sk_backlog.tail) WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } /* * Take into account size of receive queue and backlog queue * Do not take into account this skb truesize, * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); return qsize > limit; } /* The per-socket spinlock must be held here. */ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, unsigned int limit) { if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) return -ENOMEM; __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; } int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)); static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); return INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) { int cpu = raw_smp_processor_id(); if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu)) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in sock_rps_record_flow(). */ if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS /* Paired with READ_ONCE() in sock_rps_record_flow() */ WRITE_ONCE(sk->sk_rxhash, 0); #endif } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc, __dis = __sk->sk_disconnects; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ *(__timeo) = wait_woken(__wait, \ TASK_INTERRUPTIBLE, \ *(__timeo)); \ } \ sched_annotate_sleep(); \ lock_sock(__sk); \ __rc = __dis == __sk->sk_disconnects ? __condition : -EPIPE; \ __rc; \ }) int sk_stream_wait_connect(struct sock *sk, long *timeo_p); int sk_stream_wait_memory(struct sock *sk, long *timeo_p); void sk_stream_wait_close(struct sock *sk, long timeo_p); int sk_stream_error(struct sock *sk, int flags, int err); void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); void __sk_flush_backlog(struct sock *sk); static inline bool sk_flush_backlog(struct sock *sk) { if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { __sk_flush_backlog(sk); return true; } return false; } int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; struct inet_hashinfo; struct raw_hashinfo; struct smc_hashinfo; struct module; struct sk_psock; /* * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes * un-modified. Special care is taken when initializing object to zero. */ static inline void sk_prot_clear_nulls(struct sock *sk, int size) { if (offsetof(struct sock, sk_node.next) != 0) memset(sk, 0, offsetof(struct sock, sk_node.next)); memset(&sk->sk_node.pprev, 0, size - offsetof(struct sock, sk_node.pprev)); } struct proto_accept_arg { int flags; int err; int is_empty; bool kern; }; /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); struct sock * (*accept)(struct sock *sk, struct proto_accept_arg *arg); int (*ioctl)(struct sock *sk, int cmd, int *karg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); bool (*bpf_bypass_getsockopt)(int level, int optname); void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); #endif /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; u32 sysctl_wmem_offset; u32 sysctl_rmem_offset; int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; unsigned int ipv6_pinfo_offset; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; struct udp_table *udp_table; struct raw_hashinfo *raw_hash; struct smc_hashinfo *smc_hash; } h; struct module *owner; char name[32]; struct list_head node; int (*diag_destroy)(struct sock *sk, int err); } __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); int sock_load_diag_module(int family, int protocol); INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? INDIRECT_CALL_INET_1(sk->sk_prot->stream_memory_free, tcp_stream_memory_free, sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) { return __sk_stream_memory_free(sk, 0); } static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && __sk_stream_memory_free(sk, wake); } static inline bool sk_stream_is_writeable(const struct sock *sk) { return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, struct cgroup *ancestor) { #ifdef CONFIG_SOCK_CGROUP_DATA return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), ancestor); #else return -ENOTSUPP; #endif } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 static inline void sk_sockets_allocated_dec(struct sock *sk) { percpu_counter_add_batch(sk->sk_prot->sockets_allocated, -1, SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline void sk_sockets_allocated_inc(struct sock *sk) { percpu_counter_add_batch(sk->sk_prot->sockets_allocated, 1, SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int proto_sockets_allocated_sum_positive(struct proto *prot) { return percpu_counter_sum_positive(prot->sockets_allocated); } #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { int all; int val[PROTO_INUSE_NR]; }; static inline void sock_prot_inuse_add(const struct net *net, const struct proto *prot, int val) { this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } static inline void sock_inuse_add(const struct net *net, int val) { this_cpu_add(net->core.prot_inuse->all, val); } int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(const struct net *net, const struct proto *prot, int val) { } static inline void sock_inuse_add(const struct net *net, int val) { } #endif /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); return sk->sk_prot->hash(sk); } /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) /* Sockets 0-1023 can't be bound to unless you are superuser */ #define PROT_SOCK 1024 #define SHUTDOWN_MASK 3 #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 struct socket_alloc { struct socket socket; struct inode vfs_inode; }; static inline struct socket *SOCKET_I(struct inode *inode) { return &container_of(inode, struct socket_alloc, vfs_inode)->socket; } static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } /* * Functions for memory accounting */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 /* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { return READ_ONCE(sk->sk_prot->sysctl_mem[index]); } static inline int sk_mem_pages(int amt) { return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) { /* return true if protocol supports memory accounting */ return !!sk->sk_prot->memory_allocated; } static inline bool sk_wmem_schedule(struct sock *sk, int size) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool __sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || pfmemalloc; } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) { int unused_mem; if (likely(!sk->sk_reserved_mem)) return 0; unused_mem = sk->sk_reserved_mem - sk->sk_wmem_queued - atomic_read(&sk->sk_rmem_alloc); return unused_mem > 0 ? unused_mem : 0; } static inline void sk_mem_reclaim(struct sock *sk) { int reclaimable; if (!sk_has_account(sk)) return; reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } static inline void sk_mem_reclaim_final(struct sock *sk) { sk->sk_reserved_mem = 0; sk_mem_reclaim(sk); } static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk_forward_alloc_add(sk, -size); } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk_forward_alloc_add(sk, size); sk_mem_reclaim(sk); } #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) static inline void sk_owner_set(struct sock *sk, struct module *owner) { __module_get(owner); sk->sk_owner = owner; } static inline void sk_owner_clear(struct sock *sk) { sk->sk_owner = NULL; } static inline void sk_owner_put(struct sock *sk) { module_put(sk->sk_owner); } #else static inline void sk_owner_set(struct sock *sk, struct module *owner) { } static inline void sk_owner_clear(struct sock *sk) { } static inline void sk_owner_put(struct sock *sk) { } #endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. * * Mark both the sk_lock and the sk_lock.slock as a * per-address-family lock class. */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) static inline bool lockdep_sock_is_held(const struct sock *sk) { return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } void lock_sock_nested(struct sock *sk, int subclass); static inline void lock_sock(struct sock *sk) { lock_sock_nested(sk, 0); } void __lock_sock(struct sock *sk); void __release_sock(struct sock *sk); void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock)) #define bh_lock_sock_nested(__sk) \ spin_lock_nested(&((__sk)->sk_lock.slock), \ SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); /** * lock_sock_fast - fast version of lock_sock * @sk: socket * * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled * * return true if slow path is taken: * * sk_lock.slock unlocked, owned = 1, BH enabled */ static inline bool lock_sock_fast(struct sock *sk) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); return __lock_sock_fast(sk); } /* fast socket lock variant for caller already holding a [different] socket lock */ static inline bool lock_sock_fast_nested(struct sock *sk) { mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); return __lock_sock_fast(sk); } /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket * @slow: slow mode * * fast unlock socket for user context. * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) __releases(&sk->sk_lock.slock) { if (slow) { release_sock(sk); __release(&sk->sk_lock.slock); } else { mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } void sockopt_lock_sock(struct sock *sk); void sockopt_release_sock(struct sock *sk); bool sockopt_ns_capable(struct user_namespace *ns, int cap); bool sockopt_capable(int cap); /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming * packets, so that we won't get any new data or any * packets that change the state of the socket. * * While locked, BH processing will add new packets to * the backlog queue. This queue is processed by the * owner of the socket lock right before it is released. * * Since ~2.3.5 it is also exclusive sleep lock serializing * accesses from user process context. */ static inline void sock_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks); #endif } static inline void sock_not_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); #endif } static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); return sk->sk_lock.owned; } static inline bool sock_owned_by_user_nocheck(const struct sock *sk) { return sk->sk_lock.owned; } static inline void sock_release_ownership(struct sock *sk) { DEBUG_NET_WARN_ON_ONCE(!sock_owned_by_user_nocheck(sk)); sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; return !sock_owned_by_user_nocheck(sk) && !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); void sk_net_refcnt_upgrade(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); if (refcount_inc_not_zero(&sk->sk_refcnt)) { skb->sk = sk; skb->destructor = sock_edemux; } } #else #define sock_edemux sock_efree #endif int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen); int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen); int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void *sock_kmemdup(struct sock *sk, const void *src, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); static inline void sock_replace_proto(struct sock *sk, struct proto *proto) { if (sk->sk_socket) clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); WRITE_ONCE(sk->sk_prot, proto); } struct sockcm_cookie { u64 transmit_time; u32 mark; u32 tsflags; u32 ts_opt_id; u32 priority; u32 dmabuf_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { .mark = READ_ONCE(sk->sk_mark), .tsflags = READ_ONCE(sk->sk_tsflags), .priority = READ_ONCE(sk->sk_priority), }; } int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *); int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); /* * Functions to fill in entries in struct proto_ops when a protocol * uses the inet style. */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); void sk_common_release(struct sock *sk); /* * Default socket callbacks and setup code */ /* Initialise core socket variables using an explicit uid. */ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); /* Initialise core socket variables. * Assumes struct socket *sock is embedded in a struct socket_alloc. */ void sock_init_data(struct socket *sock, struct sock *sk); /* * Socket reference counting postulates. * * * Each user of socket SHOULD hold a reference count. * * Each access point to socket (an hash table bucket, reference from a list, * running timer, skb in flight MUST hold a reference count. * * When reference count hits 0, it means it will never increase back. * * When reference count hits 0, it means that no references from * outside exist to this socket and current process on current CPU * is last user and may/should destroy this socket. * * sk_free is called from any context: process, BH, IRQ. When * it is called, socket has no references from outside -> sk_free * may release descendant resources allocated by the socket, but * to the time when it is called, socket is NOT referenced by any * hash tables, lists etc. * * Packets, delivered from outside (from network or from another process) * and enqueued on receive/error queues SHOULD NOT grab reference count, * when they sit in queue. Otherwise, packets will leak to hole, when * socket is looked up by one cpu and unhasing is made by another CPU. * It is true for udp/raw, netlink (leak to receive and error queues), tcp * (leak to backlog). Packet socket does all the processing inside * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets * use separate SMP lock, so that they are prone too. */ /* Ungrab socket and destroy it, if it was the last reference. */ static inline void sock_put(struct sock *sk) { if (refcount_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } static inline int sk_tx_queue_get(const struct sock *sk) { if (sk) { /* Paired with WRITE_ONCE() in sk_tx_queue_clear() * and sk_tx_queue_set(). */ int val = READ_ONCE(sk->sk_tx_queue_mapping); if (val != NO_QUEUE_MAPPING) return val; } return -1; } static inline void __sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb, bool force_set) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); if (force_set || unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) { __sk_rx_queue_set(sk, skb, true); } static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb) { __sk_rx_queue_set(sk, skb, false); } static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING WRITE_ONCE(sk->sk_rx_queue_mapping, NO_QUEUE_MAPPING); #endif } static inline int sk_rx_queue_get(const struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (sk) { int res = READ_ONCE(sk->sk_rx_queue_mapping); if (res != NO_QUEUE_MAPPING) return res; } #endif return -1; } static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk->sk_socket = sock; } static inline wait_queue_head_t *sk_sleep(struct sock *sk) { BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, * we do not release it in this function, because protocol * probably wants some additional cleanups or even continuing * to work with this socket (TCP). */ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } kuid_t sock_i_uid(struct sock *sk); unsigned long __sock_i_ino(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); } static inline u32 net_tx_rndhash(void) { u32 v = get_random_u32(); return v ?: 1; } static inline void sk_set_txhash(struct sock *sk) { /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } static inline bool sk_rethink_txhash(struct sock *sk) { if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } return false; } static inline struct dst_entry * __sk_dst_get(const struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, lockdep_sock_is_held(sk)); } static inline struct dst_entry * sk_dst_get(const struct sock *sk) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); if (dst && !rcuref_get(&dst->__rcuref)) dst = NULL; rcu_read_unlock(); return dst; } static inline void __dst_negative_advice(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->ops->negative_advice) dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) { sk_rethink_txhash(sk); __dst_negative_advice(sk); } static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst))); dst_release(old_dst); } static inline void __sk_dst_reset(struct sock *sk) { __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { sk_dst_set(sk, NULL); } struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { if (!READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); neigh_confirm(n); } } bool sk_mc_loop(const struct sock *sk); static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst); static inline void sk_gso_disable(struct sock *sk) { sk->sk_gso_disabled = 1; sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; } static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, int copy) { int err, offset = skb->len; err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy), copy, offset); if (err) __skb_trim(skb, offset); return err; } static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from, struct sk_buff *skb, struct page *page, int off, int copy) { int err; err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off, copy, skb->len); if (err) return err; skb_len_add(skb, copy); sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } /** * sk_wmem_alloc_get - returns write allocations * @sk: socket * * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) - 1; } /** * sk_rmem_alloc_get - returns read allocations * @sk: socket * * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { return atomic_read(&sk->sk_rmem_alloc); } /** * sk_has_allocations - check if allocations are outstanding * @sk: socket * * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); } /** * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths:: * * CPU1 CPU2 * sys_select receive packet * ... ... * __add_wait_queue update tp->rcv_nxt * ... ... * tp->rcv_nxt check sock_def_readable * ... { * schedule rcu_read_lock(); * wq = rcu_dereference(sk->sk_wq); * if (wq && waitqueue_active(&wq->wait)) * wake_up_interruptible(&wq->wait) * ... * } * * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 * could then endup calling schedule and sleep forever if there are no more * data on the socket. * */ static inline bool skwq_has_sleeper(struct socket_wq *wq) { return wq && wq_has_sleeper(&wq->wait); } /** * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table * * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { /* Provides a barrier we need to be sure we are in sync * with the socket flags modification. * * This memory barrier is paired in the wq_has_sleeper. */ poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { /* This pairs with WRITE_ONCE() in sk_set_txhash() */ u32 txhash = READ_ONCE(sk->sk_txhash); if (txhash) { skb->l4_hash = 1; skb->hash = txhash; } } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in * and play with them. * * Inlined as it's very short and called for pretty much every * packet ever received. */ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; return true; } return false; } static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) { skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (skb) { if (sk_rmem_schedule(sk, skb, skb->truesize)) { skb_set_owner_r(skb, sk); return skb; } __kfree_skb(skb); } return NULL; } static inline void skb_prepare_for_gro(struct sk_buff *skb) { if (skb->destructor != sock_wfree) { skb_orphan(skb); return; } skb->slow_gro = 1; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); void sk_stop_timer(struct sock *sk, struct timer_list *timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { return sock_queue_rcv_skb_reason(sk, skb, NULL); } int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); /* * Recover an error report and clear atomically */ static inline int sock_error(struct sock *sk) { int err; /* Avoid an atomic operation for the common case. * This is racy since another cpu/thread can change sk_err under us. */ if (likely(data_race(!sk->sk_err))) return 0; err = xchg(&sk->sk_err, 0); return -err; } void sk_error_report(struct sock *sk); static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc); if (amt < 0) amt = 0; } return amt; } /* Note: * We use sk->sk_wq_raw, from contexts knowing this * pointer is not NULL and cannot disappear/change. */ static inline void sk_set_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; clear_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_wake_async(const struct sock *sk, int how, int band) { if (sock_flag(sk, SOCK_FASYNC)) { rcu_read_lock(); sock_wake_async(rcu_dereference(sk->sk_wq), how, band); rcu_read_unlock(); } } static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) { if (unlikely(sock_flag(sk, SOCK_FASYNC))) sock_wake_async(rcu_dereference(sk->sk_wq), how, band); } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at * minimum. */ #define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff))) #define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2) #define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE static inline void sk_stream_moderate_sndbuf(struct sock *sk) { u32 val; if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); val = max_t(u32, val, sk_unused_reserved_mem(sk)); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } /** * sk_page_frag - return an appropriate page_frag * @sk: socket * * Use the per task page_frag instead of the per socket one for * optimization when we know that we're in process context and own * everything that's associated with %current. * * Both direct reclaim and page faults can nest inside other * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag * when users disable sk_use_task_frag. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { if (sk->sk_use_task_frag) return ¤t->task_frag; return &sk->sk_frag; } bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); } static inline gfp_t gfp_any(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline gfp_t gfp_memcg_charge(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; } static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_sndtimeo; } static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); return v ?: 1; } /* Alas, with timeout socket operations are not restartable. * Compare this to poll(). */ static inline int sock_intr_errno(long timeo) { return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } struct sock_skb_cb { u32 dropcount; }; /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET (sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb)) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? atomic_read(&sk->sk_drops) : 0; } static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) { int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); atomic_add(segs, &sk->sk_drops); } static inline ktime_t sock_read_timestamp(struct sock *sk) { #if BITS_PER_LONG==32 unsigned int seq; ktime_t kt; do { seq = read_seqbegin(&sk->sk_stamp_seq); kt = sk->sk_stamp; } while (read_seqretry(&sk->sk_stamp_seq, seq)); return kt; #else return READ_ONCE(sk->sk_stamp); #endif } static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) { #if BITS_PER_LONG==32 write_seqlock(&sk->sk_stamp_seq); sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else WRITE_ONCE(sk->sk_stamp, kt); #endif } void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); u32 tsflags = READ_ONCE(sk->sk_tsflags); ktime_t kt = skb->tstamp; /* * generate control messages if * - receive time stamping in software requested * - software time stamp available and wanted * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb_wifi_acked_valid(skb)) __sock_recv_wifi_status(msg, sk, skb); } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ (1UL << SOCK_RCVMARK) | \ (1UL << SOCK_RCVPRIORITY) | \ (1UL << SOCK_TIMESTAMPING_ANY)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) if (READ_ONCE(sk->sk_flags) & FLAGS_RECV_CMSGS) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @sockc: pointer to socket cmsg cookie to get timestamping info * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ static inline void _sock_tx_timestamp(struct sock *sk, const struct sockcm_cookie *sockc, __u8 *tx_flags, __u32 *tskey) { __u32 tsflags = sockc->tsflags; if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { if (tsflags & SOCKCM_FLAG_TS_OPT_ID) *tskey = sockc->ts_opt_id; else *tskey = atomic_inc_return(&sk->sk_tskey) - 1; } } } static inline void sock_tx_timestamp(struct sock *sk, const struct sockcm_cookie *sockc, __u8 *tx_flags) { _sock_tx_timestamp(sk, sockc, tx_flags, NULL); } static inline void skb_setup_tx_timestamp(struct sk_buff *skb, const struct sockcm_cookie *sockc) { _sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } static inline bool sk_is_inet(const struct sock *sk) { int family = READ_ONCE(sk->sk_family); return family == AF_INET || family == AF_INET6; } static inline bool sk_is_tcp(const struct sock *sk) { return sk_is_inet(sk) && sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } static inline bool sk_is_udp(const struct sock *sk) { return sk_is_inet(sk) && sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP; } static inline bool sk_is_unix(const struct sock *sk) { return sk->sk_family == AF_UNIX; } static inline bool sk_is_stream_unix(const struct sock *sk) { return sk_is_unix(sk) && sk->sk_type == SOCK_STREAM; } static inline bool sk_is_vsock(const struct sock *sk) { return sk->sk_family == AF_VSOCK; } static inline bool sk_may_scm_recv(const struct sock *sk) { return (IS_ENABLED(CONFIG_UNIX) && sk->sk_family == AF_UNIX) || sk->sk_family == AF_NETLINK || (IS_ENABLED(CONFIG_BT) && sk->sk_family == AF_BLUETOOTH); } /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { #ifdef CONFIG_INET return skb->destructor == sock_pfree; #else return false; #endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, * ie _not_ a timewait or request socket. */ static inline bool sk_fullsock(const struct sock *sk) { return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } static inline bool sk_is_refcounted(struct sock *sk) { /* Only full sockets have sk->sk_flags. */ return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } static inline bool sk_requests_wifi_status(struct sock *sk) { return sk && sk_fullsock(sk) && sock_flag(sk, SOCK_WIFI_STATUS); } /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. */ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); } else if (unlikely(skb_is_decrypted(skb))) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; } #endif return skb; } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) */ static inline bool sk_listener(const struct sock *sk) { return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE) * TCP RST and ACK can be attached to TIME_WAIT. */ static inline bool sk_listener_or_tw(const struct sock *sk) { return (1 << READ_ONCE(sk->sk_state)) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT); } void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap); bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); void sk_get_meminfo(const struct sock *sk, u32 *meminfo); /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; #define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_wmem ? */ if (proto->sysctl_wmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset)); return READ_ONCE(*proto->sysctl_wmem); } static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_rmem ? */ if (proto->sysctl_rmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset)); return READ_ONCE(*proto->sysctl_rmem); } /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) * Some wifi drivers need to tweak it to get more chunks. * They can use this helper from their ndo_start_xmit() */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device * index is either the same or that the socket is bound to an L3 * master device and the given device index is also enslaved to * that L3 master */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); if (mdif && mdif == bound_dev_if) return true; return false; } void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_set_timestamp(struct sock *sk, int optname, bool valbool); int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping); void sock_enable_timestamps(struct sock *sk); #if defined(CONFIG_CGROUP_BPF) void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op); #else static inline void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) { } #endif void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); void sock_set_rcvbuf(struct sock *sk, int val); void sock_set_mark(struct sock *sk, u32 val); void sock_set_reuseaddr(struct sock *sk); void sock_set_reuseport(struct sock *sk); void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval); int sock_ioctl_inout(struct sock *sk, unsigned int cmd, void __user *arg, void *karg, size_t size); int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); static inline bool sk_is_readable(struct sock *sk) { const struct proto *prot = READ_ONCE(sk->sk_prot); if (prot->sock_is_readable) return prot->sock_is_readable(sk); return false; } #endif /* _SOCK_H */ |
| 406 406 359 325 346 345 272 272 337 337 2 38 38 311 311 308 311 308 311 2 2 2 262 262 | 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 | /* SPDX-License-Identifier: LGPL-2.1+ */ /* Copyright (C) 2022 Kent Overstreet */ #ifndef _BCACHEFS_PRINTBUF_H #define _BCACHEFS_PRINTBUF_H /* * Printbufs: Simple strings for printing to, with optional heap allocation * * This code has provisions for use in userspace, to aid in making other code * portable between kernelspace and userspace. * * Basic example: * struct printbuf buf = PRINTBUF; * * prt_printf(&buf, "foo="); * foo_to_text(&buf, foo); * printk("%s", buf.buf); * printbuf_exit(&buf); * * Or * struct printbuf buf = PRINTBUF_EXTERN(char_buf, char_buf_size) * * We can now write pretty printers instead of writing code that dumps * everything to the kernel log buffer, and then those pretty-printers can be * used by other code that outputs to kernel log, sysfs, debugfs, etc. * * Memory allocation: Outputing to a printbuf may allocate memory. This * allocation is done with GFP_KERNEL, by default: use the newer * memalloc_*_(save|restore) functions as needed. * * Since no equivalent yet exists for GFP_ATOMIC/GFP_NOWAIT, memory allocations * will be done with GFP_NOWAIT if printbuf->atomic is nonzero. * * It's allowed to grab the output buffer and free it later with kfree() instead * of using printbuf_exit(), if the user just needs a heap allocated string at * the end. * * Memory allocation failures: We don't return errors directly, because on * memory allocation failure we usually don't want to bail out and unwind - we * want to print what we've got, on a best-effort basis. But code that does want * to return -ENOMEM may check printbuf.allocation_failure. * * Indenting, tabstops: * * To aid is writing multi-line pretty printers spread across multiple * functions, printbufs track the current indent level. * * printbuf_indent_push() and printbuf_indent_pop() increase and decrease the current indent * level, respectively. * * To use tabstops, set printbuf->tabstops[]; they are in units of spaces, from * start of line. Once set, prt_tab() will output spaces up to the next tabstop. * prt_tab_rjust() will also advance the current line of text up to the next * tabstop, but it does so by shifting text since the previous tabstop up to the * next tabstop - right justifying it. * * Make sure you use prt_newline() instead of \n in the format string for indent * level and tabstops to work corretly. * * Output units: printbuf->units exists to tell pretty-printers how to output * numbers: a raw value (e.g. directly from a superblock field), as bytes, or as * human readable bytes. prt_units() obeys it. */ #include <linux/kernel.h> #include <linux/string.h> enum printbuf_si { PRINTBUF_UNITS_2, /* use binary powers of 2^10 */ PRINTBUF_UNITS_10, /* use powers of 10^3 (standard SI) */ }; #define PRINTBUF_INLINE_TABSTOPS 6 struct printbuf { char *buf; unsigned size; unsigned pos; unsigned last_newline; unsigned last_field; unsigned indent; /* * If nonzero, allocations will be done with GFP_ATOMIC: */ u8 atomic; bool allocation_failure:1; bool heap_allocated:1; bool overflow:1; enum printbuf_si si_units:1; bool human_readable_units:1; bool has_indent_or_tabstops:1; bool suppress_indent_tabstop_handling:1; u8 nr_tabstops; /* * Do not modify directly: use printbuf_tabstop_add(), * printbuf_tabstop_get() */ u8 cur_tabstop; u8 _tabstops[PRINTBUF_INLINE_TABSTOPS]; }; int bch2_printbuf_make_room(struct printbuf *, unsigned); __printf(2, 3) void bch2_prt_printf(struct printbuf *out, const char *fmt, ...); __printf(2, 0) void bch2_prt_vprintf(struct printbuf *out, const char *fmt, va_list); const char *bch2_printbuf_str(const struct printbuf *); void bch2_printbuf_exit(struct printbuf *); void bch2_printbuf_tabstops_reset(struct printbuf *); void bch2_printbuf_tabstop_pop(struct printbuf *); int bch2_printbuf_tabstop_push(struct printbuf *, unsigned); void bch2_printbuf_indent_add(struct printbuf *, unsigned); void bch2_printbuf_indent_add_nextline(struct printbuf *, unsigned); void bch2_printbuf_indent_sub(struct printbuf *, unsigned); void bch2_prt_newline(struct printbuf *); void bch2_printbuf_strip_trailing_newline(struct printbuf *); void bch2_prt_tab(struct printbuf *); void bch2_prt_tab_rjust(struct printbuf *); void bch2_prt_bytes_indented(struct printbuf *, const char *, unsigned); void bch2_prt_human_readable_u64(struct printbuf *, u64); void bch2_prt_human_readable_s64(struct printbuf *, s64); void bch2_prt_units_u64(struct printbuf *, u64); void bch2_prt_units_s64(struct printbuf *, s64); void bch2_prt_string_option(struct printbuf *, const char * const[], size_t); void bch2_prt_bitflags(struct printbuf *, const char * const[], u64); void bch2_prt_bitflags_vector(struct printbuf *, const char * const[], unsigned long *, unsigned); /* Initializer for a heap allocated printbuf: */ #define PRINTBUF ((struct printbuf) { .heap_allocated = true }) /* Initializer a printbuf that points to an external buffer: */ #define PRINTBUF_EXTERN(_buf, _size) \ ((struct printbuf) { \ .buf = _buf, \ .size = _size, \ }) static inline struct printbuf bch2_printbuf_init(void) { return PRINTBUF; } DEFINE_CLASS(printbuf, struct printbuf, bch2_printbuf_exit(&_T), bch2_printbuf_init(), void) /* * Returns size remaining of output buffer: */ static inline unsigned printbuf_remaining_size(struct printbuf *out) { if (WARN_ON(out->size && out->pos >= out->size)) out->pos = out->size - 1; return out->size - out->pos; } /* * Returns number of characters we can print to the output buffer - i.e. * excluding the terminating nul: */ static inline unsigned printbuf_remaining(struct printbuf *out) { return out->size ? printbuf_remaining_size(out) - 1 : 0; } static inline unsigned printbuf_written(struct printbuf *out) { return out->size ? min(out->pos, out->size - 1) : 0; } static inline void printbuf_nul_terminate_reserved(struct printbuf *out) { if (WARN_ON(out->size && out->pos >= out->size)) out->pos = out->size - 1; if (out->size) out->buf[out->pos] = 0; } static inline void printbuf_nul_terminate(struct printbuf *out) { bch2_printbuf_make_room(out, 1); printbuf_nul_terminate_reserved(out); } /* Doesn't call bch2_printbuf_make_room(), doesn't nul terminate: */ static inline void __prt_char_reserved(struct printbuf *out, char c) { if (printbuf_remaining(out)) out->buf[out->pos++] = c; } /* Doesn't nul terminate: */ static inline void __prt_char(struct printbuf *out, char c) { bch2_printbuf_make_room(out, 1); __prt_char_reserved(out, c); } static inline void prt_char(struct printbuf *out, char c) { bch2_printbuf_make_room(out, 2); __prt_char_reserved(out, c); printbuf_nul_terminate_reserved(out); } static inline void __prt_chars_reserved(struct printbuf *out, char c, unsigned n) { unsigned can_print = min(n, printbuf_remaining(out)); for (unsigned i = 0; i < can_print; i++) out->buf[out->pos++] = c; } static inline void prt_chars(struct printbuf *out, char c, unsigned n) { bch2_printbuf_make_room(out, n); __prt_chars_reserved(out, c, n); printbuf_nul_terminate_reserved(out); } static inline void prt_bytes(struct printbuf *out, const void *b, unsigned n) { bch2_printbuf_make_room(out, n); unsigned can_print = min(n, printbuf_remaining(out)); for (unsigned i = 0; i < can_print; i++) out->buf[out->pos++] = ((char *) b)[i]; printbuf_nul_terminate(out); } static inline void prt_str(struct printbuf *out, const char *str) { prt_bytes(out, str, strlen(str)); } static inline void prt_str_indented(struct printbuf *out, const char *str) { bch2_prt_bytes_indented(out, str, strlen(str)); } static inline void prt_hex_byte(struct printbuf *out, u8 byte) { bch2_printbuf_make_room(out, 3); __prt_char_reserved(out, hex_asc_hi(byte)); __prt_char_reserved(out, hex_asc_lo(byte)); printbuf_nul_terminate_reserved(out); } static inline void prt_hex_byte_upper(struct printbuf *out, u8 byte) { bch2_printbuf_make_room(out, 3); __prt_char_reserved(out, hex_asc_upper_hi(byte)); __prt_char_reserved(out, hex_asc_upper_lo(byte)); printbuf_nul_terminate_reserved(out); } static inline void printbuf_reset_keep_tabstops(struct printbuf *buf) { buf->pos = 0; buf->allocation_failure = 0; buf->last_newline = 0; buf->last_field = 0; buf->indent = 0; buf->cur_tabstop = 0; } /** * printbuf_reset - re-use a printbuf without freeing and re-initializing it: */ static inline void printbuf_reset(struct printbuf *buf) { printbuf_reset_keep_tabstops(buf); buf->nr_tabstops = 0; } /** * printbuf_atomic_inc - mark as entering an atomic section */ static inline void printbuf_atomic_inc(struct printbuf *buf) { buf->atomic++; } /** * printbuf_atomic_inc - mark as leaving an atomic section */ static inline void printbuf_atomic_dec(struct printbuf *buf) { buf->atomic--; } #endif /* _BCACHEFS_PRINTBUF_H */ |
| 1211 1211 1212 1210 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> #include <linux/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(struct chacha_state *state, int nrounds) { u32 *x = state->x; int i; /* whitelist the allowed round counts */ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); for (i = 0; i < nrounds; i += 2) { x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } } /** * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix * @out: output keystream block * @nrounds: number of rounds (20 or 12; 20 is recommended) * * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. * The caller has already converted the endianness of the input. This function * also handles incrementing the block counter in the input matrix. */ void chacha_block_generic(struct chacha_state *state, u8 out[CHACHA_BLOCK_SIZE], int nrounds) { struct chacha_state permuted_state = *state; int i; chacha_permute(&permuted_state, nrounds); for (i = 0; i < ARRAY_SIZE(state->x); i++) put_unaligned_le32(permuted_state.x[i] + state->x[i], &out[i * sizeof(u32)]); state->x[12]++; } EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix * @out: the output words * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha * skips the final addition of the initial state, and outputs only certain words * of the state. It should not be used for streaming directly. */ void hchacha_block_generic(const struct chacha_state *state, u32 out[HCHACHA_OUT_WORDS], int nrounds) { struct chacha_state permuted_state = *state; chacha_permute(&permuted_state, nrounds); memcpy(&out[0], &permuted_state.x[0], 16); memcpy(&out[4], &permuted_state.x[12], 16); } EXPORT_SYMBOL(hchacha_block_generic); |
| 5 5 2 2 14 10 4 9 2 2 2 1 24 24 1 5 8 1 3 3 6 1 6 5 4 1 20 1 2 1 1 17 2 15 6 1 10 11 2 5 3 3 3 2 2 2 2 2 2 2 16 16 16 20 23 24 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/hpfs/super.c * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * mounting, unmounting, error handling */ #include "hpfs_fn.h" #include <linux/module.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/init.h> #include <linux/statfs.h> #include <linux/magic.h> #include <linux/sched.h> #include <linux/bitmap.h> #include <linux/slab.h> #include <linux/seq_file.h> /* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */ static void mark_dirty(struct super_block *s, int remount) { if (hpfs_sb(s)->sb_chkdsk && (remount || !sb_rdonly(s))) { struct buffer_head *bh; struct hpfs_spare_block *sb; if ((sb = hpfs_map_sector(s, 17, &bh, 0))) { sb->dirty = 1; sb->old_wrote = 0; mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } } } /* Mark the filesystem clean (mark it dirty for chkdsk if chkdsk==2 or if there were errors) */ static void unmark_dirty(struct super_block *s) { struct buffer_head *bh; struct hpfs_spare_block *sb; if (sb_rdonly(s)) return; sync_blockdev(s->s_bdev); if ((sb = hpfs_map_sector(s, 17, &bh, 0))) { sb->dirty = hpfs_sb(s)->sb_chkdsk > 1 - hpfs_sb(s)->sb_was_error; sb->old_wrote = hpfs_sb(s)->sb_chkdsk >= 2 && !hpfs_sb(s)->sb_was_error; mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } } /* Filesystem error... */ void hpfs_error(struct super_block *s, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_err("filesystem error: %pV", &vaf); va_end(args); if (!hpfs_sb(s)->sb_was_error) { if (hpfs_sb(s)->sb_err == 2) { pr_cont("; crashing the system because you wanted it\n"); mark_dirty(s, 0); panic("HPFS panic"); } else if (hpfs_sb(s)->sb_err == 1) { if (sb_rdonly(s)) pr_cont("; already mounted read-only\n"); else { pr_cont("; remounting read-only\n"); mark_dirty(s, 0); s->s_flags |= SB_RDONLY; } } else if (sb_rdonly(s)) pr_cont("; going on - but anything won't be destroyed because it's read-only\n"); else pr_cont("; corrupted filesystem mounted read/write - your computer will explode within 20 seconds ... but you wanted it so!\n"); } else pr_cont("\n"); hpfs_sb(s)->sb_was_error = 1; } /* * A little trick to detect cycles in many hpfs structures and don't let the * kernel crash on corrupted filesystem. When first called, set c2 to 0. * * BTW. chkdsk doesn't detect cycles correctly. When I had 2 lost directories * nested each in other, chkdsk locked up happilly. */ int hpfs_stop_cycles(struct super_block *s, int key, int *c1, int *c2, char *msg) { if (*c2 && *c1 == key) { hpfs_error(s, "cycle detected on key %08x in %s", key, msg); return 1; } (*c2)++; if (!((*c2 - 1) & *c2)) *c1 = key; return 0; } static void free_sbi(struct hpfs_sb_info *sbi) { kfree(sbi->sb_cp_table); kfree(sbi->sb_bmp_dir); kfree(sbi); } static void lazy_free_sbi(struct rcu_head *rcu) { free_sbi(container_of(rcu, struct hpfs_sb_info, rcu)); } static void hpfs_put_super(struct super_block *s) { hpfs_lock(s); unmark_dirty(s); hpfs_unlock(s); call_rcu(&hpfs_sb(s)->rcu, lazy_free_sbi); } static unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno) { struct quad_buffer_head qbh; unsigned long *bits; unsigned count; bits = hpfs_map_4sectors(s, secno, &qbh, 0); if (!bits) return (unsigned)-1; count = bitmap_weight(bits, 2048 * BITS_PER_BYTE); hpfs_brelse4(&qbh); return count; } static unsigned count_bitmaps(struct super_block *s) { unsigned n, count, n_bands; n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14; count = 0; for (n = 0; n < COUNT_RD_AHEAD; n++) { hpfs_prefetch_bitmap(s, n); } for (n = 0; n < n_bands; n++) { unsigned c; hpfs_prefetch_bitmap(s, n + COUNT_RD_AHEAD); c = hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n])); if (c != (unsigned)-1) count += c; } return count; } unsigned hpfs_get_free_dnodes(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); if (sbi->sb_n_free_dnodes == (unsigned)-1) { unsigned c = hpfs_count_one_bitmap(s, sbi->sb_dmap); if (c == (unsigned)-1) return 0; sbi->sb_n_free_dnodes = c; } return sbi->sb_n_free_dnodes; } static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(s); u64 id = huge_encode_dev(s->s_bdev->bd_dev); hpfs_lock(s); if (sbi->sb_n_free == (unsigned)-1) sbi->sb_n_free = count_bitmaps(s); buf->f_type = s->s_magic; buf->f_bsize = 512; buf->f_blocks = sbi->sb_fs_size; buf->f_bfree = sbi->sb_n_free; buf->f_bavail = sbi->sb_n_free; buf->f_files = sbi->sb_dirband_size / 4; buf->f_ffree = hpfs_get_free_dnodes(s); buf->f_fsid = u64_to_fsid(id); buf->f_namelen = 254; hpfs_unlock(s); return 0; } long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg) { switch (cmd) { case FITRIM: { struct fstrim_range range; secno n_trimmed; int r; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; r = hpfs_trim_fs(file_inode(file)->i_sb, range.start >> 9, (range.start + range.len) >> 9, (range.minlen + 511) >> 9, &n_trimmed); if (r) return r; range.len = (u64)n_trimmed << 9; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } default: { return -ENOIOCTLCMD; } } } static struct kmem_cache * hpfs_inode_cachep; static struct inode *hpfs_alloc_inode(struct super_block *sb) { struct hpfs_inode_info *ei; ei = alloc_inode_sb(sb, hpfs_inode_cachep, GFP_NOFS); if (!ei) return NULL; return &ei->vfs_inode; } static void hpfs_free_inode(struct inode *inode) { kmem_cache_free(hpfs_inode_cachep, hpfs_i(inode)); } static void init_once(void *foo) { struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo; inode_init_once(&ei->vfs_inode); } static int init_inodecache(void) { hpfs_inode_cachep = kmem_cache_create("hpfs_inode_cache", sizeof(struct hpfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (hpfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(hpfs_inode_cachep); } enum { Opt_help, Opt_uid, Opt_gid, Opt_umask, Opt_case, Opt_check, Opt_err, Opt_eas, Opt_chkdsk, Opt_timeshift, }; static const struct constant_table hpfs_param_case[] = { {"asis", 0}, {"lower", 1}, {} }; static const struct constant_table hpfs_param_check[] = { {"none", 0}, {"normal", 1}, {"strict", 2}, {} }; static const struct constant_table hpfs_param_err[] = { {"continue", 0}, {"remount-ro", 1}, {"panic", 2}, {} }; static const struct constant_table hpfs_param_eas[] = { {"no", 0}, {"ro", 1}, {"rw", 2}, {} }; static const struct constant_table hpfs_param_chkdsk[] = { {"no", 0}, {"errors", 1}, {"always", 2}, {} }; static const struct fs_parameter_spec hpfs_param_spec[] = { fsparam_flag ("help", Opt_help), fsparam_uid ("uid", Opt_uid), fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("umask", Opt_umask), fsparam_enum ("case", Opt_case, hpfs_param_case), fsparam_enum ("check", Opt_check, hpfs_param_check), fsparam_enum ("errors", Opt_err, hpfs_param_err), fsparam_enum ("eas", Opt_eas, hpfs_param_eas), fsparam_enum ("chkdsk", Opt_chkdsk, hpfs_param_chkdsk), fsparam_s32 ("timeshift", Opt_timeshift), {} }; struct hpfs_fc_context { kuid_t uid; kgid_t gid; umode_t umask; int lowercase; int eas; int chk; int errs; int chkdsk; int timeshift; }; static inline void hpfs_help(void) { pr_info("\n\ HPFS filesystem options:\n\ help do not mount and display this text\n\ uid=xxx set uid of files that don't have uid specified in eas\n\ gid=xxx set gid of files that don't have gid specified in eas\n\ umask=xxx set mode of files that don't have mode specified in eas\n\ case=lower lowercase all files\n\ case=asis do not lowercase files (default)\n\ check=none no fs checks - kernel may crash on corrupted filesystem\n\ check=normal do some checks - it should not crash (default)\n\ check=strict do extra time-consuming checks, used for debugging\n\ errors=continue continue on errors\n\ errors=remount-ro remount read-only if errors found (default)\n\ errors=panic panic on errors\n\ chkdsk=no do not mark fs for chkdsking even if there were errors\n\ chkdsk=errors mark fs dirty if errors found (default)\n\ chkdsk=always always mark fs dirty - used for debugging\n\ eas=no ignore extended attributes\n\ eas=ro read but do not write extended attributes\n\ eas=rw r/w eas => enables chmod, chown, mknod, ln -s (default)\n\ timeshift=nnn add nnn seconds to file times\n\ \n"); } static int hpfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hpfs_fc_context *ctx = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, hpfs_param_spec, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_help: hpfs_help(); return -EINVAL; case Opt_uid: ctx->uid = result.uid; break; case Opt_gid: ctx->gid = result.gid; break; case Opt_umask: ctx->umask = result.uint_32; break; case Opt_case: ctx->lowercase = result.uint_32; break; case Opt_check: ctx->chk = result.uint_32; break; case Opt_err: ctx->errs = result.uint_32; break; case Opt_eas: ctx->eas = result.uint_32; break; case Opt_chkdsk: ctx->chkdsk = result.uint_32; break; case Opt_timeshift: { int m = 1; char *rhs = param->string; int timeshift; if (*rhs == '-') m = -1; if (*rhs == '+' || *rhs == '-') rhs++; timeshift = simple_strtoul(rhs, &rhs, 0) * m; if (*rhs) return -EINVAL; ctx->timeshift = timeshift; break; } default: return -EINVAL; } return 0; } static int hpfs_reconfigure(struct fs_context *fc) { struct hpfs_fc_context *ctx = fc->fs_private; struct super_block *s = fc->root->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(s); sync_filesystem(s); fc->sb_flags |= SB_NOATIME; hpfs_lock(s); if (ctx->timeshift != sbi->sb_timeshift) { pr_err("timeshift can't be changed using remount.\n"); goto out_err; } unmark_dirty(s); sbi->sb_uid = ctx->uid; sbi->sb_gid = ctx->gid; sbi->sb_mode = 0777 & ~ctx->umask; sbi->sb_lowercase = ctx->lowercase; sbi->sb_eas = ctx->eas; sbi->sb_chk = ctx->chk; sbi->sb_chkdsk = ctx->chkdsk; sbi->sb_err = ctx->errs; sbi->sb_timeshift = ctx->timeshift; if (!(fc->sb_flags & SB_RDONLY)) mark_dirty(s, 1); hpfs_unlock(s); return 0; out_err: hpfs_unlock(s); return -EINVAL; } static int hpfs_show_options(struct seq_file *seq, struct dentry *root) { struct hpfs_sb_info *sbi = hpfs_sb(root->d_sb); seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbi->sb_uid)); seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbi->sb_gid)); seq_printf(seq, ",umask=%03o", (~sbi->sb_mode & 0777)); if (sbi->sb_lowercase) seq_printf(seq, ",case=lower"); if (!sbi->sb_chk) seq_printf(seq, ",check=none"); if (sbi->sb_chk == 2) seq_printf(seq, ",check=strict"); if (!sbi->sb_err) seq_printf(seq, ",errors=continue"); if (sbi->sb_err == 2) seq_printf(seq, ",errors=panic"); if (!sbi->sb_chkdsk) seq_printf(seq, ",chkdsk=no"); if (sbi->sb_chkdsk == 2) seq_printf(seq, ",chkdsk=always"); if (!sbi->sb_eas) seq_printf(seq, ",eas=no"); if (sbi->sb_eas == 1) seq_printf(seq, ",eas=ro"); if (sbi->sb_timeshift) seq_printf(seq, ",timeshift=%d", sbi->sb_timeshift); return 0; } /* Super operations */ static const struct super_operations hpfs_sops = { .alloc_inode = hpfs_alloc_inode, .free_inode = hpfs_free_inode, .evict_inode = hpfs_evict_inode, .put_super = hpfs_put_super, .statfs = hpfs_statfs, .show_options = hpfs_show_options, }; static int hpfs_fill_super(struct super_block *s, struct fs_context *fc) { struct hpfs_fc_context *ctx = fc->fs_private; struct buffer_head *bh0, *bh1, *bh2; struct hpfs_boot_block *bootblock; struct hpfs_super_block *superblock; struct hpfs_spare_block *spareblock; struct hpfs_sb_info *sbi; struct inode *root; int silent = fc->sb_flags & SB_SILENT; dnode_secno root_dno; struct hpfs_dirent *de = NULL; struct quad_buffer_head qbh; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) { return -ENOMEM; } s->s_fs_info = sbi; mutex_init(&sbi->hpfs_mutex); hpfs_lock(s); /*sbi->sb_mounting = 1;*/ sb_set_blocksize(s, 512); sbi->sb_fs_size = -1; if (!(bootblock = hpfs_map_sector(s, 0, &bh0, 0))) goto bail1; if (!(superblock = hpfs_map_sector(s, 16, &bh1, 1))) goto bail2; if (!(spareblock = hpfs_map_sector(s, 17, &bh2, 0))) goto bail3; /* Check magics */ if (/*le16_to_cpu(bootblock->magic) != BB_MAGIC ||*/ le32_to_cpu(superblock->magic) != SB_MAGIC || le32_to_cpu(spareblock->magic) != SP_MAGIC) { if (!silent) pr_err("Bad magic ... probably not HPFS\n"); goto bail4; } /* Check version */ if (!sb_rdonly(s) && superblock->funcversion != 2 && superblock->funcversion != 3) { pr_err("Bad version %d,%d. Mount readonly to go around\n", (int)superblock->version, (int)superblock->funcversion); pr_err("please try recent version of HPFS driver at http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi and if it still can't understand this format, contact author - mikulas@artax.karlin.mff.cuni.cz\n"); goto bail4; } s->s_flags |= SB_NOATIME; /* Fill superblock stuff */ s->s_magic = HPFS_SUPER_MAGIC; s->s_op = &hpfs_sops; s->s_d_op = &hpfs_dentry_operations; s->s_time_min = local_to_gmt(s, 0); s->s_time_max = local_to_gmt(s, U32_MAX); sbi->sb_root = le32_to_cpu(superblock->root); sbi->sb_fs_size = le32_to_cpu(superblock->n_sectors); sbi->sb_bitmaps = le32_to_cpu(superblock->bitmaps); sbi->sb_dirband_start = le32_to_cpu(superblock->dir_band_start); sbi->sb_dirband_size = le32_to_cpu(superblock->n_dir_band); sbi->sb_dmap = le32_to_cpu(superblock->dir_band_bitmap); sbi->sb_uid = ctx->uid; sbi->sb_gid = ctx->gid; sbi->sb_mode = 0777 & ~ctx->umask; sbi->sb_n_free = -1; sbi->sb_n_free_dnodes = -1; sbi->sb_lowercase = ctx->lowercase; sbi->sb_eas = ctx->eas; sbi->sb_chk = ctx->chk; sbi->sb_chkdsk = ctx->chkdsk; sbi->sb_err = ctx->errs; sbi->sb_timeshift = ctx->timeshift; sbi->sb_was_error = 0; sbi->sb_cp_table = NULL; sbi->sb_c_bitmap = -1; sbi->sb_max_fwd_alloc = 0xffffff; if (sbi->sb_fs_size >= 0x80000000) { hpfs_error(s, "invalid size in superblock: %08x", (unsigned)sbi->sb_fs_size); goto bail4; } if (spareblock->n_spares_used) hpfs_load_hotfix_map(s, spareblock); /* Load bitmap directory */ if (!(sbi->sb_bmp_dir = hpfs_load_bitmap_directory(s, le32_to_cpu(superblock->bitmaps)))) goto bail4; /* Check for general fs errors*/ if (spareblock->dirty && !spareblock->old_wrote) { if (sbi->sb_err == 2) { pr_err("Improperly stopped, not mounted\n"); goto bail4; } hpfs_error(s, "improperly stopped"); } if (!sb_rdonly(s)) { spareblock->dirty = 1; spareblock->old_wrote = 0; mark_buffer_dirty(bh2); } if (le32_to_cpu(spareblock->n_dnode_spares) != le32_to_cpu(spareblock->n_dnode_spares_free)) { if (sbi->sb_err >= 2) { pr_err("Spare dnodes used, try chkdsk\n"); mark_dirty(s, 0); goto bail4; } hpfs_error(s, "warning: spare dnodes used, try chkdsk"); if (sbi->sb_err == 0) pr_err("Proceeding, but your filesystem could be corrupted if you delete files or directories\n"); } if (sbi->sb_chk) { unsigned a; if (le32_to_cpu(superblock->dir_band_end) - le32_to_cpu(superblock->dir_band_start) + 1 != le32_to_cpu(superblock->n_dir_band) || le32_to_cpu(superblock->dir_band_end) < le32_to_cpu(superblock->dir_band_start) || le32_to_cpu(superblock->n_dir_band) > 0x4000) { hpfs_error(s, "dir band size mismatch: dir_band_start==%08x, dir_band_end==%08x, n_dir_band==%08x", le32_to_cpu(superblock->dir_band_start), le32_to_cpu(superblock->dir_band_end), le32_to_cpu(superblock->n_dir_band)); goto bail4; } a = sbi->sb_dirband_size; sbi->sb_dirband_size = 0; if (hpfs_chk_sectors(s, le32_to_cpu(superblock->dir_band_start), le32_to_cpu(superblock->n_dir_band), "dir_band") || hpfs_chk_sectors(s, le32_to_cpu(superblock->dir_band_bitmap), 4, "dir_band_bitmap") || hpfs_chk_sectors(s, le32_to_cpu(superblock->bitmaps), 4, "bitmaps")) { mark_dirty(s, 0); goto bail4; } sbi->sb_dirband_size = a; } else pr_err("You really don't want any checks? You are crazy...\n"); /* Load code page table */ if (le32_to_cpu(spareblock->n_code_pages)) if (!(sbi->sb_cp_table = hpfs_load_code_page(s, le32_to_cpu(spareblock->code_page_dir)))) pr_err("code page support is disabled\n"); brelse(bh2); brelse(bh1); brelse(bh0); root = iget_locked(s, sbi->sb_root); if (!root) goto bail0; hpfs_init_inode(root); hpfs_read_inode(root); unlock_new_inode(root); s->s_root = d_make_root(root); if (!s->s_root) goto bail0; /* * find the root directory's . pointer & finish filling in the inode */ root_dno = hpfs_fnode_dno(s, sbi->sb_root); if (root_dno) de = map_dirent(root, root_dno, "\001\001", 2, NULL, &qbh); if (!de) hpfs_error(s, "unable to find root dir"); else { inode_set_atime(root, local_to_gmt(s, le32_to_cpu(de->read_date)), 0); inode_set_mtime(root, local_to_gmt(s, le32_to_cpu(de->write_date)), 0); inode_set_ctime(root, local_to_gmt(s, le32_to_cpu(de->creation_date)), 0); hpfs_i(root)->i_ea_size = le32_to_cpu(de->ea_size); hpfs_i(root)->i_parent_dir = root->i_ino; if (root->i_size == -1) root->i_size = 2048; if (root->i_blocks == -1) root->i_blocks = 5; hpfs_brelse4(&qbh); } hpfs_unlock(s); return 0; bail4: brelse(bh2); bail3: brelse(bh1); bail2: brelse(bh0); bail1: bail0: hpfs_unlock(s); free_sbi(sbi); return -EINVAL; } static int hpfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, hpfs_fill_super); } static void hpfs_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations hpfs_fc_context_ops = { .parse_param = hpfs_parse_param, .get_tree = hpfs_get_tree, .reconfigure = hpfs_reconfigure, .free = hpfs_free_fc, }; static int hpfs_init_fs_context(struct fs_context *fc) { struct hpfs_fc_context *ctx; ctx = kzalloc(sizeof(struct hpfs_fc_context), GFP_KERNEL); if (!ctx) return -ENOMEM; if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { struct super_block *sb = fc->root->d_sb; struct hpfs_sb_info *sbi = hpfs_sb(sb); ctx->uid = sbi->sb_uid; ctx->gid = sbi->sb_gid; ctx->umask = 0777 & ~sbi->sb_mode; ctx->lowercase = sbi->sb_lowercase; ctx->eas = sbi->sb_eas; ctx->chk = sbi->sb_chk; ctx->chkdsk = sbi->sb_chkdsk; ctx->errs = sbi->sb_err; ctx->timeshift = sbi->sb_timeshift; } else { ctx->uid = current_uid(); ctx->gid = current_gid(); ctx->umask = current_umask(); ctx->lowercase = 0; ctx->eas = 2; ctx->chk = 1; ctx->errs = 1; ctx->chkdsk = 1; ctx->timeshift = 0; } fc->fs_private = ctx; fc->ops = &hpfs_fc_context_ops; return 0; }; static struct file_system_type hpfs_fs_type = { .owner = THIS_MODULE, .name = "hpfs", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = hpfs_init_fs_context, .parameters = hpfs_param_spec, }; MODULE_ALIAS_FS("hpfs"); static int __init init_hpfs_fs(void) { int err = init_inodecache(); if (err) goto out1; err = register_filesystem(&hpfs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_hpfs_fs(void) { unregister_filesystem(&hpfs_fs_type); destroy_inodecache(); } module_init(init_hpfs_fs) module_exit(exit_hpfs_fs) MODULE_DESCRIPTION("OS/2 HPFS file system support"); MODULE_LICENSE("GPL"); |
| 87 87 652 655 266 267 11 11 47 47 129 49 125 | 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 | /* * Compatibility functions which bloat the callers too much to make inline. * All of the callers of these functions should be converted to use folios * eventually. */ #include <linux/migrate.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include "internal.h" void unlock_page(struct page *page) { return folio_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page); void end_page_writeback(struct page *page) { return folio_end_writeback(page_folio(page)); } EXPORT_SYMBOL(end_page_writeback); void wait_on_page_writeback(struct page *page) { return folio_wait_writeback(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_on_page_writeback); void mark_page_accessed(struct page *page) { folio_mark_accessed(page_folio(page)); } EXPORT_SYMBOL(mark_page_accessed); void set_page_writeback(struct page *page) { folio_start_writeback(page_folio(page)); } EXPORT_SYMBOL(set_page_writeback); bool set_page_dirty(struct page *page) { return folio_mark_dirty(page_folio(page)); } EXPORT_SYMBOL(set_page_dirty); int set_page_dirty_lock(struct page *page) { return folio_mark_dirty_lock(page_folio(page)); } EXPORT_SYMBOL(set_page_dirty_lock); bool clear_page_dirty_for_io(struct page *page) { return folio_clear_dirty_for_io(page_folio(page)); } EXPORT_SYMBOL(clear_page_dirty_for_io); bool redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { return folio_redirty_for_writepage(wbc, page_folio(page)); } EXPORT_SYMBOL(redirty_page_for_writepage); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp) { return filemap_add_folio(mapping, page_folio(page), index, gfp); } EXPORT_SYMBOL(add_to_page_cache_lru); noinline struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); if (IS_ERR(folio)) return NULL; return folio_file_page(folio, index); } EXPORT_SYMBOL(pagecache_get_page); |
| 753 758 552 554 14 14 6 6 367 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 1 6 6 6 6 6 6 6 6 5 5 5 5 4 3 5 5 5 5 5 5 5 5 4 4 5 5 5 5 5 5 5 4 3 3 5 228 138 225 365 367 366 139 227 367 366 136 366 367 135 14 14 14 14 14 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Resizable, Scalable, Concurrent Hash Table * * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * Code partially derived from nft_hash * Rewritten with rehash code from br_multicast plus single list * pointer as suggested by Josh Triplett */ #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/log2.h> #include <linux/sched.h> #include <linux/rculist.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/rhashtable.h> #include <linux/err.h> #include <linux/export.h> #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U union nested_table { union nested_table __rcu *table; struct rhash_lock_head __rcu *bucket; }; static u32 head_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, const struct rhash_head *he) { return rht_head_hashfn(ht, tbl, he, ht->p); } #ifdef CONFIG_PROVE_LOCKING #define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT)) int lockdep_rht_mutex_is_held(struct rhashtable *ht) { return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1; } EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) { if (!debug_locks) return 1; if (unlikely(tbl->nest)) return 1; return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]); } EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); #else #define ASSERT_RHT_MUTEX(HT) #endif static inline union nested_table *nested_table_top( const struct bucket_table *tbl) { /* The top-level bucket entry does not need RCU protection * because it's set at the same time as tbl->nest. */ return (void *)rcu_dereference_protected(tbl->buckets[0], 1); } static void nested_table_free(union nested_table *ntbl, unsigned int size) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); const unsigned int len = 1 << shift; unsigned int i; ntbl = rcu_dereference_protected(ntbl->table, 1); if (!ntbl) return; if (size > len) { size >>= shift; for (i = 0; i < len; i++) nested_table_free(ntbl + i, size); } kfree(ntbl); } static void nested_bucket_table_free(const struct bucket_table *tbl) { unsigned int size = tbl->size >> tbl->nest; unsigned int len = 1 << tbl->nest; union nested_table *ntbl; unsigned int i; ntbl = nested_table_top(tbl); for (i = 0; i < len; i++) nested_table_free(ntbl + i, size); kfree(ntbl); } static void bucket_table_free(const struct bucket_table *tbl) { if (tbl->nest) nested_bucket_table_free(tbl); kvfree(tbl); } static void bucket_table_free_rcu(struct rcu_head *head) { bucket_table_free(container_of(head, struct bucket_table, rcu)); } static union nested_table *nested_table_alloc(struct rhashtable *ht, union nested_table __rcu **prev, bool leaf) { union nested_table *ntbl; int i; ntbl = rcu_dereference(*prev); if (ntbl) return ntbl; ntbl = alloc_hooks_tag(ht->alloc_tag, kmalloc_noprof(PAGE_SIZE, GFP_ATOMIC|__GFP_ZERO)); if (ntbl && leaf) { for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) INIT_RHT_NULLS_HEAD(ntbl[i].bucket); } if (cmpxchg((union nested_table **)prev, NULL, ntbl) == NULL) return ntbl; /* Raced with another thread. */ kfree(ntbl); return rcu_dereference(*prev); } static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, size_t nbuckets, gfp_t gfp) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); struct bucket_table *tbl; size_t size; if (nbuckets < (1 << (shift + 1))) return NULL; size = sizeof(*tbl) + sizeof(tbl->buckets[0]); tbl = alloc_hooks_tag(ht->alloc_tag, kmalloc_noprof(size, gfp|__GFP_ZERO)); if (!tbl) return NULL; if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets, false)) { kfree(tbl); return NULL; } tbl->nest = (ilog2(nbuckets) - 1) % shift + 1; return tbl; } static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, size_t nbuckets, gfp_t gfp) { struct bucket_table *tbl = NULL; size_t size; int i; static struct lock_class_key __key; tbl = alloc_hooks_tag(ht->alloc_tag, kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets), gfp|__GFP_ZERO, NUMA_NO_NODE)); size = nbuckets; if (tbl == NULL && !gfpflags_allow_blocking(gfp)) { tbl = nested_bucket_table_alloc(ht, nbuckets, gfp); nbuckets = 0; } if (tbl == NULL) return NULL; lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0); tbl->size = size; rcu_head_init(&tbl->rcu); INIT_LIST_HEAD(&tbl->walkers); tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) INIT_RHT_NULLS_HEAD(tbl->buckets[i]); return tbl; } static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, struct bucket_table *tbl) { struct bucket_table *new_tbl; do { new_tbl = tbl; tbl = rht_dereference_rcu(tbl->future_tbl, ht); } while (tbl); return new_tbl; } static int rhashtable_rehash_one(struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); int err = -EAGAIN; struct rhash_head *head, *next, *entry; struct rhash_head __rcu **pprev = NULL; unsigned int new_hash; unsigned long flags; if (new_tbl->nest) goto out; err = -ENOENT; rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash), old_tbl, old_hash) { err = 0; next = rht_dereference_bucket(entry->next, old_tbl, old_hash); if (rht_is_a_nulls(next)) break; pprev = &entry->next; } if (err) goto out; new_hash = head_hashfn(ht, new_tbl, entry); flags = rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING); head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash); RCU_INIT_POINTER(entry->next, head); rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry, flags); if (pprev) rcu_assign_pointer(*pprev, next); else /* Need to preserved the bit lock. */ rht_assign_locked(bkt, next); out: return err; } static int rhashtable_rehash_chain(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); unsigned long flags; int err; if (!bkt) return 0; flags = rht_lock(old_tbl, bkt); while (!(err = rhashtable_rehash_one(ht, bkt, old_hash))) ; if (err == -ENOENT) err = 0; rht_unlock(old_tbl, bkt, flags); return err; } static int rhashtable_rehash_attach(struct rhashtable *ht, struct bucket_table *old_tbl, struct bucket_table *new_tbl) { /* Make insertions go into the new, empty table right away. Deletions * and lookups will be attempted in both tables until we synchronize. * As cmpxchg() provides strong barriers, we do not need * rcu_assign_pointer(). */ if (cmpxchg((struct bucket_table **)&old_tbl->future_tbl, NULL, new_tbl) != NULL) return -EEXIST; return 0; } static int rhashtable_rehash_table(struct rhashtable *ht) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct bucket_table *new_tbl; struct rhashtable_walker *walker; unsigned int old_hash; int err; new_tbl = rht_dereference(old_tbl->future_tbl, ht); if (!new_tbl) return 0; for (old_hash = 0; old_hash < old_tbl->size; old_hash++) { err = rhashtable_rehash_chain(ht, old_hash); if (err) return err; cond_resched(); } /* Publish the new table pointer. */ rcu_assign_pointer(ht->tbl, new_tbl); spin_lock(&ht->lock); list_for_each_entry(walker, &old_tbl->walkers, list) walker->tbl = NULL; /* Wait for readers. All new readers will see the new * table, and thus no references to the old table will * remain. * We do this inside the locked region so that * rhashtable_walk_stop() can use rcu_head_after_call_rcu() * to check if it should not re-link the table. */ call_rcu(&old_tbl->rcu, bucket_table_free_rcu); spin_unlock(&ht->lock); return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0; } static int rhashtable_rehash_alloc(struct rhashtable *ht, struct bucket_table *old_tbl, unsigned int size) { struct bucket_table *new_tbl; int err; ASSERT_RHT_MUTEX(ht); new_tbl = bucket_table_alloc(ht, size, GFP_KERNEL); if (new_tbl == NULL) return -ENOMEM; err = rhashtable_rehash_attach(ht, old_tbl, new_tbl); if (err) bucket_table_free(new_tbl); return err; } /** * rhashtable_shrink - Shrink hash table while allowing concurrent lookups * @ht: the hash table to shrink * * This function shrinks the hash table to fit, i.e., the smallest * size would not cause it to expand right away automatically. * * The caller must ensure that no concurrent resizing occurs by holding * ht->mutex. * * The caller must ensure that no concurrent table mutations take place. * It is however valid to have concurrent lookups if they are RCU protected. * * It is valid to have concurrent insertions and deletions protected by per * bucket locks or concurrent RCU protected lookups and traversals. */ static int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); unsigned int nelems = atomic_read(&ht->nelems); unsigned int size = 0; if (nelems) size = roundup_pow_of_two(nelems * 3 / 2); if (size < ht->p.min_size) size = ht->p.min_size; if (old_tbl->size <= size) return 0; if (rht_dereference(old_tbl->future_tbl, ht)) return -EEXIST; return rhashtable_rehash_alloc(ht, old_tbl, size); } static void rht_deferred_worker(struct work_struct *work) { struct rhashtable *ht; struct bucket_table *tbl; int err = 0; ht = container_of(work, struct rhashtable, run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); tbl = rhashtable_last_table(ht, tbl); if (rht_grow_above_75(ht, tbl)) err = rhashtable_rehash_alloc(ht, tbl, tbl->size * 2); else if (ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl)) err = rhashtable_shrink(ht); else if (tbl->nest) err = rhashtable_rehash_alloc(ht, tbl, tbl->size); if (!err || err == -EEXIST) { int nerr; nerr = rhashtable_rehash_table(ht); err = err ?: nerr; } mutex_unlock(&ht->mutex); if (err) schedule_work(&ht->run_work); } static int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl) { struct bucket_table *old_tbl; struct bucket_table *new_tbl; unsigned int size; int err; old_tbl = rht_dereference_rcu(ht->tbl, ht); size = tbl->size; err = -EBUSY; if (rht_grow_above_75(ht, tbl)) size *= 2; /* Do not schedule more than one rehash */ else if (old_tbl != tbl) goto fail; err = -ENOMEM; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC | __GFP_NOWARN); if (new_tbl == NULL) goto fail; err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { bucket_table_free(new_tbl); if (err == -EEXIST) err = 0; } else schedule_work(&ht->run_work); return err; fail: /* Do not fail the insert if someone else did a rehash. */ if (likely(rcu_access_pointer(tbl->future_tbl))) return 0; /* Schedule async rehash to retry allocation in process context. */ if (err == -ENOMEM) schedule_work(&ht->run_work); return err; } static void *rhashtable_lookup_one(struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, const void *key, struct rhash_head *obj) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; struct rhash_head __rcu **pprev = NULL; struct rhash_head *head; int elasticity; elasticity = RHT_ELASTICITY; rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; struct rhlist_head *plist; elasticity--; if (!key || (ht->p.obj_cmpfn ? ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) : rhashtable_compare(&arg, rht_obj(ht, head)))) { pprev = &head->next; continue; } if (!ht->rhlist) return rht_obj(ht, head); list = container_of(obj, struct rhlist_head, rhead); plist = container_of(head, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); if (pprev) rcu_assign_pointer(*pprev, obj); else /* Need to preserve the bit lock */ rht_assign_locked(bkt, obj); return NULL; } if (elasticity <= 0) return ERR_PTR(-EAGAIN); return ERR_PTR(-ENOENT); } static struct bucket_table *rhashtable_insert_one( struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj, void *data) { struct bucket_table *new_tbl; struct rhash_head *head; if (!IS_ERR_OR_NULL(data)) return ERR_PTR(-EEXIST); if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT) return ERR_CAST(data); new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (new_tbl) return new_tbl; if (PTR_ERR(data) != -ENOENT) return ERR_CAST(data); if (unlikely(rht_grow_above_max(ht, tbl))) return ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_100(ht, tbl))) return ERR_PTR(-EAGAIN); head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (ht->rhlist) { struct rhlist_head *list; list = container_of(obj, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, NULL); } /* bkt is always the head of the list, so it holds * the lock, which we need to preserve */ rht_assign_locked(bkt, obj); return NULL; } static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, struct rhash_head *obj) { struct bucket_table *new_tbl; struct bucket_table *tbl; struct rhash_lock_head __rcu **bkt; unsigned long flags; unsigned int hash; void *data; new_tbl = rcu_dereference(ht->tbl); do { tbl = new_tbl; hash = rht_head_hashfn(ht, tbl, obj, ht->p); if (rcu_access_pointer(tbl->future_tbl)) /* Failure is OK */ bkt = rht_bucket_var(tbl, hash); else bkt = rht_bucket_insert(ht, tbl, hash); if (bkt == NULL) { new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { bool inserted; flags = rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, hash, obj, data); inserted = data && !new_tbl; if (inserted) atomic_inc(&ht->nelems); if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); rht_unlock(tbl, bkt, flags); if (inserted && rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); } } while (!IS_ERR_OR_NULL(new_tbl)); if (PTR_ERR(data) == -EAGAIN) data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?: -EAGAIN); return data; } void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj) { void *data; do { rcu_read_lock(); data = rhashtable_try_insert(ht, key, obj); rcu_read_unlock(); } while (PTR_ERR(data) == -EAGAIN); return data; } EXPORT_SYMBOL_GPL(rhashtable_insert_slow); /** * rhashtable_walk_enter - Initialise an iterator * @ht: Table to walk over * @iter: Hash table Iterator * * This function prepares a hash table walk. * * Note that if you restart a walk after rhashtable_walk_stop you * may see the same object twice. Also, you may miss objects if * there are removals in between rhashtable_walk_stop and the next * call to rhashtable_walk_start. * * For a completely stable walk you should construct your own data * structure outside the hash table. * * This function may be called from any process context, including * non-preemptible context, but cannot be called from softirq or * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter) { iter->ht = ht; iter->p = NULL; iter->slot = 0; iter->skip = 0; iter->end_of_table = 0; spin_lock(&ht->lock); iter->walker.tbl = rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock)); list_add(&iter->walker.list, &iter->walker.tbl->walkers); spin_unlock(&ht->lock); } EXPORT_SYMBOL_GPL(rhashtable_walk_enter); /** * rhashtable_walk_exit - Free an iterator * @iter: Hash table Iterator * * This function frees resources allocated by rhashtable_walk_enter. */ void rhashtable_walk_exit(struct rhashtable_iter *iter) { spin_lock(&iter->ht->lock); if (iter->walker.tbl) list_del(&iter->walker.list); spin_unlock(&iter->ht->lock); } EXPORT_SYMBOL_GPL(rhashtable_walk_exit); /** * rhashtable_walk_start_check - Start a hash table walk * @iter: Hash table iterator * * Start a hash table walk at the current iterator position. Note that we take * the RCU lock in all cases including when we return an error. So you must * always call rhashtable_walk_stop to clean up. * * Returns zero if successful. * * Returns -EAGAIN if resize event occurred. Note that the iterator * will rewind back to the beginning and you may use it immediately * by calling rhashtable_walk_next. * * rhashtable_walk_start is defined as an inline variant that returns * void. This is preferred in cases where the caller would ignore * resize events and always continue. */ int rhashtable_walk_start_check(struct rhashtable_iter *iter) __acquires(RCU) { struct rhashtable *ht = iter->ht; bool rhlist = ht->rhlist; rcu_read_lock(); spin_lock(&ht->lock); if (iter->walker.tbl) list_del(&iter->walker.list); spin_unlock(&ht->lock); if (iter->end_of_table) return 0; if (!iter->walker.tbl) { iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht); iter->slot = 0; iter->skip = 0; return -EAGAIN; } if (iter->p && !rhlist) { /* * We need to validate that 'p' is still in the table, and * if so, update 'skip' */ struct rhash_head *p; int skip = 0; rht_for_each_rcu(p, iter->walker.tbl, iter->slot) { skip++; if (p == iter->p) { iter->skip = skip; goto found; } } iter->p = NULL; } else if (iter->p && rhlist) { /* Need to validate that 'list' is still in the table, and * if so, update 'skip' and 'p'. */ struct rhash_head *p; struct rhlist_head *list; int skip = 0; rht_for_each_rcu(p, iter->walker.tbl, iter->slot) { for (list = container_of(p, struct rhlist_head, rhead); list; list = rcu_dereference(list->next)) { skip++; if (list == iter->list) { iter->p = p; iter->skip = skip; goto found; } } } iter->p = NULL; } found: return 0; } EXPORT_SYMBOL_GPL(rhashtable_walk_start_check); /** * __rhashtable_walk_find_next - Find the next element in a table (or the first * one in case of a new walk). * * @iter: Hash table iterator * * Returns the found object or NULL when the end of the table is reached. * * Returns -EAGAIN if resize event occurred. */ static void *__rhashtable_walk_find_next(struct rhashtable_iter *iter) { struct bucket_table *tbl = iter->walker.tbl; struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; bool rhlist = ht->rhlist; if (!tbl) return NULL; for (; iter->slot < tbl->size; iter->slot++) { int skip = iter->skip; rht_for_each_rcu(p, tbl, iter->slot) { if (rhlist) { list = container_of(p, struct rhlist_head, rhead); do { if (!skip) goto next; skip--; list = rcu_dereference(list->next); } while (list); continue; } if (!skip) break; skip--; } next: if (!rht_is_a_nulls(p)) { iter->skip++; iter->p = p; iter->list = list; return rht_obj(ht, rhlist ? &list->rhead : p); } iter->skip = 0; } iter->p = NULL; /* Ensure we see any new tables. */ smp_rmb(); iter->walker.tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (iter->walker.tbl) { iter->slot = 0; iter->skip = 0; return ERR_PTR(-EAGAIN); } else { iter->end_of_table = true; } return NULL; } /** * rhashtable_walk_next - Return the next object and advance the iterator * @iter: Hash table iterator * * Note that you must call rhashtable_walk_stop when you are finished * with the walk. * * Returns the next object or NULL when the end of the table is reached. * * Returns -EAGAIN if resize event occurred. Note that the iterator * will rewind back to the beginning and you may continue to use it. */ void *rhashtable_walk_next(struct rhashtable_iter *iter) { struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; bool rhlist = ht->rhlist; if (p) { if (!rhlist || !(list = rcu_dereference(list->next))) { p = rcu_dereference(p->next); list = container_of(p, struct rhlist_head, rhead); } if (!rht_is_a_nulls(p)) { iter->skip++; iter->p = p; iter->list = list; return rht_obj(ht, rhlist ? &list->rhead : p); } /* At the end of this slot, switch to next one and then find * next entry from that point. */ iter->skip = 0; iter->slot++; } return __rhashtable_walk_find_next(iter); } EXPORT_SYMBOL_GPL(rhashtable_walk_next); /** * rhashtable_walk_peek - Return the next object but don't advance the iterator * @iter: Hash table iterator * * Returns the next object or NULL when the end of the table is reached. * * Returns -EAGAIN if resize event occurred. Note that the iterator * will rewind back to the beginning and you may continue to use it. */ void *rhashtable_walk_peek(struct rhashtable_iter *iter) { struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; if (p) return rht_obj(ht, ht->rhlist ? &list->rhead : p); /* No object found in current iter, find next one in the table. */ if (iter->skip) { /* A nonzero skip value points to the next entry in the table * beyond that last one that was found. Decrement skip so * we find the current value. __rhashtable_walk_find_next * will restore the original value of skip assuming that * the table hasn't changed. */ iter->skip--; } return __rhashtable_walk_find_next(iter); } EXPORT_SYMBOL_GPL(rhashtable_walk_peek); /** * rhashtable_walk_stop - Finish a hash table walk * @iter: Hash table iterator * * Finish a hash table walk. Does not reset the iterator to the start of the * hash table. */ void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { struct rhashtable *ht; struct bucket_table *tbl = iter->walker.tbl; if (!tbl) goto out; ht = iter->ht; spin_lock(&ht->lock); if (rcu_head_after_call_rcu(&tbl->rcu, bucket_table_free_rcu)) /* This bucket table is being freed, don't re-link it. */ iter->walker.tbl = NULL; else list_add(&iter->walker.list, &tbl->walkers); spin_unlock(&ht->lock); out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rhashtable_walk_stop); static size_t rounded_hashtable_size(const struct rhashtable_params *params) { size_t retsize; if (params->nelem_hint) retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3), (unsigned long)params->min_size); else retsize = max(HASH_DEFAULT_SIZE, (unsigned long)params->min_size); return retsize; } static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) { return jhash2(key, length, seed); } /** * rhashtable_init - initialize a new hash table * @ht: hash table to be initialized * @params: configuration parameters * * Initializes a new hash table based on the provided configuration * parameters. A table can be configured either with a variable or * fixed length key: * * Configuration Example 1: Fixed length keys * struct test_obj { * int key; * void * my_member; * struct rhash_head node; * }; * * struct rhashtable_params params = { * .head_offset = offsetof(struct test_obj, node), * .key_offset = offsetof(struct test_obj, key), * .key_len = sizeof(int), * .hashfn = jhash, * }; * * Configuration Example 2: Variable length keys * struct test_obj { * [...] * struct rhash_head node; * }; * * u32 my_hash_fn(const void *data, u32 len, u32 seed) * { * struct test_obj *obj = data; * * return [... hash ...]; * } * * struct rhashtable_params params = { * .head_offset = offsetof(struct test_obj, node), * .hashfn = jhash, * .obj_hashfn = my_hash_fn, * }; */ int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params) { struct bucket_table *tbl; size_t size; if ((!params->key_len && !params->obj_hashfn) || (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); memcpy(&ht->p, params, sizeof(*params)); alloc_tag_record(ht->alloc_tag); if (params->min_size) ht->p.min_size = roundup_pow_of_two(params->min_size); /* Cap total entries at 2^31 to avoid nelems overflow. */ ht->max_elems = 1u << 31; if (params->max_size) { ht->p.max_size = rounddown_pow_of_two(params->max_size); if (ht->p.max_size < ht->max_elems / 2) ht->max_elems = ht->p.max_size * 2; } ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); size = rounded_hashtable_size(&ht->p); ht->key_len = ht->p.key_len; if (!params->hashfn) { ht->p.hashfn = jhash; if (!(ht->key_len & (sizeof(u32) - 1))) { ht->key_len /= sizeof(u32); ht->p.hashfn = rhashtable_jhash2; } } /* * This is api initialization and thus we need to guarantee the * initial rhashtable allocation. Upon failure, retry with the * smallest possible size with __GFP_NOFAIL semantics. */ tbl = bucket_table_alloc(ht, size, GFP_KERNEL); if (unlikely(tbl == NULL)) { size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); tbl = bucket_table_alloc(ht, size, GFP_KERNEL | __GFP_NOFAIL); } atomic_set(&ht->nelems, 0); RCU_INIT_POINTER(ht->tbl, tbl); INIT_WORK(&ht->run_work, rht_deferred_worker); return 0; } EXPORT_SYMBOL_GPL(rhashtable_init_noprof); /** * rhltable_init - initialize a new hash list table * @hlt: hash list table to be initialized * @params: configuration parameters * * Initializes a new hash list table. * * See documentation for rhashtable_init. */ int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params) { int err; err = rhashtable_init_noprof(&hlt->ht, params); hlt->ht.rhlist = true; return err; } EXPORT_SYMBOL_GPL(rhltable_init_noprof); static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, void (*free_fn)(void *ptr, void *arg), void *arg) { struct rhlist_head *list; if (!ht->rhlist) { free_fn(rht_obj(ht, obj), arg); return; } list = container_of(obj, struct rhlist_head, rhead); do { obj = &list->rhead; list = rht_dereference(list->next, ht); free_fn(rht_obj(ht, obj), arg); } while (list); } /** * rhashtable_free_and_destroy - free elements and destroy hash table * @ht: the hash table to destroy * @free_fn: callback to release resources of element * @arg: pointer passed to free_fn * * Stops an eventual async resize. If defined, invokes free_fn for each * element to releasal resources. Please note that RCU protected * readers may still be accessing the elements. Releasing of resources * must occur in a compatible manner. Then frees the bucket array. * * This function will eventually sleep to wait for an async resize * to complete. The caller is responsible that no further write operations * occurs in parallel. */ void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg) { struct bucket_table *tbl, *next_tbl; unsigned int i; cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); restart: if (free_fn) { for (i = 0; i < tbl->size; i++) { struct rhash_head *pos, *next; cond_resched(); for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)), next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; !rht_is_a_nulls(pos); pos = next, next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL) rhashtable_free_one(ht, pos, free_fn, arg); } } next_tbl = rht_dereference(tbl->future_tbl, ht); bucket_table_free(tbl); if (next_tbl) { tbl = next_tbl; goto restart; } mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); void rhashtable_destroy(struct rhashtable *ht) { return rhashtable_free_and_destroy(ht, NULL, NULL); } EXPORT_SYMBOL_GPL(rhashtable_destroy); struct rhash_lock_head __rcu **__rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; unsigned int subhash = hash; union nested_table *ntbl; ntbl = nested_table_top(tbl); ntbl = rht_dereference_bucket_rcu(ntbl[index].table, tbl, hash); subhash >>= tbl->nest; while (ntbl && size > (1 << shift)) { index = subhash & ((1 << shift) - 1); ntbl = rht_dereference_bucket_rcu(ntbl[index].table, tbl, hash); size >>= shift; subhash >>= shift; } if (!ntbl) return NULL; return &ntbl[subhash].bucket; } EXPORT_SYMBOL_GPL(__rht_bucket_nested); struct rhash_lock_head __rcu **rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash) { static struct rhash_lock_head __rcu *rhnull; if (!rhnull) INIT_RHT_NULLS_HEAD(rhnull); return __rht_bucket_nested(tbl, hash) ?: &rhnull; } EXPORT_SYMBOL_GPL(rht_bucket_nested); struct rhash_lock_head __rcu **rht_bucket_nested_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; union nested_table *ntbl; ntbl = nested_table_top(tbl); hash >>= tbl->nest; ntbl = nested_table_alloc(ht, &ntbl[index].table, size <= (1 << shift)); while (ntbl && size > (1 << shift)) { index = hash & ((1 << shift) - 1); size >>= shift; hash >>= shift; ntbl = nested_table_alloc(ht, &ntbl[index].table, size <= (1 << shift)); } if (!ntbl) return NULL; return &ntbl[hash].bucket; } EXPORT_SYMBOL_GPL(rht_bucket_nested_insert); |
| 380 887 4 78 4 472 267 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov */ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> #include <linux/gfp_types.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/math.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/xarray.h> #include <linux/local_lock.h> /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node struct radix_tree_preload { local_lock_t lock; unsigned nr; /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer * 10 - internal entry * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). * This means that storing a NULL entry in the tree is the same as deleting * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL #define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { return ((unsigned long)ptr & RADIX_TREE_ENTRY_MASK) == RADIX_TREE_INTERNAL_NODE; } /*** radix-tree API starts here ***/ #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) #define RADIX_TREE_MAX_TAGS XA_MAX_MARKS #define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) #define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->xa_head == NULL; } /** * struct radix_tree_iter - radix tree iterator state * * @index: index of current slot * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is * described by a pointer to its first slot and a struct radix_tree_iter * which holds the chunk's position in the tree and its size. For tagged * iteration radix_tree_iter also holds the slots' bit-mask for one chosen * radix tree tag. */ struct radix_tree_iter { unsigned long index; unsigned long next_index; unsigned long tags; struct radix_tree_node *node; }; /** * Radix-tree synchronization * * The radix-tree API requires that users provide all synchronisation (with * specific exceptions, noted below). * * Synchronization of access to the data items being stored in the tree, and * management of their lifetimes must be completely managed by API users. * * For API usage, in general, * - any function _modifying_ the tree or tags (inserting or deleting * items, setting or clearing tags) must exclude other modifications, and * exclude any functions reading the tree. * - any function _reading_ the tree or tags (looking up items or tags, * gang lookups) must exclude modifications to the tree, but may occur * concurrently with other readers. * * The notable exceptions to this rule are the following functions: * __radix_tree_lookup * radix_tree_lookup * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. * * It is still required that the caller manage the synchronization and lifetimes * of the items. So if RCU lock-free lookups are used, typically this would mean * that the items have their own locks, or are amenable to lock-free access; and * that the items are freed by RCU (or only freed after having been deleted from * the radix tree *and* a synchronize_rcu() grace period). * * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * * Note that the value returned by radix_tree_tag_get() may not be relied upon * if only the RCU read lock is held. Functions to set/clear tags and to * delete nodes running concurrently with it may affect its result such that * two consecutive reads in the same locked section may return different * values. If reliability is required, modification functions must also be * excluded from concurrency. * * radix_tree_tagged is able to be called without locking or RCU. */ /** * radix_tree_deref_slot - dereference a slot * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is * held (ie. items cannot be concurrently inserted). * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot(void __rcu **slot) { return rcu_dereference(*slot); } /** * radix_tree_deref_slot_protected - dereference a slot with tree lock held * @slot: slot pointer, returned by radix_tree_lookup_slot * * Similar to radix_tree_deref_slot. The caller does not hold the RCU read * lock but it must hold the tree lock to prevent parallel updates. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot * Returns: 0 if retry is not required, otherwise retry is required * * radix_tree_deref_retry must be used with radix_tree_deref_slot. */ static inline int radix_tree_deref_retry(void *arg) { return unlikely(radix_tree_is_internal_node(arg)); } /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. */ static inline int radix_tree_exception(void *arg) { return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } int radix_tree_insert(struct radix_tree_root *, unsigned long index, void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ }; /** * radix_tree_iter_init - initialize radix tree iterator * * @iter: pointer to iterator state * @start: iteration starting index * Returns: NULL */ static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* * Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it * in the case of a successful tagged chunk lookup. If the lookup was * unsuccessful or non-tagged then nobody cares about ->tags. * * Set index to zero to bypass next_index overflow protection. * See the comment in radix_tree_next_chunk() for details. */ iter->index = 0; iter->next_index = start; return NULL; } /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if there no more left * * This function looks up the next chunk in the radix tree starting from * @iter->next_index. It returns a pointer to the chunk's first slot. * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** * radix_tree_iter_lookup - look up an index in the radix tree * @root: radix tree root * @iter: iterator state * @index: key to look up * * If @index is present in the radix tree, this function returns the slot * containing it and updates @iter to describe the entry. If @index is not * present, it returns NULL. */ static inline void __rcu ** radix_tree_iter_lookup(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned long index) { radix_tree_iter_init(iter, index); return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); } /** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * * If we iterate over a tree protected only by the RCU lock, a race * against deletion or creation may result in seeing a slot for which * radix_tree_deref_retry() returns true. If so, call this function * and continue the iteration. */ static inline __must_check void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; return NULL; } static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { return iter->index + slots; } /** * radix_tree_iter_resume - resume iterating when the chunk may be invalid * @slot: pointer to current slot * @iter: iterator state * Returns: New slot pointer * * If the iterator needs to release then reacquire a lock, the chunk may * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; } /** * radix_tree_next_slot - find next slot in chunk * * @slot: pointer to current slot * @iter: pointer to iterator state * @flags: RADIX_TREE_ITER_*, should be constant * Returns: pointer to next slot, or NULL if there no more left * * This function updates @iter->index in the case of a successful lookup. * For tagged lookup it also eats @iter->tags. * * There are several cases where 'slot' can be passed in as NULL to this * function. These cases result from the use of radix_tree_iter_resume() or * radix_tree_iter_retry(). In these cases we don't end up dereferencing * 'slot' because either: * a) we are doing tagged iteration and iter->tags has been set to 0, or * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; if (unlikely(!iter->tags)) return NULL; if (likely(iter->tags & 1ul)) { iter->index = __radix_tree_iter_add(iter, 1); slot++; goto found; } if (!(flags & RADIX_TREE_ITER_CONTIG)) { unsigned offset = __ffs(iter->tags); iter->tags >>= offset++; iter->index = __radix_tree_iter_add(iter, offset); slot += offset; goto found; } } else { long count = radix_tree_chunk_size(iter); while (--count > 0) { slot++; iter->index = __radix_tree_iter_add(iter, 1); if (likely(*slot)) goto found; if (flags & RADIX_TREE_ITER_CONTIG) { /* forbid switching to the next chunk */ iter->next_index = 0; break; } } } return NULL; found: return slot; } /** * radix_tree_for_each_slot - iterate over non-empty slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_slot(slot, root, iter, start) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) /** * radix_tree_for_each_tagged - iterate over tagged slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * @tag: tag index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_tagged(slot, root, iter, start, tag) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, \ RADIX_TREE_ITER_TAGGED | tag)) ; \ slot = radix_tree_next_slot(slot, iter, \ RADIX_TREE_ITER_TAGGED | tag)) #endif /* _LINUX_RADIX_TREE_H */ |
| 2162 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_alloc_contig_migrate_range_info, TP_PROTO(unsigned long start, unsigned long end, unsigned long nr_migrated, unsigned long nr_reclaimed, unsigned long nr_mapped, int migratetype), TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned long, nr_migrated) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_mapped) __field(int, migratetype) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->nr_migrated = nr_migrated; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_mapped = nr_mapped; __entry->migratetype = migratetype; ), TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", __entry->start, __entry->end, __entry->migratetype, __entry->nr_migrated, __entry->nr_reclaimed, __entry->nr_mapped) ); TRACE_EVENT(mm_setup_per_zone_wmarks, TP_PROTO(struct zone *zone), TP_ARGS(zone), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __field(unsigned long, watermark_min) __field(unsigned long, watermark_low) __field(unsigned long, watermark_high) __field(unsigned long, watermark_promo) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __entry->watermark_min = zone->_watermark[WMARK_MIN]; __entry->watermark_low = zone->_watermark[WMARK_LOW]; __entry->watermark_high = zone->_watermark[WMARK_HIGH]; __entry->watermark_promo = zone->_watermark[WMARK_PROMO]; ), TP_printk("node_id=%d zone name=%s watermark min=%lu low=%lu high=%lu promo=%lu", __entry->node_id, __get_str(name), __entry->watermark_min, __entry->watermark_low, __entry->watermark_high, __entry->watermark_promo) ); TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), TP_ARGS(zone, upper_zone, lowmem_reserve), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __string(upper_name, upper_zone->name) __field(long, lowmem_reserve) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __assign_str(upper_name); __entry->lowmem_reserve = lowmem_reserve; ), TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", __entry->node_id, __get_str(name), __get_str(upper_name), __entry->lowmem_reserve) ); TRACE_EVENT(mm_calculate_totalreserve_pages, TP_PROTO(unsigned long totalreserve_pages), TP_ARGS(totalreserve_pages), TP_STRUCT__entry( __field(unsigned long, totalreserve_pages) ), TP_fast_assign( __entry->totalreserve_pages = totalreserve_pages; ), TP_printk("totalreserve_pages=%lu", __entry->totalreserve_pages) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 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 | /* * Copyright (c) 2006,2007 The Regents of the University of Michigan. * All rights reserved. * * Andy Adamson <andros@citi.umich.edu> * Fred Isaman <iisaman@umich.edu> * * permission is granted to use, copy, create derivative works and * redistribute this software and such derivative works for any purpose, * so long as the name of the university of michigan is not used in * any advertising or publicity pertaining to the use or distribution * of this software without specific, written prior authorization. if * the above copyright notice or any other identification of the * university of michigan is included in any copy of any portion of * this software, then the disclaimer below must also be included. * * this software is provided as is, without representation from the * university of michigan as to its fitness for any purpose, and without * warranty by the university of michigan of any kind, either express * or implied, including without limitation the implied warranties of * merchantability and fitness for a particular purpose. the regents * of the university of michigan shall not be liable for any damages, * including special, indirect, incidental, or consequential damages, * with respect to any claim arising out or in connection with the use * of the software, even if it has been or is hereafter advised of the * possibility of such damages. */ #include <linux/module.h> #include <linux/blkdev.h> #include "blocklayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD static void nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b) { int i; *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(b->type); *p++ = cpu_to_be32(b->simple.nr_sigs); for (i = 0; i < b->simple.nr_sigs; i++) { p = xdr_encode_hyper(p, b->simple.sigs[i].offset); p = xdr_encode_opaque(p, b->simple.sigs[i].sig, b->simple.sigs[i].sig_len); } } dev_t bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, gfp_t gfp_mask) { struct net *net = server->nfs_client->cl_net; struct nfs_net *nn = net_generic(net, nfs_net_id); struct bl_dev_msg *reply = &nn->bl_mount_reply; struct bl_pipe_msg bl_pipe_msg; struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; struct bl_msg_hdr *bl_msg; DECLARE_WAITQUEUE(wq, current); dev_t dev = 0; int rc; dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); mutex_lock(&nn->bl_mutex); bl_pipe_msg.bl_wq = &nn->bl_wq; b->simple.len += 4; /* single volume */ if (b->simple.len > PAGE_SIZE) goto out_unlock; memset(msg, 0, sizeof(*msg)); msg->len = sizeof(*bl_msg) + b->simple.len; msg->data = kzalloc(msg->len, gfp_mask); if (!msg->data) goto out_unlock; bl_msg = msg->data; bl_msg->type = BL_DEVICE_MOUNT; bl_msg->totallen = b->simple.len; nfs4_encode_simple(msg->data + sizeof(*bl_msg), b); dprintk("%s CALLING USERSPACE DAEMON\n", __func__); add_wait_queue(&nn->bl_wq, &wq); rc = rpc_queue_upcall(nn->bl_device_pipe, msg); if (rc < 0) { remove_wait_queue(&nn->bl_wq, &wq); goto out_free_data; } set_current_state(TASK_UNINTERRUPTIBLE); schedule(); remove_wait_queue(&nn->bl_wq, &wq); if (reply->status != BL_DEVICE_REQUEST_PROC) { printk(KERN_WARNING "%s failed to decode device: %d\n", __func__, reply->status); goto out_free_data; } dev = MKDEV(reply->major, reply->minor); out_free_data: kfree(msg->data); out_unlock: mutex_unlock(&nn->bl_mutex); return dev; } static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct nfs_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfs_net_id); if (mlen != sizeof (struct bl_dev_msg)) return -EINVAL; if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0) return -EFAULT; wake_up(&nn->bl_wq); return mlen; } static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) { struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg); if (msg->errno >= 0) return; wake_up(bl_pipe_msg->bl_wq); } static const struct rpc_pipe_ops bl_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = bl_pipe_downcall, .destroy_msg = bl_pipe_destroy_msg, }; static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb, struct rpc_pipe *pipe) { struct dentry *dir, *dentry; dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME); if (dir == NULL) return ERR_PTR(-ENOENT); dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe); dput(dir); return dentry; } static void nfs4blocklayout_unregister_sb(struct super_block *sb, struct rpc_pipe *pipe) { if (pipe->dentry) rpc_unlink(pipe->dentry); } static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct super_block *sb = ptr; struct net *net = sb->s_fs_info; struct nfs_net *nn = net_generic(net, nfs_net_id); struct dentry *dentry; int ret = 0; if (!try_module_get(THIS_MODULE)) return 0; if (nn->bl_device_pipe == NULL) { module_put(THIS_MODULE); return 0; } switch (event) { case RPC_PIPEFS_MOUNT: dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); break; } nn->bl_device_pipe->dentry = dentry; break; case RPC_PIPEFS_UMOUNT: if (nn->bl_device_pipe->dentry) nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe); break; default: ret = -ENOTSUPP; break; } module_put(THIS_MODULE); return ret; } static struct notifier_block nfs4blocklayout_block = { .notifier_call = rpc_pipefs_event, }; static struct dentry *nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *pipefs_sb; struct dentry *dentry; pipefs_sb = rpc_get_sb_net(net); if (!pipefs_sb) return NULL; dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe); rpc_put_sb_net(net); return dentry; } static void nfs4blocklayout_unregister_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { nfs4blocklayout_unregister_sb(pipefs_sb, pipe); rpc_put_sb_net(net); } } static int nfs4blocklayout_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); struct dentry *dentry; mutex_init(&nn->bl_mutex); init_waitqueue_head(&nn->bl_wq); nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); if (IS_ERR(nn->bl_device_pipe)) return PTR_ERR(nn->bl_device_pipe); dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe); if (IS_ERR(dentry)) { rpc_destroy_pipe_data(nn->bl_device_pipe); return PTR_ERR(dentry); } nn->bl_device_pipe->dentry = dentry; return 0; } static void nfs4blocklayout_net_exit(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); nfs4blocklayout_unregister_net(net, nn->bl_device_pipe); rpc_destroy_pipe_data(nn->bl_device_pipe); nn->bl_device_pipe = NULL; } static struct pernet_operations nfs4blocklayout_net_ops = { .init = nfs4blocklayout_net_init, .exit = nfs4blocklayout_net_exit, }; int __init bl_init_pipefs(void) { int ret; ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block); if (ret) goto out; ret = register_pernet_subsys(&nfs4blocklayout_net_ops); if (ret) goto out_unregister_notifier; return 0; out_unregister_notifier: rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); out: return ret; } void bl_cleanup_pipefs(void) { rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); unregister_pernet_subsys(&nfs4blocklayout_net_ops); } |
| 11 9 11 11 11 56 56 56 56 56 56 50 50 49 50 50 50 49 1 50 50 50 50 50 | 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 | /* * xxHash - Extremely Fast Hash algorithm * Copyright (C) 2012-2016, Yann Collet. * * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) * * 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. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * This program is free software; you can redistribute it and/or modify it under * the terms of the GNU General Public License version 2 as published by the * Free Software Foundation. This program is dual-licensed; you may select * either version 2 of the GNU General Public License ("GPL") or BSD license * ("BSD"). * * You can contact the author at: * - xxHash homepage: https://cyan4973.github.io/xxHash/ * - xxHash source repository: https://github.com/Cyan4973/xxHash */ #include <linux/unaligned.h> #include <linux/errno.h> #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/string.h> #include <linux/xxhash.h> /*-************************************* * Macros **************************************/ #define xxh_rotl32(x, r) ((x << r) | (x >> (32 - r))) #define xxh_rotl64(x, r) ((x << r) | (x >> (64 - r))) #ifdef __LITTLE_ENDIAN # define XXH_CPU_LITTLE_ENDIAN 1 #else # define XXH_CPU_LITTLE_ENDIAN 0 #endif /*-************************************* * Constants **************************************/ static const uint32_t PRIME32_1 = 2654435761U; static const uint32_t PRIME32_2 = 2246822519U; static const uint32_t PRIME32_3 = 3266489917U; static const uint32_t PRIME32_4 = 668265263U; static const uint32_t PRIME32_5 = 374761393U; static const uint64_t PRIME64_1 = 11400714785074694791ULL; static const uint64_t PRIME64_2 = 14029467366897019727ULL; static const uint64_t PRIME64_3 = 1609587929392839161ULL; static const uint64_t PRIME64_4 = 9650029242287828579ULL; static const uint64_t PRIME64_5 = 2870177450012600261ULL; /*-************************** * Utils ***************************/ void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src) { memcpy(dst, src, sizeof(*dst)); } EXPORT_SYMBOL(xxh32_copy_state); void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src) { memcpy(dst, src, sizeof(*dst)); } EXPORT_SYMBOL(xxh64_copy_state); /*-*************************** * Simple Hash Functions ****************************/ static uint32_t xxh32_round(uint32_t seed, const uint32_t input) { seed += input * PRIME32_2; seed = xxh_rotl32(seed, 13); seed *= PRIME32_1; return seed; } uint32_t xxh32(const void *input, const size_t len, const uint32_t seed) { const uint8_t *p = (const uint8_t *)input; const uint8_t *b_end = p + len; uint32_t h32; if (len >= 16) { const uint8_t *const limit = b_end - 16; uint32_t v1 = seed + PRIME32_1 + PRIME32_2; uint32_t v2 = seed + PRIME32_2; uint32_t v3 = seed + 0; uint32_t v4 = seed - PRIME32_1; do { v1 = xxh32_round(v1, get_unaligned_le32(p)); p += 4; v2 = xxh32_round(v2, get_unaligned_le32(p)); p += 4; v3 = xxh32_round(v3, get_unaligned_le32(p)); p += 4; v4 = xxh32_round(v4, get_unaligned_le32(p)); p += 4; } while (p <= limit); h32 = xxh_rotl32(v1, 1) + xxh_rotl32(v2, 7) + xxh_rotl32(v3, 12) + xxh_rotl32(v4, 18); } else { h32 = seed + PRIME32_5; } h32 += (uint32_t)len; while (p + 4 <= b_end) { h32 += get_unaligned_le32(p) * PRIME32_3; h32 = xxh_rotl32(h32, 17) * PRIME32_4; p += 4; } while (p < b_end) { h32 += (*p) * PRIME32_5; h32 = xxh_rotl32(h32, 11) * PRIME32_1; p++; } h32 ^= h32 >> 15; h32 *= PRIME32_2; h32 ^= h32 >> 13; h32 *= PRIME32_3; h32 ^= h32 >> 16; return h32; } EXPORT_SYMBOL(xxh32); static uint64_t xxh64_round(uint64_t acc, const uint64_t input) { acc += input * PRIME64_2; acc = xxh_rotl64(acc, 31); acc *= PRIME64_1; return acc; } static uint64_t xxh64_merge_round(uint64_t acc, uint64_t val) { val = xxh64_round(0, val); acc ^= val; acc = acc * PRIME64_1 + PRIME64_4; return acc; } uint64_t xxh64(const void *input, const size_t len, const uint64_t seed) { const uint8_t *p = (const uint8_t *)input; const uint8_t *const b_end = p + len; uint64_t h64; if (len >= 32) { const uint8_t *const limit = b_end - 32; uint64_t v1 = seed + PRIME64_1 + PRIME64_2; uint64_t v2 = seed + PRIME64_2; uint64_t v3 = seed + 0; uint64_t v4 = seed - PRIME64_1; do { v1 = xxh64_round(v1, get_unaligned_le64(p)); p += 8; v2 = xxh64_round(v2, get_unaligned_le64(p)); p += 8; v3 = xxh64_round(v3, get_unaligned_le64(p)); p += 8; v4 = xxh64_round(v4, get_unaligned_le64(p)); p += 8; } while (p <= limit); h64 = xxh_rotl64(v1, 1) + xxh_rotl64(v2, 7) + xxh_rotl64(v3, 12) + xxh_rotl64(v4, 18); h64 = xxh64_merge_round(h64, v1); h64 = xxh64_merge_round(h64, v2); h64 = xxh64_merge_round(h64, v3); h64 = xxh64_merge_round(h64, v4); } else { h64 = seed + PRIME64_5; } h64 += (uint64_t)len; while (p + 8 <= b_end) { const uint64_t k1 = xxh64_round(0, get_unaligned_le64(p)); h64 ^= k1; h64 = xxh_rotl64(h64, 27) * PRIME64_1 + PRIME64_4; p += 8; } if (p + 4 <= b_end) { h64 ^= (uint64_t)(get_unaligned_le32(p)) * PRIME64_1; h64 = xxh_rotl64(h64, 23) * PRIME64_2 + PRIME64_3; p += 4; } while (p < b_end) { h64 ^= (*p) * PRIME64_5; h64 = xxh_rotl64(h64, 11) * PRIME64_1; p++; } h64 ^= h64 >> 33; h64 *= PRIME64_2; h64 ^= h64 >> 29; h64 *= PRIME64_3; h64 ^= h64 >> 32; return h64; } EXPORT_SYMBOL(xxh64); /*-************************************************** * Advanced Hash Functions ***************************************************/ void xxh32_reset(struct xxh32_state *statePtr, const uint32_t seed) { /* use a local state for memcpy() to avoid strict-aliasing warnings */ struct xxh32_state state; memset(&state, 0, sizeof(state)); state.v1 = seed + PRIME32_1 + PRIME32_2; state.v2 = seed + PRIME32_2; state.v3 = seed + 0; state.v4 = seed - PRIME32_1; memcpy(statePtr, &state, sizeof(state)); } EXPORT_SYMBOL(xxh32_reset); void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) { /* use a local state for memcpy() to avoid strict-aliasing warnings */ struct xxh64_state state; memset(&state, 0, sizeof(state)); state.v1 = seed + PRIME64_1 + PRIME64_2; state.v2 = seed + PRIME64_2; state.v3 = seed + 0; state.v4 = seed - PRIME64_1; memcpy(statePtr, &state, sizeof(state)); } EXPORT_SYMBOL(xxh64_reset); int xxh32_update(struct xxh32_state *state, const void *input, const size_t len) { const uint8_t *p = (const uint8_t *)input; const uint8_t *const b_end = p + len; if (input == NULL) return -EINVAL; state->total_len_32 += (uint32_t)len; state->large_len |= (len >= 16) | (state->total_len_32 >= 16); if (state->memsize + len < 16) { /* fill in tmp buffer */ memcpy((uint8_t *)(state->mem32) + state->memsize, input, len); state->memsize += (uint32_t)len; return 0; } if (state->memsize) { /* some data left from previous update */ const uint32_t *p32 = state->mem32; memcpy((uint8_t *)(state->mem32) + state->memsize, input, 16 - state->memsize); state->v1 = xxh32_round(state->v1, get_unaligned_le32(p32)); p32++; state->v2 = xxh32_round(state->v2, get_unaligned_le32(p32)); p32++; state->v3 = xxh32_round(state->v3, get_unaligned_le32(p32)); p32++; state->v4 = xxh32_round(state->v4, get_unaligned_le32(p32)); p32++; p += 16-state->memsize; state->memsize = 0; } if (p <= b_end - 16) { const uint8_t *const limit = b_end - 16; uint32_t v1 = state->v1; uint32_t v2 = state->v2; uint32_t v3 = state->v3; uint32_t v4 = state->v4; do { v1 = xxh32_round(v1, get_unaligned_le32(p)); p += 4; v2 = xxh32_round(v2, get_unaligned_le32(p)); p += 4; v3 = xxh32_round(v3, get_unaligned_le32(p)); p += 4; v4 = xxh32_round(v4, get_unaligned_le32(p)); p += 4; } while (p <= limit); state->v1 = v1; state->v2 = v2; state->v3 = v3; state->v4 = v4; } if (p < b_end) { memcpy(state->mem32, p, (size_t)(b_end-p)); state->memsize = (uint32_t)(b_end-p); } return 0; } EXPORT_SYMBOL(xxh32_update); uint32_t xxh32_digest(const struct xxh32_state *state) { const uint8_t *p = (const uint8_t *)state->mem32; const uint8_t *const b_end = (const uint8_t *)(state->mem32) + state->memsize; uint32_t h32; if (state->large_len) { h32 = xxh_rotl32(state->v1, 1) + xxh_rotl32(state->v2, 7) + xxh_rotl32(state->v3, 12) + xxh_rotl32(state->v4, 18); } else { h32 = state->v3 /* == seed */ + PRIME32_5; } h32 += state->total_len_32; while (p + 4 <= b_end) { h32 += get_unaligned_le32(p) * PRIME32_3; h32 = xxh_rotl32(h32, 17) * PRIME32_4; p += 4; } while (p < b_end) { h32 += (*p) * PRIME32_5; h32 = xxh_rotl32(h32, 11) * PRIME32_1; p++; } h32 ^= h32 >> 15; h32 *= PRIME32_2; h32 ^= h32 >> 13; h32 *= PRIME32_3; h32 ^= h32 >> 16; return h32; } EXPORT_SYMBOL(xxh32_digest); int xxh64_update(struct xxh64_state *state, const void *input, const size_t len) { const uint8_t *p = (const uint8_t *)input; const uint8_t *const b_end = p + len; if (input == NULL) return -EINVAL; state->total_len += len; if (state->memsize + len < 32) { /* fill in tmp buffer */ memcpy(((uint8_t *)state->mem64) + state->memsize, input, len); state->memsize += (uint32_t)len; return 0; } if (state->memsize) { /* tmp buffer is full */ uint64_t *p64 = state->mem64; memcpy(((uint8_t *)p64) + state->memsize, input, 32 - state->memsize); state->v1 = xxh64_round(state->v1, get_unaligned_le64(p64)); p64++; state->v2 = xxh64_round(state->v2, get_unaligned_le64(p64)); p64++; state->v3 = xxh64_round(state->v3, get_unaligned_le64(p64)); p64++; state->v4 = xxh64_round(state->v4, get_unaligned_le64(p64)); p += 32 - state->memsize; state->memsize = 0; } if (p + 32 <= b_end) { const uint8_t *const limit = b_end - 32; uint64_t v1 = state->v1; uint64_t v2 = state->v2; uint64_t v3 = state->v3; uint64_t v4 = state->v4; do { v1 = xxh64_round(v1, get_unaligned_le64(p)); p += 8; v2 = xxh64_round(v2, get_unaligned_le64(p)); p += 8; v3 = xxh64_round(v3, get_unaligned_le64(p)); p += 8; v4 = xxh64_round(v4, get_unaligned_le64(p)); p += 8; } while (p <= limit); state->v1 = v1; state->v2 = v2; state->v3 = v3; state->v4 = v4; } if (p < b_end) { memcpy(state->mem64, p, (size_t)(b_end-p)); state->memsize = (uint32_t)(b_end - p); } return 0; } EXPORT_SYMBOL(xxh64_update); uint64_t xxh64_digest(const struct xxh64_state *state) { const uint8_t *p = (const uint8_t *)state->mem64; const uint8_t *const b_end = (const uint8_t *)state->mem64 + state->memsize; uint64_t h64; if (state->total_len >= 32) { const uint64_t v1 = state->v1; const uint64_t v2 = state->v2; const uint64_t v3 = state->v3; const uint64_t v4 = state->v4; h64 = xxh_rotl64(v1, 1) + xxh_rotl64(v2, 7) + xxh_rotl64(v3, 12) + xxh_rotl64(v4, 18); h64 = xxh64_merge_round(h64, v1); h64 = xxh64_merge_round(h64, v2); h64 = xxh64_merge_round(h64, v3); h64 = xxh64_merge_round(h64, v4); } else { h64 = state->v3 + PRIME64_5; } h64 += (uint64_t)state->total_len; while (p + 8 <= b_end) { const uint64_t k1 = xxh64_round(0, get_unaligned_le64(p)); h64 ^= k1; h64 = xxh_rotl64(h64, 27) * PRIME64_1 + PRIME64_4; p += 8; } if (p + 4 <= b_end) { h64 ^= (uint64_t)(get_unaligned_le32(p)) * PRIME64_1; h64 = xxh_rotl64(h64, 23) * PRIME64_2 + PRIME64_3; p += 4; } while (p < b_end) { h64 ^= (*p) * PRIME64_5; h64 = xxh_rotl64(h64, 11) * PRIME64_1; p++; } h64 ^= h64 >> 33; h64 *= PRIME64_2; h64 ^= h64 >> 29; h64 *= PRIME64_3; h64 ^= h64 >> 32; return h64; } EXPORT_SYMBOL(xxh64_digest); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("xxHash"); |
| 2 2 5746 17 5733 14 5732 5738 5739 5741 44 43 5 42 42 42 5740 182 181 23 23 23 23 23 1 2 3 15 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Tag allocation using scalable bitmaps. Uses active queue tracking to support * fairer distribution of tags between multiple submitters when a shared tag map * is used. * * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" /* * Recalculate wakeup batch when tag is shared by hctx. */ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, unsigned int users) { if (!users) return; sbitmap_queue_recalculate_wake_batch(&tags->bitmap_tags, users); sbitmap_queue_recalculate_wake_batch(&tags->breserved_tags, users); } /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail * to get tag when first time, the other shared-tag users could reserve * budget for it. */ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; unsigned long flags; struct blk_mq_tags *tags = hctx->tags; /* * calling test_bit() prior to test_and_set_bit() is intentional, * it avoids dirtying the cacheline if the queue is already active. */ if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; } else { if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; } spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); spin_unlock_irqrestore(&tags->lock, flags); } /* * Wakeup all potentially sleeping on tags */ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) { sbitmap_queue_wake_all(&tags->bitmap_tags); if (include_reserve) sbitmap_queue_wake_all(&tags->breserved_tags); } /* * If a previously busy queue goes inactive, potential waiters could now * be allowed to queue. Wake them up and check. */ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; unsigned int users; if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; } else { if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; } spin_lock_irq(&tags->lock); users = tags->active_queues - 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); spin_unlock_irq(&tags->lock); blk_mq_tag_wakeup_all(tags, false); } static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { if (!data->q->elevator && !(data->flags & BLK_MQ_REQ_RESERVED) && !hctx_may_queue(data->hctx, bt)) return BLK_MQ_NO_TAG; if (data->shallow_depth) return sbitmap_queue_get_shallow(bt, data->shallow_depth); else return __sbitmap_queue_get(bt); } unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, unsigned int *offset) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt = &tags->bitmap_tags; unsigned long ret; if (data->shallow_depth ||data->flags & BLK_MQ_REQ_RESERVED || data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) return 0; ret = __sbitmap_queue_get_batch(bt, nr_tags, offset); *offset += tags->nr_reserved_tags; return ret; } unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt; struct sbq_wait_state *ws; DEFINE_SBQ_WAIT(wait); unsigned int tag_offset; int tag; if (data->flags & BLK_MQ_REQ_RESERVED) { if (unlikely(!tags->nr_reserved_tags)) { WARN_ON_ONCE(1); return BLK_MQ_NO_TAG; } bt = &tags->breserved_tags; tag_offset = 0; } else { bt = &tags->bitmap_tags; tag_offset = tags->nr_reserved_tags; } tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) goto found_tag; if (data->flags & BLK_MQ_REQ_NOWAIT) return BLK_MQ_NO_TAG; ws = bt_wait_ptr(bt, data->hctx); do { struct sbitmap_queue *bt_prev; /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for * some to complete. */ blk_mq_run_hw_queue(data->hctx, false); /* * Retry tag allocation after running the hardware queue, * as running the queue may also have found completions. */ tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE); tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; bt_prev = bt; io_schedule(); sbitmap_finish_wait(bt, ws, &wait); data->ctx = blk_mq_get_ctx(data->q); data->hctx = blk_mq_map_queue(data->cmd_flags, data->ctx); tags = blk_mq_tags_from_data(data); if (data->flags & BLK_MQ_REQ_RESERVED) bt = &tags->breserved_tags; else bt = &tags->bitmap_tags; /* * If destination hw queue is changed, fake wake up on * previous queue for compensating the wake up miss, so * other allocations on previous queue won't be starved. */ if (bt != bt_prev) sbitmap_queue_wake_up(bt_prev, 1); ws = bt_wait_ptr(bt, data->hctx); } while (1); sbitmap_finish_wait(bt, ws, &wait); found_tag: /* * Give up this allocation if the hctx is inactive. The caller will * retry on an active hctx. */ if (unlikely(test_bit(BLK_MQ_S_INACTIVE, &data->hctx->state))) { blk_mq_put_tag(tags, data->ctx, tag + tag_offset); return BLK_MQ_NO_TAG; } return tag + tag_offset; } void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag) { if (!blk_mq_tag_is_reserved(tags, tag)) { const int real_tag = tag - tags->nr_reserved_tags; BUG_ON(real_tag >= tags->nr_tags); sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu); } else { sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu); } } void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags) { sbitmap_queue_clear_batch(&tags->bitmap_tags, tags->nr_reserved_tags, tag_array, nr_tags); } struct bt_iter_data { struct blk_mq_hw_ctx *hctx; struct request_queue *q; busy_tag_iter_fn *fn; void *data; bool reserved; }; static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, unsigned int bitnr) { struct request *rq; unsigned long flags; spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; } static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; struct blk_mq_hw_ctx *hctx = iter_data->hctx; struct request_queue *q = iter_data->q; struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_tags *tags; struct request *rq; bool ret = true; if (blk_mq_is_shared_tags(set->flags)) tags = set->shared_tags; else tags = hctx->tags; if (!iter_data->reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (rq->q == q && (!hctx || rq->mq_hctx == hctx)) ret = iter_data->fn(rq, iter_data->data); blk_mq_put_rq_ref(rq); return ret; } /** * bt_for_each - iterate over the requests associated with a hardware queue * @hctx: Hardware queue to examine. * @q: Request queue to examine. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each request * associated with @hctx that has been assigned a driver tag. * @fn will be called as follows: @fn(@hctx, rq, @data, @reserved) * where rq is a pointer to a request. Return true to continue * iterating tags, false to stop. * @data: Will be passed as third argument to @fn. * @reserved: Indicates whether @bt is the breserved_tags member or the * bitmap_tags member of struct blk_mq_tags. */ static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct request_queue *q, struct sbitmap_queue *bt, busy_tag_iter_fn *fn, void *data, bool reserved) { struct bt_iter_data iter_data = { .hctx = hctx, .fn = fn, .data = data, .reserved = reserved, .q = q, }; sbitmap_for_each_set(&bt->sb, bt_iter, &iter_data); } struct bt_tags_iter_data { struct blk_mq_tags *tags; busy_tag_iter_fn *fn; void *data; unsigned int flags; }; #define BT_TAG_ITER_RESERVED (1 << 0) #define BT_TAG_ITER_STARTED (1 << 1) #define BT_TAG_ITER_STATIC_RQS (1 << 2) static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_tags_iter_data *iter_data = data; struct blk_mq_tags *tags = iter_data->tags; struct request *rq; bool ret = true; bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!(iter_data->flags & BT_TAG_ITER_RESERVED)) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (!(iter_data->flags & BT_TAG_ITER_STARTED) || blk_mq_request_started(rq)) ret = iter_data->fn(rq, iter_data->data); if (!iter_static_rqs) blk_mq_put_rq_ref(rq); return ret; } /** * bt_tags_for_each - iterate over the requests in a tag map * @tags: Tag map to iterate over. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @data, * @reserved) where rq is a pointer to a request. Return true * to continue iterating tags, false to stop. * @data: Will be passed as second argument to @fn. * @flags: BT_TAG_ITER_* */ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt, busy_tag_iter_fn *fn, void *data, unsigned int flags) { struct bt_tags_iter_data iter_data = { .tags = tags, .fn = fn, .data = data, .flags = flags, }; if (tags->rqs) sbitmap_for_each_set(&bt->sb, bt_tags_iter, &iter_data); } static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv, unsigned int flags) { WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED); if (tags->nr_reserved_tags) bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, flags | BT_TAG_ITER_RESERVED); bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags); } /** * blk_mq_all_tag_iter - iterate over all requests in a tag map * @tags: Tag map to iterate over. * @fn: Pointer to the function that will be called for each * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * Caller has to pass the tag map from which requests are allocated. */ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv) { __blk_mq_all_tag_iter(tags, fn, priv, BT_TAG_ITER_STATIC_RQS); } /** * blk_mq_tagset_busy_iter - iterate over all started requests in a tag set * @tagset: Tag set to iterate over. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * We grab one request reference before calling @fn and release it after * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) { unsigned int flags = tagset->flags; int i, nr_tags; nr_tags = blk_mq_is_shared_tags(flags) ? 1 : tagset->nr_hw_queues; for (i = 0; i < nr_tags; i++) { if (tagset->tags && tagset->tags[i]) __blk_mq_all_tag_iter(tagset->tags[i], fn, priv, BT_TAG_ITER_STARTED); } } EXPORT_SYMBOL(blk_mq_tagset_busy_iter); static bool blk_mq_tagset_count_completed_rqs(struct request *rq, void *data) { unsigned *count = data; if (blk_mq_request_completed(rq)) (*count)++; return true; } /** * blk_mq_tagset_wait_completed_request - Wait until all scheduled request * completions have finished. * @tagset: Tag set to drain completed request * * Note: This function has to be run after all IO queues are shutdown */ void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset) { while (true) { unsigned count = 0; blk_mq_tagset_busy_iter(tagset, blk_mq_tagset_count_completed_rqs, &count); if (!count) break; msleep(5); } } EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request); /** * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag * @q: Request queue to examine. * @fn: Pointer to the function that will be called for each request * on @q. @fn will be called as follows: @fn(hctx, rq, @priv, * reserved) where rq is a pointer to a request and hctx points * to the hardware queue associated with the request. 'reserved' * indicates whether or not @rq is a reserved request. * @priv: Will be passed as third argument to @fn. * * Note: if @q->tag_set is shared with other request queues then @fn will be * called for all requests on all queues that share that tag set and not only * for requests associated with @q. */ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, void *priv) { /* * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and hctx_table * while the queue is frozen. So we can use q_usage_counter to avoid * racing with it. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; if (blk_mq_is_shared_tags(q->tag_set->flags)) { struct blk_mq_tags *tags = q->tag_set->shared_tags; struct sbitmap_queue *bresv = &tags->breserved_tags; struct sbitmap_queue *btags = &tags->bitmap_tags; if (tags->nr_reserved_tags) bt_for_each(NULL, q, bresv, fn, priv, true); bt_for_each(NULL, q, btags, fn, priv, false); } else { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { struct blk_mq_tags *tags = hctx->tags; struct sbitmap_queue *bresv = &tags->breserved_tags; struct sbitmap_queue *btags = &tags->bitmap_tags; /* * If no software queues are currently mapped to this * hardware queue, there's nothing to check */ if (!blk_mq_hw_queue_mapped(hctx)) continue; if (tags->nr_reserved_tags) bt_for_each(hctx, q, bresv, fn, priv, true); bt_for_each(hctx, q, btags, fn, priv, false); } } blk_queue_exit(q); } static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, bool round_robin, int node) { return sbitmap_queue_init_node(bt, depth, -1, round_robin, GFP_KERNEL, node); } struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, unsigned int flags, int node) { unsigned int depth = total_tags - reserved_tags; bool round_robin = flags & BLK_MQ_F_TAG_RR; struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { pr_err("blk-mq: tag depth too large\n"); return NULL; } tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node); if (!tags) return NULL; tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; spin_lock_init(&tags->lock); if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node)) goto out_free_tags; if (bt_alloc(&tags->breserved_tags, reserved_tags, round_robin, node)) goto out_free_bitmap_tags; return tags; out_free_bitmap_tags: sbitmap_queue_free(&tags->bitmap_tags); out_free_tags: kfree(tags); return NULL; } void blk_mq_free_tags(struct blk_mq_tags *tags) { sbitmap_queue_free(&tags->bitmap_tags); sbitmap_queue_free(&tags->breserved_tags); kfree(tags); } int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tagsptr, unsigned int tdepth, bool can_grow) { struct blk_mq_tags *tags = *tagsptr; if (tdepth <= tags->nr_reserved_tags) return -EINVAL; /* * If we are allowed to grow beyond the original size, allocate * a new set of tags before freeing the old one. */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; struct blk_mq_tags *new; if (!can_grow) return -EINVAL; /* * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ if (tdepth > MAX_SCHED_RQ) return -EINVAL; /* * Only the sbitmap needs resizing since we allocated the max * initially. */ if (blk_mq_is_shared_tags(set->flags)) return 0; new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth); if (!new) return -ENOMEM; blk_mq_free_map_and_rqs(set, *tagsptr, hctx->queue_num); *tagsptr = new; } else { /* * Don't need (or can't) update reserved tags here, they * remain static and should never need resizing. */ sbitmap_queue_resize(&tags->bitmap_tags, tdepth - tags->nr_reserved_tags); } return 0; } void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size) { struct blk_mq_tags *tags = set->shared_tags; sbitmap_queue_resize(&tags->bitmap_tags, size - set->reserved_tags); } void blk_mq_tag_update_sched_shared_tags(struct request_queue *q) { sbitmap_queue_resize(&q->sched_shared_tags->bitmap_tags, q->nr_requests - q->tag_set->reserved_tags); } /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag * * The tag field in struct request is unique per hardware queue but not over * all hardware queues. Hence this function that returns a tag with the * hardware context index in the upper bits and the per hardware queue tag in * the lower bits. * * Note: When called for a request that is queued on a non-multiqueue request * queue, the hardware context index is set to zero. */ u32 blk_mq_unique_tag(struct request *rq) { return (rq->mq_hctx->queue_num << BLK_MQ_UNIQUE_TAG_BITS) | (rq->tag & BLK_MQ_UNIQUE_TAG_MASK); } EXPORT_SYMBOL(blk_mq_unique_tag); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles path walking and related routines * * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/fs.h> #include <linux/namei.h> #include "internal.h" /* * Mark the backing file as being a cache file if it's not already in use. The * mark tells the culling request command that it's not allowed to cull the * file or directory. The caller must hold the inode lock. */ static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object, struct inode *inode) { bool can_use = false; if (!(inode->i_flags & S_KERNEL_FILE)) { inode->i_flags |= S_KERNEL_FILE; trace_cachefiles_mark_active(object, inode); can_use = true; } else { trace_cachefiles_mark_failed(object, inode); } return can_use; } static bool cachefiles_mark_inode_in_use(struct cachefiles_object *object, struct inode *inode) { bool can_use; inode_lock(inode); can_use = __cachefiles_mark_inode_in_use(object, inode); inode_unlock(inode); return can_use; } /* * Unmark a backing inode. The caller must hold the inode lock. */ static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, struct inode *inode) { inode->i_flags &= ~S_KERNEL_FILE; trace_cachefiles_mark_inactive(object, inode); } static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object, struct inode *inode) { inode_lock(inode); __cachefiles_unmark_inode_in_use(object, inode); inode_unlock(inode); } /* * Unmark a backing inode and tell cachefilesd that there's something that can * be culled. */ void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, struct file *file) { struct cachefiles_cache *cache = object->volume->cache; struct inode *inode = file_inode(file); cachefiles_do_unmark_inode_in_use(object, inode); if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { atomic_long_add(inode->i_blocks, &cache->b_released); if (atomic_inc_return(&cache->f_released)) cachefiles_state_changed(cache); } } /* * get a subdirectory */ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, struct dentry *dir, const char *dirname, bool *_is_new) { struct dentry *subdir; struct path path; int ret; _enter(",,%s", dirname); /* search the current directory for the element name */ inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); retry: ret = cachefiles_inject_read_error(); if (ret == 0) subdir = lookup_one(&nop_mnt_idmap, &QSTR(dirname), dir); else subdir = ERR_PTR(ret); trace_cachefiles_lookup(NULL, dir, subdir); if (IS_ERR(subdir)) { trace_cachefiles_vfs_error(NULL, d_backing_inode(dir), PTR_ERR(subdir), cachefiles_trace_lookup_error); if (PTR_ERR(subdir) == -ENOMEM) goto nomem_d_alloc; goto lookup_error; } _debug("subdir -> %pd %s", subdir, d_backing_inode(subdir) ? "positive" : "negative"); /* we need to create the subdir if it doesn't exist yet */ if (d_is_negative(subdir)) { ret = cachefiles_has_space(cache, 1, 0, cachefiles_has_space_for_create); if (ret < 0) goto mkdir_error; _debug("attempt mkdir"); path.mnt = cache->mnt; path.dentry = dir; ret = security_path_mkdir(&path, subdir, 0700); if (ret < 0) goto mkdir_error; ret = cachefiles_inject_write_error(); if (ret == 0) subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); else subdir = ERR_PTR(ret); if (IS_ERR(subdir)) { trace_cachefiles_vfs_error(NULL, d_inode(dir), ret, cachefiles_trace_mkdir_error); goto mkdir_error; } trace_cachefiles_mkdir(dir, subdir); if (unlikely(d_unhashed(subdir) || d_is_negative(subdir))) { dput(subdir); goto retry; } ASSERT(d_backing_inode(subdir)); _debug("mkdir -> %pd{ino=%lu}", subdir, d_backing_inode(subdir)->i_ino); if (_is_new) *_is_new = true; } /* Tell rmdir() it's not allowed to delete the subdir */ inode_lock(d_inode(subdir)); inode_unlock(d_inode(dir)); if (!__cachefiles_mark_inode_in_use(NULL, d_inode(subdir))) { pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n", subdir, d_inode(subdir)->i_ino); goto mark_error; } inode_unlock(d_inode(subdir)); /* we need to make sure the subdir is a directory */ ASSERT(d_backing_inode(subdir)); if (!d_can_lookup(subdir)) { pr_err("%s is not a directory\n", dirname); ret = -EIO; goto check_error; } ret = -EPERM; if (!(d_backing_inode(subdir)->i_opflags & IOP_XATTR) || !d_backing_inode(subdir)->i_op->lookup || !d_backing_inode(subdir)->i_op->mkdir || !d_backing_inode(subdir)->i_op->rename || !d_backing_inode(subdir)->i_op->rmdir || !d_backing_inode(subdir)->i_op->unlink) goto check_error; _leave(" = [%lu]", d_backing_inode(subdir)->i_ino); return subdir; check_error: cachefiles_put_directory(subdir); _leave(" = %d [check]", ret); return ERR_PTR(ret); mark_error: inode_unlock(d_inode(subdir)); dput(subdir); return ERR_PTR(-EBUSY); mkdir_error: inode_unlock(d_inode(dir)); if (!IS_ERR(subdir)) dput(subdir); pr_err("mkdir %s failed with error %d\n", dirname, ret); return ERR_PTR(ret); lookup_error: inode_unlock(d_inode(dir)); ret = PTR_ERR(subdir); pr_err("Lookup %s failed with error %d\n", dirname, ret); return ERR_PTR(ret); nomem_d_alloc: inode_unlock(d_inode(dir)); _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } /* * Put a subdirectory. */ void cachefiles_put_directory(struct dentry *dir) { if (dir) { cachefiles_do_unmark_inode_in_use(NULL, d_inode(dir)); dput(dir); } } /* * Remove a regular file from the cache. */ static int cachefiles_unlink(struct cachefiles_cache *cache, struct cachefiles_object *object, struct dentry *dir, struct dentry *dentry, enum fscache_why_object_killed why) { struct path path = { .mnt = cache->mnt, .dentry = dir, }; int ret; trace_cachefiles_unlink(object, d_inode(dentry)->i_ino, why); ret = security_path_unlink(&path, dentry); if (ret < 0) { cachefiles_io_error(cache, "Unlink security error"); return ret; } ret = cachefiles_inject_remove_error(); if (ret == 0) { ret = vfs_unlink(&nop_mnt_idmap, d_backing_inode(dir), dentry, NULL); if (ret == -EIO) cachefiles_io_error(cache, "Unlink failed"); } if (ret != 0) trace_cachefiles_vfs_error(object, d_backing_inode(dir), ret, cachefiles_trace_unlink_error); return ret; } /* * Delete an object representation from the cache * - File backed objects are unlinked * - Directory backed objects are stuffed into the graveyard for userspace to * delete */ int cachefiles_bury_object(struct cachefiles_cache *cache, struct cachefiles_object *object, struct dentry *dir, struct dentry *rep, enum fscache_why_object_killed why) { struct dentry *grave, *trap; struct path path, path_to_graveyard; char nbuffer[8 + 8 + 1]; int ret; _enter(",'%pd','%pd'", dir, rep); if (rep->d_parent != dir) { inode_unlock(d_inode(dir)); _leave(" = -ESTALE"); return -ESTALE; } /* non-directories can just be unlinked */ if (!d_is_dir(rep)) { dget(rep); /* Stop the dentry being negated if it's only pinned * by a file struct. */ ret = cachefiles_unlink(cache, object, dir, rep, why); dput(rep); inode_unlock(d_inode(dir)); _leave(" = %d", ret); return ret; } /* directories have to be moved to the graveyard */ _debug("move stale object to graveyard"); inode_unlock(d_inode(dir)); try_again: /* first step is to make up a grave dentry in the graveyard */ sprintf(nbuffer, "%08x%08x", (uint32_t) ktime_get_real_seconds(), (uint32_t) atomic_inc_return(&cache->gravecounter)); /* do the multiway lock magic */ trap = lock_rename(cache->graveyard, dir); if (IS_ERR(trap)) return PTR_ERR(trap); /* do some checks before getting the grave dentry */ if (rep->d_parent != dir || IS_DEADDIR(d_inode(rep))) { /* the entry was probably culled when we dropped the parent dir * lock */ unlock_rename(cache->graveyard, dir); _leave(" = 0 [culled?]"); return 0; } if (!d_can_lookup(cache->graveyard)) { unlock_rename(cache->graveyard, dir); cachefiles_io_error(cache, "Graveyard no longer a directory"); return -EIO; } if (trap == rep) { unlock_rename(cache->graveyard, dir); cachefiles_io_error(cache, "May not make directory loop"); return -EIO; } if (d_mountpoint(rep)) { unlock_rename(cache->graveyard, dir); cachefiles_io_error(cache, "Mountpoint in cache"); return -EIO; } grave = lookup_one(&nop_mnt_idmap, &QSTR(nbuffer), cache->graveyard); if (IS_ERR(grave)) { unlock_rename(cache->graveyard, dir); trace_cachefiles_vfs_error(object, d_inode(cache->graveyard), PTR_ERR(grave), cachefiles_trace_lookup_error); if (PTR_ERR(grave) == -ENOMEM) { _leave(" = -ENOMEM"); return -ENOMEM; } cachefiles_io_error(cache, "Lookup error %ld", PTR_ERR(grave)); return -EIO; } if (d_is_positive(grave)) { unlock_rename(cache->graveyard, dir); dput(grave); grave = NULL; cond_resched(); goto try_again; } if (d_mountpoint(grave)) { unlock_rename(cache->graveyard, dir); dput(grave); cachefiles_io_error(cache, "Mountpoint in graveyard"); return -EIO; } /* target should not be an ancestor of source */ if (trap == grave) { unlock_rename(cache->graveyard, dir); dput(grave); cachefiles_io_error(cache, "May not make directory loop"); return -EIO; } /* attempt the rename */ path.mnt = cache->mnt; path.dentry = dir; path_to_graveyard.mnt = cache->mnt; path_to_graveyard.dentry = cache->graveyard; ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0); if (ret < 0) { cachefiles_io_error(cache, "Rename security error %d", ret); } else { struct renamedata rd = { .old_mnt_idmap = &nop_mnt_idmap, .old_dir = d_inode(dir), .old_dentry = rep, .new_mnt_idmap = &nop_mnt_idmap, .new_dir = d_inode(cache->graveyard), .new_dentry = grave, }; trace_cachefiles_rename(object, d_inode(rep)->i_ino, why); ret = cachefiles_inject_read_error(); if (ret == 0) ret = vfs_rename(&rd); if (ret != 0) trace_cachefiles_vfs_error(object, d_inode(dir), ret, cachefiles_trace_rename_error); if (ret != 0 && ret != -ENOMEM) cachefiles_io_error(cache, "Rename failed with error %d", ret); } __cachefiles_unmark_inode_in_use(object, d_inode(rep)); unlock_rename(cache->graveyard, dir); dput(grave); _leave(" = 0"); return 0; } /* * Delete a cache file. */ int cachefiles_delete_object(struct cachefiles_object *object, enum fscache_why_object_killed why) { struct cachefiles_volume *volume = object->volume; struct dentry *dentry = object->file->f_path.dentry; struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash]; int ret; _enter(",OBJ%x{%pD}", object->debug_id, object->file); /* Stop the dentry being negated if it's only pinned by a file struct. */ dget(dentry); inode_lock_nested(d_backing_inode(fan), I_MUTEX_PARENT); ret = cachefiles_unlink(volume->cache, object, fan, dentry, why); inode_unlock(d_backing_inode(fan)); dput(dentry); return ret; } /* * Create a temporary file and leave it unattached and un-xattr'd until the * time comes to discard the object from memory. */ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) { struct cachefiles_volume *volume = object->volume; struct cachefiles_cache *cache = volume->cache; const struct cred *saved_cred; struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash]; struct file *file; const struct path parentpath = { .mnt = cache->mnt, .dentry = fan }; uint64_t ni_size; long ret; cachefiles_begin_secure(cache, &saved_cred); ret = cachefiles_inject_write_error(); if (ret == 0) { file = kernel_tmpfile_open(&nop_mnt_idmap, &parentpath, S_IFREG | 0600, O_RDWR | O_LARGEFILE | O_DIRECT, cache->cache_cred); ret = PTR_ERR_OR_ZERO(file); } if (ret) { trace_cachefiles_vfs_error(object, d_inode(fan), ret, cachefiles_trace_tmpfile_error); if (ret == -EIO) cachefiles_io_error_obj(object, "Failed to create tmpfile"); goto err; } trace_cachefiles_tmpfile(object, file_inode(file)); /* This is a newly created file with no other possible user */ if (!cachefiles_mark_inode_in_use(object, file_inode(file))) WARN_ON(1); ret = cachefiles_ondemand_init_object(object); if (ret < 0) goto err_unuse; ni_size = object->cookie->object_size; ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); if (ni_size > 0) { trace_cachefiles_trunc(object, file_inode(file), 0, ni_size, cachefiles_trunc_expand_tmpfile); ret = cachefiles_inject_write_error(); if (ret == 0) ret = vfs_truncate(&file->f_path, ni_size); if (ret < 0) { trace_cachefiles_vfs_error( object, file_inode(file), ret, cachefiles_trace_trunc_error); goto err_unuse; } } ret = -EINVAL; if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { fput(file); pr_notice("Cache does not support read_iter and write_iter\n"); goto err_unuse; } out: cachefiles_end_secure(cache, saved_cred); return file; err_unuse: cachefiles_do_unmark_inode_in_use(object, file_inode(file)); fput(file); err: file = ERR_PTR(ret); goto out; } /* * Create a new file. */ static bool cachefiles_create_file(struct cachefiles_object *object) { struct file *file; int ret; ret = cachefiles_has_space(object->volume->cache, 1, 0, cachefiles_has_space_for_create); if (ret < 0) return false; file = cachefiles_create_tmpfile(object); if (IS_ERR(file)) return false; set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags); set_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags); _debug("create -> %pD{ino=%lu}", file, file_inode(file)->i_ino); object->file = file; return true; } /* * Open an existing file, checking its attributes and replacing it if it is * stale. */ static bool cachefiles_open_file(struct cachefiles_object *object, struct dentry *dentry) { struct cachefiles_cache *cache = object->volume->cache; struct file *file; struct path path; int ret; _enter("%pd", dentry); if (!cachefiles_mark_inode_in_use(object, d_inode(dentry))) { pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n", dentry, d_inode(dentry)->i_ino); return false; } /* We need to open a file interface onto a data file now as we can't do * it on demand because writeback called from do_exit() sees * current->fs == NULL - which breaks d_path() called from ext4 open. */ path.mnt = cache->mnt; path.dentry = dentry; file = kernel_file_open(&path, O_RDWR | O_LARGEFILE | O_DIRECT, cache->cache_cred); if (IS_ERR(file)) { trace_cachefiles_vfs_error(object, d_backing_inode(dentry), PTR_ERR(file), cachefiles_trace_open_error); goto error; } if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { pr_notice("Cache does not support read_iter and write_iter\n"); goto error_fput; } _debug("file -> %pd positive", dentry); ret = cachefiles_ondemand_init_object(object); if (ret < 0) goto error_fput; ret = cachefiles_check_auxdata(object, file); if (ret < 0) goto check_failed; clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &object->cookie->flags); object->file = file; /* Always update the atime on an object we've just looked up (this is * used to keep track of culling, and atimes are only updated by read, * write and readdir but not lookup or open). */ touch_atime(&file->f_path); return true; check_failed: fscache_cookie_lookup_negative(object->cookie); cachefiles_unmark_inode_in_use(object, file); fput(file); if (ret == -ESTALE) return cachefiles_create_file(object); return false; error_fput: fput(file); error: cachefiles_do_unmark_inode_in_use(object, d_inode(dentry)); return false; } /* * walk from the parent object to the child object through the backing * filesystem, creating directories as we go */ bool cachefiles_look_up_object(struct cachefiles_object *object) { struct cachefiles_volume *volume = object->volume; struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash]; int ret; _enter("OBJ%x,%s,", object->debug_id, object->d_name); /* Look up path "cache/vol/fanout/file". */ ret = cachefiles_inject_read_error(); if (ret == 0) dentry = lookup_one_positive_unlocked(&nop_mnt_idmap, &QSTR(object->d_name), fan); else dentry = ERR_PTR(ret); trace_cachefiles_lookup(object, fan, dentry); if (IS_ERR(dentry)) { if (dentry == ERR_PTR(-ENOENT)) goto new_file; if (dentry == ERR_PTR(-EIO)) cachefiles_io_error_obj(object, "Lookup failed"); return false; } if (!d_is_reg(dentry)) { pr_err("%pd is not a file\n", dentry); inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); ret = cachefiles_bury_object(volume->cache, object, fan, dentry, FSCACHE_OBJECT_IS_WEIRD); dput(dentry); if (ret < 0) return false; goto new_file; } ret = cachefiles_open_file(object, dentry); dput(dentry); if (!ret) return false; _leave(" = t [%lu]", file_inode(object->file)->i_ino); return true; new_file: fscache_cookie_lookup_negative(object->cookie); return cachefiles_create_file(object); } /* * Attempt to link a temporary file into its rightful place in the cache. */ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, struct cachefiles_object *object) { struct cachefiles_volume *volume = object->volume; struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash]; bool success = false; int ret; _enter(",%pD", object->file); inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); ret = cachefiles_inject_read_error(); if (ret == 0) dentry = lookup_one(&nop_mnt_idmap, &QSTR(object->d_name), fan); else dentry = ERR_PTR(ret); if (IS_ERR(dentry)) { trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry), cachefiles_trace_lookup_error); _debug("lookup fail %ld", PTR_ERR(dentry)); goto out_unlock; } if (!d_is_negative(dentry)) { ret = cachefiles_unlink(volume->cache, object, fan, dentry, FSCACHE_OBJECT_IS_STALE); if (ret < 0) goto out_dput; dput(dentry); ret = cachefiles_inject_read_error(); if (ret == 0) dentry = lookup_one(&nop_mnt_idmap, &QSTR(object->d_name), fan); else dentry = ERR_PTR(ret); if (IS_ERR(dentry)) { trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry), cachefiles_trace_lookup_error); _debug("lookup fail %ld", PTR_ERR(dentry)); goto out_unlock; } } ret = cachefiles_inject_read_error(); if (ret == 0) ret = vfs_link(object->file->f_path.dentry, &nop_mnt_idmap, d_inode(fan), dentry, NULL); if (ret < 0) { trace_cachefiles_vfs_error(object, d_inode(fan), ret, cachefiles_trace_link_error); _debug("link fail %d", ret); } else { trace_cachefiles_link(object, file_inode(object->file)); spin_lock(&object->lock); /* TODO: Do we want to switch the file pointer to the new dentry? */ clear_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags); spin_unlock(&object->lock); success = true; } out_dput: dput(dentry); out_unlock: inode_unlock(d_inode(fan)); _leave(" = %u", success); return success; } /* * Look up an inode to be checked or culled. Return -EBUSY if the inode is * marked in use. */ static struct dentry *cachefiles_lookup_for_cull(struct cachefiles_cache *cache, struct dentry *dir, char *filename) { struct dentry *victim; int ret = -ENOENT; inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); victim = lookup_one(&nop_mnt_idmap, &QSTR(filename), dir); if (IS_ERR(victim)) goto lookup_error; if (d_is_negative(victim)) goto lookup_put; if (d_inode(victim)->i_flags & S_KERNEL_FILE) goto lookup_busy; return victim; lookup_busy: ret = -EBUSY; lookup_put: inode_unlock(d_inode(dir)); dput(victim); return ERR_PTR(ret); lookup_error: inode_unlock(d_inode(dir)); ret = PTR_ERR(victim); if (ret == -ENOENT) return ERR_PTR(-ESTALE); /* Probably got retired by the netfs */ if (ret == -EIO) { cachefiles_io_error(cache, "Lookup failed"); } else if (ret != -ENOMEM) { pr_err("Internal error: %d\n", ret); ret = -EIO; } return ERR_PTR(ret); } /* * Cull an object if it's not in use * - called only by cache manager daemon */ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, char *filename) { struct dentry *victim; struct inode *inode; int ret; _enter(",%pd/,%s", dir, filename); victim = cachefiles_lookup_for_cull(cache, dir, filename); if (IS_ERR(victim)) return PTR_ERR(victim); /* check to see if someone is using this object */ inode = d_inode(victim); inode_lock(inode); if (inode->i_flags & S_KERNEL_FILE) { ret = -EBUSY; } else { /* Stop the cache from picking it back up */ inode->i_flags |= S_KERNEL_FILE; ret = 0; } inode_unlock(inode); if (ret < 0) goto error_unlock; ret = cachefiles_bury_object(cache, NULL, dir, victim, FSCACHE_OBJECT_WAS_CULLED); if (ret < 0) goto error; fscache_count_culled(); dput(victim); _leave(" = 0"); return 0; error_unlock: inode_unlock(d_inode(dir)); error: dput(victim); if (ret == -ENOENT) return -ESTALE; /* Probably got retired by the netfs */ if (ret != -ENOMEM) { pr_err("Internal error: %d\n", ret); ret = -EIO; } _leave(" = %d", ret); return ret; } /* * Find out if an object is in use or not * - called only by cache manager daemon * - returns -EBUSY or 0 to indicate whether an object is in use or not */ int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir, char *filename) { struct dentry *victim; int ret = 0; victim = cachefiles_lookup_for_cull(cache, dir, filename); if (IS_ERR(victim)) return PTR_ERR(victim); inode_unlock(d_inode(dir)); dput(victim); return ret; } |
| 15 16 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/list.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/srcu.h> #include <linux/rculist.h> #include <linux/wait.h> #include <linux/memcontrol.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #include <linux/atomic.h> /* * Final freeing of a group */ static void fsnotify_final_destroy_group(struct fsnotify_group *group) { if (group->ops->free_group_priv) group->ops->free_group_priv(group); mem_cgroup_put(group->memcg); mutex_destroy(&group->mark_mutex); kfree(group); } /* * Stop queueing new events for this group. Once this function returns * fsnotify_add_event() will not add any new events to the group's queue. */ void fsnotify_group_stop_queueing(struct fsnotify_group *group) { spin_lock(&group->notification_lock); group->shutdown = true; spin_unlock(&group->notification_lock); } /* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. * Note that another thread calling fsnotify_clear_marks_by_group() may still * hold a ref to the group. */ void fsnotify_destroy_group(struct fsnotify_group *group) { /* * Stop queueing new events. The code below is careful enough to not * require this but fanotify needs to stop queuing events even before * fsnotify_destroy_group() is called and this makes the other callers * of fsnotify_destroy_group() to see the same behavior. */ fsnotify_group_stop_queueing(group); /* Clear all marks for this group and queue them for destruction */ fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_ANY); /* * Some marks can still be pinned when waiting for response from * userspace. Wait for those now. fsnotify_prepare_user_wait() will * not succeed now so this wait is race-free. */ wait_event(group->notification_waitq, !atomic_read(&group->user_waits)); /* * Wait until all marks get really destroyed. We could actually destroy * them ourselves instead of waiting for worker to do it, however that * would be racy as worker can already be processing some marks before * we even entered fsnotify_destroy_group(). */ fsnotify_wait_marks_destroyed(); /* * Since we have waited for fsnotify_mark_srcu in * fsnotify_mark_destroy_list() there can be no outstanding event * notification against this group. So clearing the notification queue * of all events is reliable now. */ fsnotify_flush_notify(group); /* * Destroy overflow event (we cannot use fsnotify_destroy_event() as * that deliberately ignores overflow events. */ if (group->overflow_event) group->ops->free_event(group, group->overflow_event); fsnotify_put_group(group); } /* * Get reference to a group. */ void fsnotify_get_group(struct fsnotify_group *group) { refcount_inc(&group->refcnt); } /* * Drop a reference to a group. Free it if it's through. */ void fsnotify_put_group(struct fsnotify_group *group) { if (refcount_dec_and_test(&group->refcnt)) fsnotify_final_destroy_group(group); } EXPORT_SYMBOL_GPL(fsnotify_put_group); static struct fsnotify_group *__fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags, gfp_t gfp) { struct fsnotify_group *group; group = kzalloc(sizeof(struct fsnotify_group), gfp); if (!group) return ERR_PTR(-ENOMEM); /* set to 0 when there a no external references to this group */ refcount_set(&group->refcnt, 1); atomic_set(&group->user_waits, 0); spin_lock_init(&group->notification_lock); INIT_LIST_HEAD(&group->notification_list); init_waitqueue_head(&group->notification_waitq); group->max_events = UINT_MAX; mutex_init(&group->mark_mutex); INIT_LIST_HEAD(&group->marks_list); group->ops = ops; group->flags = flags; return group; } /* * Create a new fsnotify_group and hold a reference for the group returned. */ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops, int flags) { gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT : GFP_KERNEL; return __fsnotify_alloc_group(ops, flags, gfp); } EXPORT_SYMBOL_GPL(fsnotify_alloc_group); int fsnotify_fasync(int fd, struct file *file, int on) { struct fsnotify_group *group = file->private_data; return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO; } |
| 2 1 1 1 3 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Virtual NCI device simulation driver * * Copyright (C) 2020 Samsung Electronics * Bongsu Jeon <bongsu.jeon@samsung.com> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/miscdevice.h> #include <linux/mutex.h> #include <linux/wait.h> #include <net/nfc/nci_core.h> #define IOCTL_GET_NCIDEV_IDX 0 #define VIRTUAL_NFC_PROTOCOLS (NFC_PROTO_JEWEL_MASK | \ NFC_PROTO_MIFARE_MASK | \ NFC_PROTO_FELICA_MASK | \ NFC_PROTO_ISO14443_MASK | \ NFC_PROTO_ISO14443_B_MASK | \ NFC_PROTO_ISO15693_MASK) struct virtual_nci_dev { struct nci_dev *ndev; struct mutex mtx; struct sk_buff *send_buff; struct wait_queue_head wq; bool running; }; static int virtual_nci_open(struct nci_dev *ndev) { struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); vdev->running = true; return 0; } static int virtual_nci_close(struct nci_dev *ndev) { struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); mutex_lock(&vdev->mtx); kfree_skb(vdev->send_buff); vdev->send_buff = NULL; vdev->running = false; mutex_unlock(&vdev->mtx); return 0; } static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb) { struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); mutex_lock(&vdev->mtx); if (vdev->send_buff || !vdev->running) { mutex_unlock(&vdev->mtx); kfree_skb(skb); return -1; } vdev->send_buff = skb_copy(skb, GFP_KERNEL); if (!vdev->send_buff) { mutex_unlock(&vdev->mtx); kfree_skb(skb); return -1; } mutex_unlock(&vdev->mtx); wake_up_interruptible(&vdev->wq); consume_skb(skb); return 0; } static const struct nci_ops virtual_nci_ops = { .open = virtual_nci_open, .close = virtual_nci_close, .send = virtual_nci_send }; static ssize_t virtual_ncidev_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct virtual_nci_dev *vdev = file->private_data; size_t actual_len; mutex_lock(&vdev->mtx); while (!vdev->send_buff) { mutex_unlock(&vdev->mtx); if (wait_event_interruptible(vdev->wq, vdev->send_buff)) return -EFAULT; mutex_lock(&vdev->mtx); } actual_len = min_t(size_t, count, vdev->send_buff->len); if (copy_to_user(buf, vdev->send_buff->data, actual_len)) { mutex_unlock(&vdev->mtx); return -EFAULT; } skb_pull(vdev->send_buff, actual_len); if (vdev->send_buff->len == 0) { consume_skb(vdev->send_buff); vdev->send_buff = NULL; } mutex_unlock(&vdev->mtx); return actual_len; } static ssize_t virtual_ncidev_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct virtual_nci_dev *vdev = file->private_data; struct sk_buff *skb; skb = alloc_skb(count, GFP_KERNEL); if (!skb) return -ENOMEM; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); return -EFAULT; } if (strnlen(skb->data, count) != count) { kfree_skb(skb); return -EINVAL; } nci_recv_frame(vdev->ndev, skb); return count; } static int virtual_ncidev_open(struct inode *inode, struct file *file) { int ret = 0; struct virtual_nci_dev *vdev; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) return -ENOMEM; vdev->ndev = nci_allocate_device(&virtual_nci_ops, VIRTUAL_NFC_PROTOCOLS, 0, 0); if (!vdev->ndev) { kfree(vdev); return -ENOMEM; } mutex_init(&vdev->mtx); init_waitqueue_head(&vdev->wq); file->private_data = vdev; nci_set_drvdata(vdev->ndev, vdev); ret = nci_register_device(vdev->ndev); if (ret < 0) { nci_free_device(vdev->ndev); mutex_destroy(&vdev->mtx); kfree(vdev); return ret; } return 0; } static int virtual_ncidev_close(struct inode *inode, struct file *file) { struct virtual_nci_dev *vdev = file->private_data; nci_unregister_device(vdev->ndev); nci_free_device(vdev->ndev); mutex_destroy(&vdev->mtx); kfree(vdev); return 0; } static long virtual_ncidev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct virtual_nci_dev *vdev = file->private_data; const struct nfc_dev *nfc_dev = vdev->ndev->nfc_dev; void __user *p = (void __user *)arg; if (cmd != IOCTL_GET_NCIDEV_IDX) return -ENOTTY; if (copy_to_user(p, &nfc_dev->idx, sizeof(nfc_dev->idx))) return -EFAULT; return 0; } static const struct file_operations virtual_ncidev_fops = { .owner = THIS_MODULE, .read = virtual_ncidev_read, .write = virtual_ncidev_write, .open = virtual_ncidev_open, .release = virtual_ncidev_close, .unlocked_ioctl = virtual_ncidev_ioctl }; static struct miscdevice miscdev = { .minor = MISC_DYNAMIC_MINOR, .name = "virtual_nci", .fops = &virtual_ncidev_fops, .mode = 0600, }; module_misc_device(miscdev); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Virtual NCI device simulation driver"); MODULE_AUTHOR("Bongsu Jeon <bongsu.jeon@samsung.com>"); |
| 6 6 6 6 6 6 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Handle vlserver selection and rotation. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include "internal.h" #include "afs_vl.h" /* * Begin an operation on a volume location server. */ bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cell, struct key *key) { static atomic_t debug_ids; memset(vc, 0, sizeof(*vc)); vc->cell = cell; vc->key = key; vc->cumul_error.error = -EDESTADDRREQ; vc->nr_iterations = -1; if (signal_pending(current)) { vc->cumul_error.error = -EINTR; vc->flags |= AFS_VL_CURSOR_STOP; return false; } vc->debug_id = atomic_inc_return(&debug_ids); return true; } /* * Begin iteration through a server list, starting with the last used server if * possible, or the last recorded good server if not. */ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) { struct afs_cell *cell = vc->cell; unsigned int dns_lookup_count; if (cell->dns_source == DNS_RECORD_UNAVAILABLE || cell->dns_expiry <= ktime_get_real_seconds()) { dns_lookup_count = smp_load_acquire(&cell->dns_lookup_count); set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); afs_queue_cell(cell, afs_cell_trace_queue_dns); if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { if (wait_var_event_interruptible( &cell->dns_lookup_count, smp_load_acquire(&cell->dns_lookup_count) != dns_lookup_count) < 0) { vc->cumul_error.error = -ERESTARTSYS; return false; } } /* Status load is ordered after lookup counter load */ if (cell->dns_status == DNS_LOOKUP_GOT_NOT_FOUND) { pr_warn("No record of cell %s\n", cell->name); vc->cumul_error.error = -ENOENT; return false; } if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { vc->cumul_error.error = -EDESTADDRREQ; return false; } } read_lock(&cell->vl_servers_lock); vc->server_list = afs_get_vlserverlist( rcu_dereference_protected(cell->vl_servers, lockdep_is_held(&cell->vl_servers_lock))); read_unlock(&cell->vl_servers_lock); if (!vc->server_list->nr_servers) return false; vc->untried_servers = (1UL << vc->server_list->nr_servers) - 1; vc->server_index = -1; return true; } /* * Select the vlserver to use. May be called multiple times to rotate * through the vlservers. */ bool afs_select_vlserver(struct afs_vl_cursor *vc) { struct afs_addr_list *alist = vc->alist; struct afs_vlserver *vlserver; unsigned long set, failed; unsigned int rtt; s32 abort_code = vc->call_abort_code; int error = vc->call_error, i; vc->nr_iterations++; _enter("VC=%x+%x,%d{%lx},%d{%lx},%d,%d", vc->debug_id, vc->nr_iterations, vc->server_index, vc->untried_servers, vc->addr_index, vc->addr_tried, error, abort_code); if (vc->flags & AFS_VL_CURSOR_STOP) { _leave(" = f [stopped]"); return false; } if (vc->nr_iterations == 0) goto start; WRITE_ONCE(alist->addrs[vc->addr_index].last_error, error); /* Evaluate the result of the previous operation, if there was one. */ switch (error) { default: case 0: /* Success or local failure. Stop. */ vc->cumul_error.error = error; vc->flags |= AFS_VL_CURSOR_STOP; _leave(" = f [okay/local %d]", vc->cumul_error.error); return false; case -ECONNABORTED: /* The far side rejected the operation on some grounds. This * might involve the server being busy or the volume having been moved. */ switch (abort_code) { case AFSVL_IO: case AFSVL_BADVOLOPER: case AFSVL_NOMEM: /* The server went weird. */ afs_prioritise_error(&vc->cumul_error, -EREMOTEIO, abort_code); //write_lock(&vc->cell->vl_servers_lock); //vc->server_list->weird_mask |= 1 << vc->server_index; //write_unlock(&vc->cell->vl_servers_lock); goto next_server; default: afs_prioritise_error(&vc->cumul_error, error, abort_code); goto failed; } case -ERFKILL: case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: _debug("no conn %d", error); afs_prioritise_error(&vc->cumul_error, error, 0); goto iterate_address; case -ECONNRESET: _debug("call reset"); afs_prioritise_error(&vc->cumul_error, error, 0); vc->flags |= AFS_VL_CURSOR_RETRY; goto next_server; case -EOPNOTSUPP: _debug("notsupp"); goto next_server; } restart_from_beginning: _debug("restart"); if (vc->call_responded && vc->addr_index != vc->alist->preferred && test_bit(alist->preferred, &vc->addr_tried)) WRITE_ONCE(alist->preferred, vc->addr_index); afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_restart); alist = vc->alist = NULL; afs_put_vlserverlist(vc->cell->net, vc->server_list); vc->server_list = NULL; if (vc->flags & AFS_VL_CURSOR_RETRIED) goto failed; vc->flags |= AFS_VL_CURSOR_RETRIED; start: _debug("start"); ASSERTCMP(alist, ==, NULL); if (!afs_start_vl_iteration(vc)) goto failed; error = afs_send_vl_probes(vc->cell->net, vc->key, vc->server_list); if (error < 0) { afs_prioritise_error(&vc->cumul_error, error, 0); goto failed; } pick_server: _debug("pick [%lx]", vc->untried_servers); ASSERTCMP(alist, ==, NULL); error = afs_wait_for_vl_probes(vc->server_list, vc->untried_servers); if (error < 0) { afs_prioritise_error(&vc->cumul_error, error, 0); goto failed; } /* Pick the untried server with the lowest RTT. */ vc->server_index = vc->server_list->preferred; if (test_bit(vc->server_index, &vc->untried_servers)) goto selected_server; vc->server_index = -1; rtt = UINT_MAX; for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; if (!test_bit(i, &vc->untried_servers) || !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) continue; if (s->probe.rtt <= rtt) { vc->server_index = i; rtt = s->probe.rtt; } } if (vc->server_index == -1) goto no_more_servers; selected_server: _debug("use %d", vc->server_index); __clear_bit(vc->server_index, &vc->untried_servers); /* We're starting on a different vlserver from the list. We need to * check it, find its address list and probe its capabilities before we * use it. */ vlserver = vc->server_list->servers[vc->server_index].server; vc->server = vlserver; _debug("USING VLSERVER: %s", vlserver->name); read_lock(&vlserver->lock); alist = rcu_dereference_protected(vlserver->addresses, lockdep_is_held(&vlserver->lock)); vc->alist = afs_get_addrlist(alist, afs_alist_trace_get_vlrotate_set); read_unlock(&vlserver->lock); vc->addr_tried = 0; vc->addr_index = -1; iterate_address: /* Iterate over the current server's address list to try and find an * address on which it will respond to us. */ set = READ_ONCE(alist->responded); failed = READ_ONCE(alist->probe_failed); vc->addr_index = READ_ONCE(alist->preferred); _debug("%lx-%lx-%lx,%d", set, failed, vc->addr_tried, vc->addr_index); set &= ~(failed | vc->addr_tried); if (!set) goto next_server; if (!test_bit(vc->addr_index, &set)) vc->addr_index = __ffs(set); set_bit(vc->addr_index, &vc->addr_tried); vc->alist = alist; _debug("VL address %d/%d", vc->addr_index, alist->nr_addrs); vc->call_responded = false; _leave(" = t %pISpc", rxrpc_kernel_remote_addr(alist->addrs[vc->addr_index].peer)); return true; next_server: _debug("next"); ASSERT(alist); if (vc->call_responded && vc->addr_index != alist->preferred && test_bit(alist->preferred, &vc->addr_tried)) WRITE_ONCE(alist->preferred, vc->addr_index); afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_next); alist = vc->alist = NULL; goto pick_server; no_more_servers: /* That's all the servers poked to no good effect. Try again if some * of them were busy. */ if (vc->flags & AFS_VL_CURSOR_RETRY) goto restart_from_beginning; for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) vc->cumul_error.responded = true; afs_prioritise_error(&vc->cumul_error, READ_ONCE(s->probe.error), s->probe.abort_code); } failed: if (alist) { if (vc->call_responded && vc->addr_index != alist->preferred && test_bit(alist->preferred, &vc->addr_tried)) WRITE_ONCE(alist->preferred, vc->addr_index); afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_fail); alist = vc->alist = NULL; } vc->flags |= AFS_VL_CURSOR_STOP; _leave(" = f [failed %d]", vc->cumul_error.error); return false; } /* * Dump cursor state in the case of the error being EDESTADDRREQ. */ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc) { struct afs_cell *cell = vc->cell; static int count; int i; if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3) return; count++; rcu_read_lock(); pr_notice("EDESTADDR occurred\n"); pr_notice("CELL: %s err=%d\n", cell->name, cell->error); pr_notice("DNS: src=%u st=%u lc=%x\n", cell->dns_source, cell->dns_status, cell->dns_lookup_count); pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n", vc->untried_servers, vc->server_index, vc->nr_iterations, vc->flags, vc->cumul_error.error); pr_notice("VC: call er=%d ac=%d r=%u\n", vc->call_error, vc->call_abort_code, vc->call_responded); if (vc->server_list) { const struct afs_vlserver_list *sl = vc->server_list; pr_notice("VC: SL nr=%u ix=%u\n", sl->nr_servers, sl->index); for (i = 0; i < sl->nr_servers; i++) { const struct afs_vlserver *s = sl->servers[i].server; pr_notice("VC: server %s+%hu fl=%lx E=%hd\n", s->name, s->port, s->flags, s->probe.error); if (s->addresses) { const struct afs_addr_list *a = rcu_dereference(s->addresses); pr_notice("VC: - nr=%u/%u/%u pf=%u\n", a->nr_ipv4, a->nr_addrs, a->max_addrs, a->preferred); pr_notice("VC: - R=%lx F=%lx\n", a->responded, a->probe_failed); if (a == vc->alist) pr_notice("VC: - current\n"); } } } pr_notice("AC: t=%lx ax=%u\n", vc->addr_tried, vc->addr_index); rcu_read_unlock(); } /* * Tidy up a volume location server cursor and unlock the vnode. */ int afs_end_vlserver_operation(struct afs_vl_cursor *vc) { struct afs_net *net = vc->cell->net; _enter("VC=%x+%x", vc->debug_id, vc->nr_iterations); switch (vc->cumul_error.error) { case -EDESTADDRREQ: case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: afs_vl_dump_edestaddrreq(vc); break; } if (vc->alist) { if (vc->call_responded && vc->addr_index != vc->alist->preferred && test_bit(vc->alist->preferred, &vc->addr_tried)) WRITE_ONCE(vc->alist->preferred, vc->addr_index); afs_put_addrlist(vc->alist, afs_alist_trace_put_vlrotate_end); vc->alist = NULL; } afs_put_vlserverlist(net, vc->server_list); return vc->cumul_error.error; } |
| 11 10 227 226 220 220 220 220 220 220 220 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2022-2024 Oracle. All Rights Reserved. * Author: Darrick J. Wong <djwong@kernel.org> */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_btree.h" #include "xfs_alloc_btree.h" #include "xfs_rmap_btree.h" #include "xfs_alloc.h" #include "xfs_ialloc.h" #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_health.h" #include "xfs_error.h" #include "xfs_bmap.h" #include "xfs_defer.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_trace.h" #include "xfs_inode.h" #include "xfs_icache.h" #include "xfs_buf_item.h" #include "xfs_rtgroup.h" #include "xfs_rtbitmap.h" #include "xfs_metafile.h" #include "xfs_metadir.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" /* Find the first usable fsblock in this rtgroup. */ static inline uint32_t xfs_rtgroup_min_block( struct xfs_mount *mp, xfs_rgnumber_t rgno) { if (xfs_has_rtsb(mp) && rgno == 0) return mp->m_sb.sb_rextsize; return 0; } /* Precompute this group's geometry */ void xfs_rtgroup_calc_geometry( struct xfs_mount *mp, struct xfs_rtgroup *rtg, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents) { rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents); rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno); } int xfs_rtgroup_alloc( struct xfs_mount *mp, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents) { struct xfs_rtgroup *rtg; int error; rtg = kzalloc(sizeof(struct xfs_rtgroup), GFP_KERNEL); if (!rtg) return -ENOMEM; xfs_rtgroup_calc_geometry(mp, rtg, rgno, rgcount, rextents); error = xfs_group_insert(mp, rtg_group(rtg), rgno, XG_TYPE_RTG); if (error) goto out_free_rtg; return 0; out_free_rtg: kfree(rtg); return error; } void xfs_rtgroup_free( struct xfs_mount *mp, xfs_rgnumber_t rgno) { xfs_group_free(mp, rgno, XG_TYPE_RTG, NULL); } /* Free a range of incore rtgroup objects. */ void xfs_free_rtgroups( struct xfs_mount *mp, xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno) { xfs_rgnumber_t rgno; for (rgno = first_rgno; rgno < end_rgno; rgno++) xfs_rtgroup_free(mp, rgno); } /* Initialize some range of incore rtgroup objects. */ int xfs_initialize_rtgroups( struct xfs_mount *mp, xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents) { xfs_rgnumber_t index; int error; if (first_rgno >= end_rgno) return 0; for (index = first_rgno; index < end_rgno; index++) { error = xfs_rtgroup_alloc(mp, index, end_rgno, rextents); if (error) goto out_unwind_new_rtgs; } return 0; out_unwind_new_rtgs: xfs_free_rtgroups(mp, first_rgno, index); return error; } /* Compute the number of rt extents in this realtime group. */ xfs_rtxnum_t __xfs_rtgroup_extents( struct xfs_mount *mp, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents) { ASSERT(rgno < rgcount); if (rgno == rgcount - 1) return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); ASSERT(xfs_has_rtgroups(mp)); return mp->m_sb.sb_rgextents; } xfs_rtxnum_t xfs_rtgroup_extents( struct xfs_mount *mp, xfs_rgnumber_t rgno) { return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents); } /* * Update the rt extent count of the previous tail rtgroup if it changed during * recovery (i.e. recovery of a growfs). */ int xfs_update_last_rtgroup_size( struct xfs_mount *mp, xfs_rgnumber_t prev_rgcount) { struct xfs_rtgroup *rtg; ASSERT(prev_rgcount > 0); rtg = xfs_rtgroup_grab(mp, prev_rgcount - 1); if (!rtg) return -EFSCORRUPTED; rtg->rtg_extents = __xfs_rtgroup_extents(mp, prev_rgcount - 1, mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents); rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; xfs_rtgroup_rele(rtg); return 0; } /* Lock metadata inodes associated with this rt group. */ void xfs_rtgroup_lock( struct xfs_rtgroup *rtg, unsigned int rtglock_flags) { ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || !(rtglock_flags & XFS_RTGLOCK_BITMAP)); if (!xfs_has_zoned(rtg_mount(rtg))) { if (rtglock_flags & XFS_RTGLOCK_BITMAP) { /* * Lock both realtime free space metadata inodes for a * freespace update. */ xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL); } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); } } if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_EXCL); if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) xfs_ilock(rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Unlock metadata inodes associated with this rt group. */ void xfs_rtgroup_unlock( struct xfs_rtgroup *rtg, unsigned int rtglock_flags) { ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) || !(rtglock_flags & XFS_RTGLOCK_BITMAP)); if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) xfs_iunlock(rtg_refcount(rtg), XFS_ILOCK_EXCL); if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL); if (!xfs_has_zoned(rtg_mount(rtg))) { if (rtglock_flags & XFS_RTGLOCK_BITMAP) { xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL); xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL); } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) { xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED); } } } /* * Join realtime group metadata inodes to the transaction. The ILOCKs will be * released on transaction commit. */ void xfs_rtgroup_trans_join( struct xfs_trans *tp, struct xfs_rtgroup *rtg, unsigned int rtglock_flags) { ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS)); ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED)); if (!xfs_has_zoned(rtg_mount(rtg)) && (rtglock_flags & XFS_RTGLOCK_BITMAP)) { xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL); } if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg)) xfs_trans_ijoin(tp, rtg_rmap(rtg), XFS_ILOCK_EXCL); if ((rtglock_flags & XFS_RTGLOCK_REFCOUNT) && rtg_refcount(rtg)) xfs_trans_ijoin(tp, rtg_refcount(rtg), XFS_ILOCK_EXCL); } /* Retrieve rt group geometry. */ int xfs_rtgroup_get_geometry( struct xfs_rtgroup *rtg, struct xfs_rtgroup_geometry *rgeo) { /* Fill out form. */ memset(rgeo, 0, sizeof(*rgeo)); rgeo->rg_number = rtg_rgno(rtg); rgeo->rg_length = rtg_blocks(rtg); xfs_rtgroup_geom_health(rtg, rgeo); return 0; } #ifdef CONFIG_PROVE_LOCKING static struct lock_class_key xfs_rtginode_lock_class; static int xfs_rtginode_ilock_cmp_fn( const struct lockdep_map *m1, const struct lockdep_map *m2) { const struct xfs_inode *ip1 = container_of(m1, struct xfs_inode, i_lock.dep_map); const struct xfs_inode *ip2 = container_of(m2, struct xfs_inode, i_lock.dep_map); if (ip1->i_projid < ip2->i_projid) return -1; if (ip1->i_projid > ip2->i_projid) return 1; return 0; } static inline void xfs_rtginode_ilock_print_fn( const struct lockdep_map *m) { const struct xfs_inode *ip = container_of(m, struct xfs_inode, i_lock.dep_map); printk(KERN_CONT " rgno=%u metatype=%s", ip->i_projid, xfs_metafile_type_str(ip->i_metatype)); } /* * Most of the time each of the RTG inode locks are only taken one at a time. * But when committing deferred ops, more than one of a kind can be taken. * However, deferred rt ops will be committed in rgno order so there is no * potential for deadlocks. The code here is needed to tell lockdep about this * order. */ static inline void xfs_rtginode_lockdep_setup( struct xfs_inode *ip, xfs_rgnumber_t rgno, enum xfs_rtg_inodes type) { lockdep_set_class_and_subclass(&ip->i_lock, &xfs_rtginode_lock_class, type); lock_set_cmp_fn(&ip->i_lock, xfs_rtginode_ilock_cmp_fn, xfs_rtginode_ilock_print_fn); } #else #define xfs_rtginode_lockdep_setup(ip, rgno, type) do { } while (0) #endif /* CONFIG_PROVE_LOCKING */ struct xfs_rtginode_ops { const char *name; /* short name */ enum xfs_metafile_type metafile_type; unsigned int sick; /* rtgroup sickness flag */ unsigned int fmt_mask; /* all valid data fork formats */ /* Does the fs have this feature? */ bool (*enabled)(const struct xfs_mount *mp); /* Create this rtgroup metadata inode and initialize it. */ int (*create)(struct xfs_rtgroup *rtg, struct xfs_inode *ip, struct xfs_trans *tp, bool init); }; static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = { [XFS_RTGI_BITMAP] = { .name = "bitmap", .metafile_type = XFS_METAFILE_RTBITMAP, .sick = XFS_SICK_RG_BITMAP, .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | (1U << XFS_DINODE_FMT_BTREE), .enabled = xfs_has_nonzoned, .create = xfs_rtbitmap_create, }, [XFS_RTGI_SUMMARY] = { .name = "summary", .metafile_type = XFS_METAFILE_RTSUMMARY, .sick = XFS_SICK_RG_SUMMARY, .fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) | (1U << XFS_DINODE_FMT_BTREE), .enabled = xfs_has_nonzoned, .create = xfs_rtsummary_create, }, [XFS_RTGI_RMAP] = { .name = "rmap", .metafile_type = XFS_METAFILE_RTRMAP, .sick = XFS_SICK_RG_RMAPBT, .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, /* * growfs must create the rtrmap inodes before adding a * realtime volume to the filesystem, so we cannot use the * rtrmapbt predicate here. */ .enabled = xfs_has_rmapbt, .create = xfs_rtrmapbt_create, }, [XFS_RTGI_REFCOUNT] = { .name = "refcount", .metafile_type = XFS_METAFILE_RTREFCOUNT, .sick = XFS_SICK_RG_REFCNTBT, .fmt_mask = 1U << XFS_DINODE_FMT_META_BTREE, /* same comment about growfs and rmap inodes applies here */ .enabled = xfs_has_reflink, .create = xfs_rtrefcountbt_create, }, }; /* Return the shortname of this rtgroup inode. */ const char * xfs_rtginode_name( enum xfs_rtg_inodes type) { return xfs_rtginode_ops[type].name; } /* Return the metafile type of this rtgroup inode. */ enum xfs_metafile_type xfs_rtginode_metafile_type( enum xfs_rtg_inodes type) { return xfs_rtginode_ops[type].metafile_type; } /* Should this rtgroup inode be present? */ bool xfs_rtginode_enabled( struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type) { const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; if (!ops->enabled) return true; return ops->enabled(rtg_mount(rtg)); } /* Mark an rtgroup inode sick */ void xfs_rtginode_mark_sick( struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type) { const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; xfs_group_mark_sick(rtg_group(rtg), ops->sick); } /* Load and existing rtgroup inode into the rtgroup structure. */ int xfs_rtginode_load( struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_inode *ip; const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; int error; if (!xfs_rtginode_enabled(rtg, type)) return 0; if (!xfs_has_rtgroups(mp)) { xfs_ino_t ino; switch (type) { case XFS_RTGI_BITMAP: ino = mp->m_sb.sb_rbmino; break; case XFS_RTGI_SUMMARY: ino = mp->m_sb.sb_rsumino; break; default: /* None of the other types exist on !rtgroups */ return 0; } error = xfs_trans_metafile_iget(tp, ino, ops->metafile_type, &ip); } else { const char *path; if (!mp->m_rtdirip) { xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); return -EFSCORRUPTED; } path = xfs_rtginode_path(rtg_rgno(rtg), type); if (!path) return -ENOMEM; error = xfs_metadir_load(tp, mp->m_rtdirip, path, ops->metafile_type, &ip); kfree(path); } if (error) { if (xfs_metadata_is_sick(error)) xfs_rtginode_mark_sick(rtg, type); return error; } if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) { xfs_irele(ip); xfs_rtginode_mark_sick(rtg, type); return -EFSCORRUPTED; } if (XFS_IS_CORRUPT(mp, ip->i_projid != rtg_rgno(rtg))) { xfs_irele(ip); xfs_rtginode_mark_sick(rtg, type); return -EFSCORRUPTED; } xfs_rtginode_lockdep_setup(ip, rtg_rgno(rtg), type); rtg->rtg_inodes[type] = ip; return 0; } /* Release an rtgroup metadata inode. */ void xfs_rtginode_irele( struct xfs_inode **ipp) { if (*ipp) xfs_irele(*ipp); *ipp = NULL; } /* Add a metadata inode for a realtime rmap btree. */ int xfs_rtginode_create( struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, bool init) { const struct xfs_rtginode_ops *ops = &xfs_rtginode_ops[type]; struct xfs_mount *mp = rtg_mount(rtg); struct xfs_metadir_update upd = { .dp = mp->m_rtdirip, .metafile_type = ops->metafile_type, }; int error; if (!xfs_rtginode_enabled(rtg, type)) return 0; if (!mp->m_rtdirip) { xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); return -EFSCORRUPTED; } upd.path = xfs_rtginode_path(rtg_rgno(rtg), type); if (!upd.path) return -ENOMEM; error = xfs_metadir_start_create(&upd); if (error) goto out_path; error = xfs_metadir_create(&upd, S_IFREG); if (error) goto out_cancel; xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type); upd.ip->i_projid = rtg_rgno(rtg); error = ops->create(rtg, upd.ip, upd.tp, init); if (error) goto out_cancel; error = xfs_metadir_commit(&upd); if (error) goto out_path; kfree(upd.path); xfs_finish_inode_setup(upd.ip); rtg->rtg_inodes[type] = upd.ip; return 0; out_cancel: xfs_metadir_cancel(&upd, error); /* Have to finish setting up the inode to ensure it's deleted. */ if (upd.ip) { xfs_finish_inode_setup(upd.ip); xfs_irele(upd.ip); } out_path: kfree(upd.path); return error; } /* Create the parent directory for all rtgroup inodes and load it. */ int xfs_rtginode_mkdir_parent( struct xfs_mount *mp) { if (!mp->m_metadirip) { xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); return -EFSCORRUPTED; } return xfs_metadir_mkdir(mp->m_metadirip, "rtgroups", &mp->m_rtdirip); } /* Load the parent directory of all rtgroup inodes. */ int xfs_rtginode_load_parent( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; if (!mp->m_metadirip) { xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR); return -EFSCORRUPTED; } return xfs_metadir_load(tp, mp->m_metadirip, "rtgroups", XFS_METAFILE_DIR, &mp->m_rtdirip); } /* Check superblock fields for a read or a write. */ static xfs_failaddr_t xfs_rtsb_verify_common( struct xfs_buf *bp) { struct xfs_rtsb *rsb = bp->b_addr; if (!xfs_verify_magic(bp, rsb->rsb_magicnum)) return __this_address; if (rsb->rsb_pad) return __this_address; /* Everything to the end of the fs block must be zero */ if (memchr_inv(rsb + 1, 0, BBTOB(bp->b_length) - sizeof(*rsb))) return __this_address; return NULL; } /* Check superblock fields for a read or revalidation. */ static inline xfs_failaddr_t xfs_rtsb_verify_all( struct xfs_buf *bp) { struct xfs_rtsb *rsb = bp->b_addr; struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; fa = xfs_rtsb_verify_common(bp); if (fa) return fa; if (memcmp(&rsb->rsb_fname, &mp->m_sb.sb_fname, XFSLABEL_MAX)) return __this_address; if (!uuid_equal(&rsb->rsb_uuid, &mp->m_sb.sb_uuid)) return __this_address; if (!uuid_equal(&rsb->rsb_meta_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; return NULL; } static void xfs_rtsb_read_verify( struct xfs_buf *bp) { xfs_failaddr_t fa; if (!xfs_buf_verify_cksum(bp, XFS_RTSB_CRC_OFF)) { xfs_verifier_error(bp, -EFSBADCRC, __this_address); return; } fa = xfs_rtsb_verify_all(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } static void xfs_rtsb_write_verify( struct xfs_buf *bp) { xfs_failaddr_t fa; fa = xfs_rtsb_verify_common(bp); if (fa) { xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } xfs_buf_update_cksum(bp, XFS_RTSB_CRC_OFF); } const struct xfs_buf_ops xfs_rtsb_buf_ops = { .name = "xfs_rtsb", .magic = { 0, cpu_to_be32(XFS_RTSB_MAGIC) }, .verify_read = xfs_rtsb_read_verify, .verify_write = xfs_rtsb_write_verify, .verify_struct = xfs_rtsb_verify_all, }; /* Update a realtime superblock from the primary fs super */ void xfs_update_rtsb( struct xfs_buf *rtsb_bp, const struct xfs_buf *sb_bp) { const struct xfs_dsb *dsb = sb_bp->b_addr; struct xfs_rtsb *rsb = rtsb_bp->b_addr; const uuid_t *meta_uuid; rsb->rsb_magicnum = cpu_to_be32(XFS_RTSB_MAGIC); rsb->rsb_pad = 0; memcpy(&rsb->rsb_fname, &dsb->sb_fname, XFSLABEL_MAX); memcpy(&rsb->rsb_uuid, &dsb->sb_uuid, sizeof(rsb->rsb_uuid)); /* * The metadata uuid is the fs uuid if the metauuid feature is not * enabled. */ if (dsb->sb_features_incompat & cpu_to_be32(XFS_SB_FEAT_INCOMPAT_META_UUID)) meta_uuid = &dsb->sb_meta_uuid; else meta_uuid = &dsb->sb_uuid; memcpy(&rsb->rsb_meta_uuid, meta_uuid, sizeof(rsb->rsb_meta_uuid)); } /* * Update the realtime superblock from a filesystem superblock and log it to * the given transaction. */ struct xfs_buf * xfs_log_rtsb( struct xfs_trans *tp, const struct xfs_buf *sb_bp) { struct xfs_buf *rtsb_bp; if (!xfs_has_rtsb(tp->t_mountp)) return NULL; rtsb_bp = xfs_trans_getrtsb(tp); if (!rtsb_bp) { /* * It's possible for the rtgroups feature to be enabled but * there is no incore rt superblock buffer if the rt geometry * was specified at mkfs time but the rt section has not yet * been attached. In this case, rblocks must be zero. */ ASSERT(tp->t_mountp->m_sb.sb_rblocks == 0); return NULL; } xfs_update_rtsb(rtsb_bp, sb_bp); xfs_trans_ordered_buf(tp, rtsb_bp); return rtsb_bp; } |
| 231 232 232 232 230 229 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2018-2024 Oracle. All Rights Reserved. * Author: Darrick J. Wong <djwong@kernel.org> */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_btree.h" #include "xfs_btree_staging.h" #include "xfs_metafile.h" #include "xfs_rmap.h" #include "xfs_rtrmap_btree.h" #include "xfs_trace.h" #include "xfs_cksum.h" #include "xfs_error.h" #include "xfs_extent_busy.h" #include "xfs_rtgroup.h" #include "xfs_bmap.h" #include "xfs_health.h" #include "xfs_buf_mem.h" #include "xfs_btree_mem.h" static struct kmem_cache *xfs_rtrmapbt_cur_cache; /* * Realtime Reverse Map btree. * * This is a btree used to track the owner(s) of a given extent in the realtime * device. See the comments in xfs_rmap_btree.c for more information. * * This tree is basically the same as the regular rmap btree except that it * is rooted in an inode and does not live in free space. */ static struct xfs_btree_cur * xfs_rtrmapbt_dup_cursor( struct xfs_btree_cur *cur) { return xfs_rtrmapbt_init_cursor(cur->bc_tp, to_rtg(cur->bc_group)); } STATIC int xfs_rtrmapbt_get_minrecs( struct xfs_btree_cur *cur, int level) { if (level == cur->bc_nlevels - 1) { struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, level == 0) / 2; } return cur->bc_mp->m_rtrmap_mnr[level != 0]; } STATIC int xfs_rtrmapbt_get_maxrecs( struct xfs_btree_cur *cur, int level) { if (level == cur->bc_nlevels - 1) { struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); return xfs_rtrmapbt_maxrecs(cur->bc_mp, ifp->if_broot_bytes, level == 0); } return cur->bc_mp->m_rtrmap_mxr[level != 0]; } /* Calculate number of records in the ondisk realtime rmap btree inode root. */ unsigned int xfs_rtrmapbt_droot_maxrecs( unsigned int blocklen, bool leaf) { blocklen -= sizeof(struct xfs_rtrmap_root); if (leaf) return blocklen / sizeof(struct xfs_rmap_rec); return blocklen / (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rtrmap_ptr_t)); } /* * Get the maximum records we could store in the on-disk format. * * For non-root nodes this is equivalent to xfs_rtrmapbt_get_maxrecs, but * for the root node this checks the available space in the dinode fork * so that we can resize the in-memory buffer to match it. After a * resize to the maximum size this function returns the same value * as xfs_rtrmapbt_get_maxrecs for the root node, too. */ STATIC int xfs_rtrmapbt_get_dmaxrecs( struct xfs_btree_cur *cur, int level) { if (level != cur->bc_nlevels - 1) return cur->bc_mp->m_rtrmap_mxr[level != 0]; return xfs_rtrmapbt_droot_maxrecs(cur->bc_ino.forksize, level == 0); } /* * Convert the ondisk record's offset field into the ondisk key's offset field. * Fork and bmbt are significant parts of the rmap record key, but written * status is merely a record attribute. */ static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) { return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); } STATIC void xfs_rtrmapbt_init_key_from_rec( union xfs_btree_key *key, const union xfs_btree_rec *rec) { key->rmap.rm_startblock = rec->rmap.rm_startblock; key->rmap.rm_owner = rec->rmap.rm_owner; key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); } STATIC void xfs_rtrmapbt_init_high_key_from_rec( union xfs_btree_key *key, const union xfs_btree_rec *rec) { uint64_t off; int adj; adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; key->rmap.rm_startblock = rec->rmap.rm_startblock; be32_add_cpu(&key->rmap.rm_startblock, adj); key->rmap.rm_owner = rec->rmap.rm_owner; key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) return; off = be64_to_cpu(key->rmap.rm_offset); off = (XFS_RMAP_OFF(off) + adj) | (off & ~XFS_RMAP_OFF_MASK); key->rmap.rm_offset = cpu_to_be64(off); } STATIC void xfs_rtrmapbt_init_rec_from_cur( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) { rec->rmap.rm_startblock = cpu_to_be32(cur->bc_rec.r.rm_startblock); rec->rmap.rm_blockcount = cpu_to_be32(cur->bc_rec.r.rm_blockcount); rec->rmap.rm_owner = cpu_to_be64(cur->bc_rec.r.rm_owner); rec->rmap.rm_offset = cpu_to_be64( xfs_rmap_irec_offset_pack(&cur->bc_rec.r)); } STATIC void xfs_rtrmapbt_init_ptr_from_cur( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr) { ptr->l = 0; } /* * Mask the appropriate parts of the ondisk key field for a key comparison. * Fork and bmbt are significant parts of the rmap record key, but written * status is merely a record attribute. */ static inline uint64_t offset_keymask(uint64_t offset) { return offset & ~XFS_RMAP_OFF_UNWRITTEN; } STATIC int64_t xfs_rtrmapbt_key_diff( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { struct xfs_rmap_irec *rec = &cur->bc_rec.r; const struct xfs_rmap_key *kp = &key->rmap; __u64 x, y; int64_t d; d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; if (d) return d; x = be64_to_cpu(kp->rm_owner); y = rec->rm_owner; if (x > y) return 1; else if (y > x) return -1; x = offset_keymask(be64_to_cpu(kp->rm_offset)); y = offset_keymask(xfs_rmap_irec_offset_pack(rec)); if (x > y) return 1; else if (y > x) return -1; return 0; } STATIC int64_t xfs_rtrmapbt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, const union xfs_btree_key *k2, const union xfs_btree_key *mask) { const struct xfs_rmap_key *kp1 = &k1->rmap; const struct xfs_rmap_key *kp2 = &k2->rmap; int64_t d; __u64 x, y; /* Doesn't make sense to mask off the physical space part */ ASSERT(!mask || mask->rmap.rm_startblock); d = (int64_t)be32_to_cpu(kp1->rm_startblock) - be32_to_cpu(kp2->rm_startblock); if (d) return d; if (!mask || mask->rmap.rm_owner) { x = be64_to_cpu(kp1->rm_owner); y = be64_to_cpu(kp2->rm_owner); if (x > y) return 1; else if (y > x) return -1; } if (!mask || mask->rmap.rm_offset) { /* Doesn't make sense to allow offset but not owner */ ASSERT(!mask || mask->rmap.rm_owner); x = offset_keymask(be64_to_cpu(kp1->rm_offset)); y = offset_keymask(be64_to_cpu(kp2->rm_offset)); if (x > y) return 1; else if (y > x) return -1; } return 0; } static xfs_failaddr_t xfs_rtrmapbt_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_failaddr_t fa; int level; if (!xfs_verify_magic(bp, block->bb_magic)) return __this_address; if (!xfs_has_rmapbt(mp)) return __this_address; fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); if (fa) return fa; level = be16_to_cpu(block->bb_level); if (level > mp->m_rtrmap_maxlevels) return __this_address; return xfs_btree_fsblock_verify(bp, mp->m_rtrmap_mxr[level != 0]); } static void xfs_rtrmapbt_read_verify( struct xfs_buf *bp) { xfs_failaddr_t fa; if (!xfs_btree_fsblock_verify_crc(bp)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_rtrmapbt_verify(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } if (bp->b_error) trace_xfs_btree_corrupt(bp, _RET_IP_); } static void xfs_rtrmapbt_write_verify( struct xfs_buf *bp) { xfs_failaddr_t fa; fa = xfs_rtrmapbt_verify(bp); if (fa) { trace_xfs_btree_corrupt(bp, _RET_IP_); xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } xfs_btree_fsblock_calc_crc(bp); } const struct xfs_buf_ops xfs_rtrmapbt_buf_ops = { .name = "xfs_rtrmapbt", .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, .verify_read = xfs_rtrmapbt_read_verify, .verify_write = xfs_rtrmapbt_write_verify, .verify_struct = xfs_rtrmapbt_verify, }; STATIC int xfs_rtrmapbt_keys_inorder( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, const union xfs_btree_key *k2) { uint32_t x; uint32_t y; uint64_t a; uint64_t b; x = be32_to_cpu(k1->rmap.rm_startblock); y = be32_to_cpu(k2->rmap.rm_startblock); if (x < y) return 1; else if (x > y) return 0; a = be64_to_cpu(k1->rmap.rm_owner); b = be64_to_cpu(k2->rmap.rm_owner); if (a < b) return 1; else if (a > b) return 0; a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); if (a <= b) return 1; return 0; } STATIC int xfs_rtrmapbt_recs_inorder( struct xfs_btree_cur *cur, const union xfs_btree_rec *r1, const union xfs_btree_rec *r2) { uint32_t x; uint32_t y; uint64_t a; uint64_t b; x = be32_to_cpu(r1->rmap.rm_startblock); y = be32_to_cpu(r2->rmap.rm_startblock); if (x < y) return 1; else if (x > y) return 0; a = be64_to_cpu(r1->rmap.rm_owner); b = be64_to_cpu(r2->rmap.rm_owner); if (a < b) return 1; else if (a > b) return 0; a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); if (a <= b) return 1; return 0; } STATIC enum xbtree_key_contig xfs_rtrmapbt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, const union xfs_btree_key *key2, const union xfs_btree_key *mask) { ASSERT(!mask || mask->rmap.rm_startblock); /* * We only support checking contiguity of the physical space component. * If any callers ever need more specificity than that, they'll have to * implement it here. */ ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), be32_to_cpu(key2->rmap.rm_startblock)); } static inline void xfs_rtrmapbt_move_ptrs( struct xfs_mount *mp, struct xfs_btree_block *broot, short old_size, size_t new_size, unsigned int numrecs) { void *dptr; void *sptr; sptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, old_size); dptr = xfs_rtrmap_broot_ptr_addr(mp, broot, 1, new_size); memmove(dptr, sptr, numrecs * sizeof(xfs_rtrmap_ptr_t)); } static struct xfs_btree_block * xfs_rtrmapbt_broot_realloc( struct xfs_btree_cur *cur, unsigned int new_numrecs) { struct xfs_mount *mp = cur->bc_mp; struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); struct xfs_btree_block *broot; unsigned int new_size; unsigned int old_size = ifp->if_broot_bytes; const unsigned int level = cur->bc_nlevels - 1; new_size = xfs_rtrmap_broot_space_calc(mp, level, new_numrecs); /* Handle the nop case quietly. */ if (new_size == old_size) return ifp->if_broot; if (new_size > old_size) { unsigned int old_numrecs; /* * If there wasn't any memory allocated before, just allocate * it now and get out. */ if (old_size == 0) return xfs_broot_realloc(ifp, new_size); /* * If there is already an existing if_broot, then we need to * realloc it and possibly move the node block pointers because * those are not butted up against the btree block header. */ old_numrecs = xfs_rtrmapbt_maxrecs(mp, old_size, level == 0); broot = xfs_broot_realloc(ifp, new_size); if (level > 0) xfs_rtrmapbt_move_ptrs(mp, broot, old_size, new_size, old_numrecs); goto out_broot; } /* * We're reducing numrecs. If we're going all the way to zero, just * free the block. */ ASSERT(ifp->if_broot != NULL && old_size > 0); if (new_size == 0) return xfs_broot_realloc(ifp, 0); /* * Shrink the btree root by possibly moving the rtrmapbt pointers, * since they are not butted up against the btree block header. Then * reallocate broot. */ if (level > 0) xfs_rtrmapbt_move_ptrs(mp, ifp->if_broot, old_size, new_size, new_numrecs); broot = xfs_broot_realloc(ifp, new_size); out_broot: ASSERT(xfs_rtrmap_droot_space(broot) <= xfs_inode_fork_size(cur->bc_ino.ip, cur->bc_ino.whichfork)); return broot; } const struct xfs_btree_ops xfs_rtrmapbt_ops = { .name = "rtrmap", .type = XFS_BTREE_TYPE_INODE, .geom_flags = XFS_BTGEO_OVERLAPPING | XFS_BTGEO_IROOT_RECORDS, .rec_len = sizeof(struct xfs_rmap_rec), /* Overlapping btree; 2 keys per pointer. */ .key_len = 2 * sizeof(struct xfs_rmap_key), .ptr_len = XFS_BTREE_LONG_PTR_LEN, .lru_refs = XFS_RMAP_BTREE_REF, .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_2), .sick_mask = XFS_SICK_RG_RMAPBT, .dup_cursor = xfs_rtrmapbt_dup_cursor, .alloc_block = xfs_btree_alloc_metafile_block, .free_block = xfs_btree_free_metafile_block, .get_minrecs = xfs_rtrmapbt_get_minrecs, .get_maxrecs = xfs_rtrmapbt_get_maxrecs, .get_dmaxrecs = xfs_rtrmapbt_get_dmaxrecs, .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, .init_ptr_from_cur = xfs_rtrmapbt_init_ptr_from_cur, .key_diff = xfs_rtrmapbt_key_diff, .buf_ops = &xfs_rtrmapbt_buf_ops, .diff_two_keys = xfs_rtrmapbt_diff_two_keys, .keys_inorder = xfs_rtrmapbt_keys_inorder, .recs_inorder = xfs_rtrmapbt_recs_inorder, .keys_contiguous = xfs_rtrmapbt_keys_contiguous, .broot_realloc = xfs_rtrmapbt_broot_realloc, }; /* Allocate a new rt rmap btree cursor. */ struct xfs_btree_cur * xfs_rtrmapbt_init_cursor( struct xfs_trans *tp, struct xfs_rtgroup *rtg) { struct xfs_inode *ip = rtg_rmap(rtg); struct xfs_mount *mp = rtg_mount(rtg); struct xfs_btree_cur *cur; xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL); cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops, mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); cur->bc_ino.ip = ip; cur->bc_group = xfs_group_hold(rtg_group(rtg)); cur->bc_ino.whichfork = XFS_DATA_FORK; cur->bc_nlevels = be16_to_cpu(ip->i_df.if_broot->bb_level) + 1; cur->bc_ino.forksize = xfs_inode_fork_size(ip, XFS_DATA_FORK); return cur; } #ifdef CONFIG_XFS_BTREE_IN_MEM /* * Validate an in-memory realtime rmap btree block. Callers are allowed to * generate an in-memory btree even if the ondisk feature is not enabled. */ static xfs_failaddr_t xfs_rtrmapbt_mem_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_failaddr_t fa; unsigned int level; unsigned int maxrecs; if (!xfs_verify_magic(bp, block->bb_magic)) return __this_address; fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN); if (fa) return fa; level = be16_to_cpu(block->bb_level); if (xfs_has_rmapbt(mp)) { if (level >= mp->m_rtrmap_maxlevels) return __this_address; } else { if (level >= xfs_rtrmapbt_maxlevels_ondisk()) return __this_address; } maxrecs = xfs_rtrmapbt_maxrecs(mp, XFBNO_BLOCKSIZE, level == 0); return xfs_btree_memblock_verify(bp, maxrecs); } static void xfs_rtrmapbt_mem_rw_verify( struct xfs_buf *bp) { xfs_failaddr_t fa = xfs_rtrmapbt_mem_verify(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } /* skip crc checks on in-memory btrees to save time */ static const struct xfs_buf_ops xfs_rtrmapbt_mem_buf_ops = { .name = "xfs_rtrmapbt_mem", .magic = { 0, cpu_to_be32(XFS_RTRMAP_CRC_MAGIC) }, .verify_read = xfs_rtrmapbt_mem_rw_verify, .verify_write = xfs_rtrmapbt_mem_rw_verify, .verify_struct = xfs_rtrmapbt_mem_verify, }; const struct xfs_btree_ops xfs_rtrmapbt_mem_ops = { .type = XFS_BTREE_TYPE_MEM, .geom_flags = XFS_BTGEO_OVERLAPPING, .rec_len = sizeof(struct xfs_rmap_rec), /* Overlapping btree; 2 keys per pointer. */ .key_len = 2 * sizeof(struct xfs_rmap_key), .ptr_len = XFS_BTREE_LONG_PTR_LEN, .lru_refs = XFS_RMAP_BTREE_REF, .statoff = XFS_STATS_CALC_INDEX(xs_rtrmap_mem_2), .dup_cursor = xfbtree_dup_cursor, .set_root = xfbtree_set_root, .alloc_block = xfbtree_alloc_block, .free_block = xfbtree_free_block, .get_minrecs = xfbtree_get_minrecs, .get_maxrecs = xfbtree_get_maxrecs, .init_key_from_rec = xfs_rtrmapbt_init_key_from_rec, .init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec, .init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur, .init_ptr_from_cur = xfbtree_init_ptr_from_cur, .key_diff = xfs_rtrmapbt_key_diff, .buf_ops = &xfs_rtrmapbt_mem_buf_ops, .diff_two_keys = xfs_rtrmapbt_diff_two_keys, .keys_inorder = xfs_rtrmapbt_keys_inorder, .recs_inorder = xfs_rtrmapbt_recs_inorder, .keys_contiguous = xfs_rtrmapbt_keys_contiguous, }; /* Create a cursor for an in-memory btree. */ struct xfs_btree_cur * xfs_rtrmapbt_mem_cursor( struct xfs_rtgroup *rtg, struct xfs_trans *tp, struct xfbtree *xfbt) { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_btree_cur *cur; cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); cur->bc_mem.xfbtree = xfbt; cur->bc_nlevels = xfbt->nlevels; cur->bc_group = xfs_group_hold(rtg_group(rtg)); return cur; } /* Create an in-memory realtime rmap btree. */ int xfs_rtrmapbt_mem_init( struct xfs_mount *mp, struct xfbtree *xfbt, struct xfs_buftarg *btp, xfs_rgnumber_t rgno) { xfbt->owner = rgno; return xfbtree_init(mp, xfbt, btp, &xfs_rtrmapbt_mem_ops); } #endif /* CONFIG_XFS_BTREE_IN_MEM */ /* * Install a new rt reverse mapping btree root. Caller is responsible for * invalidating and freeing the old btree blocks. */ void xfs_rtrmapbt_commit_staged_btree( struct xfs_btree_cur *cur, struct xfs_trans *tp) { struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake; struct xfs_ifork *ifp; int flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT; ASSERT(cur->bc_flags & XFS_BTREE_STAGING); ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_META_BTREE); /* * Free any resources hanging off the real fork, then shallow-copy the * staging fork's contents into the real fork to transfer everything * we just built. */ ifp = xfs_ifork_ptr(cur->bc_ino.ip, XFS_DATA_FORK); xfs_idestroy_fork(ifp); memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork)); cur->bc_ino.ip->i_projid = cur->bc_group->xg_gno; xfs_trans_log_inode(tp, cur->bc_ino.ip, flags); xfs_btree_commit_ifakeroot(cur, tp, XFS_DATA_FORK); } /* Calculate number of records in a rt reverse mapping btree block. */ static inline unsigned int xfs_rtrmapbt_block_maxrecs( unsigned int blocklen, bool leaf) { if (leaf) return blocklen / sizeof(struct xfs_rmap_rec); return blocklen / (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rtrmap_ptr_t)); } /* * Calculate number of records in an rt reverse mapping btree block. */ unsigned int xfs_rtrmapbt_maxrecs( struct xfs_mount *mp, unsigned int blocklen, bool leaf) { blocklen -= XFS_RTRMAP_BLOCK_LEN; return xfs_rtrmapbt_block_maxrecs(blocklen, leaf); } /* Compute the max possible height for realtime reverse mapping btrees. */ unsigned int xfs_rtrmapbt_maxlevels_ondisk(void) { unsigned long long max_dblocks; unsigned int minrecs[2]; unsigned int blocklen; blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN; minrecs[0] = xfs_rtrmapbt_block_maxrecs(blocklen, true) / 2; minrecs[1] = xfs_rtrmapbt_block_maxrecs(blocklen, false) / 2; /* * Compute the asymptotic maxlevels for an rtrmapbt on any rtreflink fs. * * On a reflink filesystem, each block in an rtgroup can have up to * 2^32 (per the refcount record format) owners, which means that * theoretically we could face up to 2^64 rmap records. However, we're * likely to run out of blocks in the data device long before that * happens, which means that we must compute the max height based on * what the btree will look like if it consumes almost all the blocks * in the data device due to maximal sharing factor. */ max_dblocks = -1U; /* max ag count */ max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; return xfs_btree_space_to_height(minrecs, max_dblocks); } int __init xfs_rtrmapbt_init_cur_cache(void) { xfs_rtrmapbt_cur_cache = kmem_cache_create("xfs_rtrmapbt_cur", xfs_btree_cur_sizeof(xfs_rtrmapbt_maxlevels_ondisk()), 0, 0, NULL); if (!xfs_rtrmapbt_cur_cache) return -ENOMEM; return 0; } void xfs_rtrmapbt_destroy_cur_cache(void) { kmem_cache_destroy(xfs_rtrmapbt_cur_cache); xfs_rtrmapbt_cur_cache = NULL; } /* Compute the maximum height of an rt reverse mapping btree. */ void xfs_rtrmapbt_compute_maxlevels( struct xfs_mount *mp) { unsigned int d_maxlevels, r_maxlevels; if (!xfs_has_rtrmapbt(mp)) { mp->m_rtrmap_maxlevels = 0; return; } /* * The realtime rmapbt lives on the data device, which means that its * maximum height is constrained by the size of the data device and * the height required to store one rmap record for each block in an * rt group. * * On a reflink filesystem, each rt block can have up to 2^32 (per the * refcount record format) owners, which means that theoretically we * could face up to 2^64 rmap records. This makes the computation of * maxlevels based on record count meaningless, so we only consider the * size of the data device. */ d_maxlevels = xfs_btree_space_to_height(mp->m_rtrmap_mnr, mp->m_sb.sb_dblocks); if (xfs_has_rtreflink(mp)) { mp->m_rtrmap_maxlevels = d_maxlevels + 1; return; } r_maxlevels = xfs_btree_compute_maxlevels(mp->m_rtrmap_mnr, mp->m_groups[XG_TYPE_RTG].blocks); /* Add one level to handle the inode root level. */ mp->m_rtrmap_maxlevels = min(d_maxlevels, r_maxlevels) + 1; } /* Calculate the rtrmap btree size for some records. */ unsigned long long xfs_rtrmapbt_calc_size( struct xfs_mount *mp, unsigned long long len) { return xfs_btree_calc_size(mp->m_rtrmap_mnr, len); } /* * Calculate the maximum rmap btree size. */ static unsigned long long xfs_rtrmapbt_max_size( struct xfs_mount *mp, xfs_rtblock_t rtblocks) { /* Bail out if we're uninitialized, which can happen in mkfs. */ if (mp->m_rtrmap_mxr[0] == 0) return 0; return xfs_rtrmapbt_calc_size(mp, rtblocks); } /* * Figure out how many blocks to reserve and how many are used by this btree. */ xfs_filblks_t xfs_rtrmapbt_calc_reserves( struct xfs_mount *mp) { uint32_t blocks = mp->m_groups[XG_TYPE_RTG].blocks; if (!xfs_has_rtrmapbt(mp)) return 0; /* Reserve 1% of the rtgroup or enough for 1 block per record. */ return max_t(xfs_filblks_t, blocks / 100, xfs_rtrmapbt_max_size(mp, blocks)); } /* Convert on-disk form of btree root to in-memory form. */ STATIC void xfs_rtrmapbt_from_disk( struct xfs_inode *ip, struct xfs_rtrmap_root *dblock, unsigned int dblocklen, struct xfs_btree_block *rblock) { struct xfs_mount *mp = ip->i_mount; struct xfs_rmap_key *fkp; __be64 *fpp; struct xfs_rmap_key *tkp; __be64 *tpp; struct xfs_rmap_rec *frp; struct xfs_rmap_rec *trp; unsigned int rblocklen = xfs_rtrmap_broot_space(mp, dblock); unsigned int numrecs; unsigned int maxrecs; xfs_btree_init_block(mp, rblock, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); rblock->bb_level = dblock->bb_level; rblock->bb_numrecs = dblock->bb_numrecs; numrecs = be16_to_cpu(dblock->bb_numrecs); if (be16_to_cpu(rblock->bb_level) > 0) { maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); fkp = xfs_rtrmap_droot_key_addr(dblock, 1); tkp = xfs_rtrmap_key_addr(rblock, 1); fpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); tpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); memcpy(tpp, fpp, sizeof(*fpp) * numrecs); } else { frp = xfs_rtrmap_droot_rec_addr(dblock, 1); trp = xfs_rtrmap_rec_addr(rblock, 1); memcpy(trp, frp, sizeof(*frp) * numrecs); } } /* Load a realtime reverse mapping btree root in from disk. */ int xfs_iformat_rtrmap( struct xfs_inode *ip, struct xfs_dinode *dip) { struct xfs_mount *mp = ip->i_mount; struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); struct xfs_btree_block *broot; unsigned int numrecs; unsigned int level; int dsize; /* * growfs must create the rtrmap inodes before adding a realtime volume * to the filesystem, so we cannot use the rtrmapbt predicate here. */ if (!xfs_has_rmapbt(ip->i_mount)) { xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } dsize = XFS_DFORK_SIZE(dip, mp, XFS_DATA_FORK); numrecs = be16_to_cpu(dfp->bb_numrecs); level = be16_to_cpu(dfp->bb_level); if (level > mp->m_rtrmap_maxlevels || xfs_rtrmap_droot_space_calc(level, numrecs) > dsize) { xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return -EFSCORRUPTED; } broot = xfs_broot_alloc(xfs_ifork_ptr(ip, XFS_DATA_FORK), xfs_rtrmap_broot_space_calc(mp, level, numrecs)); if (broot) xfs_rtrmapbt_from_disk(ip, dfp, dsize, broot); return 0; } /* Convert in-memory form of btree root to on-disk form. */ void xfs_rtrmapbt_to_disk( struct xfs_mount *mp, struct xfs_btree_block *rblock, unsigned int rblocklen, struct xfs_rtrmap_root *dblock, unsigned int dblocklen) { struct xfs_rmap_key *fkp; __be64 *fpp; struct xfs_rmap_key *tkp; __be64 *tpp; struct xfs_rmap_rec *frp; struct xfs_rmap_rec *trp; unsigned int numrecs; unsigned int maxrecs; ASSERT(rblock->bb_magic == cpu_to_be32(XFS_RTRMAP_CRC_MAGIC)); ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)); ASSERT(rblock->bb_u.l.bb_blkno == cpu_to_be64(XFS_BUF_DADDR_NULL)); ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)); ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)); dblock->bb_level = rblock->bb_level; dblock->bb_numrecs = rblock->bb_numrecs; numrecs = be16_to_cpu(rblock->bb_numrecs); if (be16_to_cpu(rblock->bb_level) > 0) { maxrecs = xfs_rtrmapbt_droot_maxrecs(dblocklen, false); fkp = xfs_rtrmap_key_addr(rblock, 1); tkp = xfs_rtrmap_droot_key_addr(dblock, 1); fpp = xfs_rtrmap_broot_ptr_addr(mp, rblock, 1, rblocklen); tpp = xfs_rtrmap_droot_ptr_addr(dblock, 1, maxrecs); memcpy(tkp, fkp, 2 * sizeof(*fkp) * numrecs); memcpy(tpp, fpp, sizeof(*fpp) * numrecs); } else { frp = xfs_rtrmap_rec_addr(rblock, 1); trp = xfs_rtrmap_droot_rec_addr(dblock, 1); memcpy(trp, frp, sizeof(*frp) * numrecs); } } /* Flush a realtime reverse mapping btree root out to disk. */ void xfs_iflush_rtrmap( struct xfs_inode *ip, struct xfs_dinode *dip) { struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); struct xfs_rtrmap_root *dfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK); ASSERT(ifp->if_broot != NULL); ASSERT(ifp->if_broot_bytes > 0); ASSERT(xfs_rtrmap_droot_space(ifp->if_broot) <= xfs_inode_fork_size(ip, XFS_DATA_FORK)); xfs_rtrmapbt_to_disk(ip->i_mount, ifp->if_broot, ifp->if_broot_bytes, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, XFS_DATA_FORK)); } /* * Create a realtime rmap btree inode. */ int xfs_rtrmapbt_create( struct xfs_rtgroup *rtg, struct xfs_inode *ip, struct xfs_trans *tp, bool init) { struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); struct xfs_mount *mp = ip->i_mount; struct xfs_btree_block *broot; ifp->if_format = XFS_DINODE_FMT_META_BTREE; ASSERT(ifp->if_broot_bytes == 0); ASSERT(ifp->if_bytes == 0); /* Initialize the empty incore btree root. */ broot = xfs_broot_realloc(ifp, xfs_rtrmap_broot_space_calc(mp, 0, 0)); if (broot) xfs_btree_init_block(mp, broot, &xfs_rtrmapbt_ops, 0, 0, ip->i_ino); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE | XFS_ILOG_DBROOT); return 0; } /* * Initialize an rmap for a realtime superblock using the potentially updated * rt geometry in the provided @mp. */ int xfs_rtrmapbt_init_rtsb( struct xfs_mount *mp, struct xfs_rtgroup *rtg, struct xfs_trans *tp) { struct xfs_rmap_irec rmap = { .rm_blockcount = mp->m_sb.sb_rextsize, .rm_owner = XFS_RMAP_OWN_FS, }; struct xfs_btree_cur *cur; int error; ASSERT(xfs_has_rtsb(mp)); ASSERT(rtg_rgno(rtg) == 0); cur = xfs_rtrmapbt_init_cursor(tp, rtg); error = xfs_rmap_map_raw(cur, &rmap); xfs_btree_del_cursor(cur, error); return error; } /* * Return the highest rgbno currently tracked by the rmap for this rtg. */ xfs_rgblock_t xfs_rtrmap_highest_rgbno( struct xfs_rtgroup *rtg) { struct xfs_btree_block *block = rtg_rmap(rtg)->i_df.if_broot; union xfs_btree_key key = {}; struct xfs_btree_cur *cur; if (block->bb_numrecs == 0) return NULLRGBLOCK; cur = xfs_rtrmapbt_init_cursor(NULL, rtg); xfs_btree_get_keys(cur, block, &key); xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return be32_to_cpu(key.__rmap_bigkey[1].rm_startblock); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of the Linux kernel. * * Copyright (c) 2011-2014, Intel Corporation * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ #ifndef ASM_X86_ARCHRANDOM_H #define ASM_X86_ARCHRANDOM_H #include <asm/processor.h> #include <asm/cpufeature.h> #define RDRAND_RETRY_LOOPS 10 /* Unconditional execution of RDRAND and RDSEED */ static inline bool __must_check rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked. */ static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) { return max_longs && static_cpu_has(X86_FEATURE_RDRAND) && rdrand_long(v) ? 1 : 0; } static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) { return max_longs && static_cpu_has(X86_FEATURE_RDSEED) && rdseed_long(v) ? 1 : 0; } #ifndef CONFIG_UML void x86_init_rdrand(struct cpuinfo_x86 *c); #endif #endif /* ASM_X86_ARCHRANDOM_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2011-2014, Intel Corporation. */ #ifndef _NVME_H #define _NVME_H #include <linux/nvme.h> #include <linux/cdev.h> #include <linux/pci.h> #include <linux/kref.h> #include <linux/blk-mq.h> #include <linux/sed-opal.h> #include <linux/fault-inject.h> #include <linux/rcupdate.h> #include <linux/wait.h> #include <linux/t10-pi.h> #include <linux/ratelimit_types.h> #include <trace/events/block.h> extern const struct pr_ops nvme_pr_ops; extern unsigned int nvme_io_timeout; #define NVME_IO_TIMEOUT (nvme_io_timeout * HZ) extern unsigned int admin_timeout; #define NVME_ADMIN_TIMEOUT (admin_timeout * HZ) #define NVME_DEFAULT_KATO 5 #ifdef CONFIG_ARCH_NO_SG_CHAIN #define NVME_INLINE_SG_CNT 0 #define NVME_INLINE_METADATA_SG_CNT 0 #else #define NVME_INLINE_SG_CNT 2 #define NVME_INLINE_METADATA_SG_CNT 1 #endif /* * Default to a 4K page size, with the intention to update this * path in the future to accommodate architectures with differing * kernel and IO page sizes. */ #define NVME_CTRL_PAGE_SHIFT 12 #define NVME_CTRL_PAGE_SIZE (1 << NVME_CTRL_PAGE_SHIFT) extern struct workqueue_struct *nvme_wq; extern struct workqueue_struct *nvme_reset_wq; extern struct workqueue_struct *nvme_delete_wq; extern struct mutex nvme_subsystems_lock; /* * List of workarounds for devices that required behavior not specified in * the standard. */ enum nvme_quirks { /* * Prefers I/O aligned to a stripe size specified in a vendor * specific Identify field. */ NVME_QUIRK_STRIPE_SIZE = (1 << 0), /* * The controller doesn't handle Identify value others than 0 or 1 * correctly. */ NVME_QUIRK_IDENTIFY_CNS = (1 << 1), /* * The controller deterministically returns O's on reads to * logical blocks that deallocate was called on. */ NVME_QUIRK_DEALLOCATE_ZEROES = (1 << 2), /* * The controller needs a delay before starts checking the device * readiness, which is done by reading the NVME_CSTS_RDY bit. */ NVME_QUIRK_DELAY_BEFORE_CHK_RDY = (1 << 3), /* * APST should not be used. */ NVME_QUIRK_NO_APST = (1 << 4), /* * The deepest sleep state should not be used. */ NVME_QUIRK_NO_DEEPEST_PS = (1 << 5), /* * Problems seen with concurrent commands */ NVME_QUIRK_QDEPTH_ONE = (1 << 6), /* * Set MEDIUM priority on SQ creation */ NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7), /* * Ignore device provided subnqn. */ NVME_QUIRK_IGNORE_DEV_SUBNQN = (1 << 8), /* * Broken Write Zeroes. */ NVME_QUIRK_DISABLE_WRITE_ZEROES = (1 << 9), /* * Force simple suspend/resume path. */ NVME_QUIRK_SIMPLE_SUSPEND = (1 << 10), /* * Use only one interrupt vector for all queues */ NVME_QUIRK_SINGLE_VECTOR = (1 << 11), /* * Use non-standard 128 bytes SQEs. */ NVME_QUIRK_128_BYTES_SQES = (1 << 12), /* * Prevent tag overlap between queues */ NVME_QUIRK_SHARED_TAGS = (1 << 13), /* * Don't change the value of the temperature threshold feature */ NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14), /* * The controller doesn't handle the Identify Namespace * Identification Descriptor list subcommand despite claiming * NVMe 1.3 compliance. */ NVME_QUIRK_NO_NS_DESC_LIST = (1 << 15), /* * The controller does not properly handle DMA addresses over * 48 bits. */ NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16), /* * The controller requires the command_id value be limited, so skip * encoding the generation sequence number. */ NVME_QUIRK_SKIP_CID_GEN = (1 << 17), /* * Reports garbage in the namespace identifiers (eui64, nguid, uuid). */ NVME_QUIRK_BOGUS_NID = (1 << 18), /* * No temperature thresholds for channels other than 0 (Composite). */ NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), /* * Disables simple suspend/resume path. */ NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND = (1 << 20), /* * MSI (but not MSI-X) interrupts are broken and never fire. */ NVME_QUIRK_BROKEN_MSI = (1 << 21), /* * Align dma pool segment size to 512 bytes */ NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22), }; /* * Common request structure for NVMe passthrough. All drivers must have * this structure as the first member of their request-private data. */ struct nvme_request { struct nvme_command *cmd; union nvme_result result; u8 genctr; u8 retries; u8 flags; u16 status; #ifdef CONFIG_NVME_MULTIPATH unsigned long start_time; #endif struct nvme_ctrl *ctrl; }; /* * Mark a bio as coming in through the mpath node. */ #define REQ_NVME_MPATH REQ_DRV enum { NVME_REQ_CANCELLED = (1 << 0), NVME_REQ_USERCMD = (1 << 1), NVME_MPATH_IO_STATS = (1 << 2), NVME_MPATH_CNT_ACTIVE = (1 << 3), }; static inline struct nvme_request *nvme_req(struct request *req) { return blk_mq_rq_to_pdu(req); } static inline u16 nvme_req_qid(struct request *req) { if (!req->q->queuedata) return 0; return req->mq_hctx->queue_num + 1; } /* The below value is the specific amount of delay needed before checking * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was * found empirically. */ #define NVME_QUIRK_DELAY_AMOUNT 2300 /* * enum nvme_ctrl_state: Controller state * * @NVME_CTRL_NEW: New controller just allocated, initial state * @NVME_CTRL_LIVE: Controller is connected and I/O capable * @NVME_CTRL_RESETTING: Controller is resetting (or scheduled reset) * @NVME_CTRL_CONNECTING: Controller is disconnected, now connecting the * transport * @NVME_CTRL_DELETING: Controller is deleting (or scheduled deletion) * @NVME_CTRL_DELETING_NOIO: Controller is deleting and I/O is not * disabled/failed immediately. This state comes * after all async event processing took place and * before ns removal and the controller deletion * progress * @NVME_CTRL_DEAD: Controller is non-present/unresponsive during * shutdown or removal. In this case we forcibly * kill all inflight I/O as they have no chance to * complete */ enum nvme_ctrl_state { NVME_CTRL_NEW, NVME_CTRL_LIVE, NVME_CTRL_RESETTING, NVME_CTRL_CONNECTING, NVME_CTRL_DELETING, NVME_CTRL_DELETING_NOIO, NVME_CTRL_DEAD, }; struct nvme_fault_inject { #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS struct fault_attr attr; struct dentry *parent; bool dont_retry; /* DNR, do not retry */ u16 status; /* status code */ #endif }; enum nvme_ctrl_flags { NVME_CTRL_FAILFAST_EXPIRED = 0, NVME_CTRL_ADMIN_Q_STOPPED = 1, NVME_CTRL_STARTED_ONCE = 2, NVME_CTRL_STOPPED = 3, NVME_CTRL_SKIP_ID_CNS_CS = 4, NVME_CTRL_DIRTY_CAPABILITY = 5, NVME_CTRL_FROZEN = 6, }; struct nvme_ctrl { bool comp_seen; bool identified; bool passthru_err_log_enabled; enum nvme_ctrl_state state; spinlock_t lock; struct mutex scan_lock; const struct nvme_ctrl_ops *ops; struct request_queue *admin_q; struct request_queue *connect_q; struct request_queue *fabrics_q; struct device *dev; int instance; int numa_node; struct blk_mq_tag_set *tagset; struct blk_mq_tag_set *admin_tagset; struct list_head namespaces; struct mutex namespaces_lock; struct srcu_struct srcu; struct device ctrl_device; struct device *device; /* char device */ #ifdef CONFIG_NVME_HWMON struct device *hwmon_device; #endif struct cdev cdev; struct work_struct reset_work; struct work_struct delete_work; wait_queue_head_t state_wq; struct nvme_subsystem *subsys; struct list_head subsys_entry; struct opal_dev *opal_dev; u16 cntlid; u16 mtfa; u32 ctrl_config; u32 queue_count; u64 cap; u32 max_hw_sectors; u32 max_segments; u32 max_integrity_segments; u32 max_zeroes_sectors; #ifdef CONFIG_BLK_DEV_ZONED u32 max_zone_append; #endif u16 crdt[3]; u16 oncs; u8 dmrl; u32 dmrsl; u16 oacs; u16 sqsize; u32 max_namespaces; atomic_t abort_limit; u8 vwc; u32 vs; u32 sgls; u16 kas; u8 npss; u8 apsta; u16 wctemp; u16 cctemp; u32 oaes; u32 aen_result; u32 ctratt; unsigned int shutdown_timeout; unsigned int kato; bool subsystem; unsigned long quirks; struct nvme_id_power_state psd[32]; struct nvme_effects_log *effects; struct xarray cels; struct work_struct scan_work; struct work_struct async_event_work; struct delayed_work ka_work; struct delayed_work failfast_work; struct nvme_command ka_cmd; unsigned long ka_last_check_time; struct work_struct fw_act_work; unsigned long events; #ifdef CONFIG_NVME_MULTIPATH /* asymmetric namespace access: */ u8 anacap; u8 anatt; u32 anagrpmax; u32 nanagrpid; struct mutex ana_lock; struct nvme_ana_rsp_hdr *ana_log_buf; size_t ana_log_size; struct timer_list anatt_timer; struct work_struct ana_work; atomic_t nr_active; #endif #ifdef CONFIG_NVME_HOST_AUTH struct work_struct dhchap_auth_work; struct mutex dhchap_auth_mutex; struct nvme_dhchap_queue_context *dhchap_ctxs; struct nvme_dhchap_key *host_key; struct nvme_dhchap_key *ctrl_key; u16 transaction; #endif key_serial_t tls_pskid; /* Power saving configuration */ u64 ps_max_latency_us; bool apst_enabled; /* PCIe only: */ u16 hmmaxd; u32 hmpre; u32 hmmin; u32 hmminds; /* Fabrics only */ u32 ioccsz; u32 iorcsz; u16 icdoff; u16 maxcmd; int nr_reconnects; unsigned long flags; struct nvmf_ctrl_options *opts; struct page *discard_page; unsigned long discard_page_busy; struct nvme_fault_inject fault_inject; enum nvme_ctrl_type cntrltype; enum nvme_dctype dctype; }; static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) { return READ_ONCE(ctrl->state); } enum nvme_iopolicy { NVME_IOPOLICY_NUMA, NVME_IOPOLICY_RR, NVME_IOPOLICY_QD, }; struct nvme_subsystem { int instance; struct device dev; /* * Because we unregister the device on the last put we need * a separate refcount. */ struct kref ref; struct list_head entry; struct mutex lock; struct list_head ctrls; struct list_head nsheads; char subnqn[NVMF_NQN_SIZE]; char serial[20]; char model[40]; char firmware_rev[8]; u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; u16 awupf; /* 0's based value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; #endif }; /* * Container structure for uniqueue namespace identifiers. */ struct nvme_ns_ids { u8 eui64[8]; u8 nguid[16]; uuid_t uuid; u8 csi; }; /* * Anchor structure for namespaces. There is one for each namespace in a * NVMe subsystem that any of our controllers can see, and the namespace * structure for each controller is chained of it. For private namespaces * there is a 1:1 relation to our namespace structures, that is ->list * only ever has a single entry for private namespaces. */ struct nvme_ns_head { struct list_head list; struct srcu_struct srcu; struct nvme_subsystem *subsys; struct nvme_ns_ids ids; u8 lba_shift; u16 ms; u16 pi_size; u8 pi_type; u8 guard_type; struct list_head entry; struct kref ref; bool shared; bool rotational; bool passthru_err_log_enabled; struct nvme_effects_log *effects; u64 nuse; unsigned ns_id; int instance; #ifdef CONFIG_BLK_DEV_ZONED u64 zsze; #endif unsigned long features; struct ratelimit_state rs_nuse; struct cdev cdev; struct device cdev_device; struct gendisk *disk; u16 nr_plids; u16 *plids; #ifdef CONFIG_NVME_MULTIPATH struct bio_list requeue_list; spinlock_t requeue_lock; struct work_struct requeue_work; struct work_struct partition_scan_work; struct mutex lock; unsigned long flags; struct delayed_work remove_work; unsigned int delayed_removal_secs; #define NVME_NSHEAD_DISK_LIVE 0 #define NVME_NSHEAD_QUEUE_IF_NO_PATH 1 struct nvme_ns __rcu *current_path[]; #endif }; static inline bool nvme_ns_head_multipath(struct nvme_ns_head *head) { return IS_ENABLED(CONFIG_NVME_MULTIPATH) && head->disk; } enum nvme_ns_features { NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */ NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */ NVME_NS_DEAC = 1 << 2, /* DEAC bit in Write Zeroes supported */ }; struct nvme_ns { struct list_head list; struct nvme_ctrl *ctrl; struct request_queue *queue; struct gendisk *disk; #ifdef CONFIG_NVME_MULTIPATH enum nvme_ana_state ana_state; u32 ana_grpid; #endif struct list_head siblings; struct kref kref; struct nvme_ns_head *head; unsigned long flags; #define NVME_NS_REMOVING 0 #define NVME_NS_ANA_PENDING 2 #define NVME_NS_FORCE_RO 3 #define NVME_NS_READY 4 #define NVME_NS_SYSFS_ATTR_LINK 5 struct cdev cdev; struct device cdev_device; struct nvme_fault_inject fault_inject; }; /* NVMe ns supports metadata actions by the controller (generate/strip) */ static inline bool nvme_ns_has_pi(struct nvme_ns_head *head) { return head->pi_type && head->ms == head->pi_size; } struct nvme_ctrl_ops { const char *name; struct module *module; unsigned int flags; #define NVME_F_FABRICS (1 << 0) #define NVME_F_METADATA_SUPPORTED (1 << 1) #define NVME_F_BLOCKING (1 << 2) const struct attribute_group **dev_attr_groups; int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val); int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val); int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val); void (*free_ctrl)(struct nvme_ctrl *ctrl); void (*submit_async_event)(struct nvme_ctrl *ctrl); int (*subsystem_reset)(struct nvme_ctrl *ctrl); void (*delete_ctrl)(struct nvme_ctrl *ctrl); void (*stop_ctrl)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); void (*print_device_info)(struct nvme_ctrl *ctrl); bool (*supports_pci_p2pdma)(struct nvme_ctrl *ctrl); }; /* * nvme command_id is constructed as such: * | xxxx | xxxxxxxxxxxx | * gen request tag */ #define nvme_genctr_mask(gen) (gen & 0xf) #define nvme_cid_install_genctr(gen) (nvme_genctr_mask(gen) << 12) #define nvme_genctr_from_cid(cid) ((cid & 0xf000) >> 12) #define nvme_tag_from_cid(cid) (cid & 0xfff) static inline u16 nvme_cid(struct request *rq) { return nvme_cid_install_genctr(nvme_req(rq)->genctr) | rq->tag; } static inline struct request *nvme_find_rq(struct blk_mq_tags *tags, u16 command_id) { u8 genctr = nvme_genctr_from_cid(command_id); u16 tag = nvme_tag_from_cid(command_id); struct request *rq; rq = blk_mq_tag_to_rq(tags, tag); if (unlikely(!rq)) { pr_err("could not locate request for tag %#x\n", tag); return NULL; } if (unlikely(nvme_genctr_mask(nvme_req(rq)->genctr) != genctr)) { dev_err(nvme_req(rq)->ctrl->device, "request %#x genctr mismatch (got %#x expected %#x)\n", tag, genctr, nvme_genctr_mask(nvme_req(rq)->genctr)); return NULL; } return rq; } static inline struct request *nvme_cid_to_rq(struct blk_mq_tags *tags, u16 command_id) { return blk_mq_tag_to_rq(tags, nvme_tag_from_cid(command_id)); } /* * Return the length of the string without the space padding */ static inline int nvme_strlen(char *s, int len) { while (s[len - 1] == ' ') len--; return len; } static inline void nvme_print_device_info(struct nvme_ctrl *ctrl) { struct nvme_subsystem *subsys = ctrl->subsys; if (ctrl->ops->print_device_info) { ctrl->ops->print_device_info(ctrl); return; } dev_err(ctrl->device, "VID:%04x model:%.*s firmware:%.*s\n", subsys->vendor_id, nvme_strlen(subsys->model, sizeof(subsys->model)), subsys->model, nvme_strlen(subsys->firmware_rev, sizeof(subsys->firmware_rev)), subsys->firmware_rev); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, const char *dev_name); void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject); void nvme_should_fail(struct request *req); #else static inline void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, const char *dev_name) { } static inline void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inj) { } static inline void nvme_should_fail(struct request *req) {} #endif bool nvme_wait_reset(struct nvme_ctrl *ctrl); int nvme_try_sched_reset(struct nvme_ctrl *ctrl); static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) { if (!ctrl->subsystem || !ctrl->ops->subsystem_reset) return -ENOTTY; return ctrl->ops->subsystem_reset(ctrl); } /* * Convert a 512B sector number to a device logical block number. */ static inline u64 nvme_sect_to_lba(struct nvme_ns_head *head, sector_t sector) { return sector >> (head->lba_shift - SECTOR_SHIFT); } /* * Convert a device logical block number to a 512B sector number. */ static inline sector_t nvme_lba_to_sect(struct nvme_ns_head *head, u64 lba) { return lba << (head->lba_shift - SECTOR_SHIFT); } /* * Convert byte length to nvme's 0-based num dwords */ static inline u32 nvme_bytes_to_numd(size_t len) { return (len >> 2) - 1; } static inline bool nvme_is_ana_error(u16 status) { switch (status & NVME_SCT_SC_MASK) { case NVME_SC_ANA_TRANSITION: case NVME_SC_ANA_INACCESSIBLE: case NVME_SC_ANA_PERSISTENT_LOSS: return true; default: return false; } } static inline bool nvme_is_path_error(u16 status) { /* check for a status code type of 'path related status' */ return (status & NVME_SCT_MASK) == NVME_SCT_PATH; } /* * Fill in the status and result information from the CQE, and then figure out * if blk-mq will need to use IPI magic to complete the request, and if yes do * so. If not let the caller complete the request without an indirect function * call. */ static inline bool nvme_try_complete_req(struct request *req, __le16 status, union nvme_result result) { struct nvme_request *rq = nvme_req(req); struct nvme_ctrl *ctrl = rq->ctrl; if (!(ctrl->quirks & NVME_QUIRK_SKIP_CID_GEN)) rq->genctr++; rq->status = le16_to_cpu(status) >> 1; rq->result = result; /* inject error when permitted by fault injection framework */ nvme_should_fail(req); if (unlikely(blk_should_fake_timeout(req->q))) return true; return blk_mq_complete_request_remote(req); } static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl) { get_device(ctrl->device); } static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl) { put_device(ctrl->device); } static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) { return !qid && nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH; } /* * Returns true for sink states that can't ever transition back to live. */ static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl) { switch (nvme_ctrl_state(ctrl)) { case NVME_CTRL_NEW: case NVME_CTRL_LIVE: case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: return false; case NVME_CTRL_DELETING: case NVME_CTRL_DELETING_NOIO: case NVME_CTRL_DEAD: return true; default: WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state); return true; } } void nvme_end_req(struct request *req); void nvme_complete_rq(struct request *req); void nvme_complete_batch_req(struct request *req); static __always_inline void nvme_complete_batch(struct io_comp_batch *iob, void (*fn)(struct request *rq)) { struct request *req; rq_list_for_each(&iob->req_list, req) { fn(req); nvme_complete_batch_req(req); } blk_mq_end_request_batch(iob); } blk_status_t nvme_host_path_error(struct request *req); bool nvme_cancel_request(struct request *req, void *data); void nvme_cancel_tagset(struct nvme_ctrl *ctrl); void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state); int nvme_disable_ctrl(struct nvme_ctrl *ctrl, bool shutdown); int nvme_enable_ctrl(struct nvme_ctrl *ctrl); int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, const struct nvme_ctrl_ops *ops, unsigned long quirks); int nvme_add_ctrl(struct nvme_ctrl *ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl); void nvme_start_ctrl(struct nvme_ctrl *ctrl); void nvme_stop_ctrl(struct nvme_ctrl *ctrl); int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl, bool was_suspended); int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int cmd_size); void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl); int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int nr_maps, unsigned int cmd_size); void nvme_remove_io_tag_set(struct nvme_ctrl *ctrl); void nvme_remove_namespaces(struct nvme_ctrl *ctrl); void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, volatile union nvme_result *res); void nvme_quiesce_io_queues(struct nvme_ctrl *ctrl); void nvme_unquiesce_io_queues(struct nvme_ctrl *ctrl); void nvme_quiesce_admin_queue(struct nvme_ctrl *ctrl); void nvme_unquiesce_admin_queue(struct nvme_ctrl *ctrl); void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl); void nvme_sync_queues(struct nvme_ctrl *ctrl); void nvme_sync_io_queues(struct nvme_ctrl *ctrl); void nvme_unfreeze(struct nvme_ctrl *ctrl); void nvme_wait_freeze(struct nvme_ctrl *ctrl); int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout); void nvme_start_freeze(struct nvme_ctrl *ctrl); static inline enum req_op nvme_req_op(struct nvme_command *cmd) { return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN; } #define NVME_QID_ANY -1 void nvme_init_request(struct request *req, struct nvme_command *cmd); void nvme_cleanup_cmd(struct request *req); blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req); blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, struct request *req); bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live, enum nvme_ctrl_state state); static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live) { enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); if (likely(state == NVME_CTRL_LIVE)) return true; if (ctrl->ops->flags & NVME_F_FABRICS && state == NVME_CTRL_DELETING) return queue_live; return __nvme_check_ready(ctrl, rq, queue_live, state); } /* * NSID shall be unique for all shared namespaces, or if at least one of the * following conditions is met: * 1. Namespace Management is supported by the controller * 2. ANA is supported by the controller * 3. NVM Set are supported by the controller * * In other case, private namespace are not required to report a unique NSID. */ static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { return head->shared || (ctrl->oacs & NVME_CTRL_OACS_NS_MNGT_SUPP) || (ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) || (ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS); } /* * Flags for __nvme_submit_sync_cmd() */ typedef __u32 __bitwise nvme_submit_flags_t; enum { /* Insert request at the head of the queue */ NVME_SUBMIT_AT_HEAD = (__force nvme_submit_flags_t)(1 << 0), /* Set BLK_MQ_REQ_NOWAIT when allocating request */ NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1), /* Set BLK_MQ_REQ_RESERVED when allocating request */ NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2), /* Retry command when NVME_STATUS_DNR is not set in the result */ NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3), }; int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buf, unsigned bufflen); int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, int qid, nvme_submit_flags_t flags); int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, void *result); int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, void *result); int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl); int nvme_delete_ctrl(struct nvme_ctrl *ctrl); void nvme_queue_scan(struct nvme_ctrl *ctrl); int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, void *log, size_t size, u64 offset); bool nvme_tryget_ns_head(struct nvme_ns_head *head); void nvme_put_ns_head(struct nvme_ns_head *head); int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, const struct file_operations *fops, struct module *owner); void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device); int nvme_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long nvme_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd, struct io_comp_batch *iob, unsigned int poll_flags); int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, struct nvme_id_ns **id); int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo); int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); extern const struct attribute_group *nvme_ns_attr_groups[]; extern const struct attribute_group nvme_ns_mpath_attr_group; extern const struct pr_ops nvme_pr_ops; extern const struct block_device_operations nvme_ns_head_ops; extern const struct attribute_group nvme_dev_attrs_group; extern const struct attribute_group *nvme_subsys_attrs_groups[]; extern const struct attribute_group *nvme_dev_attr_groups[]; extern const struct block_device_operations nvme_bdev_ops; void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl); struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); #ifdef CONFIG_NVME_MULTIPATH static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) { return ctrl->ana_log_buf != NULL; } void nvme_mpath_unfreeze(struct nvme_subsystem *subsys); void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys); void nvme_mpath_start_freeze(struct nvme_subsystem *subsys); void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys); void nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_sysfs_link(struct nvme_ns_head *ns); void nvme_mpath_remove_sysfs_link(struct nvme_ns *ns); void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid); void nvme_mpath_put_disk(struct nvme_ns_head *head); int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); void nvme_mpath_update(struct nvme_ctrl *ctrl); void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); void nvme_mpath_revalidate_paths(struct nvme_ns *ns); void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl); void nvme_mpath_remove_disk(struct nvme_ns_head *head); void nvme_mpath_start_request(struct request *rq); void nvme_mpath_end_request(struct request *rq); static inline void nvme_trace_bio_complete(struct request *req) { struct nvme_ns *ns = req->q->queuedata; if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio) trace_block_bio_complete(ns->head->disk->queue, req->bio); } extern bool multipath; extern struct device_attribute dev_attr_ana_grpid; extern struct device_attribute dev_attr_ana_state; extern struct device_attribute dev_attr_queue_depth; extern struct device_attribute dev_attr_numa_nodes; extern struct device_attribute dev_attr_delayed_removal_secs; extern struct device_attribute subsys_attr_iopolicy; static inline bool nvme_disk_is_ns_head(struct gendisk *disk) { return disk->fops == &nvme_ns_head_ops; } static inline bool nvme_mpath_queue_if_no_path(struct nvme_ns_head *head) { if (test_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags)) return true; return false; } #else #define multipath false static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) { return false; } static inline void nvme_failover_req(struct request *req) { } static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) { } static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { return 0; } static inline void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) { } static inline void nvme_mpath_put_disk(struct nvme_ns_head *head) { } static inline void nvme_mpath_add_sysfs_link(struct nvme_ns *ns) { } static inline void nvme_mpath_remove_sysfs_link(struct nvme_ns *ns) { } static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns) { return false; } static inline void nvme_mpath_revalidate_paths(struct nvme_ns *ns) { } static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) { } static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) { } static inline void nvme_trace_bio_complete(struct request *req) { } static inline void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) { } static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { if (ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) dev_warn(ctrl->device, "Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n"); return 0; } static inline void nvme_mpath_update(struct nvme_ctrl *ctrl) { } static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl) { } static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl) { } static inline void nvme_mpath_unfreeze(struct nvme_subsystem *subsys) { } static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) { } static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) { } static inline void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys) { } static inline void nvme_mpath_start_request(struct request *rq) { } static inline void nvme_mpath_end_request(struct request *rq) { } static inline bool nvme_disk_is_ns_head(struct gendisk *disk) { return false; } static inline bool nvme_mpath_queue_if_no_path(struct nvme_ns_head *head) { return false; } #endif /* CONFIG_NVME_MULTIPATH */ int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16], enum blk_unique_id type); struct nvme_zone_info { u64 zone_size; unsigned int max_open_zones; unsigned int max_active_zones; }; int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf, struct nvme_zone_info *zi); void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim, struct nvme_zone_info *zi); #ifdef CONFIG_BLK_DEV_ZONED blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_zone_mgmt_action action); #else static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_zone_mgmt_action action) { return BLK_STS_NOTSUPP; } #endif static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); WARN_ON(nvme_disk_is_ns_head(disk)); return disk->private_data; } #ifdef CONFIG_NVME_HWMON int nvme_hwmon_init(struct nvme_ctrl *ctrl); void nvme_hwmon_exit(struct nvme_ctrl *ctrl); #else static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl) { return 0; } static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl) { } #endif static inline void nvme_start_request(struct request *rq) { if (rq->cmd_flags & REQ_NVME_MPATH) nvme_mpath_start_request(rq); blk_mq_start_request(rq); } static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl) { return ctrl->sgls & (NVME_CTRL_SGLS_BYTE_ALIGNED | NVME_CTRL_SGLS_DWORD_ALIGNED); } static inline bool nvme_ctrl_meta_sgl_supported(struct nvme_ctrl *ctrl) { if (ctrl->ops->flags & NVME_F_FABRICS) return true; return ctrl->sgls & NVME_CTRL_SGLS_MSDS; } #ifdef CONFIG_NVME_HOST_AUTH int __init nvme_init_auth(void); void __exit nvme_exit_auth(void); int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl); void nvme_auth_stop(struct nvme_ctrl *ctrl); int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid); int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid); void nvme_auth_free(struct nvme_ctrl *ctrl); void nvme_auth_revoke_tls_key(struct nvme_ctrl *ctrl); #else static inline int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl) { return 0; } static inline int __init nvme_init_auth(void) { return 0; } static inline void __exit nvme_exit_auth(void) { } static inline void nvme_auth_stop(struct nvme_ctrl *ctrl) {}; static inline int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) { return -EPROTONOSUPPORT; } static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid) { return -EPROTONOSUPPORT; } static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; static inline void nvme_auth_revoke_tls_key(struct nvme_ctrl *ctrl) {}; #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); int nvme_execute_rq(struct request *rq, bool at_head); void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status); struct nvme_ctrl *nvme_ctrl_from_file(struct file *file); struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid); bool nvme_get_ns(struct nvme_ns *ns); void nvme_put_ns(struct nvme_ns *ns); static inline bool nvme_multi_css(struct nvme_ctrl *ctrl) { return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI; } #endif /* _NVME_H */ |
| 19 18 19 19 2 19 2 18 19 2 17 19 2 17 19 19 19 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Power Management Quality of Service (PM QoS) support base. * * Copyright (C) 2020 Intel Corporation * * Authors: * Mark Gross <mgross@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * * Provided here is an interface for specifying PM QoS dependencies. It allows * entities depending on QoS constraints to register their requests which are * aggregated as appropriate to produce effective constraints (target values) * that can be monitored by entities needing to respect them, either by polling * or through a built-in notification mechanism. * * In addition to the basic functionality, more specific interfaces for managing * global CPU latency QoS requests and frequency QoS requests are provided. */ /*#define DEBUG*/ #include <linux/pm_qos.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/miscdevice.h> #include <linux/string.h> #include <linux/platform_device.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/export.h> #include <trace/events/power.h> /* * locking rule: all changes to constraints or notifiers lists * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock * held, taken with _irqsave. One lock to rule them all */ static DEFINE_SPINLOCK(pm_qos_lock); /** * pm_qos_read_value - Return the current effective constraint value. * @c: List of PM QoS constraint requests. */ s32 pm_qos_read_value(struct pm_qos_constraints *c) { return READ_ONCE(c->target_value); } static int pm_qos_get_value(struct pm_qos_constraints *c) { if (plist_head_empty(&c->list)) return c->no_constraint_value; switch (c->type) { case PM_QOS_MIN: return plist_first(&c->list)->prio; case PM_QOS_MAX: return plist_last(&c->list)->prio; default: WARN(1, "Unknown PM QoS type in %s\n", __func__); return PM_QOS_DEFAULT_VALUE; } } static void pm_qos_set_value(struct pm_qos_constraints *c, s32 value) { WRITE_ONCE(c->target_value, value); } /** * pm_qos_update_target - Update a list of PM QoS constraint requests. * @c: List of PM QoS requests. * @node: Target list entry. * @action: Action to carry out (add, update or remove). * @value: New request value for the target list entry. * * Update the given list of PM QoS constraint requests, @c, by carrying an * @action involving the @node list entry and @value on it. * * The recognized values of @action are PM_QOS_ADD_REQ (store @value in @node * and add it to the list), PM_QOS_UPDATE_REQ (remove @node from the list, store * @value in it and add it to the list again), and PM_QOS_REMOVE_REQ (remove * @node from the list, ignore @value). * * Return: 1 if the aggregate constraint value has changed, 0 otherwise. */ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, enum pm_qos_req_action action, int value) { int prev_value, curr_value, new_value; unsigned long flags; spin_lock_irqsave(&pm_qos_lock, flags); prev_value = pm_qos_get_value(c); if (value == PM_QOS_DEFAULT_VALUE) new_value = c->default_value; else new_value = value; switch (action) { case PM_QOS_REMOVE_REQ: plist_del(node, &c->list); break; case PM_QOS_UPDATE_REQ: /* * To change the list, atomically remove, reinit with new value * and add, then see if the aggregate has changed. */ plist_del(node, &c->list); fallthrough; case PM_QOS_ADD_REQ: plist_node_init(node, new_value); plist_add(node, &c->list); break; default: /* no action */ ; } curr_value = pm_qos_get_value(c); pm_qos_set_value(c, curr_value); spin_unlock_irqrestore(&pm_qos_lock, flags); trace_pm_qos_update_target(action, prev_value, curr_value); if (prev_value == curr_value) return 0; if (c->notifiers) blocking_notifier_call_chain(c->notifiers, curr_value, NULL); return 1; } /** * pm_qos_flags_remove_req - Remove device PM QoS flags request. * @pqf: Device PM QoS flags set to remove the request from. * @req: Request to remove from the set. */ static void pm_qos_flags_remove_req(struct pm_qos_flags *pqf, struct pm_qos_flags_request *req) { s32 val = 0; list_del(&req->node); list_for_each_entry(req, &pqf->list, node) val |= req->flags; pqf->effective_flags = val; } /** * pm_qos_update_flags - Update a set of PM QoS flags. * @pqf: Set of PM QoS flags to update. * @req: Request to add to the set, to modify, or to remove from the set. * @action: Action to take on the set. * @val: Value of the request to add or modify. * * Return: 1 if the aggregate constraint value has changed, 0 otherwise. */ bool pm_qos_update_flags(struct pm_qos_flags *pqf, struct pm_qos_flags_request *req, enum pm_qos_req_action action, s32 val) { unsigned long irqflags; s32 prev_value, curr_value; spin_lock_irqsave(&pm_qos_lock, irqflags); prev_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags; switch (action) { case PM_QOS_REMOVE_REQ: pm_qos_flags_remove_req(pqf, req); break; case PM_QOS_UPDATE_REQ: pm_qos_flags_remove_req(pqf, req); fallthrough; case PM_QOS_ADD_REQ: req->flags = val; INIT_LIST_HEAD(&req->node); list_add_tail(&req->node, &pqf->list); pqf->effective_flags |= val; break; default: /* no action */ ; } curr_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags; spin_unlock_irqrestore(&pm_qos_lock, irqflags); trace_pm_qos_update_flags(action, prev_value, curr_value); return prev_value != curr_value; } #ifdef CONFIG_CPU_IDLE /* Definitions related to the CPU latency QoS. */ static struct pm_qos_constraints cpu_latency_constraints = { .list = PLIST_HEAD_INIT(cpu_latency_constraints.list), .target_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE, .default_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE, .no_constraint_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE, .type = PM_QOS_MIN, }; static inline bool cpu_latency_qos_value_invalid(s32 value) { return value < 0 && value != PM_QOS_DEFAULT_VALUE; } /** * cpu_latency_qos_limit - Return current system-wide CPU latency QoS limit. */ s32 cpu_latency_qos_limit(void) { return pm_qos_read_value(&cpu_latency_constraints); } /** * cpu_latency_qos_request_active - Check the given PM QoS request. * @req: PM QoS request to check. * * Return: 'true' if @req has been added to the CPU latency QoS list, 'false' * otherwise. */ bool cpu_latency_qos_request_active(struct pm_qos_request *req) { return req->qos == &cpu_latency_constraints; } EXPORT_SYMBOL_GPL(cpu_latency_qos_request_active); static void cpu_latency_qos_apply(struct pm_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret = pm_qos_update_target(req->qos, &req->node, action, value); if (ret > 0) wake_up_all_idle_cpus(); } /** * cpu_latency_qos_add_request - Add new CPU latency QoS request. * @req: Pointer to a preallocated handle. * @value: Requested constraint value. * * Use @value to initialize the request handle pointed to by @req, insert it as * a new entry to the CPU latency QoS list and recompute the effective QoS * constraint for that list. * * Callers need to save the handle for later use in updates and removal of the * QoS request represented by it. */ void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value) { if (!req || cpu_latency_qos_value_invalid(value)) return; if (cpu_latency_qos_request_active(req)) { WARN(1, KERN_ERR "%s called for already added request\n", __func__); return; } trace_pm_qos_add_request(value); req->qos = &cpu_latency_constraints; cpu_latency_qos_apply(req, PM_QOS_ADD_REQ, value); } EXPORT_SYMBOL_GPL(cpu_latency_qos_add_request); /** * cpu_latency_qos_update_request - Modify existing CPU latency QoS request. * @req : QoS request to update. * @new_value: New requested constraint value. * * Use @new_value to update the QoS request represented by @req in the CPU * latency QoS list along with updating the effective constraint value for that * list. */ void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value) { if (!req || cpu_latency_qos_value_invalid(new_value)) return; if (!cpu_latency_qos_request_active(req)) { WARN(1, KERN_ERR "%s called for unknown object\n", __func__); return; } trace_pm_qos_update_request(new_value); if (new_value == req->node.prio) return; cpu_latency_qos_apply(req, PM_QOS_UPDATE_REQ, new_value); } EXPORT_SYMBOL_GPL(cpu_latency_qos_update_request); /** * cpu_latency_qos_remove_request - Remove existing CPU latency QoS request. * @req: QoS request to remove. * * Remove the CPU latency QoS request represented by @req from the CPU latency * QoS list along with updating the effective constraint value for that list. */ void cpu_latency_qos_remove_request(struct pm_qos_request *req) { if (!req) return; if (!cpu_latency_qos_request_active(req)) { WARN(1, KERN_ERR "%s called for unknown object\n", __func__); return; } trace_pm_qos_remove_request(PM_QOS_DEFAULT_VALUE); cpu_latency_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } EXPORT_SYMBOL_GPL(cpu_latency_qos_remove_request); /* User space interface to the CPU latency QoS via misc device. */ static int cpu_latency_qos_open(struct inode *inode, struct file *filp) { struct pm_qos_request *req; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; cpu_latency_qos_add_request(req, PM_QOS_DEFAULT_VALUE); filp->private_data = req; return 0; } static int cpu_latency_qos_release(struct inode *inode, struct file *filp) { struct pm_qos_request *req = filp->private_data; filp->private_data = NULL; cpu_latency_qos_remove_request(req); kfree(req); return 0; } static ssize_t cpu_latency_qos_read(struct file *filp, char __user *buf, size_t count, loff_t *f_pos) { struct pm_qos_request *req = filp->private_data; unsigned long flags; s32 value; if (!req || !cpu_latency_qos_request_active(req)) return -EINVAL; spin_lock_irqsave(&pm_qos_lock, flags); value = pm_qos_get_value(&cpu_latency_constraints); spin_unlock_irqrestore(&pm_qos_lock, flags); return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32)); } static ssize_t cpu_latency_qos_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) { s32 value; if (count == sizeof(s32)) { if (copy_from_user(&value, buf, sizeof(s32))) return -EFAULT; } else { int ret; ret = kstrtos32_from_user(buf, count, 16, &value); if (ret) return ret; } cpu_latency_qos_update_request(filp->private_data, value); return count; } static const struct file_operations cpu_latency_qos_fops = { .write = cpu_latency_qos_write, .read = cpu_latency_qos_read, .open = cpu_latency_qos_open, .release = cpu_latency_qos_release, .llseek = noop_llseek, }; static struct miscdevice cpu_latency_qos_miscdev = { .minor = MISC_DYNAMIC_MINOR, .name = "cpu_dma_latency", .fops = &cpu_latency_qos_fops, }; static int __init cpu_latency_qos_init(void) { int ret; ret = misc_register(&cpu_latency_qos_miscdev); if (ret < 0) pr_err("%s: %s setup failed\n", __func__, cpu_latency_qos_miscdev.name); return ret; } late_initcall(cpu_latency_qos_init); #endif /* CONFIG_CPU_IDLE */ /* Definitions related to the frequency QoS below. */ static inline bool freq_qos_value_invalid(s32 value) { return value < 0 && value != PM_QOS_DEFAULT_VALUE; } /** * freq_constraints_init - Initialize frequency QoS constraints. * @qos: Frequency QoS constraints to initialize. */ void freq_constraints_init(struct freq_constraints *qos) { struct pm_qos_constraints *c; c = &qos->min_freq; plist_head_init(&c->list); c->target_value = FREQ_QOS_MIN_DEFAULT_VALUE; c->default_value = FREQ_QOS_MIN_DEFAULT_VALUE; c->no_constraint_value = FREQ_QOS_MIN_DEFAULT_VALUE; c->type = PM_QOS_MAX; c->notifiers = &qos->min_freq_notifiers; BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers); c = &qos->max_freq; plist_head_init(&c->list); c->target_value = FREQ_QOS_MAX_DEFAULT_VALUE; c->default_value = FREQ_QOS_MAX_DEFAULT_VALUE; c->no_constraint_value = FREQ_QOS_MAX_DEFAULT_VALUE; c->type = PM_QOS_MIN; c->notifiers = &qos->max_freq_notifiers; BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers); } /** * freq_qos_read_value - Get frequency QoS constraint for a given list. * @qos: Constraints to evaluate. * @type: QoS request type. */ s32 freq_qos_read_value(struct freq_constraints *qos, enum freq_qos_req_type type) { s32 ret; switch (type) { case FREQ_QOS_MIN: ret = IS_ERR_OR_NULL(qos) ? FREQ_QOS_MIN_DEFAULT_VALUE : pm_qos_read_value(&qos->min_freq); break; case FREQ_QOS_MAX: ret = IS_ERR_OR_NULL(qos) ? FREQ_QOS_MAX_DEFAULT_VALUE : pm_qos_read_value(&qos->max_freq); break; default: WARN_ON(1); ret = 0; } return ret; } /** * freq_qos_apply - Add/modify/remove frequency QoS request. * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. * * This is only meant to be called from inside pm_qos, not drivers. */ int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; switch(req->type) { case FREQ_QOS_MIN: ret = pm_qos_update_target(&req->qos->min_freq, &req->pnode, action, value); break; case FREQ_QOS_MAX: ret = pm_qos_update_target(&req->qos->max_freq, &req->pnode, action, value); break; default: ret = -EINVAL; } return ret; } /** * freq_qos_add_request - Insert new frequency QoS request into a given list. * @qos: Constraints to update. * @req: Preallocated request object. * @type: Request type. * @value: Request value. * * Insert a new entry into the @qos list of requests, recompute the effective * QoS constraint value for that list and initialize the @req object. The * caller needs to save that object for later use in updates and removal. * * Return 1 if the effective constraint value has changed, 0 if the effective * constraint value has not changed, or a negative error code on failures. */ int freq_qos_add_request(struct freq_constraints *qos, struct freq_qos_request *req, enum freq_qos_req_type type, s32 value) { int ret; if (IS_ERR_OR_NULL(qos) || !req || freq_qos_value_invalid(value)) return -EINVAL; if (WARN(freq_qos_request_active(req), "%s() called for active request\n", __func__)) return -EINVAL; req->qos = qos; req->type = type; ret = freq_qos_apply(req, PM_QOS_ADD_REQ, value); if (ret < 0) { req->qos = NULL; req->type = 0; } return ret; } EXPORT_SYMBOL_GPL(freq_qos_add_request); /** * freq_qos_update_request - Modify existing frequency QoS request. * @req: Request to modify. * @new_value: New request value. * * Update an existing frequency QoS request along with the effective constraint * value for the list of requests it belongs to. * * Return 1 if the effective constraint value has changed, 0 if the effective * constraint value has not changed, or a negative error code on failures. */ int freq_qos_update_request(struct freq_qos_request *req, s32 new_value) { if (!req || freq_qos_value_invalid(new_value)) return -EINVAL; if (WARN(!freq_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (req->pnode.prio == new_value) return 0; return freq_qos_apply(req, PM_QOS_UPDATE_REQ, new_value); } EXPORT_SYMBOL_GPL(freq_qos_update_request); /** * freq_qos_remove_request - Remove frequency QoS request from its list. * @req: Request to remove. * * Remove the given frequency QoS request from the list of constraints it * belongs to and recompute the effective constraint value for that list. * * Return 1 if the effective constraint value has changed, 0 if the effective * constraint value has not changed, or a negative error code on failures. */ int freq_qos_remove_request(struct freq_qos_request *req) { int ret; if (!req) return -EINVAL; if (WARN(!freq_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; ret = freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); req->qos = NULL; req->type = 0; return ret; } EXPORT_SYMBOL_GPL(freq_qos_remove_request); /** * freq_qos_add_notifier - Add frequency QoS change notifier. * @qos: List of requests to add the notifier to. * @type: Request type. * @notifier: Notifier block to add. */ int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, struct notifier_block *notifier) { int ret; if (IS_ERR_OR_NULL(qos) || !notifier) return -EINVAL; switch (type) { case FREQ_QOS_MIN: ret = blocking_notifier_chain_register(qos->min_freq.notifiers, notifier); break; case FREQ_QOS_MAX: ret = blocking_notifier_chain_register(qos->max_freq.notifiers, notifier); break; default: WARN_ON(1); ret = -EINVAL; } return ret; } EXPORT_SYMBOL_GPL(freq_qos_add_notifier); /** * freq_qos_remove_notifier - Remove frequency QoS change notifier. * @qos: List of requests to remove the notifier from. * @type: Request type. * @notifier: Notifier block to remove. */ int freq_qos_remove_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, struct notifier_block *notifier) { int ret; if (IS_ERR_OR_NULL(qos) || !notifier) return -EINVAL; switch (type) { case FREQ_QOS_MIN: ret = blocking_notifier_chain_unregister(qos->min_freq.notifiers, notifier); break; case FREQ_QOS_MAX: ret = blocking_notifier_chain_unregister(qos->max_freq.notifiers, notifier); break; default: WARN_ON(1); ret = -EINVAL; } return ret; } EXPORT_SYMBOL_GPL(freq_qos_remove_notifier); |
| 4 315 556 7 651 53 262 4 24 145 638 128 132 9 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * fscrypt.h: declarations for per-file encryption * * Filesystems that implement per-file encryption must include this header * file. * * Copyright (C) 2015, Google, Inc. * * Written by Michael Halcrow, 2015. * Modified by Jaegeuk Kim, 2015. */ #ifndef _LINUX_FSCRYPT_H #define _LINUX_FSCRYPT_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/slab.h> #include <uapi/linux/fscrypt.h> /* * The lengths of all file contents blocks must be divisible by this value. * This is needed to ensure that all contents encryption modes will work, as * some of the supported modes don't support arbitrarily byte-aligned messages. * * Since the needed alignment is 16 bytes, most filesystems will meet this * requirement naturally, as typical block sizes are powers of 2. However, if a * filesystem can generate arbitrarily byte-aligned block lengths (e.g., via * compression), then it will need to pad to this alignment before encryption. */ #define FSCRYPT_CONTENTS_ALIGNMENT 16 union fscrypt_policy; struct fscrypt_inode_info; struct fs_parameter; struct seq_file; struct fscrypt_str { unsigned char *name; u32 len; }; struct fscrypt_name { const struct qstr *usr_fname; struct fscrypt_str disk_name; u32 hash; u32 minor_hash; struct fscrypt_str crypto_buf; bool is_nokey_name; }; #define FSTR_INIT(n, l) { .name = n, .len = l } #define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) #define fname_name(p) ((p)->disk_name.name) #define fname_len(p) ((p)->disk_name.len) /* Maximum value for the third parameter of fscrypt_operations.set_context(). */ #define FSCRYPT_SET_CONTEXT_MAX_SIZE 40 #ifdef CONFIG_FS_ENCRYPTION /* Crypto operations for filesystems */ struct fscrypt_operations { /* * If set, then fs/crypto/ will allocate a global bounce page pool the * first time an encryption key is set up for a file. The bounce page * pool is required by the following functions: * * - fscrypt_encrypt_pagecache_blocks() * - fscrypt_zeroout_range() for files not using inline crypto * * If the filesystem doesn't use those, it doesn't need to set this. */ unsigned int needs_bounce_pages : 1; /* * If set, then fs/crypto/ will allow the use of encryption settings * that assume inode numbers fit in 32 bits (i.e. * FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64}), provided that the other * prerequisites for these settings are also met. This is only useful * if the filesystem wants to support inline encryption hardware that is * limited to 32-bit or 64-bit data unit numbers and where programming * keyslots is very slow. */ unsigned int has_32bit_inodes : 1; /* * If set, then fs/crypto/ will allow users to select a crypto data unit * size that is less than the filesystem block size. This is done via * the log2_data_unit_size field of the fscrypt policy. This flag is * not compatible with filesystems that encrypt variable-length blocks * (i.e. blocks that aren't all equal to filesystem's block size), for * example as a result of compression. It's also not compatible with * the fscrypt_encrypt_block_inplace() and * fscrypt_decrypt_block_inplace() functions. */ unsigned int supports_subblock_data_units : 1; /* * This field exists only for backwards compatibility reasons and should * only be set by the filesystems that are setting it already. It * contains the filesystem-specific key description prefix that is * accepted for "logon" keys for v1 fscrypt policies. This * functionality is deprecated in favor of the generic prefix * "fscrypt:", which itself is deprecated in favor of the filesystem * keyring ioctls such as FS_IOC_ADD_ENCRYPTION_KEY. Filesystems that * are newly adding fscrypt support should not set this field. */ const char *legacy_key_prefix; /* * Get the fscrypt context of the given inode. * * @inode: the inode whose context to get * @ctx: the buffer into which to get the context * @len: length of the @ctx buffer in bytes * * Return: On success, returns the length of the context in bytes; this * may be less than @len. On failure, returns -ENODATA if the * inode doesn't have a context, -ERANGE if the context is * longer than @len, or another -errno code. */ int (*get_context)(struct inode *inode, void *ctx, size_t len); /* * Set an fscrypt context on the given inode. * * @inode: the inode whose context to set. The inode won't already have * an fscrypt context. * @ctx: the context to set * @len: length of @ctx in bytes (at most FSCRYPT_SET_CONTEXT_MAX_SIZE) * @fs_data: If called from fscrypt_set_context(), this will be the * value the filesystem passed to fscrypt_set_context(). * Otherwise (i.e. when called from * FS_IOC_SET_ENCRYPTION_POLICY) this will be NULL. * * i_rwsem will be held for write. * * Return: 0 on success, -errno on failure. */ int (*set_context)(struct inode *inode, const void *ctx, size_t len, void *fs_data); /* * Get the dummy fscrypt policy in use on the filesystem (if any). * * Filesystems only need to implement this function if they support the * test_dummy_encryption mount option. * * Return: A pointer to the dummy fscrypt policy, if the filesystem is * mounted with test_dummy_encryption; otherwise NULL. */ const union fscrypt_policy *(*get_dummy_policy)(struct super_block *sb); /* * Check whether a directory is empty. i_rwsem will be held for write. */ bool (*empty_dir)(struct inode *inode); /* * Check whether the filesystem's inode numbers and UUID are stable, * meaning that they will never be changed even by offline operations * such as filesystem shrinking and therefore can be used in the * encryption without the possibility of files becoming unreadable. * * Filesystems only need to implement this function if they want to * support the FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64} flags. These * flags are designed to work around the limitations of UFS and eMMC * inline crypto hardware, and they shouldn't be used in scenarios where * such hardware isn't being used. * * Leaving this NULL is equivalent to always returning false. */ bool (*has_stable_inodes)(struct super_block *sb); /* * Return an array of pointers to the block devices to which the * filesystem may write encrypted file contents, NULL if the filesystem * only has a single such block device, or an ERR_PTR() on error. * * On successful non-NULL return, *num_devs is set to the number of * devices in the returned array. The caller must free the returned * array using kfree(). * * If the filesystem can use multiple block devices (other than block * devices that aren't used for encrypted file contents, such as * external journal devices), and wants to support inline encryption, * then it must implement this function. Otherwise it's not needed. */ struct block_device **(*get_devices)(struct super_block *sb, unsigned int *num_devs); }; int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags); static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) { /* * Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info(). * I.e., another task may publish ->i_crypt_info concurrently, executing * a RELEASE barrier. We need to use smp_load_acquire() here to safely * ACQUIRE the memory the other task published. */ return smp_load_acquire(&inode->i_crypt_info); } /** * fscrypt_needs_contents_encryption() - check whether an inode needs * contents encryption * @inode: the inode to check * * Return: %true iff the inode is an encrypted regular file and the kernel was * built with fscrypt support. * * If you need to know whether the encrypt bit is set even when the kernel was * built without fscrypt support, you must use IS_ENCRYPTED() directly instead. */ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) { return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); } /* * When d_splice_alias() moves a directory's no-key alias to its * plaintext alias as a result of the encryption key being added, * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity * to disable d_revalidate. Note that we don't have to support the * inverse operation because fscrypt doesn't allow no-key names to be * the source or target of a rename(). */ static inline void fscrypt_handle_d_move(struct dentry *dentry) { /* * VFS calls fscrypt_handle_d_move even for non-fscrypt * filesystems. */ if (dentry->d_flags & DCACHE_NOKEY_NAME) { dentry->d_flags &= ~DCACHE_NOKEY_NAME; /* * Other filesystem features might be handling dentry * revalidation, in which case it cannot be disabled. */ if (dentry->d_op->d_revalidate == fscrypt_d_revalidate) dentry->d_flags &= ~DCACHE_OP_REVALIDATE; } } /** * fscrypt_is_nokey_name() - test whether a dentry is a no-key name * @dentry: the dentry to check * * This returns true if the dentry is a no-key dentry. A no-key dentry is a * dentry that was created in an encrypted directory that hasn't had its * encryption key added yet. Such dentries may be either positive or negative. * * When a filesystem is asked to create a new filename in an encrypted directory * and the new filename's dentry is a no-key dentry, it must fail the operation * with ENOKEY. This includes ->create(), ->mkdir(), ->mknod(), ->symlink(), * ->rename(), and ->link(). (However, ->rename() and ->link() are already * handled by fscrypt_prepare_rename() and fscrypt_prepare_link().) * * This is necessary because creating a filename requires the directory's * encryption key, but just checking for the key on the directory inode during * the final filesystem operation doesn't guarantee that the key was available * during the preceding dentry lookup. And the key must have already been * available during the dentry lookup in order for it to have been checked * whether the filename already exists in the directory and for the new file's * dentry not to be invalidated due to it incorrectly having the no-key flag. * * Return: %true if the dentry is a no-key name */ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) { return dentry->d_flags & DCACHE_NOKEY_NAME; } static inline void fscrypt_prepare_dentry(struct dentry *dentry, bool is_nokey_name) { /* * This code tries to only take ->d_lock when necessary to write * to ->d_flags. We shouldn't be peeking on d_flags for * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case * there is a race, the worst it can happen is that we fail to * unset DCACHE_OP_REVALIDATE and pay the cost of an extra * d_revalidate. */ if (is_nokey_name) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_NOKEY_NAME; spin_unlock(&dentry->d_lock); } else if (dentry->d_flags & DCACHE_OP_REVALIDATE && dentry->d_op->d_revalidate == fscrypt_d_revalidate) { /* * Unencrypted dentries and encrypted dentries where the * key is available are always valid from fscrypt * perspective. Avoid the cost of calling * fscrypt_d_revalidate unnecessarily. */ spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_OP_REVALIDATE; spin_unlock(&dentry->d_lock); } } /* crypto.c */ void fscrypt_enqueue_decrypt_work(struct work_struct *); struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs, gfp_t gfp_flags); int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num, gfp_t gfp_flags); int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs); int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num); static inline bool fscrypt_is_bounce_page(struct page *page) { return page->mapping == NULL; } static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) { return (struct page *)page_private(bounce_page); } static inline bool fscrypt_is_bounce_folio(struct folio *folio) { return folio->mapping == NULL; } static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) { return bounce_folio->private; } void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); int fscrypt_context_for_new_inode(void *ctx, struct inode *inode); int fscrypt_set_context(struct inode *inode, void *fs_data); struct fscrypt_dummy_policy { const union fscrypt_policy *policy; }; int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, struct fscrypt_dummy_policy *dummy_policy); bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, const struct fscrypt_dummy_policy *p2); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); static inline bool fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) { return dummy_policy->policy != NULL; } static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { kfree(dummy_policy->policy); dummy_policy->policy = NULL; } /* keyring.c */ void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode, bool *encrypt_ret); void fscrypt_put_encryption_info(struct inode *inode); void fscrypt_free_inode(struct inode *inode); int fscrypt_drop_inode(struct inode *inode); /* fname.c */ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, u8 *out, unsigned int olen); bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, u32 max_len, u32 *encrypted_len_ret); int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } int fscrypt_fname_alloc_buffer(u32 max_encrypted_len, struct fscrypt_str *crypto_str); void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, struct fscrypt_str *oname); bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len); u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); /* bio.c */ bool fscrypt_decrypt_bio(struct bio *bio); int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len); /* hooks.c */ int fscrypt_file_open(struct inode *inode, struct file *filp); int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, struct dentry *dentry); int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname); int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry); int __fscrypt_prepare_readdir(struct inode *dir); int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr); int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags); int fscrypt_prepare_symlink(struct inode *dir, const char *target, unsigned int len, unsigned int max_len, struct fscrypt_str *disk_link); int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link); const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done); int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat); static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { sb->s_cop = s_cop; } #else /* !CONFIG_FS_ENCRYPTION */ static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) { return NULL; } static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) { return false; } static inline void fscrypt_handle_d_move(struct dentry *dentry) { } static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) { return false; } static inline void fscrypt_prepare_dentry(struct dentry *dentry, bool is_nokey_name) { } /* crypto.c */ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { } static inline struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs, gfp_t gfp_flags) { return ERR_PTR(-EOPNOTSUPP); } static inline int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num, gfp_t gfp_flags) { return -EOPNOTSUPP; } static inline int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs) { return -EOPNOTSUPP; } static inline int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num) { return -EOPNOTSUPP; } static inline bool fscrypt_is_bounce_page(struct page *page) { return false; } static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) { WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); } static inline bool fscrypt_is_bounce_folio(struct folio *folio) { return false; } static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) { WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); } static inline void fscrypt_free_bounce_page(struct page *bounce_page) { } /* policy.c */ static inline int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) { return 0; } static inline int fscrypt_set_context(struct inode *inode, void *fs_data) { return -EOPNOTSUPP; } struct fscrypt_dummy_policy { }; static inline int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, struct fscrypt_dummy_policy *dummy_policy) { return -EINVAL; } static inline bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, const struct fscrypt_dummy_policy *p2) { return true; } static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb) { } static inline bool fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) { return false; } static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { } /* keyring.c */ static inline void fscrypt_destroy_keyring(struct super_block *sb) { } static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } static inline int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg) { return -EOPNOTSUPP; } /* keysetup.c */ static inline int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode, bool *encrypt_ret) { if (IS_ENCRYPTED(dir)) return -EOPNOTSUPP; return 0; } static inline void fscrypt_put_encryption_info(struct inode *inode) { return; } static inline void fscrypt_free_inode(struct inode *inode) { } static inline int fscrypt_drop_inode(struct inode *inode) { return 0; } /* fname.c */ static inline int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct fscrypt_name *fname) { if (IS_ENCRYPTED(dir)) return -EOPNOTSUPP; memset(fname, 0, sizeof(*fname)); fname->usr_fname = iname; fname->disk_name.name = (unsigned char *)iname->name; fname->disk_name.len = iname->len; return 0; } static inline void fscrypt_free_filename(struct fscrypt_name *fname) { return; } static inline int fscrypt_fname_alloc_buffer(u32 max_encrypted_len, struct fscrypt_str *crypto_str) { return -EOPNOTSUPP; } static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) { return; } static inline int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, struct fscrypt_str *oname) { return -EOPNOTSUPP; } static inline bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len) { /* Encryption support disabled; use standard comparison */ if (de_name_len != fname->disk_name.len) return false; return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); } static inline u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name) { WARN_ON_ONCE(1); return 0; } static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { return 1; } /* bio.c */ static inline bool fscrypt_decrypt_bio(struct bio *bio) { return true; } static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { return -EOPNOTSUPP; } /* hooks.c */ static inline int fscrypt_file_open(struct inode *inode, struct file *filp) { if (IS_ENCRYPTED(inode)) return -EOPNOTSUPP; return 0; } static inline int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, struct dentry *dentry) { return -EOPNOTSUPP; } static inline int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { return -EOPNOTSUPP; } static inline int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname) { return -EOPNOTSUPP; } static inline int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry) { return -EOPNOTSUPP; } static inline int __fscrypt_prepare_readdir(struct inode *dir) { return -EOPNOTSUPP; } static inline int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr) { return -EOPNOTSUPP; } static inline int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { return 0; } static inline int fscrypt_prepare_symlink(struct inode *dir, const char *target, unsigned int len, unsigned int max_len, struct fscrypt_str *disk_link) { if (IS_ENCRYPTED(dir)) return -EOPNOTSUPP; disk_link->name = (unsigned char *)target; disk_link->len = len + 1; if (disk_link->len > max_len) return -ENAMETOOLONG; return 0; } static inline int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link) { return -EOPNOTSUPP; } static inline const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done) { return ERR_PTR(-EOPNOTSUPP); } static inline int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) { return -EOPNOTSUPP; } static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { } #endif /* !CONFIG_FS_ENCRYPTION */ /* inline_crypt.c */ #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode); void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, u64 first_lblk, gfp_t gfp_mask); void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio, const struct buffer_head *first_bh, gfp_t gfp_mask); bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, u64 next_lblk); bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh); bool fscrypt_dio_supported(struct inode *inode); u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) { return false; } static inline void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, u64 first_lblk, gfp_t gfp_mask) { } static inline void fscrypt_set_bio_crypt_ctx_bh( struct bio *bio, const struct buffer_head *first_bh, gfp_t gfp_mask) { } static inline bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, u64 next_lblk) { return true; } static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh) { return true; } static inline bool fscrypt_dio_supported(struct inode *inode) { return !fscrypt_needs_contents_encryption(inode); } static inline u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks) { return nr_blocks; } #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ /** * fscrypt_inode_uses_inline_crypto() - test whether an inode uses inline * encryption * @inode: an inode. If encrypted, its key must be set up. * * Return: true if the inode requires file contents encryption and if the * encryption should be done in the block layer via blk-crypto rather * than in the filesystem layer. */ static inline bool fscrypt_inode_uses_inline_crypto(const struct inode *inode) { return fscrypt_needs_contents_encryption(inode) && __fscrypt_inode_uses_inline_crypto(inode); } /** * fscrypt_inode_uses_fs_layer_crypto() - test whether an inode uses fs-layer * encryption * @inode: an inode. If encrypted, its key must be set up. * * Return: true if the inode requires file contents encryption and if the * encryption should be done in the filesystem layer rather than in the * block layer via blk-crypto. */ static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode) { return fscrypt_needs_contents_encryption(inode) && !__fscrypt_inode_uses_inline_crypto(inode); } /** * fscrypt_has_encryption_key() - check whether an inode has had its key set up * @inode: the inode to check * * Return: %true if the inode has had its encryption key set up, else %false. * * Usually this should be preceded by fscrypt_get_encryption_info() to try to * set up the key first. */ static inline bool fscrypt_has_encryption_key(const struct inode *inode) { return fscrypt_get_inode_info(inode) != NULL; } /** * fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted * directory * @old_dentry: an existing dentry for the inode being linked * @dir: the target directory * @dentry: negative dentry for the target filename * * A new link can only be added to an encrypted directory if the directory's * encryption key is available --- since otherwise we'd have no way to encrypt * the filename. * * We also verify that the link will not violate the constraint that all files * in an encrypted directory tree use the same encryption policy. * * Return: 0 on success, -ENOKEY if the directory's encryption key is missing, * -EXDEV if the link would result in an inconsistent encryption policy, or * another -errno code. */ static inline int fscrypt_prepare_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { if (IS_ENCRYPTED(dir)) return __fscrypt_prepare_link(d_inode(old_dentry), dir, dentry); return 0; } /** * fscrypt_prepare_rename() - prepare for a rename between possibly-encrypted * directories * @old_dir: source directory * @old_dentry: dentry for source file * @new_dir: target directory * @new_dentry: dentry for target location (may be negative unless exchanging) * @flags: rename flags (we care at least about %RENAME_EXCHANGE) * * Prepare for ->rename() where the source and/or target directories may be * encrypted. A new link can only be added to an encrypted directory if the * directory's encryption key is available --- since otherwise we'd have no way * to encrypt the filename. A rename to an existing name, on the other hand, * *is* cryptographically possible without the key. However, we take the more * conservative approach and just forbid all no-key renames. * * We also verify that the rename will not violate the constraint that all files * in an encrypted directory tree use the same encryption policy. * * Return: 0 on success, -ENOKEY if an encryption key is missing, -EXDEV if the * rename would cause inconsistent encryption policies, or another -errno code. */ static inline int fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (IS_ENCRYPTED(old_dir) || IS_ENCRYPTED(new_dir)) return __fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry, flags); return 0; } /** * fscrypt_prepare_lookup() - prepare to lookup a name in a possibly-encrypted * directory * @dir: directory being searched * @dentry: filename being looked up * @fname: (output) the name to use to search the on-disk directory * * Prepare for ->lookup() in a directory which may be encrypted by determining * the name that will actually be used to search the directory on-disk. If the * directory's encryption policy is supported by this kernel and its encryption * key is available, then the lookup is assumed to be by plaintext name; * otherwise, it is assumed to be by no-key name. * * This will set DCACHE_NOKEY_NAME on the dentry if the lookup is by no-key * name. In this case the filesystem must assign the dentry a dentry_operations * which contains fscrypt_d_revalidate (or contains a d_revalidate method that * calls fscrypt_d_revalidate), so that the dentry will be invalidated if the * directory's encryption key is later added. * * Return: 0 on success; -ENOENT if the directory's key is unavailable but the * filename isn't a valid no-key name, so a negative dentry should be created; * or another -errno code. */ static inline int fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname) { if (IS_ENCRYPTED(dir)) return __fscrypt_prepare_lookup(dir, dentry, fname); memset(fname, 0, sizeof(*fname)); fname->usr_fname = &dentry->d_name; fname->disk_name.name = (unsigned char *)dentry->d_name.name; fname->disk_name.len = dentry->d_name.len; fscrypt_prepare_dentry(dentry, false); return 0; } /** * fscrypt_prepare_readdir() - prepare to read a possibly-encrypted directory * @dir: the directory inode * * If the directory is encrypted and it doesn't already have its encryption key * set up, try to set it up so that the filenames will be listed in plaintext * form rather than in no-key form. * * Return: 0 on success; -errno on error. Note that the encryption key being * unavailable is not considered an error. It is also not an error if * the encryption policy is unsupported by this kernel; that is treated * like the key being unavailable, so that files can still be deleted. */ static inline int fscrypt_prepare_readdir(struct inode *dir) { if (IS_ENCRYPTED(dir)) return __fscrypt_prepare_readdir(dir); return 0; } /** * fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's * attributes * @dentry: dentry through which the inode is being changed * @attr: attributes to change * * Prepare for ->setattr() on a possibly-encrypted inode. On an encrypted file, * most attribute changes are allowed even without the encryption key. However, * without the encryption key we do have to forbid truncates. This is needed * because the size being truncated to may not be a multiple of the filesystem * block size, and in that case we'd have to decrypt the final block, zero the * portion past i_size, and re-encrypt it. (We *could* allow truncating to a * filesystem block boundary, but it's simpler to just forbid all truncates --- * and we already forbid all other contents modifications without the key.) * * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code * if a problem occurred while setting up the encryption key. */ static inline int fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr) { if (IS_ENCRYPTED(d_inode(dentry))) return __fscrypt_prepare_setattr(dentry, attr); return 0; } /** * fscrypt_encrypt_symlink() - encrypt the symlink target if needed * @inode: symlink inode * @target: plaintext symlink target * @len: length of @target excluding null terminator * @disk_link: (in/out) the on-disk symlink target being prepared * * If the symlink target needs to be encrypted, then this function encrypts it * into @disk_link->name. fscrypt_prepare_symlink() must have been called * previously to compute @disk_link->len. If the filesystem did not allocate a * buffer for @disk_link->name after calling fscrypt_prepare_link(), then one * will be kmalloc()'ed and the filesystem will be responsible for freeing it. * * Return: 0 on success, -errno on failure */ static inline int fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link) { if (IS_ENCRYPTED(inode)) return __fscrypt_encrypt_symlink(inode, target, len, disk_link); return 0; } /* If *pagep is a bounce page, free it and set *pagep to the pagecache page */ static inline void fscrypt_finalize_bounce_page(struct page **pagep) { struct page *page = *pagep; if (fscrypt_is_bounce_page(page)) { *pagep = fscrypt_pagecache_page(page); fscrypt_free_bounce_page(page); } } #endif /* _LINUX_FSCRYPT_H */ |
| 7 17 15 6 5 67 67 67 27 11 67 67 18 18 18 16 2 18 18 104 103 67 17 6 12 77 6 7 7 103 103 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/hash.c * * Copyright (C) 2002 by Theodore Ts'o */ #include <linux/fs.h> #include <linux/unicode.h> #include <linux/compiler.h> #include <linux/bitops.h> #include "ext4.h" #define DELTA 0x9E3779B9 static void TEA_transform(__u32 buf[4], __u32 const in[]) { __u32 sum = 0; __u32 b0 = buf[0], b1 = buf[1]; __u32 a = in[0], b = in[1], c = in[2], d = in[3]; int n = 16; do { sum += DELTA; b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b); b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d); } while (--n); buf[0] += b0; buf[1] += b1; } /* F, G and H are basic MD4 functions: selection, majority, parity */ #define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z)))) #define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z))) #define H(x, y, z) ((x) ^ (y) ^ (z)) /* * The generic round function. The application is so specific that * we don't bother protecting all the arguments with parens, as is generally * good macro practice, in favor of extra legibility. * Rotation is separate from addition to prevent recomputation */ #define ROUND(f, a, b, c, d, x, s) \ (a += f(b, c, d) + x, a = rol32(a, s)) #define K1 0 #define K2 013240474631UL #define K3 015666365641UL /* * Basic cut-down MD4 transform. Returns only 32 bits of result. */ static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8]) { __u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3]; /* Round 1 */ ROUND(F, a, b, c, d, in[0] + K1, 3); ROUND(F, d, a, b, c, in[1] + K1, 7); ROUND(F, c, d, a, b, in[2] + K1, 11); ROUND(F, b, c, d, a, in[3] + K1, 19); ROUND(F, a, b, c, d, in[4] + K1, 3); ROUND(F, d, a, b, c, in[5] + K1, 7); ROUND(F, c, d, a, b, in[6] + K1, 11); ROUND(F, b, c, d, a, in[7] + K1, 19); /* Round 2 */ ROUND(G, a, b, c, d, in[1] + K2, 3); ROUND(G, d, a, b, c, in[3] + K2, 5); ROUND(G, c, d, a, b, in[5] + K2, 9); ROUND(G, b, c, d, a, in[7] + K2, 13); ROUND(G, a, b, c, d, in[0] + K2, 3); ROUND(G, d, a, b, c, in[2] + K2, 5); ROUND(G, c, d, a, b, in[4] + K2, 9); ROUND(G, b, c, d, a, in[6] + K2, 13); /* Round 3 */ ROUND(H, a, b, c, d, in[3] + K3, 3); ROUND(H, d, a, b, c, in[7] + K3, 9); ROUND(H, c, d, a, b, in[2] + K3, 11); ROUND(H, b, c, d, a, in[6] + K3, 15); ROUND(H, a, b, c, d, in[1] + K3, 3); ROUND(H, d, a, b, c, in[5] + K3, 9); ROUND(H, c, d, a, b, in[0] + K3, 11); ROUND(H, b, c, d, a, in[4] + K3, 15); buf[0] += a; buf[1] += b; buf[2] += c; buf[3] += d; return buf[1]; /* "most hashed" word */ } #undef ROUND #undef K1 #undef K2 #undef K3 #undef F #undef G #undef H /* The old legacy hash */ static __u32 dx_hack_hash_unsigned(const char *name, int len) { __u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9; const unsigned char *ucp = (const unsigned char *) name; while (len--) { hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373)); if (hash & 0x80000000) hash -= 0x7fffffff; hash1 = hash0; hash0 = hash; } return hash0 << 1; } static __u32 dx_hack_hash_signed(const char *name, int len) { __u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9; const signed char *scp = (const signed char *) name; while (len--) { hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373)); if (hash & 0x80000000) hash -= 0x7fffffff; hash1 = hash0; hash0 = hash; } return hash0 << 1; } static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num) { __u32 pad, val; int i; const signed char *scp = (const signed char *) msg; pad = (__u32)len | ((__u32)len << 8); pad |= pad << 16; val = pad; if (len > num*4) len = num * 4; for (i = 0; i < len; i++) { val = ((int) scp[i]) + (val << 8); if ((i % 4) == 3) { *buf++ = val; val = pad; num--; } } if (--num >= 0) *buf++ = val; while (--num >= 0) *buf++ = pad; } static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num) { __u32 pad, val; int i; const unsigned char *ucp = (const unsigned char *) msg; pad = (__u32)len | ((__u32)len << 8); pad |= pad << 16; val = pad; if (len > num*4) len = num * 4; for (i = 0; i < len; i++) { val = ((int) ucp[i]) + (val << 8); if ((i % 4) == 3) { *buf++ = val; val = pad; num--; } } if (--num >= 0) *buf++ = val; while (--num >= 0) *buf++ = pad; } /* * Returns the hash of a filename. If len is 0 and name is NULL, then * this function can be used to test whether or not a hash version is * supported. * * The seed is an 4 longword (32 bits) "secret" which can be used to * uniquify a hash. If the seed is all zero's, then some default seed * may be used. * * A particular hash version specifies whether or not the seed is * represented, and whether or not the returned hash is 32 bits or 64 * bits. 32 bit hashes will return 0 for the minor hash. */ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { __u32 hash; __u32 minor_hash = 0; const char *p; int i; __u32 in[8], buf[4]; void (*str2hashbuf)(const char *, int, __u32 *, int) = str2hashbuf_signed; /* Initialize the default seed for the hash checksum functions */ buf[0] = 0x67452301; buf[1] = 0xefcdab89; buf[2] = 0x98badcfe; buf[3] = 0x10325476; /* Check to see if the seed is all zero's */ if (hinfo->seed) { for (i = 0; i < 4; i++) { if (hinfo->seed[i]) { memcpy(buf, hinfo->seed, sizeof(buf)); break; } } } switch (hinfo->hash_version) { case DX_HASH_LEGACY_UNSIGNED: hash = dx_hack_hash_unsigned(name, len); break; case DX_HASH_LEGACY: hash = dx_hack_hash_signed(name, len); break; case DX_HASH_HALF_MD4_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; fallthrough; case DX_HASH_HALF_MD4: p = name; while (len > 0) { (*str2hashbuf)(p, len, in, 8); half_md4_transform(buf, in); len -= 32; p += 32; } minor_hash = buf[2]; hash = buf[1]; break; case DX_HASH_TEA_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; fallthrough; case DX_HASH_TEA: p = name; while (len > 0) { (*str2hashbuf)(p, len, in, 4); TEA_transform(buf, in); len -= 16; p += 16; } hash = buf[0]; minor_hash = buf[1]; break; case DX_HASH_SIPHASH: { struct qstr qname = QSTR_INIT(name, len); __u64 combined_hash; if (fscrypt_has_encryption_key(dir)) { combined_hash = fscrypt_fname_siphash(dir, &qname); } else { ext4_warning_inode(dir, "Siphash requires key"); return -1; } hash = (__u32)(combined_hash >> 32); minor_hash = (__u32)combined_hash; break; } default: hinfo->hash = 0; hinfo->minor_hash = 0; ext4_warning(dir->i_sb, "invalid/unsupported hash tree version %u", hinfo->hash_version); return -EINVAL; } hash = hash & ~1; if (hash == (EXT4_HTREE_EOF_32BIT << 1)) hash = (EXT4_HTREE_EOF_32BIT - 1) << 1; hinfo->hash = hash; hinfo->minor_hash = minor_hash; return 0; } int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { #if IS_ENABLED(CONFIG_UNICODE) const struct unicode_map *um = dir->i_sb->s_encoding; int r, dlen; unsigned char *buff; struct qstr qstr = {.name = name, .len = len }; if (len && IS_CASEFOLDED(dir) && (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) { buff = kzalloc(PATH_MAX, GFP_KERNEL); if (!buff) return -ENOMEM; dlen = utf8_casefold(um, &qstr, buff, PATH_MAX); if (dlen < 0) { kfree(buff); goto opaque_seq; } r = __ext4fs_dirhash(dir, buff, dlen, hinfo); kfree(buff); return r; } opaque_seq: #endif return __ext4fs_dirhash(dir, name, len, hinfo); } |
| 725 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * ACPI support * * Copyright (C) 2020, Intel Corporation * Author: Mika Westerberg <mika.westerberg@linux.intel.com> */ #include <linux/acpi.h> #include <linux/pm_runtime.h> #include "tb.h" static acpi_status tb_acpi_add_link(acpi_handle handle, u32 level, void *data, void **ret) { struct acpi_device *adev = acpi_fetch_acpi_dev(handle); struct fwnode_handle *fwnode; struct tb_nhi *nhi = data; struct pci_dev *pdev; struct device *dev; if (!adev) return AE_OK; fwnode = fwnode_find_reference(acpi_fwnode_handle(adev), "usb4-host-interface", 0); if (IS_ERR(fwnode)) return AE_OK; /* It needs to reference this NHI */ if (dev_fwnode(&nhi->pdev->dev) != fwnode) goto out_put; /* * Ignore USB3 ports here as USB core will set up device links between * tunneled USB3 devices and NHI host during USB device creation. * USB3 ports might not even have a physical device yet if xHCI driver * isn't bound yet. */ dev = acpi_get_first_physical_node(adev); if (!dev || !dev_is_pci(dev)) goto out_put; /* Check that this matches a PCIe root/downstream port. */ pdev = to_pci_dev(dev); if (pci_is_pcie(pdev) && (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT || pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)) { const struct device_link *link; /* * Make them both active first to make sure the NHI does * not runtime suspend before the consumer. The * pm_runtime_put() below then allows the consumer to * runtime suspend again (which then allows NHI runtime * suspend too now that the device link is established). */ pm_runtime_get_sync(&pdev->dev); link = device_link_add(&pdev->dev, &nhi->pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER | DL_FLAG_RPM_ACTIVE | DL_FLAG_PM_RUNTIME); if (link) { dev_dbg(&nhi->pdev->dev, "created link from %s\n", dev_name(&pdev->dev)); *(bool *)ret = true; } else { dev_warn(&nhi->pdev->dev, "device link creation from %s failed\n", dev_name(&pdev->dev)); } pm_runtime_put(&pdev->dev); } out_put: fwnode_handle_put(fwnode); return AE_OK; } /** * tb_acpi_add_links() - Add device links based on ACPI description * @nhi: Pointer to NHI * * Goes over ACPI namespace finding tunneled ports that reference to * @nhi ACPI node. For each reference a device link is added. The link * is automatically removed by the driver core. * * Returns %true if at least one link was created. */ bool tb_acpi_add_links(struct tb_nhi *nhi) { acpi_status status; bool ret = false; if (!has_acpi_companion(&nhi->pdev->dev)) return false; /* * Find all devices that have usb4-host-controller interface * property that references to this NHI. */ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, 32, tb_acpi_add_link, NULL, nhi, (void **)&ret); if (ACPI_FAILURE(status)) { dev_warn(&nhi->pdev->dev, "failed to enumerate tunneled ports\n"); return false; } return ret; } /** * tb_acpi_is_native() - Did the platform grant native TBT/USB4 control * * Returns %true if the platform granted OS native control over * TBT/USB4. In this case software based connection manager can be used, * otherwise there is firmware based connection manager running. */ bool tb_acpi_is_native(void) { return osc_sb_native_usb4_support_confirmed && osc_sb_native_usb4_control; } /** * tb_acpi_may_tunnel_usb3() - Is USB3 tunneling allowed by the platform * * When software based connection manager is used, this function * returns %true if platform allows native USB3 tunneling. */ bool tb_acpi_may_tunnel_usb3(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_USB3_TUNNELING; return true; } /** * tb_acpi_may_tunnel_dp() - Is DisplayPort tunneling allowed by the platform * * When software based connection manager is used, this function * returns %true if platform allows native DP tunneling. */ bool tb_acpi_may_tunnel_dp(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_DP_TUNNELING; return true; } /** * tb_acpi_may_tunnel_pcie() - Is PCIe tunneling allowed by the platform * * When software based connection manager is used, this function * returns %true if platform allows native PCIe tunneling. */ bool tb_acpi_may_tunnel_pcie(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_PCIE_TUNNELING; return true; } /** * tb_acpi_is_xdomain_allowed() - Are XDomain connections allowed * * When software based connection manager is used, this function * returns %true if platform allows XDomain connections. */ bool tb_acpi_is_xdomain_allowed(void) { if (tb_acpi_is_native()) return osc_sb_native_usb4_control & OSC_USB_XDOMAIN; return true; } /* UUID for retimer _DSM: e0053122-795b-4122-8a5e-57be1d26acb3 */ static const guid_t retimer_dsm_guid = GUID_INIT(0xe0053122, 0x795b, 0x4122, 0x8a, 0x5e, 0x57, 0xbe, 0x1d, 0x26, 0xac, 0xb3); #define RETIMER_DSM_QUERY_ONLINE_STATE 1 #define RETIMER_DSM_SET_ONLINE_STATE 2 static int tb_acpi_retimer_set_power(struct tb_port *port, bool power) { struct usb4_port *usb4 = port->usb4; union acpi_object argv4[2]; struct acpi_device *adev; union acpi_object *obj; int ret; if (!usb4->can_offline) return 0; adev = ACPI_COMPANION(&usb4->dev); if (WARN_ON(!adev)) return 0; /* Check if we are already powered on (and in correct mode) */ obj = acpi_evaluate_dsm_typed(adev->handle, &retimer_dsm_guid, 1, RETIMER_DSM_QUERY_ONLINE_STATE, NULL, ACPI_TYPE_INTEGER); if (!obj) { tb_port_warn(port, "ACPI: query online _DSM failed\n"); return -EIO; } ret = obj->integer.value; ACPI_FREE(obj); if (power == ret) return 0; tb_port_dbg(port, "ACPI: calling _DSM to power %s retimers\n", power ? "on" : "off"); argv4[0].type = ACPI_TYPE_PACKAGE; argv4[0].package.count = 1; argv4[0].package.elements = &argv4[1]; argv4[1].integer.type = ACPI_TYPE_INTEGER; argv4[1].integer.value = power; obj = acpi_evaluate_dsm_typed(adev->handle, &retimer_dsm_guid, 1, RETIMER_DSM_SET_ONLINE_STATE, argv4, ACPI_TYPE_INTEGER); if (!obj) { tb_port_warn(port, "ACPI: set online state _DSM evaluation failed\n"); return -EIO; } ret = obj->integer.value; ACPI_FREE(obj); if (ret >= 0) { if (power) return ret == 1 ? 0 : -EBUSY; return 0; } tb_port_warn(port, "ACPI: set online state _DSM failed with error %d\n", ret); return -EIO; } /** * tb_acpi_power_on_retimers() - Call platform to power on retimers * @port: USB4 port * * Calls platform to turn on power to all retimers behind this USB4 * port. After this function returns successfully the caller can * continue with the normal retimer flows (as specified in the USB4 * spec). Note if this returns %-EBUSY it means the type-C port is in * non-USB4/TBT mode (there is non-USB4/TBT device connected). * * This should only be called if the USB4/TBT link is not up. * * Returns %0 on success. */ int tb_acpi_power_on_retimers(struct tb_port *port) { return tb_acpi_retimer_set_power(port, true); } /** * tb_acpi_power_off_retimers() - Call platform to power off retimers * @port: USB4 port * * This is the opposite of tb_acpi_power_on_retimers(). After returning * successfully the normal operations with the @port can continue. * * Returns %0 on success. */ int tb_acpi_power_off_retimers(struct tb_port *port) { return tb_acpi_retimer_set_power(port, false); } static bool tb_acpi_bus_match(struct device *dev) { return tb_is_switch(dev) || tb_is_usb4_port_device(dev); } static struct acpi_device *tb_acpi_switch_find_companion(struct tb_switch *sw) { struct tb_switch *parent_sw = tb_switch_parent(sw); struct acpi_device *adev = NULL; /* * Device routers exists under the downstream facing USB4 port * of the parent router. Their _ADR is always 0. */ if (parent_sw) { struct tb_port *port = tb_switch_downstream_port(sw); struct acpi_device *port_adev; port_adev = acpi_find_child_by_adr(ACPI_COMPANION(&parent_sw->dev), port->port); if (port_adev) adev = acpi_find_child_device(port_adev, 0, false); } else { struct tb_nhi *nhi = sw->tb->nhi; struct acpi_device *parent_adev; parent_adev = ACPI_COMPANION(&nhi->pdev->dev); if (parent_adev) adev = acpi_find_child_device(parent_adev, 0, false); } return adev; } static struct acpi_device *tb_acpi_find_companion(struct device *dev) { /* * The Thunderbolt/USB4 hierarchy looks like following: * * Device (NHI) * Device (HR) // Host router _ADR == 0 * Device (DFP0) // Downstream port _ADR == lane 0 adapter * Device (DR) // Device router _ADR == 0 * Device (UFP) // Upstream port _ADR == lane 0 adapter * Device (DFP1) // Downstream port _ADR == lane 0 adapter number * * At the moment we bind the host router to the corresponding * Linux device. */ if (tb_is_switch(dev)) return tb_acpi_switch_find_companion(tb_to_switch(dev)); if (tb_is_usb4_port_device(dev)) return acpi_find_child_by_adr(ACPI_COMPANION(dev->parent), tb_to_usb4_port_device(dev)->port->port); return NULL; } static void tb_acpi_setup(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); struct usb4_port *usb4 = tb_to_usb4_port_device(dev); if (!adev || !usb4) return; if (acpi_check_dsm(adev->handle, &retimer_dsm_guid, 1, BIT(RETIMER_DSM_QUERY_ONLINE_STATE) | BIT(RETIMER_DSM_SET_ONLINE_STATE))) usb4->can_offline = true; } static struct acpi_bus_type tb_acpi_bus = { .name = "thunderbolt", .match = tb_acpi_bus_match, .find_companion = tb_acpi_find_companion, .setup = tb_acpi_setup, }; int tb_acpi_init(void) { return register_acpi_bus_type(&tb_acpi_bus); } void tb_acpi_exit(void) { unregister_acpi_bus_type(&tb_acpi_bus); } |
| 12 12 12 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/once.h> #include <linux/random.h> #include <linux/module.h> struct once_work { struct work_struct work; struct static_key_true *key; struct module *module; }; static void once_deferred(struct work_struct *w) { struct once_work *work; work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); module_put(work->module); kfree(work); } static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; w = kmalloc(sizeof(*w), GFP_ATOMIC); if (!w) return; INIT_WORK(&w->work, once_deferred); w->key = key; w->module = mod; __module_get(mod); schedule_work(&w->work); } static DEFINE_SPINLOCK(once_lock); bool __do_once_start(bool *done, unsigned long *flags) __acquires(once_lock) { spin_lock_irqsave(&once_lock, *flags); if (*done) { spin_unlock_irqrestore(&once_lock, *flags); /* Keep sparse happy by restoring an even lock count on * this lock. In case we return here, we don't call into * __do_once_done but return early in the DO_ONCE() macro. */ __acquire(once_lock); return false; } return true; } EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); static DEFINE_MUTEX(once_mutex); bool __do_once_sleepable_start(bool *done) __acquires(once_mutex) { mutex_lock(&once_mutex); if (*done) { mutex_unlock(&once_mutex); /* Keep sparse happy by restoring an even lock count on * this mutex. In case we return here, we don't call into * __do_once_done but return early in the DO_ONCE_SLEEPABLE() macro. */ __acquire(once_mutex); return false; } return true; } EXPORT_SYMBOL(__do_once_sleepable_start); void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, struct module *mod) __releases(once_mutex) { *done = true; mutex_unlock(&once_mutex); once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_sleepable_done); |
| 2152 2159 2156 12 223 2652 2654 2 2654 1263 2652 1342 1 1362 280 280 10 270 269 223 250 33 11 7 7 3 4 7 17 2 992 16 450 991 262 968 3613 2112 2335 2152 2150 1311 2148 2147 2212 243 234 14 13 1 241 2330 2262 20 3 22 43 2317 24 31 31 32 32 32 32 1479 1787 1649 416 1002 1003 828 993 969 617 994 989 1002 130 1 130 131 5 131 130 19 124 325 204 163 60 131 131 15 131 131 130 131 129 164 24 441 381 279 110 396 393 396 174 104 27 99 2 37 67 102 190 10 178 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include "internal.h" static void clear_shadow_entries(struct address_space *mapping, unsigned long start, unsigned long max) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return; xas_set_update(&xas, workingset_update_node); spin_lock(&mapping->host->i_lock); xas_lock_irq(&xas); /* Clear all shadow entries from start to max */ xas_for_each(&xas, folio, max) { if (xa_is_value(folio)) xas_store(&xas, NULL); } xas_unlock_irq(&xas); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what folio_batch_remove_exceptionals() does. * Please note that indices[] has entries in ascending order as guaranteed by * either find_get_entries() or find_lock_entries(). */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, indices[0]); int nr = folio_batch_count(fbatch); struct folio *folio; int i, j; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < nr; j++) if (xa_is_value(fbatch->folios[j])) break; if (j == nr) return; if (dax_mapping(mapping)) { for (i = j; i < nr; i++) { if (xa_is_value(fbatch->folios[i])) { /* * File systems should already have called * dax_break_layout_entry() to remove all DAX * entries while holding a lock to prevent * establishing new entries. Therefore we * shouldn't find any here. */ WARN_ON_ONCE(1); /* * Delete the mapping so truncate_pagecache() * doesn't loop forever. */ dax_delete_mapping_entry(mapping, indices[i]); } } goto out; } xas_set(&xas, indices[j]); xas_set_update(&xas, workingset_update_node); spin_lock(&mapping->host->i_lock); xas_lock_irq(&xas); xas_for_each(&xas, folio, indices[nr-1]) { if (xa_is_value(folio)) xas_store(&xas, NULL); } xas_unlock_irq(&xas); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); out: folio_batch_remove_exceptionals(fbatch); } /** * folio_invalidate - Invalidate part or all of a folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * folio_invalidate() is called when all or part of the folio has become * invalidated by a truncate operation. * * folio_invalidate() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void folio_invalidate(struct folio *folio, size_t offset, size_t length) { const struct address_space_operations *aops = folio->mapping->a_ops; if (aops->invalidate_folio) aops->invalidate_folio(folio, offset, length); } EXPORT_SYMBOL_GPL(folio_invalidate); /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_folio(struct folio *folio) { if (folio_mapped(folio)) unmap_mapping_folio(folio); if (folio_needs_release(folio)) folio_invalidate(folio, 0, folio_size(folio)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ folio_cancel_dirty(folio); } int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { if (folio->mapping != mapping) return -EIO; truncate_cleanup_folio(folio); filemap_remove_folio(folio); return 0; } /* * Handle partial folios. The folio may be entirely within the * range if a split has raced with us. If not, we zero the part of the * folio that's within the [start, end] range, and then split the folio if * it's large. split_page_range() will discard pages which now lie beyond * i_size, and we rely on the caller to discard pages which lie within a * newly created hole. * * Returns false if splitting failed so the caller can avoid * discarding the entire folio which is stubbornly unsplit. */ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); size_t size = folio_size(folio); unsigned int offset, length; struct page *split_at, *split_at2; if (pos < start) offset = start - pos; else offset = 0; if (pos + size <= (u64)end) length = size - offset; else length = end + 1 - pos - offset; folio_wait_writeback(folio); if (length == size) { truncate_inode_folio(folio->mapping, folio); return true; } /* * We may be zeroing pages we're about to discard, but it avoids * doing a complex calculation here, and then doing the zeroing * anyway if the page split fails. */ if (!mapping_inaccessible(folio->mapping)) folio_zero_range(folio, offset, length); if (folio_needs_release(folio)) folio_invalidate(folio, offset, length); if (!folio_test_large(folio)) return true; split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE); if (!try_folio_split(folio, split_at, NULL)) { /* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste * for shmem truncate */ struct folio *folio2; if (offset + length == size) goto no_split; split_at2 = folio_page(folio, PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE); folio2 = page_folio(split_at2); if (!folio_try_get(folio2)) goto no_split; if (!folio_test_large(folio2)) goto out; if (!folio_trylock(folio2)) goto out; /* * make sure folio2 is large and does not change its mapping. * Its split result does not matter here. */ if (folio_test_large(folio2) && folio2->mapping == folio->mapping) try_folio_split(folio2, split_at2, NULL); folio_unlock(folio2); out: folio_put(folio2); no_split: return true; } if (folio_test_dirty(folio)) return false; truncate_inode_folio(folio->mapping, folio); return true; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_folio(struct address_space *mapping, struct folio *folio) { if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_folio(mapping, folio); } EXPORT_SYMBOL(generic_error_remove_folio); /** * mapping_evict_folio() - Remove an unused folio from the page-cache. * @mapping: The mapping this folio belongs to. * @folio: The folio to remove. * * Safely remove one folio from the page cache. * It only drops clean, unused folios. * * Context: Folio must be locked. * Return: The number of pages successfully removed. */ long mapping_evict_folio(struct address_space *mapping, struct folio *folio) { /* The page may have been truncated before it was locked */ if (!mapping) return 0; if (folio_test_dirty(folio) || folio_test_writeback(folio)) return 0; /* The refcount will be elevated if any page in the folio is mapped */ if (folio_ref_count(folio) > folio_nr_pages(folio) + folio_has_private(folio) + 1) return 0; if (!filemap_release_folio(folio, 0)) return 0; return remove_mapping(mapping, folio); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidate_folio() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; struct folio *folio; bool same_folio; if (mapping_empty(mapping)) return; /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, &index, end - 1, &fbatch, indices)) { truncate_folio_batch_exceptionals(mapping, &fbatch, indices); for (i = 0; i < folio_batch_count(&fbatch); i++) truncate_cleanup_folio(fbatch.folios[i]); delete_from_page_cache_batch(mapping, &fbatch); for (i = 0; i < folio_batch_count(&fbatch); i++) folio_unlock(fbatch.folios[i]); folio_batch_release(&fbatch); cond_resched(); } same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0); if (!IS_ERR(folio)) { same_folio = lend < folio_pos(folio) + folio_size(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio_next_index(folio); if (same_folio) end = folio->index; } folio_unlock(folio); folio_put(folio); folio = NULL; } if (!same_folio) { folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT, FGP_LOCK, 0); if (!IS_ERR(folio)) { if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index; folio_unlock(folio); folio_put(folio); } } index = start; while (index < end) { cond_resched(); if (!find_get_entries(mapping, &index, end - 1, &fbatch, indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) continue; folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); truncate_inode_folio(mapping, folio); folio_unlock(folio); } truncate_folio_batch_exceptionals(mapping, &fbatch, indices); folio_batch_release(&fbatch); } } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_rwsem and * mapping->invalidate_lock. * * Note: When this function returns, there can be a page in the process of * deletion (inside __filemap_remove_folio()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_rwsem. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); if (!mapping_empty(mapping)) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); /** * mapping_try_invalidate - Invalidate all the evictable folios of one inode * @mapping: the address_space which holds the folios to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * @nr_failed: How many folio invalidations failed * * This function is similar to invalidate_mapping_pages(), except that it * returns the number of folios which could not be evicted in @nr_failed. */ unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; folio_batch_init(&fbatch); while (find_lock_entries(mapping, &index, end, &fbatch, indices)) { bool xa_has_values = false; int nr = folio_batch_count(&fbatch); for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) { xa_has_values = true; count++; continue; } ret = mapping_evict_folio(mapping, folio); folio_unlock(folio); /* * Invalidation is a hint that the folio is no longer * of interest and try to speed up its reclaim. */ if (!ret) { deactivate_file_folio(folio); /* Likely in the lru cache of a remote CPU */ if (nr_failed) (*nr_failed)++; } count += ret; } if (xa_has_values) clear_shadow_entries(mapping, indices[0], indices[nr-1]); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } return count; } /** * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode * @mapping: the address_space which holds the cache to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function removes pages that are clean, unmapped and unlocked, * as well as shadow entries. It will not block on IO activity. * * If you want to remove all the pages of one inode, regardless of * their use and writeback state, use truncate_inode_pages(). * * Return: The number of indices that had their contents invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { return mapping_try_invalidate(mapping, start, end, NULL); } EXPORT_SYMBOL(invalidate_mapping_pages); static int folio_launder(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return 0; if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) return 0; return mapping->a_ops->launder_folio(folio); } /* * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave folios behind because * shrink_folio_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, gfp_t gfp) { int ret; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_mapped(folio)) unmap_mapping_folio(folio); BUG_ON(folio_mapped(folio)); ret = folio_launder(mapping, folio); if (ret) return ret; if (folio->mapping != mapping) return -EBUSY; if (!filemap_release_folio(folio, gfp)) return -EBUSY; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); if (folio_test_dirty(folio)) goto failed; BUG_ON(folio_has_private(folio)); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); return 1; failed: xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); return -EBUSY; } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; if (mapping_empty(mapping)) return 0; folio_batch_init(&fbatch); index = start; while (find_get_entries(mapping, &index, end, &fbatch, indices)) { bool xa_has_values = false; int nr = folio_batch_count(&fbatch); for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) { xa_has_values = true; if (dax_mapping(mapping) && !dax_invalidate_mapping_entry_sync(mapping, indices[i])) ret = -EBUSY; continue; } if (!did_range_unmap && folio_mapped(folio)) { /* * If folio is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, indices[i], (1 + end - indices[i]), false); did_range_unmap = 1; } folio_lock(folio); if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); continue; } VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL); if (ret2 < 0) ret = ret2; folio_unlock(folio); } if (xa_has_values) clear_shadow_entries(mapping, indices[0], indices[nr-1]); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_rwsem but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or * by write starting after current i_size. We mark the page straddling * current i_size RO so that page_mkwrite() is called on the first * write access to the page. The filesystem will update its per-block * information before user writes to the page via mmap after the i_size * has been changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the folio will already see the new i_size. * The function must be called while we still hold i_rwsem - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct folio *folio; WARN_ON(to > inode->i_size); if (from >= to || bsize >= PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; folio = filemap_lock_folio(inode->i_mapping, from / PAGE_SIZE); /* Folio not cached? Nothing to do */ if (IS_ERR(folio)) return; /* * See folio_clear_dirty_for_io() for details why folio_mark_dirty() * is needed. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * The post-eof range of the folio must be zeroed before it is exposed * to the file. Writeback normally does this, but since i_size has been * increased we handle it here. */ if (folio_test_dirty(folio)) { unsigned int offset, end; offset = from - folio_pos(folio); end = min_t(unsigned int, to - folio_pos(folio), folio_size(folio)); folio_zero_segment(folio, offset, end); } folio_unlock(folio); folio_put(folio); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 65 5 19 48 3 45 37 12 27 27 9 9 47 37 26 11 47 2 19 26 15 16 15 27 20 15 47 47 47 2 47 21 47 47 47 44 44 4 3 21 33 33 5 3 3 3 47 47 3 6 12 8 4 26 26 1 26 24 24 14 24 24 10 23 4 23 1 18 2 11 6 2 3 1 10 68 183 33 38 63 211 22 4 12 8 100 62 152 156 156 152 152 21 4 17 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2012-2013 Samsung Electronics Co., Ltd. */ #include <linux/init.h> #include <linux/buffer_head.h> #include <linux/mpage.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/time.h> #include <linux/writeback.h> #include <linux/uio.h> #include <linux/random.h> #include <linux/iversion.h> #include "exfat_raw.h" #include "exfat_fs.h" int __exfat_write_inode(struct inode *inode, int sync) { unsigned long long on_disk_size; struct exfat_dentry *ep, *ep2; struct exfat_entry_set_cache es; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); bool is_dir = (ei->type == TYPE_DIR) ? true : false; struct timespec64 ts; if (inode->i_ino == EXFAT_ROOT_INO) return 0; /* * If the inode is already unlinked, there is no need for updating it. */ if (ei->dir.dir == DIR_DELETED) return 0; if (is_dir && ei->dir.dir == sbi->root_dir && ei->entry == -1) return 0; exfat_set_volume_dirty(sb); /* get the directory entry of given file or directory */ if (exfat_get_dentry_set_by_ei(&es, sb, ei)) return -EIO; ep = exfat_get_dentry_cached(&es, ES_IDX_FILE); ep2 = exfat_get_dentry_cached(&es, ES_IDX_STREAM); ep->dentry.file.attr = cpu_to_le16(exfat_make_attr(inode)); /* set FILE_INFO structure using the acquired struct exfat_dentry */ exfat_set_entry_time(sbi, &ei->i_crtime, &ep->dentry.file.create_tz, &ep->dentry.file.create_time, &ep->dentry.file.create_date, &ep->dentry.file.create_time_cs); ts = inode_get_mtime(inode); exfat_set_entry_time(sbi, &ts, &ep->dentry.file.modify_tz, &ep->dentry.file.modify_time, &ep->dentry.file.modify_date, &ep->dentry.file.modify_time_cs); ts = inode_get_atime(inode); exfat_set_entry_time(sbi, &ts, &ep->dentry.file.access_tz, &ep->dentry.file.access_time, &ep->dentry.file.access_date, NULL); /* File size should be zero if there is no cluster allocated */ on_disk_size = i_size_read(inode); if (ei->start_clu == EXFAT_EOF_CLUSTER) on_disk_size = 0; ep2->dentry.stream.size = cpu_to_le64(on_disk_size); /* * mmap write does not use exfat_write_end(), valid_size may be * extended to the sector-aligned length in exfat_get_block(). * So we need to fixup valid_size to the writren length. */ if (on_disk_size < ei->valid_size) ep2->dentry.stream.valid_size = ep2->dentry.stream.size; else ep2->dentry.stream.valid_size = cpu_to_le64(ei->valid_size); if (on_disk_size) { ep2->dentry.stream.flags = ei->flags; ep2->dentry.stream.start_clu = cpu_to_le32(ei->start_clu); } else { ep2->dentry.stream.flags = ALLOC_FAT_CHAIN; ep2->dentry.stream.start_clu = EXFAT_FREE_CLUSTER; } exfat_update_dir_chksum(&es); return exfat_put_dentry_set(&es, sync); } int exfat_write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (unlikely(exfat_forced_shutdown(inode->i_sb))) return -EIO; mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock); ret = __exfat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock); return ret; } void exfat_sync_inode(struct inode *inode) { lockdep_assert_held(&EXFAT_SB(inode->i_sb)->s_lock); __exfat_write_inode(inode, 1); } /* * Input: inode, (logical) clu_offset, target allocation area * Output: errcode, cluster number * *clu = (~0), if it's unable to allocate a new cluster */ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, unsigned int *clu, int create) { int ret; unsigned int last_clu; struct exfat_chain new_clu; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); unsigned int local_clu_offset = clu_offset; unsigned int num_to_be_allocated = 0, num_clusters; num_clusters = EXFAT_B_TO_CLU(exfat_ondisk_size(inode), sbi); if (clu_offset >= num_clusters) num_to_be_allocated = clu_offset - num_clusters + 1; if (!create && (num_to_be_allocated > 0)) { *clu = EXFAT_EOF_CLUSTER; return 0; } *clu = last_clu = ei->start_clu; if (ei->flags == ALLOC_NO_FAT_CHAIN) { if (clu_offset > 0 && *clu != EXFAT_EOF_CLUSTER) { last_clu += clu_offset - 1; if (clu_offset == num_clusters) *clu = EXFAT_EOF_CLUSTER; else *clu += clu_offset; } } else if (ei->type == TYPE_FILE) { unsigned int fclus = 0; int err = exfat_get_cluster(inode, clu_offset, &fclus, clu, &last_clu, 1); if (err) return -EIO; clu_offset -= fclus; } else { /* hint information */ if (clu_offset > 0 && ei->hint_bmap.off != EXFAT_EOF_CLUSTER && ei->hint_bmap.off > 0 && clu_offset >= ei->hint_bmap.off) { clu_offset -= ei->hint_bmap.off; /* hint_bmap.clu should be valid */ WARN_ON(ei->hint_bmap.clu < 2); *clu = ei->hint_bmap.clu; } while (clu_offset > 0 && *clu != EXFAT_EOF_CLUSTER) { last_clu = *clu; if (exfat_get_next_cluster(sb, clu)) return -EIO; clu_offset--; } } if (*clu == EXFAT_EOF_CLUSTER) { exfat_set_volume_dirty(sb); new_clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ? EXFAT_EOF_CLUSTER : last_clu + 1; new_clu.size = 0; new_clu.flags = ei->flags; /* allocate a cluster */ if (num_to_be_allocated < 1) { /* Broken FAT (i_sze > allocated FAT) */ exfat_fs_error(sb, "broken FAT chain."); return -EIO; } ret = exfat_alloc_cluster(inode, num_to_be_allocated, &new_clu, inode_needs_sync(inode)); if (ret) return ret; if (new_clu.dir == EXFAT_EOF_CLUSTER || new_clu.dir == EXFAT_FREE_CLUSTER) { exfat_fs_error(sb, "bogus cluster new allocated (last_clu : %u, new_clu : %u)", last_clu, new_clu.dir); return -EIO; } /* append to the FAT chain */ if (last_clu == EXFAT_EOF_CLUSTER) { if (new_clu.flags == ALLOC_FAT_CHAIN) ei->flags = ALLOC_FAT_CHAIN; ei->start_clu = new_clu.dir; } else { if (new_clu.flags != ei->flags) { /* no-fat-chain bit is disabled, * so fat-chain should be synced with * alloc-bitmap */ exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters); ei->flags = ALLOC_FAT_CHAIN; } if (new_clu.flags == ALLOC_FAT_CHAIN) if (exfat_ent_set(sb, last_clu, new_clu.dir)) return -EIO; } num_clusters += num_to_be_allocated; *clu = new_clu.dir; inode->i_blocks += EXFAT_CLU_TO_B(num_to_be_allocated, sbi) >> 9; /* * Move *clu pointer along FAT chains (hole care) because the * caller of this function expect *clu to be the last cluster. * This only works when num_to_be_allocated >= 2, * *clu = (the first cluster of the allocated chain) => * (the last cluster of ...) */ if (ei->flags == ALLOC_NO_FAT_CHAIN) { *clu += num_to_be_allocated - 1; } else { while (num_to_be_allocated > 1) { if (exfat_get_next_cluster(sb, clu)) return -EIO; num_to_be_allocated--; } } } /* hint information */ ei->hint_bmap.off = local_clu_offset; ei->hint_bmap.clu = *clu; return 0; } static int exfat_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct exfat_inode_info *ei = EXFAT_I(inode); struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err = 0; unsigned long mapped_blocks = 0; unsigned int cluster, sec_offset; sector_t last_block; sector_t phys = 0; sector_t valid_blks; loff_t i_size; mutex_lock(&sbi->s_lock); i_size = i_size_read(inode); last_block = EXFAT_B_TO_BLK_ROUND_UP(i_size, sb); if (iblock >= last_block && !create) goto done; /* Is this block already allocated? */ err = exfat_map_cluster(inode, iblock >> sbi->sect_per_clus_bits, &cluster, create); if (err) { if (err != -ENOSPC) exfat_fs_error_ratelimit(sb, "failed to bmap (inode : %p iblock : %llu, err : %d)", inode, (unsigned long long)iblock, err); goto unlock_ret; } if (cluster == EXFAT_EOF_CLUSTER) goto done; /* sector offset in cluster */ sec_offset = iblock & (sbi->sect_per_clus - 1); phys = exfat_cluster_to_sector(sbi, cluster) + sec_offset; mapped_blocks = sbi->sect_per_clus - sec_offset; max_blocks = min(mapped_blocks, max_blocks); map_bh(bh_result, sb, phys); if (buffer_delay(bh_result)) clear_buffer_delay(bh_result); /* * In most cases, we just need to set bh_result to mapped, unmapped * or new status as follows: * 1. i_size == valid_size * 2. write case (create == 1) * 3. direct_read (!bh_result->b_folio) * -> the unwritten part will be zeroed in exfat_direct_IO() * * Otherwise, in the case of buffered read, it is necessary to take * care the last nested block if valid_size is not equal to i_size. */ if (i_size == ei->valid_size || create || !bh_result->b_folio) valid_blks = EXFAT_B_TO_BLK_ROUND_UP(ei->valid_size, sb); else valid_blks = EXFAT_B_TO_BLK(ei->valid_size, sb); /* The range has been fully written, map it */ if (iblock + max_blocks < valid_blks) goto done; /* The range has been partially written, map the written part */ if (iblock < valid_blks) { max_blocks = valid_blks - iblock; goto done; } /* The area has not been written, map and mark as new for create case */ if (create) { set_buffer_new(bh_result); ei->valid_size = EXFAT_BLK_TO_B(iblock + max_blocks, sb); mark_inode_dirty(inode); goto done; } /* * The area has just one block partially written. * In that case, we should read and fill the unwritten part of * a block with zero. */ if (bh_result->b_folio && iblock == valid_blks && (ei->valid_size & (sb->s_blocksize - 1))) { loff_t size, pos; void *addr; max_blocks = 1; /* * No buffer_head is allocated. * (1) bmap: It's enough to set blocknr without I/O. * (2) read: The unwritten part should be filled with zero. * If a folio does not have any buffers, * let's returns -EAGAIN to fallback to * block_read_full_folio() for per-bh IO. */ if (!folio_buffers(bh_result->b_folio)) { err = -EAGAIN; goto done; } pos = EXFAT_BLK_TO_B(iblock, sb); size = ei->valid_size - pos; addr = folio_address(bh_result->b_folio) + offset_in_folio(bh_result->b_folio, pos); /* Check if bh->b_data points to proper addr in folio */ if (bh_result->b_data != addr) { exfat_fs_error_ratelimit(sb, "b_data(%p) != folio_addr(%p)", bh_result->b_data, addr); err = -EINVAL; goto done; } /* Read a block */ err = bh_read(bh_result, 0); if (err < 0) goto done; /* Zero unwritten part of a block */ memset(bh_result->b_data + size, 0, bh_result->b_size - size); err = 0; goto done; } /* * The area has not been written, clear mapped for read/bmap cases. * If so, it will be filled with zero without reading from disk. */ clear_buffer_mapped(bh_result); done: bh_result->b_size = EXFAT_BLK_TO_B(max_blocks, sb); if (err < 0) clear_buffer_mapped(bh_result); unlock_ret: mutex_unlock(&sbi->s_lock); return err; } static int exfat_read_folio(struct file *file, struct folio *folio) { return mpage_read_folio(folio, exfat_get_block); } static void exfat_readahead(struct readahead_control *rac) { struct address_space *mapping = rac->mapping; struct inode *inode = mapping->host; struct exfat_inode_info *ei = EXFAT_I(inode); loff_t pos = readahead_pos(rac); /* Range cross valid_size, read it page by page. */ if (ei->valid_size < i_size_read(inode) && pos <= ei->valid_size && ei->valid_size < pos + readahead_length(rac)) return; mpage_readahead(rac, exfat_get_block); } static int exfat_writepages(struct address_space *mapping, struct writeback_control *wbc) { if (unlikely(exfat_forced_shutdown(mapping->host->i_sb))) return -EIO; return mpage_writepages(mapping, wbc, exfat_get_block); } static void exfat_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; if (to > i_size_read(inode)) { truncate_pagecache(inode, i_size_read(inode)); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); exfat_truncate(inode); } } static int exfat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, struct folio **foliop, void **fsdata) { int ret; if (unlikely(exfat_forced_shutdown(mapping->host->i_sb))) return -EIO; ret = block_write_begin(mapping, pos, len, foliop, exfat_get_block); if (ret < 0) exfat_write_failed(mapping, pos+len); return ret; } static int exfat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; struct exfat_inode_info *ei = EXFAT_I(inode); int err; err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (err < len) exfat_write_failed(mapping, pos+len); if (!(err < 0) && pos + err > ei->valid_size) { ei->valid_size = pos + err; mark_inode_dirty(inode); } if (!(err < 0) && !(ei->attr & EXFAT_ATTR_ARCHIVE)) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ei->attr |= EXFAT_ATTR_ARCHIVE; mark_inode_dirty(inode); } return err; } static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; struct exfat_inode_info *ei = EXFAT_I(inode); loff_t pos = iocb->ki_pos; loff_t size = pos + iov_iter_count(iter); int rw = iov_iter_rw(iter); ssize_t ret; /* * Need to use the DIO_LOCKING for avoiding the race * condition of exfat_get_block() and ->truncate(). */ ret = blockdev_direct_IO(iocb, inode, iter, exfat_get_block); if (ret < 0) { if (rw == WRITE && ret != -EIOCBQUEUED) exfat_write_failed(mapping, size); return ret; } else size = pos + ret; if (rw == WRITE) { /* * If the block had been partially written before this write, * ->valid_size will not be updated in exfat_get_block(), * update it here. */ if (ei->valid_size < size) { ei->valid_size = size; mark_inode_dirty(inode); } } else if (pos < ei->valid_size && ei->valid_size < size) { /* zero the unwritten part in the partially written block */ iov_iter_revert(iter, size - ei->valid_size); iov_iter_zero(size - ei->valid_size, iter); } return ret; } static sector_t exfat_aop_bmap(struct address_space *mapping, sector_t block) { sector_t blocknr; /* exfat_get_cluster() assumes the requested blocknr isn't truncated. */ down_read(&EXFAT_I(mapping->host)->truncate_lock); blocknr = generic_block_bmap(mapping, block, exfat_get_block); up_read(&EXFAT_I(mapping->host)->truncate_lock); return blocknr; } /* * exfat_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This is required during truncate to physically zeroout the tail end * of that block so it doesn't yield old data if the file is later grown. * Also, avoid causing failure from fsx for cases of "data past EOF" */ int exfat_block_truncate_page(struct inode *inode, loff_t from) { return block_truncate_page(inode->i_mapping, from, exfat_get_block); } static const struct address_space_operations exfat_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, .read_folio = exfat_read_folio, .readahead = exfat_readahead, .writepages = exfat_writepages, .write_begin = exfat_write_begin, .write_end = exfat_write_end, .direct_IO = exfat_direct_IO, .bmap = exfat_aop_bmap, .migrate_folio = buffer_migrate_folio, }; static inline unsigned long exfat_hash(loff_t i_pos) { return hash_32(i_pos, EXFAT_HASH_BITS); } void exfat_hash_inode(struct inode *inode, loff_t i_pos) { struct exfat_sb_info *sbi = EXFAT_SB(inode->i_sb); struct hlist_head *head = sbi->inode_hashtable + exfat_hash(i_pos); spin_lock(&sbi->inode_hash_lock); EXFAT_I(inode)->i_pos = i_pos; hlist_add_head(&EXFAT_I(inode)->i_hash_fat, head); spin_unlock(&sbi->inode_hash_lock); } void exfat_unhash_inode(struct inode *inode) { struct exfat_sb_info *sbi = EXFAT_SB(inode->i_sb); spin_lock(&sbi->inode_hash_lock); hlist_del_init(&EXFAT_I(inode)->i_hash_fat); EXFAT_I(inode)->i_pos = 0; spin_unlock(&sbi->inode_hash_lock); } struct inode *exfat_iget(struct super_block *sb, loff_t i_pos) { struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *info; struct hlist_head *head = sbi->inode_hashtable + exfat_hash(i_pos); struct inode *inode = NULL; spin_lock(&sbi->inode_hash_lock); hlist_for_each_entry(info, head, i_hash_fat) { WARN_ON(info->vfs_inode.i_sb != sb); if (i_pos != info->i_pos) continue; inode = igrab(&info->vfs_inode); if (inode) break; } spin_unlock(&sbi->inode_hash_lock); return inode; } /* doesn't deal with root inode */ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) { struct exfat_sb_info *sbi = EXFAT_SB(inode->i_sb); struct exfat_inode_info *ei = EXFAT_I(inode); loff_t size = info->size; ei->dir = info->dir; ei->entry = info->entry; ei->attr = info->attr; ei->start_clu = info->start_clu; ei->flags = info->flags; ei->type = info->type; ei->valid_size = info->valid_size; ei->version = 0; ei->hint_stat.eidx = 0; ei->hint_stat.clu = info->start_clu; ei->hint_femp.eidx = EXFAT_HINT_NONE; ei->hint_bmap.off = EXFAT_EOF_CLUSTER; ei->i_pos = 0; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = get_random_u32(); if (info->attr & EXFAT_ATTR_SUBDIR) { /* directory */ inode->i_generation &= ~1; inode->i_mode = exfat_make_mode(sbi, info->attr, 0777); inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; set_nlink(inode, info->num_subdirs); } else { /* regular file */ inode->i_generation |= 1; inode->i_mode = exfat_make_mode(sbi, info->attr, 0777); inode->i_op = &exfat_file_inode_operations; inode->i_fop = &exfat_file_operations; inode->i_mapping->a_ops = &exfat_aops; inode->i_mapping->nrpages = 0; } i_size_write(inode, size); exfat_save_attr(inode, info->attr); inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; inode_set_mtime_to_ts(inode, info->mtime); inode_set_ctime_to_ts(inode, info->mtime); ei->i_crtime = info->crtime; inode_set_atime_to_ts(inode, info->atime); return 0; } struct inode *exfat_build_inode(struct super_block *sb, struct exfat_dir_entry *info, loff_t i_pos) { struct inode *inode; int err; inode = exfat_iget(sb, i_pos); if (inode) goto out; inode = new_inode(sb); if (!inode) { inode = ERR_PTR(-ENOMEM); goto out; } inode->i_ino = iunique(sb, EXFAT_ROOT_INO); inode_set_iversion(inode, 1); err = exfat_fill_inode(inode, info); if (err) { iput(inode); inode = ERR_PTR(err); goto out; } exfat_hash_inode(inode, i_pos); insert_inode_hash(inode); out: return inode; } void exfat_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); if (!inode->i_nlink) { i_size_write(inode, 0); mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock); __exfat_truncate(inode); mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock); } invalidate_inode_buffers(inode); clear_inode(inode); exfat_cache_inval_inode(inode); exfat_unhash_inode(inode); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #ifndef ZSTD_COMPILER_H #define ZSTD_COMPILER_H #include <linux/types.h> #include "portability_macros.h" /*-******************************************************* * Compiler specifics *********************************************************/ /* force inlining */ #if !defined(ZSTD_NO_INLINE) #if (defined(__GNUC__) && !defined(__STRICT_ANSI__)) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ # define INLINE_KEYWORD inline #else # define INLINE_KEYWORD #endif #define FORCE_INLINE_ATTR __attribute__((always_inline)) #else #define INLINE_KEYWORD #define FORCE_INLINE_ATTR #endif /* On MSVC qsort requires that functions passed into it use the __cdecl calling conversion(CC). This explicitly marks such functions as __cdecl so that the code will still compile if a CC other than __cdecl has been made the default. */ #define WIN_CDECL /* UNUSED_ATTR tells the compiler it is okay if the function is unused. */ #define UNUSED_ATTR __attribute__((unused)) /* * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant * parameters. They must be inlined for the compiler to eliminate the constant * branches. */ #define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR UNUSED_ATTR /* * HINT_INLINE is used to help the compiler generate better code. It is *not* * used for "templates", so it can be tweaked based on the compilers * performance. * * gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the * always_inline attribute. * * clang up to 5.0.0 (trunk) benefit tremendously from the always_inline * attribute. */ #if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5 # define HINT_INLINE static INLINE_KEYWORD #else # define HINT_INLINE FORCE_INLINE_TEMPLATE #endif /* "soft" inline : * The compiler is free to select if it's a good idea to inline or not. * The main objective is to silence compiler warnings * when a defined function in included but not used. * * Note : this macro is prefixed `MEM_` because it used to be provided by `mem.h` unit. * Updating the prefix is probably preferable, but requires a fairly large codemod, * since this name is used everywhere. */ #ifndef MEM_STATIC /* already defined in Linux Kernel mem.h */ #define MEM_STATIC static __inline UNUSED_ATTR #endif /* force no inlining */ #define FORCE_NOINLINE static __attribute__((__noinline__)) /* target attribute */ #define TARGET_ATTRIBUTE(target) __attribute__((__target__(target))) /* Target attribute for BMI2 dynamic dispatch. * Enable lzcnt, bmi, and bmi2. * We test for bmi1 & bmi2. lzcnt is included in bmi1. */ #define BMI2_TARGET_ATTRIBUTE TARGET_ATTRIBUTE("lzcnt,bmi,bmi2") /* prefetch * can be disabled, by declaring NO_PREFETCH build macro */ #if ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) ) # define PREFETCH_L1(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 3 /* locality */) # define PREFETCH_L2(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */) #elif defined(__aarch64__) # define PREFETCH_L1(ptr) do { __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr))); } while (0) # define PREFETCH_L2(ptr) do { __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr))); } while (0) #else # define PREFETCH_L1(ptr) do { (void)(ptr); } while (0) /* disabled */ # define PREFETCH_L2(ptr) do { (void)(ptr); } while (0) /* disabled */ #endif /* NO_PREFETCH */ #define CACHELINE_SIZE 64 #define PREFETCH_AREA(p, s) \ do { \ const char* const _ptr = (const char*)(p); \ size_t const _size = (size_t)(s); \ size_t _pos; \ for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) { \ PREFETCH_L2(_ptr + _pos); \ } \ } while (0) /* vectorization * older GCC (pre gcc-4.3 picked as the cutoff) uses a different syntax, * and some compilers, like Intel ICC and MCST LCC, do not support it at all. */ #if !defined(__INTEL_COMPILER) && !defined(__clang__) && defined(__GNUC__) && !defined(__LCC__) # if (__GNUC__ == 4 && __GNUC_MINOR__ > 3) || (__GNUC__ >= 5) # define DONT_VECTORIZE __attribute__((optimize("no-tree-vectorize"))) # else # define DONT_VECTORIZE _Pragma("GCC optimize(\"no-tree-vectorize\")") # endif #else # define DONT_VECTORIZE #endif /* Tell the compiler that a branch is likely or unlikely. * Only use these macros if it causes the compiler to generate better code. * If you can remove a LIKELY/UNLIKELY annotation without speed changes in gcc * and clang, please do. */ #define LIKELY(x) (__builtin_expect((x), 1)) #define UNLIKELY(x) (__builtin_expect((x), 0)) #if __has_builtin(__builtin_unreachable) || (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5))) # define ZSTD_UNREACHABLE do { assert(0), __builtin_unreachable(); } while (0) #else # define ZSTD_UNREACHABLE do { assert(0); } while (0) #endif /* disable warnings */ /* compile time determination of SIMD support */ /* C-language Attributes are added in C23. */ #if defined(__STDC_VERSION__) && (__STDC_VERSION__ > 201710L) && defined(__has_c_attribute) # define ZSTD_HAS_C_ATTRIBUTE(x) __has_c_attribute(x) #else # define ZSTD_HAS_C_ATTRIBUTE(x) 0 #endif /* Only use C++ attributes in C++. Some compilers report support for C++ * attributes when compiling with C. */ #define ZSTD_HAS_CPP_ATTRIBUTE(x) 0 /* Define ZSTD_FALLTHROUGH macro for annotating switch case with the 'fallthrough' attribute. * - C23: https://en.cppreference.com/w/c/language/attributes/fallthrough * - CPP17: https://en.cppreference.com/w/cpp/language/attributes/fallthrough * - Else: __attribute__((__fallthrough__)) */ #define ZSTD_FALLTHROUGH fallthrough /*-************************************************************** * Alignment *****************************************************************/ /* @return 1 if @u is a 2^n value, 0 otherwise * useful to check a value is valid for alignment restrictions */ MEM_STATIC int ZSTD_isPower2(size_t u) { return (u & (u-1)) == 0; } /* this test was initially positioned in mem.h, * but this file is removed (or replaced) for linux kernel * so it's now hosted in compiler.h, * which remains valid for both user & kernel spaces. */ #ifndef ZSTD_ALIGNOF /* covers gcc, clang & MSVC */ /* note : this section must come first, before C11, * due to a limitation in the kernel source generator */ # define ZSTD_ALIGNOF(T) __alignof(T) #endif /* ZSTD_ALIGNOF */ #ifndef ZSTD_ALIGNED /* C90-compatible alignment macro (GCC/Clang). Adjust for other compilers if needed. */ #define ZSTD_ALIGNED(a) __attribute__((aligned(a))) #endif /* ZSTD_ALIGNED */ /*-************************************************************** * Sanitizer *****************************************************************/ /* * Zstd relies on pointer overflow in its decompressor. * We add this attribute to functions that rely on pointer overflow. */ #ifndef ZSTD_ALLOW_POINTER_OVERFLOW_ATTR # if __has_attribute(no_sanitize) # if !defined(__clang__) && defined(__GNUC__) && __GNUC__ < 8 /* gcc < 8 only has signed-integer-overlow which triggers on pointer overflow */ # define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR __attribute__((no_sanitize("signed-integer-overflow"))) # else /* older versions of clang [3.7, 5.0) will warn that pointer-overflow is ignored. */ # define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR __attribute__((no_sanitize("pointer-overflow"))) # endif # else # define ZSTD_ALLOW_POINTER_OVERFLOW_ATTR # endif #endif /* * Helper function to perform a wrapped pointer difference without triggering * UBSAN. * * @returns lhs - rhs with wrapping */ MEM_STATIC ZSTD_ALLOW_POINTER_OVERFLOW_ATTR ptrdiff_t ZSTD_wrappedPtrDiff(unsigned char const* lhs, unsigned char const* rhs) { return lhs - rhs; } /* * Helper function to perform a wrapped pointer add without triggering UBSAN. * * @return ptr + add with wrapping */ MEM_STATIC ZSTD_ALLOW_POINTER_OVERFLOW_ATTR unsigned char const* ZSTD_wrappedPtrAdd(unsigned char const* ptr, ptrdiff_t add) { return ptr + add; } /* * Helper function to perform a wrapped pointer subtraction without triggering * UBSAN. * * @return ptr - sub with wrapping */ MEM_STATIC ZSTD_ALLOW_POINTER_OVERFLOW_ATTR unsigned char const* ZSTD_wrappedPtrSub(unsigned char const* ptr, ptrdiff_t sub) { return ptr - sub; } /* * Helper function to add to a pointer that works around C's undefined behavior * of adding 0 to NULL. * * @returns `ptr + add` except it defines `NULL + 0 == NULL`. */ MEM_STATIC unsigned char* ZSTD_maybeNullPtrAdd(unsigned char* ptr, ptrdiff_t add) { return add > 0 ? ptr + add : ptr; } /* Issue #3240 reports an ASAN failure on an llvm-mingw build. Out of an * abundance of caution, disable our custom poisoning on mingw. */ #ifdef __MINGW32__ #ifndef ZSTD_ASAN_DONT_POISON_WORKSPACE #define ZSTD_ASAN_DONT_POISON_WORKSPACE 1 #endif #ifndef ZSTD_MSAN_DONT_POISON_WORKSPACE #define ZSTD_MSAN_DONT_POISON_WORKSPACE 1 #endif #endif #endif /* ZSTD_COMPILER_H */ |
| 28 2 26 26 12 12 15 12 12 20 20 3 17 16 16 1 1 1 6 3 1 2 1 4 7 2 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Opening fs-verity files * * Copyright 2019 Google LLC */ #include "fsverity_private.h" #include <linux/mm.h> #include <linux/slab.h> static struct kmem_cache *fsverity_info_cachep; /** * fsverity_init_merkle_tree_params() - initialize Merkle tree parameters * @params: the parameters struct to initialize * @inode: the inode for which the Merkle tree is being built * @hash_algorithm: number of hash algorithm to use * @log_blocksize: log base 2 of block size to use * @salt: pointer to salt (optional) * @salt_size: size of salt, possibly 0 * * Validate the hash algorithm and block size, then compute the tree topology * (num levels, num blocks in each level, etc.) and initialize @params. * * Return: 0 on success, -errno on failure */ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, const struct inode *inode, unsigned int hash_algorithm, unsigned int log_blocksize, const u8 *salt, size_t salt_size) { const struct fsverity_hash_alg *hash_alg; int err; u64 blocks; u64 blocks_in_level[FS_VERITY_MAX_LEVELS]; u64 offset; int level; memset(params, 0, sizeof(*params)); hash_alg = fsverity_get_hash_alg(inode, hash_algorithm); if (IS_ERR(hash_alg)) return PTR_ERR(hash_alg); params->hash_alg = hash_alg; params->digest_size = hash_alg->digest_size; params->hashstate = fsverity_prepare_hash_state(hash_alg, salt, salt_size); if (IS_ERR(params->hashstate)) { err = PTR_ERR(params->hashstate); params->hashstate = NULL; fsverity_err(inode, "Error %d preparing hash state", err); goto out_err; } /* * fs/verity/ directly assumes that the Merkle tree block size is a * power of 2 less than or equal to PAGE_SIZE. Another restriction * arises from the interaction between fs/verity/ and the filesystems * themselves: filesystems expect to be able to verify a single * filesystem block of data at a time. Therefore, the Merkle tree block * size must also be less than or equal to the filesystem block size. * * The above are the only hard limitations, so in theory the Merkle tree * block size could be as small as twice the digest size. However, * that's not useful, and it would result in some unusually deep and * large Merkle trees. So we currently require that the Merkle tree * block size be at least 1024 bytes. That's small enough to test the * sub-page block case on systems with 4K pages, but not too small. */ if (log_blocksize < 10 || log_blocksize > PAGE_SHIFT || log_blocksize > inode->i_blkbits) { fsverity_warn(inode, "Unsupported log_blocksize: %u", log_blocksize); err = -EINVAL; goto out_err; } params->log_blocksize = log_blocksize; params->block_size = 1 << log_blocksize; params->log_blocks_per_page = PAGE_SHIFT - log_blocksize; params->blocks_per_page = 1 << params->log_blocks_per_page; if (WARN_ON_ONCE(!is_power_of_2(params->digest_size))) { err = -EINVAL; goto out_err; } if (params->block_size < 2 * params->digest_size) { fsverity_warn(inode, "Merkle tree block size (%u) too small for hash algorithm \"%s\"", params->block_size, hash_alg->name); err = -EINVAL; goto out_err; } params->log_digestsize = ilog2(params->digest_size); params->log_arity = log_blocksize - params->log_digestsize; params->hashes_per_block = 1 << params->log_arity; /* * Compute the number of levels in the Merkle tree and create a map from * level to the starting block of that level. Level 'num_levels - 1' is * the root and is stored first. Level 0 is the level directly "above" * the data blocks and is stored last. */ /* Compute number of levels and the number of blocks in each level */ blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize; while (blocks > 1) { if (params->num_levels >= FS_VERITY_MAX_LEVELS) { fsverity_err(inode, "Too many levels in Merkle tree"); err = -EFBIG; goto out_err; } blocks = (blocks + params->hashes_per_block - 1) >> params->log_arity; blocks_in_level[params->num_levels++] = blocks; } /* Compute the starting block of each level */ offset = 0; for (level = (int)params->num_levels - 1; level >= 0; level--) { params->level_start[level] = offset; offset += blocks_in_level[level]; } /* * With block_size != PAGE_SIZE, an in-memory bitmap will need to be * allocated to track the "verified" status of hash blocks. Don't allow * this bitmap to get too large. For now, limit it to 1 MiB, which * limits the file size to about 4.4 TB with SHA-256 and 4K blocks. * * Together with the fact that the data, and thus also the Merkle tree, * cannot have more than ULONG_MAX pages, this implies that hash block * indices can always fit in an 'unsigned long'. But to be safe, we * explicitly check for that too. Note, this is only for hash block * indices; data block indices might not fit in an 'unsigned long'. */ if ((params->block_size != PAGE_SIZE && offset > 1 << 23) || offset > ULONG_MAX) { fsverity_err(inode, "Too many blocks in Merkle tree"); err = -EFBIG; goto out_err; } params->tree_size = offset << log_blocksize; params->tree_pages = PAGE_ALIGN(params->tree_size) >> PAGE_SHIFT; return 0; out_err: kfree(params->hashstate); memset(params, 0, sizeof(*params)); return err; } /* * Compute the file digest by hashing the fsverity_descriptor excluding the * builtin signature and with the sig_size field set to 0. */ static int compute_file_digest(const struct fsverity_hash_alg *hash_alg, struct fsverity_descriptor *desc, u8 *file_digest) { __le32 sig_size = desc->sig_size; int err; desc->sig_size = 0; err = fsverity_hash_buffer(hash_alg, desc, sizeof(*desc), file_digest); desc->sig_size = sig_size; return err; } /* * Create a new fsverity_info from the given fsverity_descriptor (with optional * appended builtin signature), and check the signature if present. The * fsverity_descriptor must have already undergone basic validation. */ struct fsverity_info *fsverity_create_info(const struct inode *inode, struct fsverity_descriptor *desc) { struct fsverity_info *vi; int err; vi = kmem_cache_zalloc(fsverity_info_cachep, GFP_KERNEL); if (!vi) return ERR_PTR(-ENOMEM); vi->inode = inode; err = fsverity_init_merkle_tree_params(&vi->tree_params, inode, desc->hash_algorithm, desc->log_blocksize, desc->salt, desc->salt_size); if (err) { fsverity_err(inode, "Error %d initializing Merkle tree parameters", err); goto fail; } memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size); err = compute_file_digest(vi->tree_params.hash_alg, desc, vi->file_digest); if (err) { fsverity_err(inode, "Error %d computing file digest", err); goto fail; } err = fsverity_verify_signature(vi, desc->signature, le32_to_cpu(desc->sig_size)); if (err) goto fail; if (vi->tree_params.block_size != PAGE_SIZE) { /* * When the Merkle tree block size and page size differ, we use * a bitmap to keep track of which hash blocks have been * verified. This bitmap must contain one bit per hash block, * including alignment to a page boundary at the end. * * Eventually, to support extremely large files in an efficient * way, it might be necessary to make pages of this bitmap * reclaimable. But for now, simply allocating the whole bitmap * is a simple solution that works well on the files on which * fsverity is realistically used. E.g., with SHA-256 and 4K * blocks, a 100MB file only needs a 24-byte bitmap, and the * bitmap for any file under 17GB fits in a 4K page. */ unsigned long num_bits = vi->tree_params.tree_pages << vi->tree_params.log_blocks_per_page; vi->hash_block_verified = kvcalloc(BITS_TO_LONGS(num_bits), sizeof(unsigned long), GFP_KERNEL); if (!vi->hash_block_verified) { err = -ENOMEM; goto fail; } } return vi; fail: fsverity_free_info(vi); return ERR_PTR(err); } void fsverity_set_info(struct inode *inode, struct fsverity_info *vi) { /* * Multiple tasks may race to set ->i_verity_info, so use * cmpxchg_release(). This pairs with the smp_load_acquire() in * fsverity_get_info(). I.e., here we publish ->i_verity_info with a * RELEASE barrier so that other tasks can ACQUIRE it. */ if (cmpxchg_release(&inode->i_verity_info, NULL, vi) != NULL) { /* Lost the race, so free the fsverity_info we allocated. */ fsverity_free_info(vi); /* * Afterwards, the caller may access ->i_verity_info directly, * so make sure to ACQUIRE the winning fsverity_info. */ (void)fsverity_get_info(inode); } } void fsverity_free_info(struct fsverity_info *vi) { if (!vi) return; kfree(vi->tree_params.hashstate); kvfree(vi->hash_block_verified); kmem_cache_free(fsverity_info_cachep, vi); } static bool validate_fsverity_descriptor(struct inode *inode, const struct fsverity_descriptor *desc, size_t desc_size) { if (desc_size < sizeof(*desc)) { fsverity_err(inode, "Unrecognized descriptor size: %zu bytes", desc_size); return false; } if (desc->version != 1) { fsverity_err(inode, "Unrecognized descriptor version: %u", desc->version); return false; } if (memchr_inv(desc->__reserved, 0, sizeof(desc->__reserved))) { fsverity_err(inode, "Reserved bits set in descriptor"); return false; } if (desc->salt_size > sizeof(desc->salt)) { fsverity_err(inode, "Invalid salt_size: %u", desc->salt_size); return false; } if (le64_to_cpu(desc->data_size) != inode->i_size) { fsverity_err(inode, "Wrong data_size: %llu (desc) != %lld (inode)", le64_to_cpu(desc->data_size), inode->i_size); return false; } if (le32_to_cpu(desc->sig_size) > desc_size - sizeof(*desc)) { fsverity_err(inode, "Signature overflows verity descriptor"); return false; } return true; } /* * Read the inode's fsverity_descriptor (with optional appended builtin * signature) from the filesystem, and do basic validation of it. */ int fsverity_get_descriptor(struct inode *inode, struct fsverity_descriptor **desc_ret) { int res; struct fsverity_descriptor *desc; res = inode->i_sb->s_vop->get_verity_descriptor(inode, NULL, 0); if (res < 0) { fsverity_err(inode, "Error %d getting verity descriptor size", res); return res; } if (res > FS_VERITY_MAX_DESCRIPTOR_SIZE) { fsverity_err(inode, "Verity descriptor is too large (%d bytes)", res); return -EMSGSIZE; } desc = kmalloc(res, GFP_KERNEL); if (!desc) return -ENOMEM; res = inode->i_sb->s_vop->get_verity_descriptor(inode, desc, res); if (res < 0) { fsverity_err(inode, "Error %d reading verity descriptor", res); kfree(desc); return res; } if (!validate_fsverity_descriptor(inode, desc, res)) { kfree(desc); return -EINVAL; } *desc_ret = desc; return 0; } /* Ensure the inode has an ->i_verity_info */ static int ensure_verity_info(struct inode *inode) { struct fsverity_info *vi = fsverity_get_info(inode); struct fsverity_descriptor *desc; int err; if (vi) return 0; err = fsverity_get_descriptor(inode, &desc); if (err) return err; vi = fsverity_create_info(inode, desc); if (IS_ERR(vi)) { err = PTR_ERR(vi); goto out_free_desc; } fsverity_set_info(inode, vi); err = 0; out_free_desc: kfree(desc); return err; } int __fsverity_file_open(struct inode *inode, struct file *filp) { if (filp->f_mode & FMODE_WRITE) return -EPERM; return ensure_verity_info(inode); } EXPORT_SYMBOL_GPL(__fsverity_file_open); int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr) { if (attr->ia_valid & ATTR_SIZE) return -EPERM; return 0; } EXPORT_SYMBOL_GPL(__fsverity_prepare_setattr); void __fsverity_cleanup_inode(struct inode *inode) { fsverity_free_info(inode->i_verity_info); inode->i_verity_info = NULL; } EXPORT_SYMBOL_GPL(__fsverity_cleanup_inode); void __init fsverity_init_info_cache(void) { fsverity_info_cachep = KMEM_CACHE_USERCOPY( fsverity_info, SLAB_RECLAIM_ACCOUNT | SLAB_PANIC, file_digest); } |
| 173 171 2 2 134 134 53 51 2 5 3 2 1 1 3 3 3 3 3 41 39 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "eytzinger.h" #include "journal.h" #include "journal_seq_blacklist.h" #include "super-io.h" /* * journal_seq_blacklist machinery: * * To guarantee order of btree updates after a crash, we need to detect when a * btree node entry (bset) is newer than the newest journal entry that was * successfully written, and ignore it - effectively ignoring any btree updates * that didn't make it into the journal. * * If we didn't do this, we might have two btree nodes, a and b, both with * updates that weren't written to the journal yet: if b was updated after a, * but b was flushed and not a - oops; on recovery we'll find that the updates * to b happened, but not the updates to a that happened before it. * * Ignoring bsets that are newer than the newest journal entry is always safe, * because everything they contain will also have been journalled - and must * still be present in the journal on disk until a journal entry has been * written _after_ that bset was written. * * To accomplish this, bsets record the newest journal sequence number they * contain updates for; then, on startup, the btree code queries the journal * code to ask "Is this sequence number newer than the newest journal entry? If * so, ignore it." * * When this happens, we must blacklist that journal sequence number: the * journal must not write any entries with that sequence number, and it must * record that it was blacklisted so that a) on recovery we don't think we have * missing journal entries and b) so that the btree code continues to ignore * that bset, until that btree node is rewritten. */ static unsigned sb_blacklist_u64s(unsigned nr) { struct bch_sb_field_journal_seq_blacklist *bl; return (sizeof(*bl) + sizeof(bl->start[0]) * nr) / sizeof(u64); } int bch2_journal_seq_blacklist_add(struct bch_fs *c, u64 start, u64 end) { struct bch_sb_field_journal_seq_blacklist *bl; unsigned i = 0, nr; int ret = 0; mutex_lock(&c->sb_lock); bl = bch2_sb_field_get(c->disk_sb.sb, journal_seq_blacklist); nr = blacklist_nr_entries(bl); while (i < nr) { struct journal_seq_blacklist_entry *e = bl->start + i; if (end < le64_to_cpu(e->start)) break; if (start > le64_to_cpu(e->end)) { i++; continue; } /* * Entry is contiguous or overlapping with new entry: merge it * with new entry, and delete: */ start = min(start, le64_to_cpu(e->start)); end = max(end, le64_to_cpu(e->end)); array_remove_item(bl->start, nr, i); } bl = bch2_sb_field_resize(&c->disk_sb, journal_seq_blacklist, sb_blacklist_u64s(nr + 1)); if (!bl) { ret = bch_err_throw(c, ENOSPC_sb_journal_seq_blacklist); goto out; } array_insert_item(bl->start, nr, i, ((struct journal_seq_blacklist_entry) { .start = cpu_to_le64(start), .end = cpu_to_le64(end), })); c->disk_sb.sb->features[0] |= cpu_to_le64(1ULL << BCH_FEATURE_journal_seq_blacklist_v3); ret = bch2_write_super(c); out: mutex_unlock(&c->sb_lock); return ret ?: bch2_blacklist_table_initialize(c); } static int journal_seq_blacklist_table_cmp(const void *_l, const void *_r) { const struct journal_seq_blacklist_table_entry *l = _l; const struct journal_seq_blacklist_table_entry *r = _r; return cmp_int(l->start, r->start); } bool bch2_journal_seq_is_blacklisted(struct bch_fs *c, u64 seq, bool dirty) { struct journal_seq_blacklist_table *t = c->journal_seq_blacklist_table; struct journal_seq_blacklist_table_entry search = { .start = seq }; int idx; if (!t) return false; idx = eytzinger0_find_le(t->entries, t->nr, sizeof(t->entries[0]), journal_seq_blacklist_table_cmp, &search); if (idx < 0) return false; BUG_ON(t->entries[idx].start > seq); if (seq >= t->entries[idx].end) return false; if (dirty) t->entries[idx].dirty = true; return true; } u64 bch2_journal_last_blacklisted_seq(struct bch_fs *c) { struct journal_seq_blacklist_table *t = c->journal_seq_blacklist_table; if (!t || !t->nr) return 0; return t->entries[eytzinger0_last(t->nr)].end - 1; } int bch2_blacklist_table_initialize(struct bch_fs *c) { struct bch_sb_field_journal_seq_blacklist *bl = bch2_sb_field_get(c->disk_sb.sb, journal_seq_blacklist); struct journal_seq_blacklist_table *t; unsigned i, nr = blacklist_nr_entries(bl); if (!bl) return 0; t = kzalloc(struct_size(t, entries, nr), GFP_KERNEL); if (!t) return bch_err_throw(c, ENOMEM_blacklist_table_init); t->nr = nr; for (i = 0; i < nr; i++) { t->entries[i].start = le64_to_cpu(bl->start[i].start); t->entries[i].end = le64_to_cpu(bl->start[i].end); } eytzinger0_sort(t->entries, t->nr, sizeof(t->entries[0]), journal_seq_blacklist_table_cmp, NULL); kfree(c->journal_seq_blacklist_table); c->journal_seq_blacklist_table = t; return 0; } static int bch2_sb_journal_seq_blacklist_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { struct bch_sb_field_journal_seq_blacklist *bl = field_to_type(f, journal_seq_blacklist); unsigned i, nr = blacklist_nr_entries(bl); for (i = 0; i < nr; i++) { struct journal_seq_blacklist_entry *e = bl->start + i; if (le64_to_cpu(e->start) >= le64_to_cpu(e->end)) { prt_printf(err, "entry %u start >= end (%llu >= %llu)", i, le64_to_cpu(e->start), le64_to_cpu(e->end)); return -BCH_ERR_invalid_sb_journal_seq_blacklist; } if (i + 1 < nr && le64_to_cpu(e[0].end) > le64_to_cpu(e[1].start)) { prt_printf(err, "entry %u out of order with next entry (%llu > %llu)", i + 1, le64_to_cpu(e[0].end), le64_to_cpu(e[1].start)); return -BCH_ERR_invalid_sb_journal_seq_blacklist; } } return 0; } static void bch2_sb_journal_seq_blacklist_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_journal_seq_blacklist *bl = field_to_type(f, journal_seq_blacklist); struct journal_seq_blacklist_entry *i; unsigned nr = blacklist_nr_entries(bl); for (i = bl->start; i < bl->start + nr; i++) { if (i != bl->start) prt_printf(out, " "); prt_printf(out, "%llu-%llu", le64_to_cpu(i->start), le64_to_cpu(i->end)); } prt_newline(out); } const struct bch_sb_field_ops bch_sb_field_ops_journal_seq_blacklist = { .validate = bch2_sb_journal_seq_blacklist_validate, .to_text = bch2_sb_journal_seq_blacklist_to_text }; bool bch2_blacklist_entries_gc(struct bch_fs *c) { struct journal_seq_blacklist_entry *src, *dst; struct bch_sb_field_journal_seq_blacklist *bl = bch2_sb_field_get(c->disk_sb.sb, journal_seq_blacklist); if (!bl) return false; unsigned nr = blacklist_nr_entries(bl); dst = bl->start; struct journal_seq_blacklist_table *t = c->journal_seq_blacklist_table; BUG_ON(nr != t->nr); src = bl->start; eytzinger0_for_each(i, nr) { BUG_ON(t->entries[i].start != le64_to_cpu(src->start)); BUG_ON(t->entries[i].end != le64_to_cpu(src->end)); if (t->entries[i].dirty || t->entries[i].end >= c->journal.oldest_seq_found_ondisk) *dst++ = *src; src++; } unsigned new_nr = dst - bl->start; if (new_nr == nr) return false; bch_verbose(c, "nr blacklist entries was %u, now %u", nr, new_nr); bl = bch2_sb_field_resize(&c->disk_sb, journal_seq_blacklist, new_nr ? sb_blacklist_u64s(new_nr) : 0); BUG_ON(new_nr && !bl); return true; } |
| 119 1 120 108 207 208 15 5 114 118 118 120 5 5 12 3 10 5 5 10 32 17 17 15 8 7 1 8 6 2 5 3 4 4 5 3 4 4 4 4 5 3 6 2 8 8 8 6 2 5 3 6 2 5 3 116 114 48 34 1 35 24 36 32 29 16 34 32 19 31 29 8 21 25 9 1 35 16 1 23 1 2 70 1 26 33 7 7 5 2 1 74 71 51 20 9 76 76 72 75 1 71 74 97 3 94 1 2 86 90 3 86 86 99 99 99 99 90 90 90 90 90 12 78 78 12 90 90 4 16 2 68 68 16 90 90 2 88 88 79 79 71 66 1 96 1 12 79 2 92 96 5 91 86 8 2 90 72 86 86 86 86 91 91 19 97 84 91 103 100 86 99 97 99 17 10 99 2 97 94 90 103 103 93 5 5 105 29 4 103 96 9 86 1 17 2 6 12 25 15 10 3 12 108 76 3 6 2 15 58 32 105 82 9 11 83 83 8 8 8 8 8 8 109 108 108 9 99 108 21 94 7 17 24 3 5 6 94 10 84 70 14 4 90 90 4 82 4 82 2 84 22 2 24 52 30 5 1 4 5 13 13 3 8 8 8 8 1 1 1 1 8 1 2 2 1 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * super.c * * PURPOSE * Super block routines for the OSTA-UDF(tm) filesystem. * * DESCRIPTION * OSTA-UDF(tm) = Optical Storage Technology Association * Universal Disk Format. * * This code is based on version 2.00 of the UDF specification, * and revision 3 of the ECMA 167 standard [equivalent to ISO 13346]. * http://www.osta.org/ * https://www.ecma.ch/ * https://www.iso.org/ * * COPYRIGHT * (C) 1998 Dave Boynton * (C) 1998-2004 Ben Fennema * (C) 2000 Stelias Computing Inc * * HISTORY * * 09/24/98 dgb changed to allow compiling outside of kernel, and * added some debugging. * 10/01/98 dgb updated to allow (some) possibility of compiling w/2.0.34 * 10/16/98 attempting some multi-session support * 10/17/98 added freespace count for "df" * 11/11/98 gr added novrs option * 11/26/98 dgb added fileset,anchor mount options * 12/06/98 blf really hosed things royally. vat/sparing support. sequenced * vol descs. rewrote option handling based on isofs * 12/20/98 find the free space bitmap (if it exists) */ #include "udfdecl.h" #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/stat.h> #include <linux/cdrom.h> #include <linux/nls.h> #include <linux/vfs.h> #include <linux/vmalloc.h> #include <linux/errno.h> #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/crc-itu-t.h> #include <linux/log2.h> #include <asm/byteorder.h> #include <linux/iversion.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "udf_sb.h" #include "udf_i.h" #include <linux/init.h> #include <linux/uaccess.h> enum { VDS_POS_PRIMARY_VOL_DESC, VDS_POS_UNALLOC_SPACE_DESC, VDS_POS_LOGICAL_VOL_DESC, VDS_POS_IMP_USE_VOL_DESC, VDS_POS_LENGTH }; #define VSD_FIRST_SECTOR_OFFSET 32768 #define VSD_MAX_SECTOR_OFFSET 0x800000 /* * Maximum number of Terminating Descriptor / Logical Volume Integrity * Descriptor redirections. The chosen numbers are arbitrary - just that we * hopefully don't limit any real use of rewritten inode on write-once media * but avoid looping for too long on corrupted media. */ #define UDF_MAX_TD_NESTING 64 #define UDF_MAX_LVID_NESTING 1000 enum { UDF_MAX_LINKS = 0xffff }; /* * We limit filesize to 4TB. This is arbitrary as the on-disk format supports * more but because the file space is described by a linked list of extents, * each of which can have at most 1GB, the creation and handling of extents * gets unusably slow beyond certain point... */ #define UDF_MAX_FILESIZE (1ULL << 42) /* These are the "meat" - everything else is stuffing */ static int udf_fill_super(struct super_block *sb, struct fs_context *fc); static void udf_put_super(struct super_block *); static int udf_sync_fs(struct super_block *, int); static void udf_load_logicalvolint(struct super_block *, struct kernel_extent_ad); static void udf_open_lvid(struct super_block *); static void udf_close_lvid(struct super_block *); static unsigned int udf_count_free(struct super_block *); static int udf_statfs(struct dentry *, struct kstatfs *); static int udf_show_options(struct seq_file *, struct dentry *); static int udf_init_fs_context(struct fs_context *fc); static int udf_parse_param(struct fs_context *fc, struct fs_parameter *param); static int udf_reconfigure(struct fs_context *fc); static void udf_free_fc(struct fs_context *fc); static const struct fs_parameter_spec udf_param_spec[]; struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb) { struct logicalVolIntegrityDesc *lvid; unsigned int partnum; unsigned int offset; if (!UDF_SB(sb)->s_lvid_bh) return NULL; lvid = (struct logicalVolIntegrityDesc *)UDF_SB(sb)->s_lvid_bh->b_data; partnum = le32_to_cpu(lvid->numOfPartitions); /* The offset is to skip freeSpaceTable and sizeTable arrays */ offset = partnum * 2 * sizeof(uint32_t); return (struct logicalVolIntegrityDescImpUse *) (((uint8_t *)(lvid + 1)) + offset); } /* UDF filesystem type */ static int udf_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, udf_fill_super); } static const struct fs_context_operations udf_context_ops = { .parse_param = udf_parse_param, .get_tree = udf_get_tree, .reconfigure = udf_reconfigure, .free = udf_free_fc, }; static struct file_system_type udf_fstype = { .owner = THIS_MODULE, .name = "udf", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = udf_init_fs_context, .parameters = udf_param_spec, }; MODULE_ALIAS_FS("udf"); static struct kmem_cache *udf_inode_cachep; static struct inode *udf_alloc_inode(struct super_block *sb) { struct udf_inode_info *ei; ei = alloc_inode_sb(sb, udf_inode_cachep, GFP_KERNEL); if (!ei) return NULL; ei->i_unique = 0; ei->i_lenExtents = 0; ei->i_lenStreams = 0; ei->i_next_alloc_block = 0; ei->i_next_alloc_goal = 0; ei->i_strat4096 = 0; ei->i_streamdir = 0; ei->i_hidden = 0; init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); inode_set_iversion(&ei->vfs_inode, 1); return &ei->vfs_inode; } static void udf_free_in_core_inode(struct inode *inode) { kmem_cache_free(udf_inode_cachep, UDF_I(inode)); } static void init_once(void *foo) { struct udf_inode_info *ei = foo; ei->i_data = NULL; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { udf_inode_cachep = kmem_cache_create("udf_inode_cache", sizeof(struct udf_inode_info), 0, (SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), init_once); if (!udf_inode_cachep) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(udf_inode_cachep); } /* Superblock operations */ static const struct super_operations udf_sb_ops = { .alloc_inode = udf_alloc_inode, .free_inode = udf_free_in_core_inode, .write_inode = udf_write_inode, .evict_inode = udf_evict_inode, .put_super = udf_put_super, .sync_fs = udf_sync_fs, .statfs = udf_statfs, .show_options = udf_show_options, }; struct udf_options { unsigned int blocksize; unsigned int session; unsigned int lastblock; unsigned int anchor; unsigned int flags; umode_t umask; kgid_t gid; kuid_t uid; umode_t fmode; umode_t dmode; struct nls_table *nls_map; }; /* * UDF has historically preserved prior mount options across * a remount, so copy those here if remounting, otherwise set * initial mount defaults. */ static void udf_init_options(struct fs_context *fc, struct udf_options *uopt) { if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { struct super_block *sb = fc->root->d_sb; struct udf_sb_info *sbi = UDF_SB(sb); uopt->flags = sbi->s_flags; uopt->uid = sbi->s_uid; uopt->gid = sbi->s_gid; uopt->umask = sbi->s_umask; uopt->fmode = sbi->s_fmode; uopt->dmode = sbi->s_dmode; uopt->nls_map = NULL; } else { uopt->flags = (1 << UDF_FLAG_USE_AD_IN_ICB) | (1 << UDF_FLAG_STRICT); /* * By default we'll use overflow[ug]id when UDF * inode [ug]id == -1 */ uopt->uid = make_kuid(current_user_ns(), overflowuid); uopt->gid = make_kgid(current_user_ns(), overflowgid); uopt->umask = 0; uopt->fmode = UDF_INVALID_MODE; uopt->dmode = UDF_INVALID_MODE; uopt->nls_map = NULL; uopt->session = 0xFFFFFFFF; } } static int udf_init_fs_context(struct fs_context *fc) { struct udf_options *uopt; uopt = kzalloc(sizeof(*uopt), GFP_KERNEL); if (!uopt) return -ENOMEM; udf_init_options(fc, uopt); fc->fs_private = uopt; fc->ops = &udf_context_ops; return 0; } static void udf_free_fc(struct fs_context *fc) { struct udf_options *uopt = fc->fs_private; unload_nls(uopt->nls_map); kfree(fc->fs_private); } static int __init init_udf_fs(void) { int err; err = init_inodecache(); if (err) goto out1; err = register_filesystem(&udf_fstype); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_udf_fs(void) { unregister_filesystem(&udf_fstype); destroy_inodecache(); } static int udf_sb_alloc_partition_maps(struct super_block *sb, u32 count) { struct udf_sb_info *sbi = UDF_SB(sb); sbi->s_partmaps = kcalloc(count, sizeof(*sbi->s_partmaps), GFP_KERNEL); if (!sbi->s_partmaps) { sbi->s_partitions = 0; return -ENOMEM; } sbi->s_partitions = count; return 0; } static void udf_sb_free_bitmap(struct udf_bitmap *bitmap) { int i; int nr_groups = bitmap->s_nr_groups; for (i = 0; i < nr_groups; i++) if (!IS_ERR_OR_NULL(bitmap->s_block_bitmap[i])) brelse(bitmap->s_block_bitmap[i]); kvfree(bitmap); } static void udf_free_partition(struct udf_part_map *map) { int i; struct udf_meta_data *mdata; if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE) iput(map->s_uspace.s_table); if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) udf_sb_free_bitmap(map->s_uspace.s_bitmap); if (map->s_partition_type == UDF_SPARABLE_MAP15) for (i = 0; i < 4; i++) brelse(map->s_type_specific.s_sparing.s_spar_map[i]); else if (map->s_partition_type == UDF_METADATA_MAP25) { mdata = &map->s_type_specific.s_metadata; iput(mdata->s_metadata_fe); mdata->s_metadata_fe = NULL; iput(mdata->s_mirror_fe); mdata->s_mirror_fe = NULL; iput(mdata->s_bitmap_fe); mdata->s_bitmap_fe = NULL; } } static void udf_sb_free_partitions(struct super_block *sb) { struct udf_sb_info *sbi = UDF_SB(sb); int i; if (!sbi->s_partmaps) return; for (i = 0; i < sbi->s_partitions; i++) udf_free_partition(&sbi->s_partmaps[i]); kfree(sbi->s_partmaps); sbi->s_partmaps = NULL; } static int udf_show_options(struct seq_file *seq, struct dentry *root) { struct super_block *sb = root->d_sb; struct udf_sb_info *sbi = UDF_SB(sb); if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT)) seq_puts(seq, ",nostrict"); if (UDF_QUERY_FLAG(sb, UDF_FLAG_BLOCKSIZE_SET)) seq_printf(seq, ",bs=%lu", sb->s_blocksize); if (UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) seq_puts(seq, ",unhide"); if (UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) seq_puts(seq, ",undelete"); if (!UDF_QUERY_FLAG(sb, UDF_FLAG_USE_AD_IN_ICB)) seq_puts(seq, ",noadinicb"); if (UDF_QUERY_FLAG(sb, UDF_FLAG_USE_SHORT_AD)) seq_puts(seq, ",shortad"); if (UDF_QUERY_FLAG(sb, UDF_FLAG_UID_FORGET)) seq_puts(seq, ",uid=forget"); if (UDF_QUERY_FLAG(sb, UDF_FLAG_GID_FORGET)) seq_puts(seq, ",gid=forget"); if (UDF_QUERY_FLAG(sb, UDF_FLAG_UID_SET)) seq_printf(seq, ",uid=%u", from_kuid(&init_user_ns, sbi->s_uid)); if (UDF_QUERY_FLAG(sb, UDF_FLAG_GID_SET)) seq_printf(seq, ",gid=%u", from_kgid(&init_user_ns, sbi->s_gid)); if (sbi->s_umask != 0) seq_printf(seq, ",umask=%ho", sbi->s_umask); if (sbi->s_fmode != UDF_INVALID_MODE) seq_printf(seq, ",mode=%ho", sbi->s_fmode); if (sbi->s_dmode != UDF_INVALID_MODE) seq_printf(seq, ",dmode=%ho", sbi->s_dmode); if (UDF_QUERY_FLAG(sb, UDF_FLAG_SESSION_SET)) seq_printf(seq, ",session=%d", sbi->s_session); if (UDF_QUERY_FLAG(sb, UDF_FLAG_LASTBLOCK_SET)) seq_printf(seq, ",lastblock=%u", sbi->s_last_block); if (sbi->s_anchor != 0) seq_printf(seq, ",anchor=%u", sbi->s_anchor); if (sbi->s_nls_map) seq_printf(seq, ",iocharset=%s", sbi->s_nls_map->charset); else seq_puts(seq, ",iocharset=utf8"); return 0; } /* * udf_parse_param * * PURPOSE * Parse mount options. * * DESCRIPTION * The following mount options are supported: * * gid= Set the default group. * umask= Set the default umask. * mode= Set the default file permissions. * dmode= Set the default directory permissions. * uid= Set the default user. * bs= Set the block size. * unhide Show otherwise hidden files. * undelete Show deleted files in lists. * adinicb Embed data in the inode (default) * noadinicb Don't embed data in the inode * shortad Use short ad's * longad Use long ad's (default) * nostrict Unset strict conformance * iocharset= Set the NLS character set * * The remaining are for debugging and disaster recovery: * * novrs Skip volume sequence recognition * * The following expect a offset from 0. * * session= Set the CDROM session (default= last session) * anchor= Override standard anchor location. (default= 256) * volume= Override the VolumeDesc location. (unused) * partition= Override the PartitionDesc location. (unused) * lastblock= Set the last block of the filesystem/ * * The following expect a offset from the partition root. * * fileset= Override the fileset block location. (unused) * rootdir= Override the root directory location. (unused) * WARNING: overriding the rootdir to a non-directory may * yield highly unpredictable results. * * PRE-CONDITIONS * fc fs_context with pointer to mount options variable. * param Pointer to fs_parameter being parsed. * * POST-CONDITIONS * <return> 0 Mount options parsed okay. * <return> errno Error parsing mount options. * * HISTORY * July 1, 1997 - Andrew E. Mileski * Written, tested, and released. */ enum { Opt_novrs, Opt_nostrict, Opt_bs, Opt_unhide, Opt_undelete, Opt_noadinicb, Opt_adinicb, Opt_shortad, Opt_longad, Opt_gid, Opt_uid, Opt_umask, Opt_session, Opt_lastblock, Opt_anchor, Opt_volume, Opt_partition, Opt_fileset, Opt_rootdir, Opt_utf8, Opt_iocharset, Opt_err, Opt_fmode, Opt_dmode }; static const struct fs_parameter_spec udf_param_spec[] = { fsparam_flag ("novrs", Opt_novrs), fsparam_flag ("nostrict", Opt_nostrict), fsparam_u32 ("bs", Opt_bs), fsparam_flag ("unhide", Opt_unhide), fsparam_flag ("undelete", Opt_undelete), fsparam_flag_no ("adinicb", Opt_adinicb), fsparam_flag ("shortad", Opt_shortad), fsparam_flag ("longad", Opt_longad), fsparam_string ("gid", Opt_gid), fsparam_string ("uid", Opt_uid), fsparam_u32 ("umask", Opt_umask), fsparam_u32 ("session", Opt_session), fsparam_u32 ("lastblock", Opt_lastblock), fsparam_u32 ("anchor", Opt_anchor), fsparam_u32 ("volume", Opt_volume), fsparam_u32 ("partition", Opt_partition), fsparam_u32 ("fileset", Opt_fileset), fsparam_u32 ("rootdir", Opt_rootdir), fsparam_flag ("utf8", Opt_utf8), fsparam_string ("iocharset", Opt_iocharset), fsparam_u32 ("mode", Opt_fmode), fsparam_u32 ("dmode", Opt_dmode), {} }; static int udf_parse_param(struct fs_context *fc, struct fs_parameter *param) { unsigned int uv; unsigned int n; struct udf_options *uopt = fc->fs_private; struct fs_parse_result result; int token; bool remount = (fc->purpose & FS_CONTEXT_FOR_RECONFIGURE); token = fs_parse(fc, udf_param_spec, param, &result); if (token < 0) return token; switch (token) { case Opt_novrs: uopt->flags |= (1 << UDF_FLAG_NOVRS); break; case Opt_bs: n = result.uint_32; if (n != 512 && n != 1024 && n != 2048 && n != 4096) return -EINVAL; uopt->blocksize = n; uopt->flags |= (1 << UDF_FLAG_BLOCKSIZE_SET); break; case Opt_unhide: uopt->flags |= (1 << UDF_FLAG_UNHIDE); break; case Opt_undelete: uopt->flags |= (1 << UDF_FLAG_UNDELETE); break; case Opt_adinicb: if (result.negated) uopt->flags &= ~(1 << UDF_FLAG_USE_AD_IN_ICB); else uopt->flags |= (1 << UDF_FLAG_USE_AD_IN_ICB); break; case Opt_shortad: uopt->flags |= (1 << UDF_FLAG_USE_SHORT_AD); break; case Opt_longad: uopt->flags &= ~(1 << UDF_FLAG_USE_SHORT_AD); break; case Opt_gid: if (kstrtoint(param->string, 10, &uv) == 0) { kgid_t gid = make_kgid(current_user_ns(), uv); if (!gid_valid(gid)) return -EINVAL; uopt->gid = gid; uopt->flags |= (1 << UDF_FLAG_GID_SET); } else if (!strcmp(param->string, "forget")) { uopt->flags |= (1 << UDF_FLAG_GID_FORGET); } else if (!strcmp(param->string, "ignore")) { /* this option is superseded by gid=<number> */ ; } else { return -EINVAL; } break; case Opt_uid: if (kstrtoint(param->string, 10, &uv) == 0) { kuid_t uid = make_kuid(current_user_ns(), uv); if (!uid_valid(uid)) return -EINVAL; uopt->uid = uid; uopt->flags |= (1 << UDF_FLAG_UID_SET); } else if (!strcmp(param->string, "forget")) { uopt->flags |= (1 << UDF_FLAG_UID_FORGET); } else if (!strcmp(param->string, "ignore")) { /* this option is superseded by uid=<number> */ ; } else { return -EINVAL; } break; case Opt_umask: uopt->umask = result.uint_32; break; case Opt_nostrict: uopt->flags &= ~(1 << UDF_FLAG_STRICT); break; case Opt_session: uopt->session = result.uint_32; if (!remount) uopt->flags |= (1 << UDF_FLAG_SESSION_SET); break; case Opt_lastblock: uopt->lastblock = result.uint_32; if (!remount) uopt->flags |= (1 << UDF_FLAG_LASTBLOCK_SET); break; case Opt_anchor: uopt->anchor = result.uint_32; break; case Opt_volume: case Opt_partition: case Opt_fileset: case Opt_rootdir: /* Ignored (never implemented properly) */ break; case Opt_utf8: if (!remount) { unload_nls(uopt->nls_map); uopt->nls_map = NULL; } break; case Opt_iocharset: if (!remount) { unload_nls(uopt->nls_map); uopt->nls_map = NULL; } /* When nls_map is not loaded then UTF-8 is used */ if (!remount && strcmp(param->string, "utf8") != 0) { uopt->nls_map = load_nls(param->string); if (!uopt->nls_map) { errorf(fc, "iocharset %s not found", param->string); return -EINVAL; } } break; case Opt_fmode: uopt->fmode = result.uint_32 & 0777; break; case Opt_dmode: uopt->dmode = result.uint_32 & 0777; break; default: return -EINVAL; } return 0; } static int udf_reconfigure(struct fs_context *fc) { struct udf_options *uopt = fc->fs_private; struct super_block *sb = fc->root->d_sb; struct udf_sb_info *sbi = UDF_SB(sb); int readonly = fc->sb_flags & SB_RDONLY; int error = 0; if (!readonly && UDF_QUERY_FLAG(sb, UDF_FLAG_RW_INCOMPAT)) return -EACCES; sync_filesystem(sb); write_lock(&sbi->s_cred_lock); sbi->s_flags = uopt->flags; sbi->s_uid = uopt->uid; sbi->s_gid = uopt->gid; sbi->s_umask = uopt->umask; sbi->s_fmode = uopt->fmode; sbi->s_dmode = uopt->dmode; write_unlock(&sbi->s_cred_lock); if (readonly == sb_rdonly(sb)) goto out_unlock; if (readonly) udf_close_lvid(sb); else udf_open_lvid(sb); out_unlock: return error; } /* * Check VSD descriptor. Returns -1 in case we are at the end of volume * recognition area, 0 if the descriptor is valid but non-interesting, 1 if * we found one of NSR descriptors we are looking for. */ static int identify_vsd(const struct volStructDesc *vsd) { int ret = 0; if (!memcmp(vsd->stdIdent, VSD_STD_ID_CD001, VSD_STD_ID_LEN)) { switch (vsd->structType) { case 0: udf_debug("ISO9660 Boot Record found\n"); break; case 1: udf_debug("ISO9660 Primary Volume Descriptor found\n"); break; case 2: udf_debug("ISO9660 Supplementary Volume Descriptor found\n"); break; case 3: udf_debug("ISO9660 Volume Partition Descriptor found\n"); break; case 255: udf_debug("ISO9660 Volume Descriptor Set Terminator found\n"); break; default: udf_debug("ISO9660 VRS (%u) found\n", vsd->structType); break; } } else if (!memcmp(vsd->stdIdent, VSD_STD_ID_BEA01, VSD_STD_ID_LEN)) ; /* ret = 0 */ else if (!memcmp(vsd->stdIdent, VSD_STD_ID_NSR02, VSD_STD_ID_LEN)) ret = 1; else if (!memcmp(vsd->stdIdent, VSD_STD_ID_NSR03, VSD_STD_ID_LEN)) ret = 1; else if (!memcmp(vsd->stdIdent, VSD_STD_ID_BOOT2, VSD_STD_ID_LEN)) ; /* ret = 0 */ else if (!memcmp(vsd->stdIdent, VSD_STD_ID_CDW02, VSD_STD_ID_LEN)) ; /* ret = 0 */ else { /* TEA01 or invalid id : end of volume recognition area */ ret = -1; } return ret; } /* * Check Volume Structure Descriptors (ECMA 167 2/9.1) * We also check any "CD-ROM Volume Descriptor Set" (ECMA 167 2/8.3.1) * @return 1 if NSR02 or NSR03 found, * -1 if first sector read error, 0 otherwise */ static int udf_check_vsd(struct super_block *sb) { struct volStructDesc *vsd = NULL; loff_t sector = VSD_FIRST_SECTOR_OFFSET; int sectorsize; struct buffer_head *bh = NULL; int nsr = 0; struct udf_sb_info *sbi; loff_t session_offset; sbi = UDF_SB(sb); if (sb->s_blocksize < sizeof(struct volStructDesc)) sectorsize = sizeof(struct volStructDesc); else sectorsize = sb->s_blocksize; session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits; sector += session_offset; udf_debug("Starting at sector %u (%lu byte sectors)\n", (unsigned int)(sector >> sb->s_blocksize_bits), sb->s_blocksize); /* Process the sequence (if applicable). The hard limit on the sector * offset is arbitrary, hopefully large enough so that all valid UDF * filesystems will be recognised. There is no mention of an upper * bound to the size of the volume recognition area in the standard. * The limit will prevent the code to read all the sectors of a * specially crafted image (like a bluray disc full of CD001 sectors), * potentially causing minutes or even hours of uninterruptible I/O * activity. This actually happened with uninitialised SSD partitions * (all 0xFF) before the check for the limit and all valid IDs were * added */ for (; !nsr && sector < VSD_MAX_SECTOR_OFFSET; sector += sectorsize) { /* Read a block */ bh = sb_bread(sb, sector >> sb->s_blocksize_bits); if (!bh) break; vsd = (struct volStructDesc *)(bh->b_data + (sector & (sb->s_blocksize - 1))); nsr = identify_vsd(vsd); /* Found NSR or end? */ if (nsr) { brelse(bh); break; } /* * Special handling for improperly formatted VRS (e.g., Win10) * where components are separated by 2048 bytes even though * sectors are 4K */ if (sb->s_blocksize == 4096) { nsr = identify_vsd(vsd + 1); /* Ignore unknown IDs... */ if (nsr < 0) nsr = 0; } brelse(bh); } if (nsr > 0) return 1; else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET) return -1; else return 0; } static int udf_verify_domain_identifier(struct super_block *sb, struct regid *ident, char *dname) { struct domainIdentSuffix *suffix; if (memcmp(ident->ident, UDF_ID_COMPLIANT, strlen(UDF_ID_COMPLIANT))) { udf_warn(sb, "Not OSTA UDF compliant %s descriptor.\n", dname); goto force_ro; } if (ident->flags & ENTITYID_FLAGS_DIRTY) { udf_warn(sb, "Possibly not OSTA UDF compliant %s descriptor.\n", dname); goto force_ro; } suffix = (struct domainIdentSuffix *)ident->identSuffix; if ((suffix->domainFlags & DOMAIN_FLAGS_HARD_WRITE_PROTECT) || (suffix->domainFlags & DOMAIN_FLAGS_SOFT_WRITE_PROTECT)) { if (!sb_rdonly(sb)) { udf_warn(sb, "Descriptor for %s marked write protected." " Forcing read only mount.\n", dname); } goto force_ro; } return 0; force_ro: if (!sb_rdonly(sb)) return -EACCES; UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); return 0; } static int udf_load_fileset(struct super_block *sb, struct fileSetDesc *fset, struct kernel_lb_addr *root) { int ret; ret = udf_verify_domain_identifier(sb, &fset->domainIdent, "file set"); if (ret < 0) return ret; *root = lelb_to_cpu(fset->rootDirectoryICB.extLocation); UDF_SB(sb)->s_serial_number = le16_to_cpu(fset->descTag.tagSerialNum); udf_debug("Rootdir at block=%u, partition=%u\n", root->logicalBlockNum, root->partitionReferenceNum); return 0; } static int udf_find_fileset(struct super_block *sb, struct kernel_lb_addr *fileset, struct kernel_lb_addr *root) { struct buffer_head *bh; uint16_t ident; int ret; if (fileset->logicalBlockNum == 0xFFFFFFFF && fileset->partitionReferenceNum == 0xFFFF) return -EINVAL; bh = udf_read_ptagged(sb, fileset, 0, &ident); if (!bh) return -EIO; if (ident != TAG_IDENT_FSD) { brelse(bh); return -EINVAL; } udf_debug("Fileset at block=%u, partition=%u\n", fileset->logicalBlockNum, fileset->partitionReferenceNum); UDF_SB(sb)->s_partition = fileset->partitionReferenceNum; ret = udf_load_fileset(sb, (struct fileSetDesc *)bh->b_data, root); brelse(bh); return ret; } /* * Load primary Volume Descriptor Sequence * * Return <0 on error, 0 on success. -EAGAIN is special meaning next sequence * should be tried. */ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) { struct primaryVolDesc *pvoldesc; uint8_t *outstr; struct buffer_head *bh; uint16_t ident; int ret; struct timestamp *ts; outstr = kzalloc(128, GFP_KERNEL); if (!outstr) return -ENOMEM; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) { ret = -EAGAIN; goto out2; } if (ident != TAG_IDENT_PVD) { ret = -EIO; goto out_bh; } pvoldesc = (struct primaryVolDesc *)bh->b_data; udf_disk_stamp_to_time(&UDF_SB(sb)->s_record_time, pvoldesc->recordingDateAndTime); ts = &pvoldesc->recordingDateAndTime; udf_debug("recording time %04u/%02u/%02u %02u:%02u (%x)\n", le16_to_cpu(ts->year), ts->month, ts->day, ts->hour, ts->minute, le16_to_cpu(ts->typeAndTimezone)); ret = udf_dstrCS0toChar(sb, outstr, 31, pvoldesc->volIdent, 32); if (ret < 0) { strscpy_pad(UDF_SB(sb)->s_volume_ident, "InvalidName"); pr_warn("incorrect volume identification, setting to " "'InvalidName'\n"); } else { strscpy_pad(UDF_SB(sb)->s_volume_ident, outstr); } udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident); ret = udf_dstrCS0toChar(sb, outstr, 127, pvoldesc->volSetIdent, 128); if (ret < 0) { ret = 0; goto out_bh; } outstr[ret] = 0; udf_debug("volSetIdent[] = '%s'\n", outstr); ret = 0; out_bh: brelse(bh); out2: kfree(outstr); return ret; } struct inode *udf_find_metadata_inode_efe(struct super_block *sb, u32 meta_file_loc, u32 partition_ref) { struct kernel_lb_addr addr; struct inode *metadata_fe; addr.logicalBlockNum = meta_file_loc; addr.partitionReferenceNum = partition_ref; metadata_fe = udf_iget_special(sb, &addr); if (IS_ERR(metadata_fe)) { udf_warn(sb, "metadata inode efe not found\n"); return metadata_fe; } if (UDF_I(metadata_fe)->i_alloc_type != ICBTAG_FLAG_AD_SHORT) { udf_warn(sb, "metadata inode efe does not have short allocation descriptors!\n"); iput(metadata_fe); return ERR_PTR(-EIO); } return metadata_fe; } static int udf_load_metadata_files(struct super_block *sb, int partition, int type1_index) { struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map; struct udf_meta_data *mdata; struct kernel_lb_addr addr; struct inode *fe; map = &sbi->s_partmaps[partition]; mdata = &map->s_type_specific.s_metadata; mdata->s_phys_partition_ref = type1_index; /* metadata address */ udf_debug("Metadata file location: block = %u part = %u\n", mdata->s_meta_file_loc, mdata->s_phys_partition_ref); fe = udf_find_metadata_inode_efe(sb, mdata->s_meta_file_loc, mdata->s_phys_partition_ref); if (IS_ERR(fe)) { /* mirror file entry */ udf_debug("Mirror metadata file location: block = %u part = %u\n", mdata->s_mirror_file_loc, mdata->s_phys_partition_ref); fe = udf_find_metadata_inode_efe(sb, mdata->s_mirror_file_loc, mdata->s_phys_partition_ref); if (IS_ERR(fe)) { udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n"); return PTR_ERR(fe); } mdata->s_mirror_fe = fe; } else mdata->s_metadata_fe = fe; /* * bitmap file entry * Note: * Load only if bitmap file location differs from 0xFFFFFFFF (DCN-5102) */ if (mdata->s_bitmap_file_loc != 0xFFFFFFFF) { addr.logicalBlockNum = mdata->s_bitmap_file_loc; addr.partitionReferenceNum = mdata->s_phys_partition_ref; udf_debug("Bitmap file location: block = %u part = %u\n", addr.logicalBlockNum, addr.partitionReferenceNum); fe = udf_iget_special(sb, &addr); if (IS_ERR(fe)) { if (sb_rdonly(sb)) udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n"); else { udf_err(sb, "bitmap inode efe not found and attempted read-write mount\n"); return PTR_ERR(fe); } } else mdata->s_bitmap_fe = fe; } udf_debug("udf_load_metadata_files Ok\n"); return 0; } int udf_compute_nr_groups(struct super_block *sb, u32 partition) { struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition]; return DIV_ROUND_UP(map->s_partition_len + (sizeof(struct spaceBitmapDesc) << 3), sb->s_blocksize * 8); } static struct udf_bitmap *udf_sb_alloc_bitmap(struct super_block *sb, u32 index) { struct udf_bitmap *bitmap; int nr_groups = udf_compute_nr_groups(sb, index); bitmap = kvzalloc(struct_size(bitmap, s_block_bitmap, nr_groups), GFP_KERNEL); if (!bitmap) return NULL; bitmap->s_nr_groups = nr_groups; return bitmap; } static int check_partition_desc(struct super_block *sb, struct partitionDesc *p, struct udf_part_map *map) { bool umap, utable, fmap, ftable; struct partitionHeaderDesc *phd; switch (le32_to_cpu(p->accessType)) { case PD_ACCESS_TYPE_READ_ONLY: case PD_ACCESS_TYPE_WRITE_ONCE: case PD_ACCESS_TYPE_NONE: goto force_ro; } /* No Partition Header Descriptor? */ if (strcmp(p->partitionContents.ident, PD_PARTITION_CONTENTS_NSR02) && strcmp(p->partitionContents.ident, PD_PARTITION_CONTENTS_NSR03)) goto force_ro; phd = (struct partitionHeaderDesc *)p->partitionContentsUse; utable = phd->unallocSpaceTable.extLength; umap = phd->unallocSpaceBitmap.extLength; ftable = phd->freedSpaceTable.extLength; fmap = phd->freedSpaceBitmap.extLength; /* No allocation info? */ if (!utable && !umap && !ftable && !fmap) goto force_ro; /* We don't support blocks that require erasing before overwrite */ if (ftable || fmap) goto force_ro; /* UDF 2.60: 2.3.3 - no mixing of tables & bitmaps, no VAT. */ if (utable && umap) goto force_ro; if (map->s_partition_type == UDF_VIRTUAL_MAP15 || map->s_partition_type == UDF_VIRTUAL_MAP20 || map->s_partition_type == UDF_METADATA_MAP25) goto force_ro; return 0; force_ro: if (!sb_rdonly(sb)) return -EACCES; UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); return 0; } static int udf_fill_partdesc_info(struct super_block *sb, struct partitionDesc *p, int p_index) { struct udf_part_map *map; struct udf_sb_info *sbi = UDF_SB(sb); struct partitionHeaderDesc *phd; u32 sum; int err; map = &sbi->s_partmaps[p_index]; map->s_partition_len = le32_to_cpu(p->partitionLength); /* blocks */ map->s_partition_root = le32_to_cpu(p->partitionStartingLocation); if (check_add_overflow(map->s_partition_root, map->s_partition_len, &sum)) { udf_err(sb, "Partition %d has invalid location %u + %u\n", p_index, map->s_partition_root, map->s_partition_len); return -EFSCORRUPTED; } if (p->accessType == cpu_to_le32(PD_ACCESS_TYPE_READ_ONLY)) map->s_partition_flags |= UDF_PART_FLAG_READ_ONLY; if (p->accessType == cpu_to_le32(PD_ACCESS_TYPE_WRITE_ONCE)) map->s_partition_flags |= UDF_PART_FLAG_WRITE_ONCE; if (p->accessType == cpu_to_le32(PD_ACCESS_TYPE_REWRITABLE)) map->s_partition_flags |= UDF_PART_FLAG_REWRITABLE; if (p->accessType == cpu_to_le32(PD_ACCESS_TYPE_OVERWRITABLE)) map->s_partition_flags |= UDF_PART_FLAG_OVERWRITABLE; udf_debug("Partition (%d type %x) starts at physical %u, block length %u\n", p_index, map->s_partition_type, map->s_partition_root, map->s_partition_len); err = check_partition_desc(sb, p, map); if (err) return err; /* * Skip loading allocation info it we cannot ever write to the fs. * This is a correctness thing as we may have decided to force ro mount * to avoid allocation info we don't support. */ if (UDF_QUERY_FLAG(sb, UDF_FLAG_RW_INCOMPAT)) return 0; phd = (struct partitionHeaderDesc *)p->partitionContentsUse; if (phd->unallocSpaceTable.extLength) { struct kernel_lb_addr loc = { .logicalBlockNum = le32_to_cpu( phd->unallocSpaceTable.extPosition), .partitionReferenceNum = p_index, }; struct inode *inode; inode = udf_iget_special(sb, &loc); if (IS_ERR(inode)) { udf_debug("cannot load unallocSpaceTable (part %d)\n", p_index); return PTR_ERR(inode); } map->s_uspace.s_table = inode; map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_TABLE; udf_debug("unallocSpaceTable (part %d) @ %lu\n", p_index, map->s_uspace.s_table->i_ino); } if (phd->unallocSpaceBitmap.extLength) { struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index); if (!bitmap) return -ENOMEM; map->s_uspace.s_bitmap = bitmap; bitmap->s_extPosition = le32_to_cpu( phd->unallocSpaceBitmap.extPosition); map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_BITMAP; /* Check whether math over bitmap won't overflow. */ if (check_add_overflow(map->s_partition_len, sizeof(struct spaceBitmapDesc) << 3, &sum)) { udf_err(sb, "Partition %d is too long (%u)\n", p_index, map->s_partition_len); return -EFSCORRUPTED; } udf_debug("unallocSpaceBitmap (part %d) @ %u\n", p_index, bitmap->s_extPosition); } return 0; } static void udf_find_vat_block(struct super_block *sb, int p_index, int type1_index, sector_t start_block) { struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map = &sbi->s_partmaps[p_index]; sector_t vat_block; struct kernel_lb_addr ino; struct inode *inode; /* * VAT file entry is in the last recorded block. Some broken disks have * it a few blocks before so try a bit harder... */ ino.partitionReferenceNum = type1_index; for (vat_block = start_block; vat_block >= map->s_partition_root && vat_block >= start_block - 3; vat_block--) { ino.logicalBlockNum = vat_block - map->s_partition_root; inode = udf_iget_special(sb, &ino); if (!IS_ERR(inode)) { sbi->s_vat_inode = inode; break; } } } static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) { struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map = &sbi->s_partmaps[p_index]; struct buffer_head *bh = NULL; struct udf_inode_info *vati; struct virtualAllocationTable20 *vat20; sector_t blocks = sb_bdev_nr_blocks(sb); udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block); if (!sbi->s_vat_inode && sbi->s_last_block != blocks - 1) { pr_notice("Failed to read VAT inode from the last recorded block (%lu), retrying with the last block of the device (%lu).\n", (unsigned long)sbi->s_last_block, (unsigned long)blocks - 1); udf_find_vat_block(sb, p_index, type1_index, blocks - 1); } if (!sbi->s_vat_inode) return -EIO; if (map->s_partition_type == UDF_VIRTUAL_MAP15) { map->s_type_specific.s_virtual.s_start_offset = 0; map->s_type_specific.s_virtual.s_num_entries = (sbi->s_vat_inode->i_size - 36) >> 2; } else if (map->s_partition_type == UDF_VIRTUAL_MAP20) { vati = UDF_I(sbi->s_vat_inode); if (vati->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { int err = 0; bh = udf_bread(sbi->s_vat_inode, 0, 0, &err); if (!bh) { if (!err) err = -EFSCORRUPTED; return err; } vat20 = (struct virtualAllocationTable20 *)bh->b_data; } else { vat20 = (struct virtualAllocationTable20 *) vati->i_data; } map->s_type_specific.s_virtual.s_start_offset = le16_to_cpu(vat20->lengthHeader); map->s_type_specific.s_virtual.s_num_entries = (sbi->s_vat_inode->i_size - map->s_type_specific.s_virtual. s_start_offset) >> 2; brelse(bh); } return 0; } /* * Load partition descriptor block * * Returns <0 on error, 0 on success, -EAGAIN is special - try next descriptor * sequence. */ static int udf_load_partdesc(struct super_block *sb, sector_t block) { struct buffer_head *bh; struct partitionDesc *p; struct udf_part_map *map; struct udf_sb_info *sbi = UDF_SB(sb); int i, type1_idx; uint16_t partitionNumber; uint16_t ident; int ret; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) return -EAGAIN; if (ident != TAG_IDENT_PD) { ret = 0; goto out_bh; } p = (struct partitionDesc *)bh->b_data; partitionNumber = le16_to_cpu(p->partitionNumber); /* First scan for TYPE1 and SPARABLE partitions */ for (i = 0; i < sbi->s_partitions; i++) { map = &sbi->s_partmaps[i]; udf_debug("Searching map: (%u == %u)\n", map->s_partition_num, partitionNumber); if (map->s_partition_num == partitionNumber && (map->s_partition_type == UDF_TYPE1_MAP15 || map->s_partition_type == UDF_SPARABLE_MAP15)) break; } if (i >= sbi->s_partitions) { udf_debug("Partition (%u) not found in partition map\n", partitionNumber); ret = 0; goto out_bh; } ret = udf_fill_partdesc_info(sb, p, i); if (ret < 0) goto out_bh; /* * Now rescan for VIRTUAL or METADATA partitions when SPARABLE and * PHYSICAL partitions are already set up */ type1_idx = i; map = NULL; /* supress 'maybe used uninitialized' warning */ for (i = 0; i < sbi->s_partitions; i++) { map = &sbi->s_partmaps[i]; if (map->s_partition_num == partitionNumber && (map->s_partition_type == UDF_VIRTUAL_MAP15 || map->s_partition_type == UDF_VIRTUAL_MAP20 || map->s_partition_type == UDF_METADATA_MAP25)) break; } if (i >= sbi->s_partitions) { ret = 0; goto out_bh; } ret = udf_fill_partdesc_info(sb, p, i); if (ret < 0) goto out_bh; if (map->s_partition_type == UDF_METADATA_MAP25) { ret = udf_load_metadata_files(sb, i, type1_idx); if (ret < 0) { udf_err(sb, "error loading MetaData partition map %d\n", i); goto out_bh; } } else { /* * If we have a partition with virtual map, we don't handle * writing to it (we overwrite blocks instead of relocating * them). */ if (!sb_rdonly(sb)) { ret = -EACCES; goto out_bh; } UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); ret = udf_load_vat(sb, i, type1_idx); if (ret < 0) goto out_bh; } ret = 0; out_bh: /* In case loading failed, we handle cleanup in udf_fill_super */ brelse(bh); return ret; } static int udf_load_sparable_map(struct super_block *sb, struct udf_part_map *map, struct sparablePartitionMap *spm) { uint32_t loc; uint16_t ident; struct sparingTable *st; struct udf_sparing_data *sdata = &map->s_type_specific.s_sparing; int i; struct buffer_head *bh; map->s_partition_type = UDF_SPARABLE_MAP15; sdata->s_packet_len = le16_to_cpu(spm->packetLength); if (!is_power_of_2(sdata->s_packet_len)) { udf_err(sb, "error loading logical volume descriptor: " "Invalid packet length %u\n", (unsigned)sdata->s_packet_len); return -EIO; } if (spm->numSparingTables > 4) { udf_err(sb, "error loading logical volume descriptor: " "Too many sparing tables (%d)\n", (int)spm->numSparingTables); return -EIO; } if (le32_to_cpu(spm->sizeSparingTable) > sb->s_blocksize) { udf_err(sb, "error loading logical volume descriptor: " "Too big sparing table size (%u)\n", le32_to_cpu(spm->sizeSparingTable)); return -EIO; } for (i = 0; i < spm->numSparingTables; i++) { loc = le32_to_cpu(spm->locSparingTable[i]); bh = udf_read_tagged(sb, loc, loc, &ident); if (!bh) continue; st = (struct sparingTable *)bh->b_data; if (ident != 0 || strncmp(st->sparingIdent.ident, UDF_ID_SPARING, strlen(UDF_ID_SPARING)) || sizeof(*st) + le16_to_cpu(st->reallocationTableLen) > sb->s_blocksize) { brelse(bh); continue; } sdata->s_spar_map[i] = bh; } map->s_partition_func = udf_get_pblock_spar15; return 0; } static int udf_load_logicalvol(struct super_block *sb, sector_t block, struct kernel_lb_addr *fileset) { struct logicalVolDesc *lvd; int i, offset; uint8_t type; struct udf_sb_info *sbi = UDF_SB(sb); struct genericPartitionMap *gpm; uint16_t ident; struct buffer_head *bh; unsigned int table_len; int ret; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) return -EAGAIN; BUG_ON(ident != TAG_IDENT_LVD); lvd = (struct logicalVolDesc *)bh->b_data; table_len = le32_to_cpu(lvd->mapTableLength); if (table_len > sb->s_blocksize - sizeof(*lvd)) { udf_err(sb, "error loading logical volume descriptor: " "Partition table too long (%u > %lu)\n", table_len, sb->s_blocksize - sizeof(*lvd)); ret = -EIO; goto out_bh; } ret = udf_verify_domain_identifier(sb, &lvd->domainIdent, "logical volume"); if (ret) goto out_bh; ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); if (ret) goto out_bh; for (i = 0, offset = 0; i < sbi->s_partitions && offset < table_len; i++, offset += gpm->partitionMapLength) { struct udf_part_map *map = &sbi->s_partmaps[i]; gpm = (struct genericPartitionMap *) &(lvd->partitionMaps[offset]); type = gpm->partitionMapType; if (type == 1) { struct genericPartitionMap1 *gpm1 = (struct genericPartitionMap1 *)gpm; map->s_partition_type = UDF_TYPE1_MAP15; map->s_volumeseqnum = le16_to_cpu(gpm1->volSeqNum); map->s_partition_num = le16_to_cpu(gpm1->partitionNum); map->s_partition_func = NULL; } else if (type == 2) { struct udfPartitionMap2 *upm2 = (struct udfPartitionMap2 *)gpm; if (!strncmp(upm2->partIdent.ident, UDF_ID_VIRTUAL, strlen(UDF_ID_VIRTUAL))) { u16 suf = le16_to_cpu(((__le16 *)upm2->partIdent. identSuffix)[0]); if (suf < 0x0200) { map->s_partition_type = UDF_VIRTUAL_MAP15; map->s_partition_func = udf_get_pblock_virt15; } else { map->s_partition_type = UDF_VIRTUAL_MAP20; map->s_partition_func = udf_get_pblock_virt20; } } else if (!strncmp(upm2->partIdent.ident, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { ret = udf_load_sparable_map(sb, map, (struct sparablePartitionMap *)gpm); if (ret < 0) goto out_bh; } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { struct udf_meta_data *mdata = &map->s_type_specific.s_metadata; struct metadataPartitionMap *mdm = (struct metadataPartitionMap *) &(lvd->partitionMaps[offset]); udf_debug("Parsing Logical vol part %d type %u id=%s\n", i, type, UDF_ID_METADATA); map->s_partition_type = UDF_METADATA_MAP25; map->s_partition_func = udf_get_pblock_meta25; mdata->s_meta_file_loc = le32_to_cpu(mdm->metadataFileLoc); mdata->s_mirror_file_loc = le32_to_cpu(mdm->metadataMirrorFileLoc); mdata->s_bitmap_file_loc = le32_to_cpu(mdm->metadataBitmapFileLoc); mdata->s_alloc_unit_size = le32_to_cpu(mdm->allocUnitSize); mdata->s_align_unit_size = le16_to_cpu(mdm->alignUnitSize); if (mdm->flags & 0x01) mdata->s_flags |= MF_DUPLICATE_MD; udf_debug("Metadata Ident suffix=0x%x\n", le16_to_cpu(*(__le16 *) mdm->partIdent.identSuffix)); udf_debug("Metadata part num=%u\n", le16_to_cpu(mdm->partitionNum)); udf_debug("Metadata part alloc unit size=%u\n", le32_to_cpu(mdm->allocUnitSize)); udf_debug("Metadata file loc=%u\n", le32_to_cpu(mdm->metadataFileLoc)); udf_debug("Mirror file loc=%u\n", le32_to_cpu(mdm->metadataMirrorFileLoc)); udf_debug("Bitmap file loc=%u\n", le32_to_cpu(mdm->metadataBitmapFileLoc)); udf_debug("Flags: %d %u\n", mdata->s_flags, mdm->flags); } else { udf_debug("Unknown ident: %s\n", upm2->partIdent.ident); continue; } map->s_volumeseqnum = le16_to_cpu(upm2->volSeqNum); map->s_partition_num = le16_to_cpu(upm2->partitionNum); } udf_debug("Partition (%d:%u) type %u on volume %u\n", i, map->s_partition_num, type, map->s_volumeseqnum); } if (fileset) { struct long_ad *la = (struct long_ad *)&(lvd->logicalVolContentsUse[0]); *fileset = lelb_to_cpu(la->extLocation); udf_debug("FileSet found in LogicalVolDesc at block=%u, partition=%u\n", fileset->logicalBlockNum, fileset->partitionReferenceNum); } if (lvd->integritySeqExt.extLength) udf_load_logicalvolint(sb, leea_to_cpu(lvd->integritySeqExt)); ret = 0; if (!sbi->s_lvid_bh) { /* We can't generate unique IDs without a valid LVID */ if (sb_rdonly(sb)) { UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); } else { udf_warn(sb, "Damaged or missing LVID, forcing " "readonly mount\n"); ret = -EACCES; } } out_bh: brelse(bh); return ret; } static bool udf_lvid_valid(struct super_block *sb, struct logicalVolIntegrityDesc *lvid) { u32 parts, impuselen; parts = le32_to_cpu(lvid->numOfPartitions); impuselen = le32_to_cpu(lvid->lengthOfImpUse); if (parts >= sb->s_blocksize || impuselen >= sb->s_blocksize || sizeof(struct logicalVolIntegrityDesc) + impuselen + 2 * parts * sizeof(u32) > sb->s_blocksize) return false; return true; } /* * Find the prevailing Logical Volume Integrity Descriptor. */ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ad loc) { struct buffer_head *bh, *final_bh; uint16_t ident; struct udf_sb_info *sbi = UDF_SB(sb); struct logicalVolIntegrityDesc *lvid; int indirections = 0; while (++indirections <= UDF_MAX_LVID_NESTING) { final_bh = NULL; while (loc.extLength > 0 && (bh = udf_read_tagged(sb, loc.extLocation, loc.extLocation, &ident))) { if (ident != TAG_IDENT_LVID) { brelse(bh); break; } brelse(final_bh); final_bh = bh; loc.extLength -= sb->s_blocksize; loc.extLocation++; } if (!final_bh) return; lvid = (struct logicalVolIntegrityDesc *)final_bh->b_data; if (udf_lvid_valid(sb, lvid)) { brelse(sbi->s_lvid_bh); sbi->s_lvid_bh = final_bh; } else { udf_warn(sb, "Corrupted LVID (parts=%u, impuselen=%u), " "ignoring.\n", le32_to_cpu(lvid->numOfPartitions), le32_to_cpu(lvid->lengthOfImpUse)); } if (lvid->nextIntegrityExt.extLength == 0) return; loc = leea_to_cpu(lvid->nextIntegrityExt); } udf_warn(sb, "Too many LVID indirections (max %u), ignoring.\n", UDF_MAX_LVID_NESTING); brelse(sbi->s_lvid_bh); sbi->s_lvid_bh = NULL; } /* * Step for reallocation of table of partition descriptor sequence numbers. * Must be power of 2. */ #define PART_DESC_ALLOC_STEP 32 struct part_desc_seq_scan_data { struct udf_vds_record rec; u32 partnum; }; struct desc_seq_scan_data { struct udf_vds_record vds[VDS_POS_LENGTH]; unsigned int size_part_descs; unsigned int num_part_descs; struct part_desc_seq_scan_data *part_descs_loc; }; static struct udf_vds_record *handle_partition_descriptor( struct buffer_head *bh, struct desc_seq_scan_data *data) { struct partitionDesc *desc = (struct partitionDesc *)bh->b_data; int partnum; int i; partnum = le16_to_cpu(desc->partitionNumber); for (i = 0; i < data->num_part_descs; i++) if (partnum == data->part_descs_loc[i].partnum) return &(data->part_descs_loc[i].rec); if (data->num_part_descs >= data->size_part_descs) { struct part_desc_seq_scan_data *new_loc; unsigned int new_size = ALIGN(partnum, PART_DESC_ALLOC_STEP); new_loc = kcalloc(new_size, sizeof(*new_loc), GFP_KERNEL); if (!new_loc) return ERR_PTR(-ENOMEM); memcpy(new_loc, data->part_descs_loc, data->size_part_descs * sizeof(*new_loc)); kfree(data->part_descs_loc); data->part_descs_loc = new_loc; data->size_part_descs = new_size; } return &(data->part_descs_loc[data->num_part_descs++].rec); } static struct udf_vds_record *get_volume_descriptor_record(uint16_t ident, struct buffer_head *bh, struct desc_seq_scan_data *data) { switch (ident) { case TAG_IDENT_PVD: /* ISO 13346 3/10.1 */ return &(data->vds[VDS_POS_PRIMARY_VOL_DESC]); case TAG_IDENT_IUVD: /* ISO 13346 3/10.4 */ return &(data->vds[VDS_POS_IMP_USE_VOL_DESC]); case TAG_IDENT_LVD: /* ISO 13346 3/10.6 */ return &(data->vds[VDS_POS_LOGICAL_VOL_DESC]); case TAG_IDENT_USD: /* ISO 13346 3/10.8 */ return &(data->vds[VDS_POS_UNALLOC_SPACE_DESC]); case TAG_IDENT_PD: /* ISO 13346 3/10.5 */ return handle_partition_descriptor(bh, data); } return NULL; } /* * Process a main/reserve volume descriptor sequence. * @block First block of first extent of the sequence. * @lastblock Lastblock of first extent of the sequence. * @fileset There we store extent containing root fileset * * Returns <0 on error, 0 on success. -EAGAIN is special - try next descriptor * sequence */ static noinline int udf_process_sequence( struct super_block *sb, sector_t block, sector_t lastblock, struct kernel_lb_addr *fileset) { struct buffer_head *bh = NULL; struct udf_vds_record *curr; struct generic_desc *gd; struct volDescPtr *vdp; bool done = false; uint32_t vdsn; uint16_t ident; int ret; unsigned int indirections = 0; struct desc_seq_scan_data data; unsigned int i; memset(data.vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH); data.size_part_descs = PART_DESC_ALLOC_STEP; data.num_part_descs = 0; data.part_descs_loc = kcalloc(data.size_part_descs, sizeof(*data.part_descs_loc), GFP_KERNEL); if (!data.part_descs_loc) return -ENOMEM; /* * Read the main descriptor sequence and find which descriptors * are in it. */ for (; (!done && block <= lastblock); block++) { bh = udf_read_tagged(sb, block, block, &ident); if (!bh) break; /* Process each descriptor (ISO 13346 3/8.3-8.4) */ gd = (struct generic_desc *)bh->b_data; vdsn = le32_to_cpu(gd->volDescSeqNum); switch (ident) { case TAG_IDENT_VDP: /* ISO 13346 3/10.3 */ if (++indirections > UDF_MAX_TD_NESTING) { udf_err(sb, "too many Volume Descriptor " "Pointers (max %u supported)\n", UDF_MAX_TD_NESTING); brelse(bh); ret = -EIO; goto out; } vdp = (struct volDescPtr *)bh->b_data; block = le32_to_cpu(vdp->nextVolDescSeqExt.extLocation); lastblock = le32_to_cpu( vdp->nextVolDescSeqExt.extLength) >> sb->s_blocksize_bits; lastblock += block - 1; /* For loop is going to increment 'block' again */ block--; break; case TAG_IDENT_PVD: /* ISO 13346 3/10.1 */ case TAG_IDENT_IUVD: /* ISO 13346 3/10.4 */ case TAG_IDENT_LVD: /* ISO 13346 3/10.6 */ case TAG_IDENT_USD: /* ISO 13346 3/10.8 */ case TAG_IDENT_PD: /* ISO 13346 3/10.5 */ curr = get_volume_descriptor_record(ident, bh, &data); if (IS_ERR(curr)) { brelse(bh); ret = PTR_ERR(curr); goto out; } /* Descriptor we don't care about? */ if (!curr) break; if (vdsn >= curr->volDescSeqNum) { curr->volDescSeqNum = vdsn; curr->block = block; } break; case TAG_IDENT_TD: /* ISO 13346 3/10.9 */ done = true; break; } brelse(bh); } /* * Now read interesting descriptors again and process them * in a suitable order */ if (!data.vds[VDS_POS_PRIMARY_VOL_DESC].block) { udf_err(sb, "Primary Volume Descriptor not found!\n"); ret = -EAGAIN; goto out; } ret = udf_load_pvoldesc(sb, data.vds[VDS_POS_PRIMARY_VOL_DESC].block); if (ret < 0) goto out; if (data.vds[VDS_POS_LOGICAL_VOL_DESC].block) { ret = udf_load_logicalvol(sb, data.vds[VDS_POS_LOGICAL_VOL_DESC].block, fileset); if (ret < 0) goto out; } /* Now handle prevailing Partition Descriptors */ for (i = 0; i < data.num_part_descs; i++) { ret = udf_load_partdesc(sb, data.part_descs_loc[i].rec.block); if (ret < 0) goto out; } ret = 0; out: kfree(data.part_descs_loc); return ret; } /* * Load Volume Descriptor Sequence described by anchor in bh * * Returns <0 on error, 0 on success */ static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh, struct kernel_lb_addr *fileset) { struct anchorVolDescPtr *anchor; sector_t main_s, main_e, reserve_s, reserve_e; int ret; anchor = (struct anchorVolDescPtr *)bh->b_data; /* Locate the main sequence */ main_s = le32_to_cpu(anchor->mainVolDescSeqExt.extLocation); main_e = le32_to_cpu(anchor->mainVolDescSeqExt.extLength); main_e = main_e >> sb->s_blocksize_bits; main_e += main_s - 1; /* Locate the reserve sequence */ reserve_s = le32_to_cpu(anchor->reserveVolDescSeqExt.extLocation); reserve_e = le32_to_cpu(anchor->reserveVolDescSeqExt.extLength); reserve_e = reserve_e >> sb->s_blocksize_bits; reserve_e += reserve_s - 1; /* Process the main & reserve sequences */ /* responsible for finding the PartitionDesc(s) */ ret = udf_process_sequence(sb, main_s, main_e, fileset); if (ret != -EAGAIN) return ret; udf_sb_free_partitions(sb); ret = udf_process_sequence(sb, reserve_s, reserve_e, fileset); if (ret < 0) { udf_sb_free_partitions(sb); /* No sequence was OK, return -EIO */ if (ret == -EAGAIN) ret = -EIO; } return ret; } /* * Check whether there is an anchor block in the given block and * load Volume Descriptor Sequence if so. * * Returns <0 on error, 0 on success, -EAGAIN is special - try next anchor * block */ static int udf_check_anchor_block(struct super_block *sb, sector_t block, struct kernel_lb_addr *fileset) { struct buffer_head *bh; uint16_t ident; int ret; bh = udf_read_tagged(sb, block, block, &ident); if (!bh) return -EAGAIN; if (ident != TAG_IDENT_AVDP) { brelse(bh); return -EAGAIN; } ret = udf_load_sequence(sb, bh, fileset); brelse(bh); return ret; } /* * Search for an anchor volume descriptor pointer. * * Returns < 0 on error, 0 on success. -EAGAIN is special - try next set * of anchors. */ static int udf_scan_anchors(struct super_block *sb, udf_pblk_t *lastblock, struct kernel_lb_addr *fileset) { udf_pblk_t last[6]; int i; struct udf_sb_info *sbi = UDF_SB(sb); int last_count = 0; int ret; /* First try user provided anchor */ if (sbi->s_anchor) { ret = udf_check_anchor_block(sb, sbi->s_anchor, fileset); if (ret != -EAGAIN) return ret; } /* * according to spec, anchor is in either: * block 256 * lastblock-256 * lastblock * however, if the disc isn't closed, it could be 512. */ ret = udf_check_anchor_block(sb, sbi->s_session + 256, fileset); if (ret != -EAGAIN) return ret; /* * The trouble is which block is the last one. Drives often misreport * this so we try various possibilities. */ last[last_count++] = *lastblock; if (*lastblock >= 1) last[last_count++] = *lastblock - 1; last[last_count++] = *lastblock + 1; if (*lastblock >= 2) last[last_count++] = *lastblock - 2; if (*lastblock >= 150) last[last_count++] = *lastblock - 150; if (*lastblock >= 152) last[last_count++] = *lastblock - 152; for (i = 0; i < last_count; i++) { if (last[i] >= sb_bdev_nr_blocks(sb)) continue; ret = udf_check_anchor_block(sb, last[i], fileset); if (ret != -EAGAIN) { if (!ret) *lastblock = last[i]; return ret; } if (last[i] < 256) continue; ret = udf_check_anchor_block(sb, last[i] - 256, fileset); if (ret != -EAGAIN) { if (!ret) *lastblock = last[i]; return ret; } } /* Finally try block 512 in case media is open */ return udf_check_anchor_block(sb, sbi->s_session + 512, fileset); } /* * Check Volume Structure Descriptor, find Anchor block and load Volume * Descriptor Sequence. * * Returns < 0 on error, 0 on success. -EAGAIN is special meaning anchor * block was not found. */ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, int silent, struct kernel_lb_addr *fileset) { struct udf_sb_info *sbi = UDF_SB(sb); int nsr = 0; int ret; if (!sb_set_blocksize(sb, uopt->blocksize)) { if (!silent) udf_warn(sb, "Bad block size\n"); return -EINVAL; } sbi->s_last_block = uopt->lastblock; if (!UDF_QUERY_FLAG(sb, UDF_FLAG_NOVRS)) { /* Check that it is NSR02 compliant */ nsr = udf_check_vsd(sb); if (!nsr) { if (!silent) udf_warn(sb, "No VRS found\n"); return -EINVAL; } if (nsr == -1) udf_debug("Failed to read sector at offset %d. " "Assuming open disc. Skipping validity " "check\n", VSD_FIRST_SECTOR_OFFSET); if (!sbi->s_last_block) sbi->s_last_block = udf_get_last_block(sb); } else { udf_debug("Validity check skipped because of novrs option\n"); } /* Look for anchor block and load Volume Descriptor Sequence */ sbi->s_anchor = uopt->anchor; ret = udf_scan_anchors(sb, &sbi->s_last_block, fileset); if (ret < 0) { if (!silent && ret == -EAGAIN) udf_warn(sb, "No anchor found\n"); return ret; } return 0; } static void udf_finalize_lvid(struct logicalVolIntegrityDesc *lvid) { struct timespec64 ts; ktime_get_real_ts64(&ts); udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); lvid->descTag.descCRC = cpu_to_le16( crc_itu_t(0, (char *)lvid + sizeof(struct tag), le16_to_cpu(lvid->descTag.descCRCLength))); lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); } static void udf_open_lvid(struct super_block *sb) { struct udf_sb_info *sbi = UDF_SB(sb); struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; if (!bh) return; lvid = (struct logicalVolIntegrityDesc *)bh->b_data; lvidiu = udf_sb_lvidiu(sb); if (!lvidiu) return; mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; if (le32_to_cpu(lvid->integrityType) == LVID_INTEGRITY_TYPE_CLOSE) lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN); else UDF_SET_FLAG(sb, UDF_FLAG_INCONSISTENT); udf_finalize_lvid(lvid); mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; mutex_unlock(&sbi->s_alloc_mutex); /* Make opening of filesystem visible on the media immediately */ sync_dirty_buffer(bh); } static void udf_close_lvid(struct super_block *sb) { struct udf_sb_info *sbi = UDF_SB(sb); struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; if (!bh) return; lvid = (struct logicalVolIntegrityDesc *)bh->b_data; lvidiu = udf_sb_lvidiu(sb); if (!lvidiu) return; mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; if (UDF_MAX_WRITE_VERSION > le16_to_cpu(lvidiu->maxUDFWriteRev)) lvidiu->maxUDFWriteRev = cpu_to_le16(UDF_MAX_WRITE_VERSION); if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFReadRev)) lvidiu->minUDFReadRev = cpu_to_le16(sbi->s_udfrev); if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFWriteRev)) lvidiu->minUDFWriteRev = cpu_to_le16(sbi->s_udfrev); if (!UDF_QUERY_FLAG(sb, UDF_FLAG_INCONSISTENT)) lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_CLOSE); /* * We set buffer uptodate unconditionally here to avoid spurious * warnings from mark_buffer_dirty() when previous EIO has marked * the buffer as !uptodate */ set_buffer_uptodate(bh); udf_finalize_lvid(lvid); mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; mutex_unlock(&sbi->s_alloc_mutex); /* Make closing of filesystem visible on the media immediately */ sync_dirty_buffer(bh); } u64 lvid_get_unique_id(struct super_block *sb) { struct buffer_head *bh; struct udf_sb_info *sbi = UDF_SB(sb); struct logicalVolIntegrityDesc *lvid; struct logicalVolHeaderDesc *lvhd; u64 uniqueID; u64 ret; bh = sbi->s_lvid_bh; if (!bh) return 0; lvid = (struct logicalVolIntegrityDesc *)bh->b_data; lvhd = (struct logicalVolHeaderDesc *)lvid->logicalVolContentsUse; mutex_lock(&sbi->s_alloc_mutex); ret = uniqueID = le64_to_cpu(lvhd->uniqueID); if (!(++uniqueID & 0xFFFFFFFF)) uniqueID += 16; lvhd->uniqueID = cpu_to_le64(uniqueID); udf_updated_lvid(sb); mutex_unlock(&sbi->s_alloc_mutex); return ret; } static int udf_fill_super(struct super_block *sb, struct fs_context *fc) { int ret = -EINVAL; struct inode *inode = NULL; struct udf_options *uopt = fc->fs_private; struct kernel_lb_addr rootdir, fileset; struct udf_sb_info *sbi; bool lvid_open = false; int silent = fc->sb_flags & SB_SILENT; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; mutex_init(&sbi->s_alloc_mutex); fileset.logicalBlockNum = 0xFFFFFFFF; fileset.partitionReferenceNum = 0xFFFF; sbi->s_flags = uopt->flags; sbi->s_uid = uopt->uid; sbi->s_gid = uopt->gid; sbi->s_umask = uopt->umask; sbi->s_fmode = uopt->fmode; sbi->s_dmode = uopt->dmode; sbi->s_nls_map = uopt->nls_map; uopt->nls_map = NULL; rwlock_init(&sbi->s_cred_lock); if (uopt->session == 0xFFFFFFFF) sbi->s_session = udf_get_last_session(sb); else sbi->s_session = uopt->session; udf_debug("Multi-session=%d\n", sbi->s_session); /* Fill in the rest of the superblock */ sb->s_op = &udf_sb_ops; sb->s_export_op = &udf_export_ops; sb->s_magic = UDF_SUPER_MAGIC; sb->s_time_gran = 1000; if (uopt->flags & (1 << UDF_FLAG_BLOCKSIZE_SET)) { ret = udf_load_vrs(sb, uopt, silent, &fileset); } else { uopt->blocksize = bdev_logical_block_size(sb->s_bdev); while (uopt->blocksize <= 4096) { ret = udf_load_vrs(sb, uopt, silent, &fileset); if (ret < 0) { if (!silent && ret != -EACCES) { pr_notice("Scanning with blocksize %u failed\n", uopt->blocksize); } brelse(sbi->s_lvid_bh); sbi->s_lvid_bh = NULL; /* * EACCES is special - we want to propagate to * upper layers that we cannot handle RW mount. */ if (ret == -EACCES) break; } else break; uopt->blocksize <<= 1; } } if (ret < 0) { if (ret == -EAGAIN) { udf_warn(sb, "No partition found (1)\n"); ret = -EINVAL; } goto error_out; } udf_debug("Lastblock=%u\n", sbi->s_last_block); if (sbi->s_lvid_bh) { struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); uint16_t minUDFReadRev; uint16_t minUDFWriteRev; if (!lvidiu) { ret = -EINVAL; goto error_out; } minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev); minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev); if (minUDFReadRev > UDF_MAX_READ_VERSION) { udf_err(sb, "minUDFReadRev=%x (max is %x)\n", minUDFReadRev, UDF_MAX_READ_VERSION); ret = -EINVAL; goto error_out; } else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION) { if (!sb_rdonly(sb)) { ret = -EACCES; goto error_out; } UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); } sbi->s_udfrev = minUDFWriteRev; if (minUDFReadRev >= UDF_VERS_USE_EXTENDED_FE) UDF_SET_FLAG(sb, UDF_FLAG_USE_EXTENDED_FE); if (minUDFReadRev >= UDF_VERS_USE_STREAMS) UDF_SET_FLAG(sb, UDF_FLAG_USE_STREAMS); } if (!sbi->s_partitions) { udf_warn(sb, "No partition found (2)\n"); ret = -EINVAL; goto error_out; } if (sbi->s_partmaps[sbi->s_partition].s_partition_flags & UDF_PART_FLAG_READ_ONLY) { if (!sb_rdonly(sb)) { ret = -EACCES; goto error_out; } UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); } ret = udf_find_fileset(sb, &fileset, &rootdir); if (ret < 0) { udf_warn(sb, "No fileset found\n"); goto error_out; } if (!silent) { struct timestamp ts; udf_time_to_disk_stamp(&ts, sbi->s_record_time); udf_info("Mounting volume '%s', timestamp %04u/%02u/%02u %02u:%02u (%x)\n", sbi->s_volume_ident, le16_to_cpu(ts.year), ts.month, ts.day, ts.hour, ts.minute, le16_to_cpu(ts.typeAndTimezone)); } if (!sb_rdonly(sb)) { udf_open_lvid(sb); lvid_open = true; } /* Assign the root inode */ /* assign inodes by physical block number */ /* perhaps it's not extensible enough, but for now ... */ inode = udf_iget(sb, &rootdir); if (IS_ERR(inode)) { udf_err(sb, "Error in udf_iget, block=%u, partition=%u\n", rootdir.logicalBlockNum, rootdir.partitionReferenceNum); ret = PTR_ERR(inode); goto error_out; } /* Allocate a dentry for the root inode */ sb->s_root = d_make_root(inode); if (!sb->s_root) { udf_err(sb, "Couldn't allocate root dentry\n"); ret = -ENOMEM; goto error_out; } sb->s_maxbytes = UDF_MAX_FILESIZE; sb->s_max_links = UDF_MAX_LINKS; return 0; error_out: iput(sbi->s_vat_inode); unload_nls(uopt->nls_map); if (lvid_open) udf_close_lvid(sb); brelse(sbi->s_lvid_bh); udf_sb_free_partitions(sb); kfree(sbi); sb->s_fs_info = NULL; return ret; } void _udf_err(struct super_block *sb, const char *function, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_err("error (device %s): %s: %pV", sb->s_id, function, &vaf); va_end(args); } void _udf_warn(struct super_block *sb, const char *function, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_warn("warning (device %s): %s: %pV", sb->s_id, function, &vaf); va_end(args); } static void udf_put_super(struct super_block *sb) { struct udf_sb_info *sbi; sbi = UDF_SB(sb); iput(sbi->s_vat_inode); unload_nls(sbi->s_nls_map); if (!sb_rdonly(sb)) udf_close_lvid(sb); brelse(sbi->s_lvid_bh); udf_sb_free_partitions(sb); mutex_destroy(&sbi->s_alloc_mutex); kfree(sb->s_fs_info); sb->s_fs_info = NULL; } static int udf_sync_fs(struct super_block *sb, int wait) { struct udf_sb_info *sbi = UDF_SB(sb); mutex_lock(&sbi->s_alloc_mutex); if (sbi->s_lvid_dirty) { struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; lvid = (struct logicalVolIntegrityDesc *)bh->b_data; udf_finalize_lvid(lvid); /* * Blockdevice will be synced later so we don't have to submit * the buffer for IO */ mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; } mutex_unlock(&sbi->s_alloc_mutex); return 0; } static int udf_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct udf_sb_info *sbi = UDF_SB(sb); struct logicalVolIntegrityDescImpUse *lvidiu; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); lvidiu = udf_sb_lvidiu(sb); buf->f_type = UDF_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = sbi->s_partmaps[sbi->s_partition].s_partition_len; buf->f_bfree = udf_count_free(sb); buf->f_bavail = buf->f_bfree; /* * Let's pretend each free block is also a free 'inode' since UDF does * not have separate preallocated table of inodes. */ buf->f_files = (lvidiu != NULL ? (le32_to_cpu(lvidiu->numFiles) + le32_to_cpu(lvidiu->numDirs)) : 0) + buf->f_bfree; buf->f_ffree = buf->f_bfree; buf->f_namelen = UDF_NAME_LEN; buf->f_fsid = u64_to_fsid(id); return 0; } static unsigned int udf_count_free_bitmap(struct super_block *sb, struct udf_bitmap *bitmap) { struct buffer_head *bh = NULL; unsigned int accum = 0; int index; udf_pblk_t block = 0, newblock; struct kernel_lb_addr loc; uint32_t bytes; uint8_t *ptr; uint16_t ident; struct spaceBitmapDesc *bm; loc.logicalBlockNum = bitmap->s_extPosition; loc.partitionReferenceNum = UDF_SB(sb)->s_partition; bh = udf_read_ptagged(sb, &loc, 0, &ident); if (!bh) { udf_err(sb, "udf_count_free failed\n"); goto out; } else if (ident != TAG_IDENT_SBD) { brelse(bh); udf_err(sb, "udf_count_free failed\n"); goto out; } bm = (struct spaceBitmapDesc *)bh->b_data; bytes = le32_to_cpu(bm->numOfBytes); index = sizeof(struct spaceBitmapDesc); /* offset in first block only */ ptr = (uint8_t *)bh->b_data; while (bytes > 0) { u32 cur_bytes = min_t(u32, bytes, sb->s_blocksize - index); accum += bitmap_weight((const unsigned long *)(ptr + index), cur_bytes * 8); bytes -= cur_bytes; if (bytes) { brelse(bh); newblock = udf_get_lb_pblock(sb, &loc, ++block); bh = sb_bread(sb, newblock); if (!bh) { udf_debug("read failed\n"); goto out; } index = 0; ptr = (uint8_t *)bh->b_data; } } brelse(bh); out: return accum; } static unsigned int udf_count_free_table(struct super_block *sb, struct inode *table) { unsigned int accum = 0; uint32_t elen; struct kernel_lb_addr eloc; struct extent_position epos; int8_t etype; mutex_lock(&UDF_SB(sb)->s_alloc_mutex); epos.block = UDF_I(table)->i_location; epos.offset = sizeof(struct unallocSpaceEntry); epos.bh = NULL; while (udf_next_aext(table, &epos, &eloc, &elen, &etype, 1) > 0) accum += (elen >> table->i_sb->s_blocksize_bits); brelse(epos.bh); mutex_unlock(&UDF_SB(sb)->s_alloc_mutex); return accum; } static unsigned int udf_count_free(struct super_block *sb) { unsigned int accum = 0; struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map; unsigned int part = sbi->s_partition; int ptype = sbi->s_partmaps[part].s_partition_type; if (ptype == UDF_METADATA_MAP25) { part = sbi->s_partmaps[part].s_type_specific.s_metadata. s_phys_partition_ref; } else if (ptype == UDF_VIRTUAL_MAP15 || ptype == UDF_VIRTUAL_MAP20) { /* * Filesystems with VAT are append-only and we cannot write to * them. Let's just report 0 here. */ return 0; } if (sbi->s_lvid_bh) { struct logicalVolIntegrityDesc *lvid = (struct logicalVolIntegrityDesc *) sbi->s_lvid_bh->b_data; if (le32_to_cpu(lvid->numOfPartitions) > part) { accum = le32_to_cpu( lvid->freeSpaceTable[part]); if (accum == 0xFFFFFFFF) accum = 0; } } if (accum) return accum; map = &sbi->s_partmaps[part]; if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) { accum += udf_count_free_bitmap(sb, map->s_uspace.s_bitmap); } if (accum) return accum; if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE) { accum += udf_count_free_table(sb, map->s_uspace.s_table); } return accum; } MODULE_AUTHOR("Ben Fennema"); MODULE_DESCRIPTION("Universal Disk Format Filesystem"); MODULE_LICENSE("GPL"); module_init(init_udf_fs) module_exit(exit_udf_fs) |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" #define DEVLINK_PORT_FN_CAPS_VALID_MASK \ (_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1) static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, DEVLINK_PORT_FN_STATE_ACTIVE), [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), [DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] = { .type = NLA_U32 }, }; #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ WARN_ON_ONCE((devlink_port)->registered) struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, unsigned int port_index) { return xa_load(&devlink->ports, port_index); } struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_PORT_INDEX]) { u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (!devlink_port) return ERR_PTR(-ENODEV); return devlink_port; } return ERR_PTR(-EINVAL); } struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_port_get_from_attrs(devlink, info->attrs); } static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps, u32 cap, bool is_enable) { caps->selector |= cap; if (is_enable) caps->value |= cap; } static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_roce_get) return 0; err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable); return 0; } static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_migratable_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_migratable_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable); return 0; } static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_ipsec_crypto_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable); return 0; } static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_ipsec_packet_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable); return 0; } static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { struct nla_bitfield32 caps = {}; int err; err = devlink_port_fn_roce_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack); if (err) return err; if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, caps.selector); if (err) return err; *msg_updated = true; return 0; } static int devlink_port_fn_max_io_eqs_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { u32 max_io_eqs; int err; if (!port->ops->port_fn_max_io_eqs_get) return 0; err = port->ops->port_fn_max_io_eqs_get(port, &max_io_eqs, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } err = nla_put_u32(msg, DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, max_io_eqs); if (err) return err; *msg_updated = true; return 0; } int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) { if (devlink_nl_put_handle(msg, devlink_port->devlink)) return -EMSGSIZE; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) return -EMSGSIZE; return 0; } size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ } static int devlink_nl_port_attrs_put(struct sk_buff *msg, struct devlink_port *devlink_port) { struct devlink_port_attrs *attrs = &devlink_port->attrs; if (!devlink_port->attrs_set) return 0; if (attrs->lanes) { if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes)) return -EMSGSIZE; } if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable)) return -EMSGSIZE; if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) return -EMSGSIZE; switch (devlink_port->attrs.flavour) { case DEVLINK_PORT_FLAVOUR_PCI_PF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_pf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_VF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_vf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_SF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_sf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_sf.pf) || nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, attrs->pci_sf.sf)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->phys.port_number)) return -EMSGSIZE; if (!attrs->split) return 0; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->phys.port_number)) return -EMSGSIZE; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, attrs->phys.split_subport_number)) return -EMSGSIZE; break; default: break; } return 0; } static int devlink_port_fn_hw_addr_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { u8 hw_addr[MAX_ADDR_LEN]; int hw_addr_len; int err; if (!port->ops->port_fn_hw_addr_get) return 0; err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); if (err) return err; *msg_updated = true; return 0; } static bool devlink_port_fn_state_valid(enum devlink_port_fn_state state) { return state == DEVLINK_PORT_FN_STATE_INACTIVE || state == DEVLINK_PORT_FN_STATE_ACTIVE; } static bool devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) { return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; } static int devlink_port_fn_state_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { enum devlink_port_fn_opstate opstate; enum devlink_port_fn_state state; int err; if (!port->ops->port_fn_state_get) return 0; err = port->ops->port_fn_state_get(port, &state, &opstate, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } if (!devlink_port_fn_state_valid(state)) { WARN_ON_ONCE(1); NL_SET_ERR_MSG(extack, "Invalid state read from driver"); return -EINVAL; } if (!devlink_port_fn_opstate_valid(opstate)) { WARN_ON_ONCE(1); NL_SET_ERR_MSG(extack, "Invalid operational state read from driver"); return -EINVAL; } if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) return -EMSGSIZE; *msg_updated = true; return 0; } static int devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_migratable_set(devlink_port, enable, extack); } static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_roce_set(devlink_port, enable, extack); } static int devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack); } static int devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack); } static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nla_bitfield32 caps; u32 caps_value; int err; caps = nla_get_bitfield32(attr); caps_value = caps.value & caps.selector; if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) { err = devlink_port_fn_roce_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_ROCE, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { err = devlink_port_fn_mig_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_MIGRATABLE, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_IPSEC_PACKET, extack); if (err) return err; } return 0; } static int devlink_port_fn_max_io_eqs_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) { u32 max_io_eqs; max_io_eqs = nla_get_u32(attr); return devlink_port->ops->port_fn_max_io_eqs_set(devlink_port, max_io_eqs, extack); } static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { struct nlattr *function_attr; bool msg_updated = false; int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_max_io_eqs_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_rel_devlink_handle_put(msg, port->devlink, port->rel_index, DEVLINK_PORT_FN_ATTR_DEVLINK, &msg_updated); out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); return err; } static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink_port *devlink_port, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct devlink *devlink = devlink_port->devlink; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { if (devlink_port->type_eth.netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, devlink_port->type_eth.ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, devlink_port->type_eth.ifname))) goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { struct ib_device *ibdev = devlink_port->type_ib.ibdev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, ibdev->name)) goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) goto nla_put_failure; if (devlink_port->linecard && nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, devlink_linecard_index(devlink_port->linecard))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { struct devlink *devlink = devlink_port->devlink; struct devlink_obj_desc desc; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } devlink_nl_obj_desc_init(&desc, devlink); devlink_nl_obj_desc_port_set(&desc, devlink_port); devlink_nl_notify_send_desc(devlink, msg, &desc); } static void devlink_ports_notify(struct devlink *devlink, enum devlink_command cmd) { struct devlink_port *devlink_port; unsigned long port_index; xa_for_each(&devlink->ports, port_index, devlink_port) devlink_port_notify(devlink_port, cmd); } void devlink_ports_notify_register(struct devlink *devlink) { devlink_ports_notify(devlink, DEVLINK_CMD_PORT_NEW); } void devlink_ports_notify_unregister(struct devlink *devlink) { devlink_ports_notify(devlink, DEVLINK_CMD_PORT_DEL); } int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_port *devlink_port; unsigned long port_index; int err = 0; xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) { err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); if (err) { state->idx = port_index; break; } } return err; } int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one); } static int devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type port_type) { int err; if (!devlink_port->ops->port_type_set) return -EOPNOTSUPP; if (port_type == devlink_port->type) return 0; err = devlink_port->ops->port_type_set(devlink_port, port_type); if (err) return err; devlink_port->desired_type = port_type; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } static int devlink_port_function_hw_addr_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { const u8 *hw_addr; int hw_addr_len; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); if (hw_addr_len > MAX_ADDR_LEN) { NL_SET_ERR_MSG(extack, "Port function hardware address too long"); return -EINVAL; } if (port->type == DEVLINK_PORT_TYPE_ETH) { if (hw_addr_len != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Address must be 6 bytes for Ethernet device"); return -EINVAL; } if (!is_unicast_ether_addr(hw_addr)) { NL_SET_ERR_MSG(extack, "Non-unicast hardware address unsupported"); return -EINVAL; } } return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len, extack); } static int devlink_port_fn_state_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { enum devlink_port_fn_state state; state = nla_get_u8(attr); return port->ops->port_fn_state_set(port, state, extack); } static int devlink_port_function_validate(struct devlink_port *devlink_port, struct nlattr **tb, struct netlink_ext_ack *extack) { const struct devlink_port_ops *ops = devlink_port->ops; struct nlattr *attr; if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] && !ops->port_fn_hw_addr_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR], "Port doesn't support function attributes"); return -EOPNOTSUPP; } if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE], "Function does not support state setting"); return -EOPNOTSUPP; } attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; if (attr) { struct nla_bitfield32 caps; caps = nla_get_bitfield32(attr); if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE && !ops->port_fn_roce_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support RoCE function attribute"); return -EOPNOTSUPP; } if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { if (!ops->port_fn_migratable_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support migratable function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "migratable function attribute supported for VFs only"); return -EOPNOTSUPP; } } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { if (!ops->port_fn_ipsec_crypto_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support ipsec_crypto function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "ipsec_crypto function attribute supported for VFs only"); return -EOPNOTSUPP; } } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { if (!ops->port_fn_ipsec_packet_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support ipsec_packet function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "ipsec_packet function attribute supported for VFs only"); return -EOPNOTSUPP; } } } if (tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] && !ops->port_fn_max_io_eqs_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS], "Function does not support max_io_eqs setting"); return -EOPNOTSUPP; } return 0; } static int devlink_port_function_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1]; int err; err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr, devlink_function_nl_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Fail to parse port function attributes"); return err; } err = devlink_port_function_validate(port, tb, extack); if (err) return err; attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; if (attr) { err = devlink_port_function_hw_addr_set(port, attr, extack); if (err) return err; } attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; if (attr) { err = devlink_port_fn_caps_set(port, attr, extack); if (err) return err; } attr = tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS]; if (attr) { err = devlink_port_fn_max_io_eqs_set(port, attr, extack); if (err) return err; } /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. */ attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; if (attr) err = devlink_port_fn_state_set(port, attr, extack); if (!err) devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; int err; if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { enum devlink_port_type port_type; port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); err = devlink_port_type_set(devlink_port, port_type); if (err) return err; } if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) { struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION]; struct netlink_ext_ack *extack = info->extack; err = devlink_port_function_set(devlink_port, attr, extack); if (err) return err; } return 0; } int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; u32 count; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT)) return -EINVAL; if (!devlink_port->ops->port_split) return -EOPNOTSUPP; count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); if (!devlink_port->attrs.splittable) { /* Split ports cannot be split. */ if (devlink_port->attrs.split) NL_SET_ERR_MSG(info->extack, "Port cannot be split further"); else NL_SET_ERR_MSG(info->extack, "Port cannot be split"); return -EINVAL; } if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) { NL_SET_ERR_MSG(info->extack, "Invalid split count"); return -EINVAL; } return devlink_port->ops->port_split(devlink, devlink_port, count, info->extack); } int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; if (!devlink_port->ops->port_unsplit) return -EOPNOTSUPP; return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack); } int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink_port_new_attrs new_attrs = {}; struct devlink *devlink = info->user_ptr[0]; struct devlink_port *devlink_port; struct sk_buff *msg; int err; if (!devlink->ops->port_new) return -EOPNOTSUPP; if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { NL_SET_ERR_MSG(extack, "Port flavour or PCI PF are not specified"); return -EINVAL; } new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); new_attrs.pfnum = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { /* Port index of the new port being created by driver. */ new_attrs.port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); new_attrs.port_index_valid = true; } if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { new_attrs.controller = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); new_attrs.controller_valid = true; } if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); new_attrs.sfnum_valid = true; } err = devlink->ops->port_new(devlink, &new_attrs, extack, &devlink_port); if (err) return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto err_out_port_del; } err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, NULL); if (WARN_ON_ONCE(err)) goto err_out_msg_free; err = genlmsg_reply(msg, info); if (err) goto err_out_port_del; return 0; err_out_msg_free: nlmsg_free(msg); err_out_port_del: devlink_port->ops->port_del(devlink, devlink_port, NULL); return err; } int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; if (!devlink_port->ops->port_del) return -EOPNOTSUPP; return devlink_port->ops->port_del(devlink, devlink_port, extack); } static void devlink_port_type_warn(struct work_struct *work) { struct devlink_port *port = container_of(to_delayed_work(work), struct devlink_port, type_warn_dw); dev_warn(port->devlink->dev, "Type was not set for devlink port."); } static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) { /* Ignore CPU and DSA flavours. */ return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; } #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) { if (!devlink_port_type_should_warn(devlink_port)) return; /* Schedule a work to WARN in case driver does not set port * type within timeout. */ schedule_delayed_work(&devlink_port->type_warn_dw, DEVLINK_PORT_TYPE_WARN_TIMEOUT); } static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) { if (!devlink_port_type_should_warn(devlink_port)) return; cancel_delayed_work_sync(&devlink_port->type_warn_dw); } /** * devlink_port_init() - Init devlink port * * @devlink: devlink * @devlink_port: devlink port * * Initialize essential stuff that is needed for functions * that may be called before devlink port registration. * Call to this function is optional and not needed * in case the driver does not use such functions. */ void devlink_port_init(struct devlink *devlink, struct devlink_port *devlink_port) { if (devlink_port->initialized) return; devlink_port->devlink = devlink; INIT_LIST_HEAD(&devlink_port->region_list); devlink_port->initialized = true; } EXPORT_SYMBOL_GPL(devlink_port_init); /** * devlink_port_fini() - Deinitialize devlink port * * @devlink_port: devlink port * * Deinitialize essential stuff that is in use for functions * that may be called after devlink port unregistration. * Call to this function is optional and not needed * in case the driver does not use such functions. */ void devlink_port_fini(struct devlink_port *devlink_port) { WARN_ON(!list_empty(&devlink_port->region_list)); } EXPORT_SYMBOL_GPL(devlink_port_fini); static const struct devlink_port_ops devlink_port_dummy_ops = {}; /** * devl_port_register_with_ops() - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. */ int devl_port_register_with_ops(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index, const struct devlink_port_ops *ops) { int err; devl_assert_locked(devlink); ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port_init(devlink, devlink_port); devlink_port->registered = true; devlink_port->index = port_index; devlink_port->ops = ops ? ops : &devlink_port_dummy_ops; spin_lock_init(&devlink_port->type_lock); INIT_LIST_HEAD(&devlink_port->reporter_list); err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL); if (err) { devlink_port->registered = false; return err; } INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } EXPORT_SYMBOL_GPL(devl_port_register_with_ops); /** * devlink_port_register_with_ops - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. * * Context: Takes and release devlink->lock <mutex>. */ int devlink_port_register_with_ops(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index, const struct devlink_port_ops *ops) { int err; devl_lock(devlink); err = devl_port_register_with_ops(devlink, devlink_port, port_index, ops); devl_unlock(devlink); return err; } EXPORT_SYMBOL_GPL(devlink_port_register_with_ops); /** * devl_port_unregister() - Unregister devlink port * * @devlink_port: devlink port */ void devl_port_unregister(struct devlink_port *devlink_port) { lockdep_assert_held(&devlink_port->devlink->lock); WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); xa_erase(&devlink_port->devlink->ports, devlink_port->index); WARN_ON(!list_empty(&devlink_port->reporter_list)); devlink_port->registered = false; } EXPORT_SYMBOL_GPL(devl_port_unregister); /** * devlink_port_unregister - Unregister devlink port * * @devlink_port: devlink port * * Context: Takes and release devlink->lock <mutex>. */ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; devl_lock(devlink); devl_port_unregister(devlink_port); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_port_unregister); static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, struct net_device *netdev) { const struct net_device_ops *ops = netdev->netdev_ops; /* If driver registers devlink port, it should set devlink port * attributes accordingly so the compat functions are called * and the original ops are not used. */ if (ops->ndo_get_phys_port_name) { /* Some drivers use the same set of ndos for netdevs * that have devlink_port registered and also for * those who don't. Make sure that ndo_get_phys_port_name * returns -EOPNOTSUPP here in case it is defined. * Warn if not. */ char name[IFNAMSIZ]; int err; err = ops->ndo_get_phys_port_name(netdev, name, sizeof(name)); WARN_ON(err != -EOPNOTSUPP); } if (ops->ndo_get_port_parent_id) { /* Some drivers use the same set of ndos for netdevs * that have devlink_port registered and also for * those who don't. Make sure that ndo_get_port_parent_id * returns -EOPNOTSUPP here in case it is defined. * Warn if not. */ struct netdev_phys_item_id ppid; int err; err = ops->ndo_get_port_parent_id(netdev, &ppid); WARN_ON(err != -EOPNOTSUPP); } } static void __devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type type, void *type_dev) { struct net_device *netdev = type_dev; ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); if (type == DEVLINK_PORT_TYPE_NOTSET) { devlink_port_type_warn_schedule(devlink_port); } else { devlink_port_type_warn_cancel(devlink_port); if (type == DEVLINK_PORT_TYPE_ETH && netdev) devlink_port_type_netdev_checks(devlink_port, netdev); } spin_lock_bh(&devlink_port->type_lock); devlink_port->type = type; switch (type) { case DEVLINK_PORT_TYPE_ETH: devlink_port->type_eth.netdev = netdev; if (netdev) { ASSERT_RTNL(); devlink_port->type_eth.ifindex = netdev->ifindex; BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) != sizeof(netdev->name)); strcpy(devlink_port->type_eth.ifname, netdev->name); } break; case DEVLINK_PORT_TYPE_IB: devlink_port->type_ib.ibdev = type_dev; break; default: break; } spin_unlock_bh(&devlink_port->type_lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } /** * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port * * If driver is calling this, most likely it is doing something wrong. */ void devlink_port_type_eth_set(struct devlink_port *devlink_port) { dev_warn(devlink_port->devlink->dev, "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); /** * devlink_port_type_ib_set - Set port type to InfiniBand * * @devlink_port: devlink port * @ibdev: related IB device */ void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev) { __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); } EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); /** * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port * * If driver is calling this for clearing Ethernet type, |