| 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | // SPDX-License-Identifier: GPL-2.0 #include <linux/sysctl.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/xfrm.h> static void __net_init __xfrm_sysctl_init(struct net *net) { net->xfrm.sysctl_aevent_etime = XFRM_AE_ETIME; net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE; net->xfrm.sysctl_larval_drop = 1; net->xfrm.sysctl_acq_expires = 30; } #ifdef CONFIG_SYSCTL static const struct ctl_table xfrm_table[] = { { .procname = "xfrm_aevent_etime", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec }, { .procname = "xfrm_aevent_rseqth", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec }, { .procname = "xfrm_larval_drop", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "xfrm_acq_expires", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, }; int __net_init xfrm_sysctl_init(struct net *net) { struct ctl_table *table; size_t table_size = ARRAY_SIZE(xfrm_table); __xfrm_sysctl_init(net); table = kmemdup(xfrm_table, sizeof(xfrm_table), GFP_KERNEL); if (!table) goto out_kmemdup; table[0].data = &net->xfrm.sysctl_aevent_etime; table[1].data = &net->xfrm.sysctl_aevent_rseqth; table[2].data = &net->xfrm.sysctl_larval_drop; table[3].data = &net->xfrm.sysctl_acq_expires; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table_size = 0; net->xfrm.sysctl_hdr = register_net_sysctl_sz(net, "net/core", table, table_size); if (!net->xfrm.sysctl_hdr) goto out_register; return 0; out_register: kfree(table); out_kmemdup: return -ENOMEM; } void __net_exit xfrm_sysctl_fini(struct net *net) { const struct ctl_table *table; table = net->xfrm.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->xfrm.sysctl_hdr); kfree(table); } #else int __net_init xfrm_sysctl_init(struct net *net) { __xfrm_sysctl_init(net); return 0; } #endif |
| 174 4 834 14 253 31 71 33 57 95 47 54 97 38 8 1154 1101 32 16 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> extern struct file_system_type nullfs_fs_type; extern struct list_head notify_list; struct mnt_namespace { struct ns_common ns; struct mount * root; struct { struct rb_root mounts; /* Protected by namespace_sem */ struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ }; struct user_namespace *user_ns; struct ucounts *ucounts; wait_queue_head_t poll; u64 seq_origin; /* Sequence number of origin mount namespace */ u64 event; #ifdef CONFIG_FSNOTIFY __u32 n_fsnotify_mask; struct fsnotify_mark_connector __rcu *n_fsnotify_marks; #endif struct hlist_head mnt_visible_mounts; /* SB_I_USERNS_VISIBLE mounts */ unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; refcount_t passive; /* number references not pinning @mounts */ bool is_anon; } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct mount *mnt_next_for_sb; /* the next two fields are hlist_node, */ struct mount * __aligned(1) *mnt_pprev_for_sb; /* except that LSB of pprev is stolen */ #define WRITE_HOLD 1 /* ... for use by mnt_hold_writers() */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct hlist_head mnt_slave_list;/* list of slave mounts */ struct hlist_node mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ /* * Containing namespace (active or deactivating, non-refcounted). * Normally protected by namespace_sem. * Can also be accessed locklessly under RCU. RCU readers can't rely on * the namespace still being active, but implicitly hold a passive * reference (because an RCU delay happens between a namespace being * deactivated and the corresponding passive refcount drop). */ struct mnt_namespace *mnt_ns; struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; struct list_head to_notify; /* need to queue notification */ struct mnt_namespace *prev_ns; /* previous namespace (NULL if none) */ #endif int mnt_t_flags; /* namespace_sem-protected flags */ int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; struct hlist_node mnt_ns_visible; /* link in ns->mnt_visible_mounts */ struct mount *overmount; /* mounted on ->mnt_root */ } __randomize_layout; enum { T_SHARED = 1, /* mount is shared */ T_UNBINDABLE = 2, /* mount is unbindable */ T_MARKED = 4, /* internal mark for propagate_... */ T_UMOUNT_CANDIDATE = 8, /* for propagate_umount */ /* * T_SHARED_MASK is the set of flags that should be cleared when a * mount becomes shared. Currently, this is only the flag that says a * mount cannot be bind mounted, since this is how we create a mount * that shares events with another mount. If you add a new T_* * flag, consider how it interacts with shared mounts. */ T_SHARED_MASK = T_UNBINDABLE, }; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(const struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { ns_ref_inc(ns); } extern seqlock_t mount_lock; DEFINE_LOCK_GUARD_0(mount_writer, write_seqlock(&mount_lock), write_sequnlock(&mount_lock)) DEFINE_LOCK_GUARD_0(mount_locked_reader, read_seqlock_excl(&mount_lock), read_sequnlock_excl(&mount_lock)) struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(const struct dentry *dentry); static inline bool is_local_mountpoint(const struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->is_anon; } static inline bool anon_ns_root(const struct mount *m) { struct mnt_namespace *ns = READ_ONCE(m->mnt_ns); return !IS_ERR_OR_NULL(ns) && is_anon_ns(ns) && m == ns->root; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline bool mnt_ns_empty(const struct mnt_namespace *ns) { return RB_EMPTY_ROOT(&ns->mounts); } static inline void move_from_ns(struct mount *mnt) { struct mnt_namespace *ns = mnt->mnt_ns; WARN_ON(!mnt_ns_attached(mnt)); if (ns->mnt_last_node == &mnt->mnt_node) ns->mnt_last_node = rb_prev(&mnt->mnt_node); if (ns->mnt_first_node == &mnt->mnt_node) ns->mnt_first_node = rb_next(&mnt->mnt_node); rb_erase(&mnt->mnt_node, &ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); if (!hlist_unhashed(&mnt->mnt_ns_visible)) hlist_del_init(&mnt->mnt_ns_visible); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } #ifdef CONFIG_FSNOTIFY static inline void mnt_notify_add(struct mount *m) { /* Optimize the case where there are no watches */ if ((m->mnt_ns && m->mnt_ns->n_fsnotify_marks) || (m->prev_ns && m->prev_ns->n_fsnotify_marks)) list_add_tail(&m->to_notify, ¬ify_list); else m->prev_ns = m->mnt_ns; } #else static inline void mnt_notify_add(struct mount *m) { } #endif static inline struct mount *topmost_overmount(struct mount *m) { while (m->overmount) m = m->overmount; return m; } static inline bool __test_write_hold(struct mount * __aligned(1) *val) { return (unsigned long)val & WRITE_HOLD; } static inline bool test_write_hold(const struct mount *m) { return __test_write_hold(m->mnt_pprev_for_sb); } static inline void set_write_hold(struct mount *m) { m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb | WRITE_HOLD); } static inline void clear_write_hold(struct mount *m) { m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb & ~WRITE_HOLD); } struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry); |
| 207 156 63 7 51 7 26 26 26 2 30 336 80 343 343 158 158 158 158 34 74 126 113 3 649 73 110 112 25 25 18 1 1 449 243 427 427 243 590 449 206 493 204 212 441 212 3 3 5 5 75 75 365 31 261 75 1 1 1 1 1 1 1 1 26 195 195 195 312 306 25 195 157 110 104 6 110 110 28 183 183 183 183 120 70 573 573 12 24 224 224 183 120 17 224 306 306 306 148 148 45 45 27 7 5 5 17 32 9 4 4 1 17 72 17 17 55 55 5 24 41 40 77 129 130 129 24 24 12 12 12 12 111 111 111 111 9 9 9 9 9 13 13 13 1 1 1 1 1 257 73 73 257 257 257 257 257 246 14 73 256 256 256 110 110 110 110 26 26 26 26 51 51 51 51 51 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk> */ #include <linux/mm.h> #include <linux/swap.h> #include <linux/bio-integrity.h> #include <linux/blkdev.h> #include <linux/uio.h> #include <linux/iocontext.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/cgroup.h> #include <linux/highmem.h> #include <linux/blk-crypto.h> #include <linux/xarray.h> #include <linux/kmemleak.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" #include "blk-cgroup.h" #define ALLOC_CACHE_THRESHOLD 16 #define ALLOC_CACHE_MAX 256 struct bio_alloc_cache { struct bio *free_list; struct bio *free_list_irq; unsigned int nr; unsigned int nr_irq; }; #define BIO_INLINE_VECS 4 static struct biovec_slab { int nr_vecs; char *name; struct kmem_cache *slab; } bvec_slabs[] __read_mostly = { { .nr_vecs = 16, .name = "biovec-16" }, { .nr_vecs = 64, .name = "biovec-64" }, { .nr_vecs = 128, .name = "biovec-128" }, { .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" }, }; static struct biovec_slab *biovec_slab(unsigned short nr_vecs) { switch (nr_vecs) { /* smaller bios use inline vecs */ case 5 ... 16: return &bvec_slabs[0]; case 17 ... 64: return &bvec_slabs[1]; case 65 ... 128: return &bvec_slabs[2]; case 129 ... BIO_MAX_VECS: return &bvec_slabs[3]; default: BUG(); return NULL; } } /* * fs_bio_set is the bio_set containing bio and iovec memory pools used by * IO code that does not need private memory pools. */ struct bio_set fs_bio_set; EXPORT_SYMBOL(fs_bio_set); /* * Our slab pool management */ struct bio_slab { struct kmem_cache *slab; unsigned int slab_ref; unsigned int slab_size; char name[12]; }; static DEFINE_MUTEX(bio_slab_lock); static DEFINE_XARRAY(bio_slabs); static struct bio_slab *create_bio_slab(unsigned int size) { struct bio_slab *bslab = kzalloc_obj(*bslab); if (!bslab) return NULL; snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size); bslab->slab = kmem_cache_create(bslab->name, size, ARCH_KMALLOC_MINALIGN, SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL); if (!bslab->slab) goto fail_alloc_slab; bslab->slab_ref = 1; bslab->slab_size = size; if (!xa_err(xa_store(&bio_slabs, size, bslab, GFP_KERNEL))) return bslab; kmem_cache_destroy(bslab->slab); fail_alloc_slab: kfree(bslab); return NULL; } static inline unsigned int bs_bio_slab_size(struct bio_set *bs) { return bs->front_pad + sizeof(struct bio) + bs->back_pad; } static inline void *bio_slab_addr(struct bio *bio) { return (void *)bio - bio->bi_pool->front_pad; } static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs) { unsigned int size = bs_bio_slab_size(bs); struct bio_slab *bslab; mutex_lock(&bio_slab_lock); bslab = xa_load(&bio_slabs, size); if (bslab) bslab->slab_ref++; else bslab = create_bio_slab(size); mutex_unlock(&bio_slab_lock); if (bslab) return bslab->slab; return NULL; } static void bio_put_slab(struct bio_set *bs) { struct bio_slab *bslab = NULL; unsigned int slab_size = bs_bio_slab_size(bs); mutex_lock(&bio_slab_lock); bslab = xa_load(&bio_slabs, slab_size); if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n")) goto out; WARN_ON_ONCE(bslab->slab != bs->bio_slab); WARN_ON(!bslab->slab_ref); if (--bslab->slab_ref) goto out; xa_erase(&bio_slabs, slab_size); kmem_cache_destroy(bslab->slab); kfree(bslab); out: mutex_unlock(&bio_slab_lock); } /* * Make the first allocation restricted and don't dump info on allocation * failures, since we'll fall back to the mempool in case of failure. */ static inline gfp_t try_alloc_gfp(gfp_t gfp) { return (gfp & ~(__GFP_DIRECT_RECLAIM | __GFP_IO)) | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; } void bio_uninit(struct bio *bio) { #ifdef CONFIG_BLK_CGROUP if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; } #endif if (bio_integrity(bio)) bio_integrity_free(bio); bio_crypt_free_ctx(bio); } EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; void *p = bio; WARN_ON_ONCE(!bs); WARN_ON_ONCE(bio->bi_max_vecs > BIO_MAX_VECS); bio_uninit(bio); if (bio->bi_max_vecs == BIO_MAX_VECS) mempool_free(bio->bi_io_vec, &bs->bvec_pool); else if (bio->bi_max_vecs > BIO_INLINE_VECS) kmem_cache_free(biovec_slab(bio->bi_max_vecs)->slab, bio->bi_io_vec); mempool_free(p - bs->front_pad, &bs->bio_pool); } /* * Users of this function have their own bio allocation. Subsequently, * they must remember to pair any call to bio_init() with bio_uninit() * when IO has completed, or when the bio is released. */ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, unsigned short max_vecs, blk_opf_t opf) { bio->bi_next = NULL; bio->bi_bdev = bdev; bio->bi_opf = opf; bio->bi_flags = 0; bio->bi_ioprio = 0; bio->bi_write_hint = 0; bio->bi_write_stream = 0; bio->bi_status = 0; bio->bi_bvec_gap_bit = 0; bio->bi_iter.bi_sector = 0; bio->bi_iter.bi_size = 0; bio->bi_iter.bi_idx = 0; bio->bi_iter.bi_offset = 0; bio->bi_end_io = NULL; bio->bi_private = NULL; #ifdef CONFIG_BLK_CGROUP bio->bi_blkg = NULL; bio->issue_time_ns = 0; if (bdev) bio_associate_blkg(bio); #ifdef CONFIG_BLK_CGROUP_IOCOST bio->bi_iocost_cost = 0; #endif #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION bio->bi_crypt_context = NULL; #endif #ifdef CONFIG_BLK_DEV_INTEGRITY bio->bi_integrity = NULL; #endif bio->bi_vcnt = 0; atomic_set(&bio->__bi_remaining, 1); atomic_set(&bio->__bi_cnt, 1); bio->bi_cookie = BLK_QC_T_NONE; bio->bi_max_vecs = max_vecs; bio->bi_io_vec = table; bio->bi_pool = NULL; } EXPORT_SYMBOL(bio_init); /** * bio_reset - reinitialize a bio * @bio: bio to reset * @bdev: block device to use the bio for * @opf: operation and flags for bio * * Description: * After calling bio_reset(), @bio will be in the same state as a freshly * allocated bio returned bio bio_alloc_bioset() - the only fields that are * preserved are the ones that are initialized by bio_alloc_bioset(). See * comment in struct bio. */ void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf) { struct bio_vec *bv = bio->bi_io_vec; bio_uninit(bio); memset(bio, 0, BIO_RESET_BYTES); atomic_set(&bio->__bi_remaining, 1); bio->bi_io_vec = bv; bio->bi_bdev = bdev; if (bio->bi_bdev) bio_associate_blkg(bio); bio->bi_opf = opf; } EXPORT_SYMBOL(bio_reset); /** * bio_reuse - reuse a bio with the payload left intact * @bio: bio to reuse * @opf: operation and flags for the next I/O * * Allow reusing an existing bio for another operation with all set up * fields including the payload, device and end_io handler left intact. * * Typically used when @bio is first used to read data which is then written * to another location without modification. @bio must not be in-flight and * owned by the caller. Can't be used for cloned bios. * * Note: Can't be used when @bio has integrity or blk-crypto contexts for now. * Feel free to add that support when you need it, though. */ void bio_reuse(struct bio *bio, blk_opf_t opf) { unsigned short vcnt = bio->bi_vcnt, i; bio_end_io_t *end_io = bio->bi_end_io; void *private = bio->bi_private; WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_integrity(bio)); WARN_ON_ONCE(bio_has_crypt_ctx(bio)); bio_reset(bio, bio->bi_bdev, opf); for (i = 0; i < vcnt; i++) bio->bi_iter.bi_size += bio->bi_io_vec[i].bv_len; bio->bi_vcnt = vcnt; bio->bi_private = private; bio->bi_end_io = end_io; } EXPORT_SYMBOL_GPL(bio_reuse); static struct bio *__bio_chain_endio(struct bio *bio) { struct bio *parent = bio->bi_private; if (bio->bi_status && !parent->bi_status) parent->bi_status = bio->bi_status; bio_put(bio); return parent; } /* * This function should only be used as a flag and must never be called. * If execution reaches here, it indicates a serious programming error. */ static void bio_chain_endio(struct bio *bio) { BUG(); } /** * bio_chain - chain bio completions * @bio: the target bio * @parent: the parent bio of @bio * * The caller won't have a bi_end_io called when @bio completes - instead, * @parent's bi_end_io won't be called until both @parent and @bio have * completed; the chained bio will also be freed when it completes. * * The caller must not set bi_private or bi_end_io in @bio. */ void bio_chain(struct bio *bio, struct bio *parent) { BUG_ON(bio->bi_private || bio->bi_end_io); bio->bi_private = parent; bio->bi_end_io = bio_chain_endio; bio_inc_remaining(parent); } EXPORT_SYMBOL(bio_chain); /** * bio_chain_and_submit - submit a bio after chaining it to another one * @prev: bio to chain and submit * @new: bio to chain to * * If @prev is non-NULL, chain it to @new and submit it. * * Return: @new. */ struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new) { if (prev) { bio_chain(prev, new); submit_bio(prev); } return new; } struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp) { return bio_chain_and_submit(bio, bio_alloc(bdev, nr_pages, opf, gfp)); } EXPORT_SYMBOL_GPL(blk_next_bio); static void bio_alloc_rescue(struct work_struct *work) { struct bio_set *bs = container_of(work, struct bio_set, rescue_work); struct bio *bio; while (1) { spin_lock(&bs->rescue_lock); bio = bio_list_pop(&bs->rescue_list); spin_unlock(&bs->rescue_lock); if (!bio) break; submit_bio_noacct(bio); } } /* * submit_bio_noacct() converts recursion to iteration; this means if we're * running beneath it, any bios we allocate and submit will not be submitted * (and thus freed) until after we return. * * This exposes us to a potential deadlock if we allocate multiple bios from the * same bio_set while running underneath submit_bio_noacct(). If we were to * allocate multiple bios (say a stacking block driver that was splitting bios), * we would deadlock if we exhausted the mempool's reserve. * * We solve this, and guarantee forward progress by punting the bios on * current->bio_list to a per bio_set rescuer workqueue before blocking to wait * for elements being returned to the mempool. */ static void punt_bios_to_rescuer(struct bio_set *bs) { struct bio_list punt, nopunt; struct bio *bio; if (!current->bio_list || !bs->rescue_workqueue) return; if (bio_list_empty(¤t->bio_list[0]) && bio_list_empty(¤t->bio_list[1])) return; /* * In order to guarantee forward progress we must punt only bios that * were allocated from this bio_set; otherwise, if there was a bio on * there for a stacking driver higher up in the stack, processing it * could require allocating bios from this bio_set, and doing that from * our own rescuer would be bad. * * Since bio lists are singly linked, pop them all instead of trying to * remove from the middle of the list: */ bio_list_init(&punt); bio_list_init(&nopunt); while ((bio = bio_list_pop(¤t->bio_list[0]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); current->bio_list[0] = nopunt; bio_list_init(&nopunt); while ((bio = bio_list_pop(¤t->bio_list[1]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); current->bio_list[1] = nopunt; spin_lock(&bs->rescue_lock); bio_list_merge(&bs->rescue_list, &punt); spin_unlock(&bs->rescue_lock); queue_work(bs->rescue_workqueue, &bs->rescue_work); } static void bio_alloc_irq_cache_splice(struct bio_alloc_cache *cache) { unsigned long flags; /* cache->free_list must be empty */ if (WARN_ON_ONCE(cache->free_list)) return; local_irq_save(flags); cache->free_list = cache->free_list_irq; cache->free_list_irq = NULL; cache->nr += cache->nr_irq; cache->nr_irq = 0; local_irq_restore(flags); } static struct bio *bio_alloc_percpu_cache(struct bio_set *bs) { struct bio_alloc_cache *cache; struct bio *bio; cache = per_cpu_ptr(bs->cache, get_cpu()); if (!cache->free_list) { if (READ_ONCE(cache->nr_irq) >= ALLOC_CACHE_THRESHOLD) bio_alloc_irq_cache_splice(cache); if (!cache->free_list) { put_cpu(); return NULL; } } bio = cache->free_list; cache->free_list = bio->bi_next; cache->nr--; put_cpu(); bio->bi_pool = bs; kmemleak_alloc(bio_slab_addr(bio), kmem_cache_size(bs->bio_slab), 1, GFP_NOIO); return bio; } /** * bio_alloc_bioset - allocate a bio for I/O * @bdev: block device to allocate the bio for (can be %NULL) * @nr_vecs: number of bvecs to pre-allocate * @opf: operation and flags for bio * @gfp: the GFP_* mask given to the slab allocator * @bs: the bio_set to allocate from. * * Allocate a bio from the mempools in @bs. * * If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to * allocate a bio. This is due to the mempool guarantees. To make this work, * callers must never allocate more than 1 bio at a time from the general pool. * Callers that need to allocate more than 1 bio must always submit the * previously allocated bio for IO before attempting to allocate a new one. * Failure to do so can cause deadlocks under memory pressure. * * Note that when running under submit_bio_noacct() (i.e. any block driver), * bios are not submitted until after you return - see the code in * submit_bio_noacct() that converts recursion into iteration, to prevent * stack overflows. * * This would normally mean allocating multiple bios under submit_bio_noacct() * would be susceptible to deadlocks, but we have * deadlock avoidance code that resubmits any blocked bios from a rescuer * thread. * * However, we do not guarantee forward progress for allocations from other * mempools. Doing multiple allocations from the same mempool under * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp, struct bio_set *bs) { struct bio_vec *bvecs = NULL; struct bio *bio = NULL; gfp_t saved_gfp = gfp; void *p; /* should not use nobvec bioset for nr_vecs > 0 */ if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0)) return NULL; if (saved_gfp & __GFP_DIRECT_RECLAIM) gfp = try_alloc_gfp(gfp); if (bs->cache && nr_vecs <= BIO_INLINE_VECS) { /* * Set REQ_ALLOC_CACHE even if no cached bio is available to * return the allocated bio to the percpu cache when done. */ opf |= REQ_ALLOC_CACHE; bio = bio_alloc_percpu_cache(bs); } else { opf &= ~REQ_ALLOC_CACHE; } /* * For a bioset without a percpu cache, or when the percpu cache was * empty, try a slab allocation with optimistic GFP_ flags before * falling back to the mempool. */ if (!bio) { p = kmem_cache_alloc(bs->bio_slab, gfp); if (p) bio = p + bs->front_pad; } if (bio && nr_vecs > BIO_INLINE_VECS) { struct biovec_slab *bvs = biovec_slab(nr_vecs); /* * Upgrade nr_vecs to take full advantage of the allocation. * We also rely on this in bio_free(). */ nr_vecs = bvs->nr_vecs; bvecs = kmem_cache_alloc(bvs->slab, gfp); if (unlikely(!bvecs)) { kmem_cache_free(bs->bio_slab, p); bio = NULL; } } if (unlikely(!bio)) { /* * Give up if we are not allow to sleep as non-blocking mempool * allocations just go back to the slab allocation. */ if (!(saved_gfp & __GFP_DIRECT_RECLAIM)) return NULL; punt_bios_to_rescuer(bs); /* * Don't rob the mempools by returning to the per-CPU cache if * we're tight on memory. */ opf &= ~REQ_ALLOC_CACHE; p = mempool_alloc(&bs->bio_pool, saved_gfp); bio = p + bs->front_pad; if (nr_vecs > BIO_INLINE_VECS) { nr_vecs = BIO_MAX_VECS; bvecs = mempool_alloc(&bs->bvec_pool, saved_gfp); } } if (nr_vecs && nr_vecs <= BIO_INLINE_VECS) bio_init_inline(bio, bdev, nr_vecs, opf); else bio_init(bio, bdev, bvecs, nr_vecs, opf); bio->bi_pool = bs; return bio; } EXPORT_SYMBOL(bio_alloc_bioset); /** * bio_kmalloc - kmalloc a bio * @nr_vecs: number of bio_vecs to allocate * @gfp_mask: the GFP_* mask given to the slab allocator * * Use kmalloc to allocate a bio (including bvecs). The bio must be initialized * using bio_init() before use. To free a bio returned from this function use * kfree() after calling bio_uninit(). A bio returned from this function can * be reused by calling bio_uninit() before calling bio_init() again. * * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this * function are not backed by a mempool can fail. Do not use this function * for allocations in the file system I/O path. * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; if (nr_vecs > BIO_MAX_INLINE_VECS) return NULL; return kmalloc(sizeof(*bio) + nr_vecs * sizeof(struct bio_vec), gfp_mask); } EXPORT_SYMBOL(bio_kmalloc); void zero_fill_bio(struct bio *bio) { struct bio_vec bv; struct bvec_iter iter; bio_for_each_segment(bv, bio, iter) memzero_bvec(&bv); } EXPORT_SYMBOL(zero_fill_bio); /** * bio_truncate - truncate the bio to small size of @new_size * @bio: the bio to be truncated * @new_size: new size for truncating the bio * * Description: * Truncate the bio to new size of @new_size. If bio_op(bio) is * REQ_OP_READ, zero the truncated part. This function should only * be used for handling corner cases, such as bio eod. */ static void bio_truncate(struct bio *bio, unsigned new_size) { struct bio_vec bv; struct bvec_iter iter; unsigned int done = 0; bool truncated = false; if (new_size >= bio->bi_iter.bi_size) return; if (bio_op(bio) != REQ_OP_READ) goto exit; bio_for_each_segment(bv, bio, iter) { if (done + bv.bv_len > new_size) { size_t offset; if (!truncated) offset = new_size - done; else offset = 0; memzero_page(bv.bv_page, bv.bv_offset + offset, bv.bv_len - offset); truncated = true; } done += bv.bv_len; } exit: /* * Don't touch bvec table here and make it really immutable, since * fs bio user has to retrieve all pages via bio_for_each_segment_all * in its .end_bio() callback. * * It is enough to truncate bio by updating .bi_size since we can make * correct bvec with the updated .bi_size for drivers. */ bio->bi_iter.bi_size = new_size; } /** * guard_bio_eod - truncate a BIO to fit the block device * @bio: bio to truncate * * This allows us to do IO even on the odd last sectors of a device, even if the * block size is some multiple of the physical sector size. * * We'll just truncate the bio to the size of the device, and clear the end of * the buffer head manually. Truly out-of-range accesses will turn into actual * I/O errors, this only handles the "we need to be able to do I/O at the final * sector" case. */ void guard_bio_eod(struct bio *bio) { sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); if (!maxsector) return; /* * If the *whole* IO is past the end of the device, * let it through, and the IO layer will turn it into * an EIO. */ if (unlikely(bio->bi_iter.bi_sector >= maxsector)) return; maxsector -= bio->bi_iter.bi_sector; if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) return; bio_truncate(bio, maxsector << 9); } static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache, unsigned int nr) { unsigned int i = 0; struct bio *bio; while ((bio = cache->free_list) != NULL) { cache->free_list = bio->bi_next; cache->nr--; kmemleak_alloc(bio_slab_addr(bio), kmem_cache_size(bio->bi_pool->bio_slab), 1, GFP_KERNEL); bio_free(bio); if (++i == nr) break; } return i; } static void bio_alloc_cache_prune(struct bio_alloc_cache *cache, unsigned int nr) { nr -= __bio_alloc_cache_prune(cache, nr); if (!READ_ONCE(cache->free_list)) { bio_alloc_irq_cache_splice(cache); __bio_alloc_cache_prune(cache, nr); } } static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node) { struct bio_set *bs; bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead); if (bs->cache) { struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu); bio_alloc_cache_prune(cache, -1U); } return 0; } static void bio_alloc_cache_destroy(struct bio_set *bs) { int cpu; if (!bs->cache) return; cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); for_each_possible_cpu(cpu) { struct bio_alloc_cache *cache; cache = per_cpu_ptr(bs->cache, cpu); bio_alloc_cache_prune(cache, -1U); } free_percpu(bs->cache); bs->cache = NULL; } static inline void bio_put_percpu_cache(struct bio *bio) { struct bio_alloc_cache *cache; cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu()); if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) goto out_free; if (in_task()) { bio_uninit(bio); bio->bi_next = cache->free_list; /* Not necessary but helps not to iopoll already freed bios */ bio->bi_bdev = NULL; cache->free_list = bio; cache->nr++; kmemleak_free(bio_slab_addr(bio)); } else if (in_hardirq()) { lockdep_assert_irqs_disabled(); bio_uninit(bio); bio->bi_next = cache->free_list_irq; cache->free_list_irq = bio; cache->nr_irq++; kmemleak_free(bio_slab_addr(bio)); } else { goto out_free; } put_cpu(); return; out_free: put_cpu(); bio_free(bio); } /** * bio_put - release a reference to a bio * @bio: bio to release reference to * * Description: * Put a reference to a &struct bio, either one you have gotten with * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it. **/ void bio_put(struct bio *bio) { if (unlikely(bio_flagged(bio, BIO_REFFED))) { BUG_ON(!atomic_read(&bio->__bi_cnt)); if (!atomic_dec_and_test(&bio->__bi_cnt)) return; } if (bio->bi_opf & REQ_ALLOC_CACHE) bio_put_percpu_cache(bio); else bio_free(bio); } EXPORT_SYMBOL(bio_put); static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) { bio_set_flag(bio, BIO_CLONED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_write_stream = bio_src->bi_write_stream; bio->bi_bvec_gap_bit = bio_src->bi_bvec_gap_bit; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; if (bio->bi_bdev) { if (bio->bi_bdev == bio_src->bi_bdev && bio_flagged(bio_src, BIO_REMAPPED)) bio_set_flag(bio, BIO_REMAPPED); bio_clone_blkg_association(bio, bio_src); } if (bio_crypt_clone(bio, bio_src, gfp) < 0) return -ENOMEM; if (bio_integrity(bio_src) && bio_integrity_clone(bio, bio_src, gfp) < 0) return -ENOMEM; return 0; } /** * bio_alloc_clone - clone a bio that shares the original bio's biovec * @bdev: block_device to clone onto * @bio_src: bio to clone from * @gfp: allocation priority * @bs: bio_set to allocate from * * Allocate a new bio that is a clone of @bio_src. This reuses the bio_vecs * pointed to by @bio_src->bi_io_vec, and clones the iterator pointing to * the current position in it. The caller owns the returned bio, but not * the bio_vecs, and must ensure the bio is freed before the memory * pointed to by @bio_Src->bi_io_vecs. */ struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, gfp_t gfp, struct bio_set *bs) { struct bio *bio; bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs); if (!bio) return NULL; if (__bio_clone(bio, bio_src, gfp) < 0) { bio_put(bio); return NULL; } return bio; } EXPORT_SYMBOL(bio_alloc_clone); /** * bio_init_clone - clone a bio that shares the original bio's biovec * @bdev: block_device to clone onto * @bio: bio to clone into * @bio_src: bio to clone from * @gfp: allocation priority * * Initialize a new bio in caller provided memory that is a clone of @bio_src. * The same bio_vecs reuse and bio lifetime rules as bio_alloc_clone() apply. */ int bio_init_clone(struct block_device *bdev, struct bio *bio, struct bio *bio_src, gfp_t gfp) { int ret; bio_init(bio, bdev, NULL, 0, bio_src->bi_opf); ret = __bio_clone(bio, bio_src, gfp); if (ret) bio_uninit(bio); return ret; } EXPORT_SYMBOL(bio_init_clone); /** * bio_full - check if the bio is full * @bio: bio to check * @len: length of one segment to be added * * Return true if @bio is full and one segment with @len bytes can't be * added to the bio, otherwise return false */ static inline bool bio_full(struct bio *bio, unsigned len) { if (bio->bi_vcnt >= bio->bi_max_vecs) return true; if (bio->bi_iter.bi_size > BIO_MAX_SIZE - len) return true; return false; } static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, unsigned int len, unsigned int off) { size_t bv_end = bv->bv_offset + bv->bv_len; phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1; phys_addr_t page_addr = page_to_phys(page); if (vec_end_addr + 1 != page_addr + off) return false; if (xen_domain() && !xen_biovec_phys_mergeable(bv, page)) return false; if ((vec_end_addr & PAGE_MASK) != ((page_addr + off) & PAGE_MASK)) { if (IS_ENABLED(CONFIG_KMSAN)) return false; if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE) return false; } bv->bv_len += len; return true; } /* * Try to merge a page into a segment, while obeying the hardware segment * size limit. * * This is kept around for the integrity metadata, which is still tries * to build the initial bio to the hardware limit and doesn't have proper * helpers to split. Hopefully this will go away soon. */ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, struct page *page, unsigned len, unsigned offset) { unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = bvec_phys(bv); phys_addr_t addr2 = page_to_phys(page) + offset + len - 1; if ((addr1 | mask) != (addr2 | mask)) return false; if (len > queue_max_segment_size(q) - bv->bv_len) return false; return bvec_try_merge_page(bv, page, len, offset); } /** * __bio_add_page - add page(s) to a bio in a new segment * @bio: destination bio * @page: start page to add * @len: length of the data to add, may cross pages * @off: offset of the data relative to @page, may cross pages * * Add the data at @page + @off to @bio as a new bvec. The caller must ensure * that @bio has space for another bvec. */ void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); if (is_pci_p2pdma_page(page)) bio->bi_opf |= REQ_NOMERGE; bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off); bio->bi_iter.bi_size += len; bio->bi_vcnt++; } EXPORT_SYMBOL_GPL(__bio_add_page); /** * bio_add_virt_nofail - add data in the direct kernel mapping to a bio * @bio: destination bio * @vaddr: data to add * @len: length of the data to add, may cross pages * * Add the data at @vaddr to @bio. The caller must have ensure a segment * is available for the added data. No merging into an existing segment * will be performed. */ void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len) { __bio_add_page(bio, virt_to_page(vaddr), len, offset_in_page(vaddr)); } EXPORT_SYMBOL_GPL(bio_add_virt_nofail); /** * bio_add_page - attempt to add page(s) to bio * @bio: destination bio * @page: start page to add * @len: vec entry length, may cross pages * @offset: vec entry offset relative to @page, may cross pages * * Attempt to add page(s) to the bio_vec maplist. This will only fail * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. */ int bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; if (WARN_ON_ONCE(len == 0)) return 0; if (bio->bi_iter.bi_size > BIO_MAX_SIZE - len) return 0; if (bio->bi_vcnt > 0) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (!zone_device_pages_compatible(bv->bv_page, page)) return 0; if (zone_device_pages_have_same_pgmap(bv->bv_page, page) && bvec_try_merge_page(bv, page, len, offset)) { bio->bi_iter.bi_size += len; return len; } } if (bio->bi_vcnt >= bio->bi_max_vecs) return 0; __bio_add_page(bio, page, len, offset); return len; } EXPORT_SYMBOL(bio_add_page); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, size_t off) { unsigned long nr = off / PAGE_SIZE; WARN_ON_ONCE(len > BIO_MAX_SIZE); __bio_add_page(bio, folio_page(folio, nr), len, off % PAGE_SIZE); } EXPORT_SYMBOL_GPL(bio_add_folio_nofail); /** * bio_add_folio - Attempt to add part of a folio to a bio. * @bio: BIO to add to. * @folio: Folio to add. * @len: How many bytes from the folio to add. * @off: First byte in this folio to add. * * Filesystems that use folios can call this function instead of calling * bio_add_page() for each page in the folio. If @off is bigger than * PAGE_SIZE, this function can create a bio_vec that starts in a page * after the bv_page. BIOs do not support folios that are 4GiB or larger. * * Return: Whether the addition was successful. */ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off) { unsigned long nr = off / PAGE_SIZE; if (len > BIO_MAX_SIZE) return false; return bio_add_page(bio, folio_page(folio, nr), len, off % PAGE_SIZE) > 0; } EXPORT_SYMBOL(bio_add_folio); /** * bio_add_vmalloc_chunk - add a vmalloc chunk to a bio * @bio: destination bio * @vaddr: vmalloc address to add * @len: total length in bytes of the data to add * * Add data starting at @vaddr to @bio and return how many bytes were added. * This may be less than the amount originally asked. Returns 0 if no data * could be added to @bio. * * This helper calls flush_kernel_vmap_range() for the range added. For reads * the caller still needs to manually call invalidate_kernel_vmap_range() in * the completion handler. */ unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len) { unsigned int offset = offset_in_page(vaddr); len = min(len, PAGE_SIZE - offset); if (bio_add_page(bio, vmalloc_to_page(vaddr), len, offset) < len) return 0; if (op_is_write(bio_op(bio))) flush_kernel_vmap_range(vaddr, len); return len; } EXPORT_SYMBOL_GPL(bio_add_vmalloc_chunk); /** * bio_add_vmalloc - add a vmalloc region to a bio * @bio: destination bio * @vaddr: vmalloc address to add * @len: total length in bytes of the data to add * * Add data starting at @vaddr to @bio. Return %true on success or %false if * @bio does not have enough space for the payload. * * This helper calls flush_kernel_vmap_range() for the range added. For reads * the caller still needs to manually call invalidate_kernel_vmap_range() in * the completion handler. */ bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len) { do { unsigned int added = bio_add_vmalloc_chunk(bio, vaddr, len); if (!added) return false; vaddr += added; len -= added; } while (len); return true; } EXPORT_SYMBOL_GPL(bio_add_vmalloc); void __bio_release_pages(struct bio *bio, bool mark_dirty) { struct folio_iter fi; bio_for_each_folio_all(fi, bio) { size_t nr_pages; if (mark_dirty) { folio_lock(fi.folio); folio_mark_dirty(fi.folio); folio_unlock(fi.folio); } nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE - fi.offset / PAGE_SIZE + 1; unpin_user_folio(fi.folio, nr_pages); } } EXPORT_SYMBOL_GPL(__bio_release_pages); bool bio_iov_iter_set(struct bio *bio, const struct iov_iter *iter) { if (!iov_iter_is_bvec(iter)) return false; WARN_ON_ONCE(bio->bi_max_vecs); bio->bi_io_vec = (struct bio_vec *)iter->bvec; bio->bi_iter.bi_idx = 0; bio->bi_iter.bi_offset = iter->iov_offset; bio->bi_iter.bi_size = iov_iter_count(iter); bio_set_flag(bio, BIO_CLONED); return true; } /* * Aligns the bio size to the len_align_mask, releasing excessive bio vecs that * __bio_iov_iter_get_pages may have inserted, and reverts the trimmed length * for the next iteration. */ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, struct bio_vec *bv, unsigned len_align_mask) { size_t nbytes = bio->bi_iter.bi_size & len_align_mask; if (!nbytes) return 0; iov_iter_revert(iter, nbytes); bio->bi_iter.bi_size -= nbytes; while (nbytes >= bv->bv_len) { if (bio_flagged(bio, BIO_PAGE_PINNED)) unpin_user_page(bv->bv_page); if (!--bio->bi_vcnt) return -EFAULT; nbytes -= bv->bv_len; bv--; } bv->bv_len -= nbytes; return 0; } #ifdef CONFIG_DEBUG_KERNEL static inline bool bio_iov_bvec_aligned(const struct bio *bio, unsigned mem_align_mask) { struct bvec_iter iter; struct bio_vec bv; /* * Correct callers never break the alignment requirements, so this * exhaustive check is only paid for in debug builds. */ for_each_mp_bvec(bv, bio->bi_io_vec, iter, bio->bi_iter) if ((bv.bv_offset | bv.bv_len) & mem_align_mask) return false; return true; } #else static inline bool bio_iov_bvec_aligned(const struct bio *bio, unsigned mem_align_mask) { /* * We forward the bio_vec as-is, so ITER_BVEC callers must provide * segments already aligned to the device's DMA alignment. The only * unchecked user-controllable offset that reaches here is an io_uring * registered buffer where just the first segment can be unaligned * (the rest is virtually contiguous), so checking only that one is * sufficient to know if the entire vector is valid. */ return !(mp_bvec_iter_offset(bio->bi_io_vec, bio->bi_iter) & mem_align_mask); } #endif /** * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be added * @mem_align_mask: the mask the source address and length must be aligned to, * 0 for no requirement * @len_align_mask: the mask to align the total size to, 0 for any length * * This takes either an iterator pointing to user memory, or one pointing to * kernel pages (BVEC iterator). If we're adding user pages, we pin them and * map them into the kernel. On IO completion, the caller should put those * pages. For bvec based iterators bio_iov_iter_get_pages() uses the provided * bvecs rather than copying them. Hence anyone issuing kiocb based IO needs * to ensure the bvecs and pages stay referenced until the submitted I/O is * completed by a call to ->ki_complete() or returns with an error other than * -EIOCBQUEUED. The caller needs to check if the bio is flagged BIO_NO_PAGE_REF * on IO completion. If it isn't, then pages should be released. * * The function tries, but does not guarantee, to pin as many pages as * fit into the bio, or are requested in @iter, whatever is smaller. If * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, unsigned mem_align_mask, unsigned len_align_mask) { iov_iter_extraction_t flags = 0; if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return -EIO; if (bio_iov_iter_set(bio, iter)) { if (iov_iter_is_bvec(iter) && !bio_iov_bvec_aligned(bio, mem_align_mask)) return -EINVAL; iov_iter_advance(iter, bio->bi_iter.bi_size); return 0; } if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue)) flags |= ITER_ALLOW_P2PDMA; do { ssize_t ret; ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec, BIO_MAX_SIZE - bio->bi_iter.bi_size, &bio->bi_vcnt, bio->bi_max_vecs, mem_align_mask, flags); if (ret <= 0) { /* * A misaligned vector fails the whole I/O. Release any * pages pinned by earlier iterations before returning * since this bio won't be submitted to release them. */ if (ret == -EINVAL) { bio_release_pages(bio, false); bio_clear_flag(bio, BIO_PAGE_PINNED); bio->bi_vcnt = 0; } if (!bio->bi_vcnt) return ret; break; } bio->bi_iter.bi_size += ret; } while (iov_iter_count(iter) && !bio_full(bio, 0)); if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page)) bio->bi_opf |= REQ_NOMERGE; return bio_iov_iter_align_down(bio, iter, &bio->bi_io_vec[bio->bi_vcnt - 1], len_align_mask); } static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, size_t minsize) { struct folio *folio; while (*size > minsize) { folio = folio_alloc(gfp | __GFP_NORETRY | __GFP_NOWARN, get_order(*size)); if (folio) return folio; *size = rounddown_pow_of_two(*size - 1); } return folio_alloc(gfp, get_order(*size)); } static void bio_free_folios(struct bio *bio) { struct bio_vec *bv; int i; bio_for_each_bvec_all(bv, bio, i) { struct folio *folio = bvec_folio(bv); if (!is_zero_folio(folio) && !is_huge_zero_folio(folio)) folio_put(folio); } } static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, size_t maxlen, size_t minsize) { size_t total_len = min(maxlen, iov_iter_count(iter)); if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return -EINVAL; if (WARN_ON_ONCE(bio->bi_iter.bi_size)) return -EINVAL; if (WARN_ON_ONCE(bio->bi_vcnt >= bio->bi_max_vecs)) return -EINVAL; do { size_t this_len = min(total_len, SZ_1M); size_t copied; struct folio *folio; if (this_len > minsize * 2) this_len = rounddown_pow_of_two(this_len); if (bio->bi_iter.bi_size > BIO_MAX_SIZE - this_len) break; folio = folio_alloc_greedy(GFP_KERNEL, &this_len, minsize); if (!folio) break; bio_add_folio_nofail(bio, folio, this_len, 0); if (iter->nofault) copied = copy_folio_from_iter_atomic(folio, 0, this_len, iter); else copied = copy_folio_from_iter(folio, 0, this_len, iter); if (copied < this_len) { /* * Need to revert the iov iter for all bytes we have * copied. * * However the bio size differs from the real copied * bytes as @this_len is queued but only advanced * less than that. * Need to compensate that for the revert. */ iov_iter_revert(iter, bio->bi_iter.bi_size - this_len + copied); bio_free_folios(bio); return -EFAULT; } total_len -= this_len; } while (total_len && bio->bi_vcnt < bio->bi_max_vecs); if (!bio->bi_iter.bi_size) return -ENOMEM; return bio_iov_iter_align_down(bio, iter, &bio->bi_io_vec[bio->bi_vcnt - 1], minsize - 1); } static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, size_t maxlen, size_t minsize) { size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M); struct folio *folio; ssize_t ret; folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize); if (!folio) return -ENOMEM; do { ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec + 1, len, &bio->bi_vcnt, bio->bi_max_vecs - 1, 0, 0); if (ret <= 0) { if (!bio->bi_vcnt) goto out_folio_put; break; } len -= ret; bio->bi_iter.bi_size += ret; } while (len && bio->bi_vcnt < bio->bi_max_vecs - 1); /* * Set the folio directly here. The above loop has already calculated * the correct bi_size, and we use bi_vcnt for the user buffers. That * is safe as bi_vcnt is only used by the submitter and not the actual * I/O path. */ bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0); if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); /* The first vec stores the bounce buffer, so do not subtract 1 here. */ ret = bio_iov_iter_align_down(bio, iter, &bio->bi_io_vec[bio->bi_vcnt], minsize - 1); if (ret) goto out_folio_put; /* Update the bounc buffer bv_len to the aligned down size. */ bio->bi_io_vec[0].bv_len = bio->bi_iter.bi_size; return 0; out_folio_put: folio_put(folio); return ret; } /** * bio_iov_iter_bounce - bounce buffer data from an iter into a bio * @bio: bio to send * @iter: iter to read from / write into * @maxlen: maximum size to bounce * @minsize: minimum folio allocation size * * Helper for direct I/O implementations that need to bounce buffer because * we need to checksum the data or perform other operations that require * consistency. Allocates folios to back the bounce buffer, and for writes * copies the data into it. Needs to be paired with bio_iov_iter_unbounce() * called on completion. */ int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen, size_t minsize) { if (op_is_write(bio_op(bio))) return bio_iov_iter_bounce_write(bio, iter, maxlen, minsize); return bio_iov_iter_bounce_read(bio, iter, maxlen, minsize); } static void bvec_unpin(struct bio_vec *bv, bool mark_dirty) { struct folio *folio = bvec_folio(bv); size_t nr_pages = (bv->bv_offset + bv->bv_len - 1) / PAGE_SIZE - bv->bv_offset / PAGE_SIZE + 1; if (mark_dirty) folio_mark_dirty_lock(folio); unpin_user_folio(folio, nr_pages); } static void bio_iov_iter_unbounce_read(struct bio *bio, bool is_error, bool mark_dirty) { unsigned int len = bio->bi_io_vec[0].bv_len; if (likely(!is_error)) { void *buf = bvec_virt(&bio->bi_io_vec[0]); struct iov_iter to; iov_iter_bvec(&to, ITER_DEST, bio->bi_io_vec + 1, bio->bi_vcnt, len); /* copying to pinned pages should always work */ WARN_ON_ONCE(copy_to_iter(buf, len, &to) != len); } else { /* No need to mark folios dirty if never copied to them */ mark_dirty = false; } if (bio_flagged(bio, BIO_PAGE_PINNED)) { int i; for (i = 0; i < bio->bi_vcnt; i++) bvec_unpin(&bio->bi_io_vec[1 + i], mark_dirty); } folio_put(bvec_folio(&bio->bi_io_vec[0])); } /** * bio_iov_iter_unbounce - finish a bounce buffer operation * @bio: completed bio * @is_error: %true if an I/O error occurred and data should not be copied * @mark_dirty: If %true, folios will be marked dirty. * * Helper for direct I/O implementations that need to bounce buffer because * we need to checksum the data or perform other operations that require * consistency. Called to complete a bio set up by bio_iov_iter_bounce(). * Copies data back for reads, and marks the original folios dirty if * requested and then frees the bounce buffer. */ void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty) { if (op_is_write(bio_op(bio))) bio_free_folios(bio); else bio_iov_iter_unbounce_read(bio, is_error, mark_dirty); } static void bio_wait_end_io(struct bio *bio) { complete(bio->bi_private); } /** * bio_await - call a function on a bio, and wait until it completes * @bio: the bio which describes the I/O * @submit: function called to submit the bio * @priv: private data passed to @submit * * Wait for the bio as well as any bio chained off it after executing the * passed in callback @submit. The wait for the bio is set up before calling * @submit to ensure that the completion is captured. If @submit is %NULL, * submit_bio() is used instead to submit the bio. * * Note: this overrides the bi_private and bi_end_io fields in the bio. */ void bio_await(struct bio *bio, void *priv, void (*submit)(struct bio *bio, void *priv)) { DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_bdev->bd_disk->lockdep_map); bio->bi_private = &done; bio->bi_end_io = bio_wait_end_io; bio->bi_opf |= REQ_SYNC; if (submit) submit(bio, priv); else submit_bio(bio); blk_wait_io(&done); } EXPORT_SYMBOL_GPL(bio_await); /** * submit_bio_wait - submit a bio, and wait until it completes * @bio: The &struct bio which describes the I/O * * Simple wrapper around submit_bio(). Returns 0 on success, or the error from * bio_endio() on failure. * * WARNING: Unlike to how submit_bio() is usually used, this function does not * result in bio reference to be consumed. The caller must drop the reference * on his own. */ int submit_bio_wait(struct bio *bio) { bio_await(bio, NULL, NULL); return blk_status_to_errno(bio->bi_status); } EXPORT_SYMBOL(submit_bio_wait); static void bio_endio_cb(struct bio *bio, void *priv) { bio_endio(bio); } /* * Submit @bio synchronously, or call bio_endio on it if the current process * is being killed. */ int bio_submit_or_kill(struct bio *bio, unsigned int flags) { if ((flags & BLKDEV_ZERO_KILLABLE) && fatal_signal_pending(current)) { bio_await(bio, NULL, bio_endio_cb); return -EINTR; } return submit_bio_wait(bio); } /** * bdev_rw_virt - synchronously read into / write from kernel mapping * @bdev: block device to access * @sector: sector to access * @data: data to read/write * @len: length in byte to read/write * @op: operation (e.g. REQ_OP_READ/REQ_OP_WRITE) * * Performs synchronous I/O to @bdev for @data/@len. @data must be in * the kernel direct mapping and not a vmalloc address. */ int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data, size_t len, enum req_op op) { struct bio_vec bv; struct bio bio; int error; if (WARN_ON_ONCE(is_vmalloc_addr(data))) return -EIO; bio_init(&bio, bdev, &bv, 1, op); bio.bi_iter.bi_sector = sector; bio_add_virt_nofail(&bio, data, len); error = submit_bio_wait(&bio); bio_uninit(&bio); return error; } EXPORT_SYMBOL_GPL(bdev_rw_virt); void __bio_advance(struct bio *bio, unsigned bytes) { if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); bio_crypt_advance(bio, bytes); bio_advance_iter(bio, &bio->bi_iter, bytes); } EXPORT_SYMBOL(__bio_advance); /** * bio_copy_data - copy contents of data buffers from one bio to another * @src: source bio * @dst: destination bio * * Stops when it reaches the end of either @src or @dst - that is, copies * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios). */ void bio_copy_data(struct bio *dst, struct bio *src) { struct bvec_iter src_iter = src->bi_iter; struct bvec_iter dst_iter = dst->bi_iter; while (src_iter.bi_size && dst_iter.bi_size) { struct bio_vec src_bv = bio_iter_iovec(src, src_iter); struct bio_vec dst_bv = bio_iter_iovec(dst, dst_iter); unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len); void *src_buf = bvec_kmap_local(&src_bv); void *dst_buf = bvec_kmap_local(&dst_bv); memcpy(dst_buf, src_buf, bytes); kunmap_local(dst_buf); kunmap_local(src_buf); bio_advance_iter_single(src, &src_iter, bytes); bio_advance_iter_single(dst, &dst_iter, bytes); } } EXPORT_SYMBOL(bio_copy_data); void bio_free_pages(struct bio *bio) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) __free_page(bvec->bv_page); } EXPORT_SYMBOL(bio_free_pages); /* * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * * The problem is that we cannot run folio_mark_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. * But other code (eg, flusher threads) could clean the pages if they are mapped * pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the * deferred bio dirtying paths. */ /* * bio_set_pages_dirty() will mark all the bio's pages as dirty. */ void bio_set_pages_dirty(struct bio *bio) { struct folio_iter fi; bio_for_each_folio_all(fi, bio) { folio_lock(fi.folio); folio_mark_dirty(fi.folio); folio_unlock(fi.folio); } } /* * bio_check_pages_dirty() will check that all the BIO's pages are still dirty. * If they are, then fine. If, however, some pages are clean then they must * have been written out during the direct-IO read. So we take another ref on * the BIO and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from * here on. It will unpin each page and will run one bio_put() against the * BIO. */ static void bio_dirty_fn(struct work_struct *work); static DECLARE_WORK(bio_dirty_work, bio_dirty_fn); static DEFINE_SPINLOCK(bio_dirty_lock); static struct bio *bio_dirty_list; /* * This runs in process context */ static void bio_dirty_fn(struct work_struct *work) { struct bio *bio, *next; spin_lock_irq(&bio_dirty_lock); next = bio_dirty_list; bio_dirty_list = NULL; spin_unlock_irq(&bio_dirty_lock); while ((bio = next) != NULL) { next = bio->bi_private; bio_release_pages(bio, true); bio_put(bio); } } void bio_check_pages_dirty(struct bio *bio) { struct folio_iter fi; unsigned long flags; bio_for_each_folio_all(fi, bio) { if (!folio_test_dirty(fi.folio)) goto defer; } bio_release_pages(bio, false); bio_put(bio); return; defer: spin_lock_irqsave(&bio_dirty_lock, flags); bio->bi_private = bio_dirty_list; bio_dirty_list = bio; spin_unlock_irqrestore(&bio_dirty_lock, flags); schedule_work(&bio_dirty_work); } /* * Infrastructure for deferring bio completions to task-context via a per-CPU * workqueue. Triggered either by the BIO_COMPLETE_IN_TASK bio flag (static * decision at submit time) or by calling bio_complete_in_task() from * bi_end_io() (dynamic decision at completion time). */ struct bio_complete_batch { struct bio_list list; struct work_struct work; int cpu; }; static DEFINE_PER_CPU(struct bio_complete_batch, bio_complete_batch); static struct workqueue_struct *bio_complete_wq; static void bio_complete_work_fn(struct work_struct *w) { struct bio_complete_batch *batch = container_of(w, struct bio_complete_batch, work); while (1) { struct bio_list list; struct bio *bio; local_irq_disable(); list = batch->list; bio_list_init(&batch->list); local_irq_enable(); if (bio_list_empty(&list)) break; while ((bio = bio_list_pop(&list))) bio->bi_end_io(bio); } } void __bio_complete_in_task(struct bio *bio) { struct bio_complete_batch *batch; unsigned long flags; bool was_empty; local_irq_save(flags); batch = this_cpu_ptr(&bio_complete_batch); was_empty = bio_list_empty(&batch->list); bio_list_add(&batch->list, bio); local_irq_restore(flags); if (was_empty) queue_work_on(batch->cpu, bio_complete_wq, &batch->work); } EXPORT_SYMBOL_GPL(__bio_complete_in_task); static inline bool bio_remaining_done(struct bio *bio) { /* * If we're not chaining, then ->__bi_remaining is always 1 and * we always end io on the first invocation. */ if (!bio_flagged(bio, BIO_CHAIN)) return true; BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); if (atomic_dec_and_test(&bio->__bi_remaining)) { bio_clear_flag(bio, BIO_CHAIN); return true; } return false; } /** * bio_endio - end I/O on a bio * @bio: bio * * Description: * bio_endio() will end I/O on the whole bio. bio_endio() is the preferred * way to end I/O on a bio. No one should call bi_end_io() directly on a * bio unless they own it and thus know that it has an end_io function. * * bio_endio() can be called several times on a bio that has been chained * using bio_chain(). The ->bi_end_io() function will only be called the * last time. **/ void bio_endio(struct bio *bio) { again: if (!bio_remaining_done(bio)) return; if (!bio_integrity_endio(bio)) return; blk_zone_bio_endio(bio); rq_qos_done_bio(bio); if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio); bio_clear_flag(bio, BIO_TRACE_COMPLETION); } /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that * save/restore bi_end_io) - however, we want to avoid unbounded * recursion and blowing the stack. Tail call optimization would * handle this, but compiling with frame pointers also disables * gcc's sibling call optimization. */ if (bio->bi_end_io == bio_chain_endio) { bio = __bio_chain_endio(bio); goto again; } #ifdef CONFIG_BLK_CGROUP /* * Release cgroup info. We shouldn't have to do this here, but quite * a few callers of bio_init fail to call bio_uninit, so we cover up * for that here at least for now. */ if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; } #endif if (bio_flagged(bio, BIO_COMPLETE_IN_TASK) && bio_in_atomic()) __bio_complete_in_task(bio); else if (bio->bi_end_io) bio->bi_end_io(bio); } EXPORT_SYMBOL(bio_endio); /** * bio_split - split a bio * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Allocates and returns a new bio which represents @sectors from the start of * @bio, and updates @bio to represent the remaining sectors. * * Unless this is a discard request the newly allocated bio will point * to @bio's bi_io_vec. It is the caller's responsibility to ensure that * neither @bio nor @bs are freed before the split bio. */ struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { struct bio *split; if (WARN_ON_ONCE(sectors <= 0)) return ERR_PTR(-EINVAL); if (WARN_ON_ONCE(sectors >= bio_sectors(bio))) return ERR_PTR(-EINVAL); /* Zone append commands cannot be split */ if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND)) return ERR_PTR(-EINVAL); /* atomic writes cannot be split */ if (bio->bi_opf & REQ_ATOMIC) return ERR_PTR(-EINVAL); split = bio_alloc_clone(bio->bi_bdev, bio, gfp, bs); if (!split) return ERR_PTR(-ENOMEM); split->bi_iter.bi_size = sectors << 9; if (bio_integrity(split)) bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); /* * The gap bit is set when splitting to limits and only applies to the * front bio that was split off. The remaining bio will calcualte its * gap value when it is subsequently split to limits, so it is safe to * re-initialize the value back to 0. */ bio->bi_bvec_gap_bit = 0; if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); return split; } EXPORT_SYMBOL(bio_split); /** * bio_trim - trim a bio * @bio: bio to trim * @offset: number of sectors to trim from the front of @bio * @size: size we want to trim @bio to, in sectors * * This function is typically used for bios that are cloned and submitted * to the underlying device in parts. */ void bio_trim(struct bio *bio, sector_t offset, sector_t size) { /* We should never trim an atomic write */ if (WARN_ON_ONCE(bio->bi_opf & REQ_ATOMIC && size)) return; if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || offset + size > bio_sectors(bio))) return; size <<= 9; if (offset == 0 && size == bio->bi_iter.bi_size) return; bio_advance(bio, offset << 9); bio->bi_iter.bi_size = size; if (bio_integrity(bio)) bio_integrity_trim(bio); } EXPORT_SYMBOL_GPL(bio_trim); /* * create memory pools for biovec's in a bio_set. * use the global biovec slabs created for general use. */ static int biovec_init_pool(mempool_t *pool, int pool_entries) { struct biovec_slab *bp = bvec_slabs + ARRAY_SIZE(bvec_slabs) - 1; return mempool_init_slab_pool(pool, pool_entries, bp->slab); } /* * bioset_exit - exit a bioset initialized with bioset_init() * * May be called on a zeroed but uninitialized bioset (i.e. allocated with * kzalloc()). */ void bioset_exit(struct bio_set *bs) { bio_alloc_cache_destroy(bs); if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); bs->rescue_workqueue = NULL; mempool_exit(&bs->bio_pool); mempool_exit(&bs->bvec_pool); if (bs->bio_slab) bio_put_slab(bs); bs->bio_slab = NULL; } EXPORT_SYMBOL(bioset_exit); /** * bioset_init - Initialize a bio_set * @bs: pool to initialize * @pool_size: Number of bio and bio_vecs to cache in the mempool * @front_pad: Number of bytes to allocate in front of the returned bio * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS * and %BIOSET_NEED_RESCUER * * Description: * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller * to ask for a number of bytes to be allocated in front of the bio. * Front pad allocation is useful for embedding the bio inside * another structure, to avoid allocating extra data to go with the bio. * Note that the bio must be embedded at the END of that structure always, * or things will break badly. * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated * for allocating iovecs. This pool is not needed e.g. for bio_init_clone(). * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used * to dispatch queued requests when the mempool runs out of space. * */ int bioset_init(struct bio_set *bs, unsigned int pool_size, unsigned int front_pad, int flags) { bs->front_pad = front_pad; if (flags & BIOSET_NEED_BVECS) bs->back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); else bs->back_pad = 0; spin_lock_init(&bs->rescue_lock); bio_list_init(&bs->rescue_list); INIT_WORK(&bs->rescue_work, bio_alloc_rescue); bs->bio_slab = bio_find_or_create_slab(bs); if (!bs->bio_slab) return -ENOMEM; if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab)) goto bad; if ((flags & BIOSET_NEED_BVECS) && biovec_init_pool(&bs->bvec_pool, pool_size)) goto bad; if (flags & BIOSET_NEED_RESCUER) { bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!bs->rescue_workqueue) goto bad; } if (flags & BIOSET_PERCPU_CACHE) { bs->cache = alloc_percpu(struct bio_alloc_cache); if (!bs->cache) goto bad; cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); } return 0; bad: bioset_exit(bs); return -ENOMEM; } EXPORT_SYMBOL(bioset_init); static int bio_complete_batch_cpu_online(unsigned int cpu) { struct bio_complete_batch *batch = &per_cpu(bio_complete_batch, cpu); enable_work(&batch->work); if (!bio_list_empty(&batch->list)) queue_work_on(cpu, bio_complete_wq, &batch->work); return 0; } /* * Disable this CPU's work item so that it cannot run on an unbound worker * after the CPU is offlined. */ static int bio_complete_batch_cpu_down_prep(unsigned int cpu) { disable_work_sync(&per_cpu(bio_complete_batch, cpu).work); return 0; } /* * Drain a dead CPU's deferred bio completions. The CPU is dead and the worker * is canceled so no locking is needed. */ static int bio_complete_batch_cpu_dead(unsigned int cpu) { struct bio_complete_batch *batch = per_cpu_ptr(&bio_complete_batch, cpu); struct bio *bio; while ((bio = bio_list_pop(&batch->list))) bio->bi_end_io(bio); return 0; } static void __init bio_complete_batch_init(int cpu) { struct bio_complete_batch *batch = per_cpu_ptr(&bio_complete_batch, cpu); bio_list_init(&batch->list); INIT_WORK(&batch->work, bio_complete_work_fn); batch->cpu = cpu; if (!cpu_online(cpu)) disable_work_sync(&batch->work); } static int __init init_bio(void) { int i; BUILD_BUG_ON(BIO_FLAG_LAST > 8 * sizeof_field(struct bio, bi_flags)); for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) { struct biovec_slab *bvs = bvec_slabs + i; bvs->slab = kmem_cache_create(bvs->name, bvs->nr_vecs * sizeof(struct bio_vec), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); } for_each_possible_cpu(i) bio_complete_batch_init(i); bio_complete_wq = alloc_workqueue("bio_complete", WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!bio_complete_wq) panic("bio: can't allocate bio_complete workqueue\n"); /* * bio task-context completion draining on hot-unplugged CPUs: * * 1. Stop the per-CPU work item while the CPU is still online, so * that it cannot run on an unbound worker later. * 2. Drain leftover bios added between worker disabling and CPU * offlining. */ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "block/bio:complete:online", bio_complete_batch_cpu_online, bio_complete_batch_cpu_down_prep); cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN, "block/bio:complete:dead", NULL, bio_complete_batch_cpu_dead); cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL, bio_cpu_dead); if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE)) panic("bio: can't allocate bios\n"); return 0; } subsys_initcall(init_bio); |
| 4 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ip_vs_proto_ah_esp.c: AH/ESP IPSec load balancing support for IPVS * * Authors: Julian Anastasov <ja@ssi.bg>, February 2002 * Wensong Zhang <wensong@linuxvirtualserver.org> */ #define pr_fmt(fmt) "IPVS: " fmt #include <linux/in.h> #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <net/ip_vs.h> /* TODO: struct isakmp_hdr { __u8 icookie[8]; __u8 rcookie[8]; __u8 np; __u8 version; __u8 xchgtype; __u8 flags; __u32 msgid; __u32 length; }; */ #define PORT_ISAKMP 500 static void ah_esp_conn_fill_param_proto(struct netns_ipvs *ipvs, int af, const struct ip_vs_iphdr *iph, struct ip_vs_conn_param *p) { if (likely(!ip_vs_iph_inverse(iph))) ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP, &iph->saddr, htons(PORT_ISAKMP), &iph->daddr, htons(PORT_ISAKMP), p); else ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP, &iph->daddr, htons(PORT_ISAKMP), &iph->saddr, htons(PORT_ISAKMP), p); } static struct ip_vs_conn * ah_esp_conn_in_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_in_get(&p); if (!cp) { /* * We are not sure if the packet is from our * service, so our conn_schedule hook should return NF_ACCEPT */ IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet " "%s%s %s->%s\n", ip_vs_iph_icmp(iph) ? "ICMP+" : "", ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); } return cp; } static struct ip_vs_conn * ah_esp_conn_out_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " "%s%s %s->%s\n", ip_vs_iph_icmp(iph) ? "ICMP+" : "", ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); } return cp; } static int ah_esp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { /* * AH/ESP is only related traffic. Pass the packet to IP stack. */ *verdict = NF_ACCEPT; return 0; } #ifdef CONFIG_IP_VS_PROTO_AH struct ip_vs_protocol ip_vs_protocol_ah = { .name = "AH", .protocol = IPPROTO_AH, .num_states = 1, .dont_defrag = 1, .init = NULL, .exit = NULL, .conn_schedule = ah_esp_conn_schedule, .conn_in_get = ah_esp_conn_in_get, .conn_out_get = ah_esp_conn_out_get, .snat_handler = NULL, .dnat_handler = NULL, .state_transition = NULL, .register_app = NULL, .unregister_app = NULL, .app_conn_bind = NULL, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, /* ISAKMP */ }; #endif #ifdef CONFIG_IP_VS_PROTO_ESP struct ip_vs_protocol ip_vs_protocol_esp = { .name = "ESP", .protocol = IPPROTO_ESP, .num_states = 1, .dont_defrag = 1, .init = NULL, .exit = NULL, .conn_schedule = ah_esp_conn_schedule, .conn_in_get = ah_esp_conn_in_get, .conn_out_get = ah_esp_conn_out_get, .snat_handler = NULL, .dnat_handler = NULL, .state_transition = NULL, .register_app = NULL, .unregister_app = NULL, .app_conn_bind = NULL, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, /* ISAKMP */ }; #endif |
| 13 4 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 | /* 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 */ |
| 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * cx2341x - generic code for cx23415/6/8 based devices * * Copyright (C) 2006 Hans Verkuil <hverkuil@kernel.org> */ #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> #include <linux/videodev2.h> #include <media/tuner.h> #include <media/drv-intf/cx2341x.h> #include <media/v4l2-common.h> MODULE_DESCRIPTION("cx23415/6/8 driver"); MODULE_AUTHOR("Hans Verkuil"); MODULE_LICENSE("GPL"); static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Debug level (0-1)"); /********************** COMMON CODE *********************/ /* definitions for audio properties bits 29-28 */ #define CX2341X_AUDIO_ENCODING_METHOD_MPEG 0 #define CX2341X_AUDIO_ENCODING_METHOD_AC3 1 #define CX2341X_AUDIO_ENCODING_METHOD_LPCM 2 static const char *cx2341x_get_name(u32 id) { switch (id) { case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: return "Spatial Filter Mode"; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: return "Spatial Filter"; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: return "Spatial Luma Filter Type"; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: return "Spatial Chroma Filter Type"; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: return "Temporal Filter Mode"; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER: return "Temporal Filter"; case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: return "Median Filter Type"; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: return "Median Luma Filter Maximum"; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM: return "Median Luma Filter Minimum"; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP: return "Median Chroma Filter Maximum"; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM: return "Median Chroma Filter Minimum"; case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: return "Insert Navigation Packets"; } return NULL; } static const char **cx2341x_get_menu(u32 id) { static const char *cx2341x_video_spatial_filter_mode_menu[] = { "Manual", "Auto", NULL }; static const char *cx2341x_video_luma_spatial_filter_type_menu[] = { "Off", "1D Horizontal", "1D Vertical", "2D H/V Separable", "2D Symmetric non-separable", NULL }; static const char *cx2341x_video_chroma_spatial_filter_type_menu[] = { "Off", "1D Horizontal", NULL }; static const char *cx2341x_video_temporal_filter_mode_menu[] = { "Manual", "Auto", NULL }; static const char *cx2341x_video_median_filter_type_menu[] = { "Off", "Horizontal", "Vertical", "Horizontal/Vertical", "Diagonal", NULL }; switch (id) { case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: return cx2341x_video_spatial_filter_mode_menu; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: return cx2341x_video_luma_spatial_filter_type_menu; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: return cx2341x_video_chroma_spatial_filter_type_menu; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: return cx2341x_video_temporal_filter_mode_menu; case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: return cx2341x_video_median_filter_type_menu; } return NULL; } static void cx2341x_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, s32 *min, s32 *max, s32 *step, s32 *def, u32 *flags) { *name = cx2341x_get_name(id); *flags = 0; switch (id) { case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: *type = V4L2_CTRL_TYPE_MENU; *min = 0; *step = 0; break; case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: *type = V4L2_CTRL_TYPE_BOOLEAN; *min = 0; *max = *step = 1; break; default: *type = V4L2_CTRL_TYPE_INTEGER; break; } switch (id) { case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: *flags |= V4L2_CTRL_FLAG_UPDATE; break; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM: *flags |= V4L2_CTRL_FLAG_SLIDER; break; case V4L2_CID_MPEG_VIDEO_ENCODING: *flags |= V4L2_CTRL_FLAG_READ_ONLY; break; } } /********************** OLD CODE *********************/ /* Must be sorted from low to high control ID! */ const u32 cx2341x_mpeg_ctrls[] = { V4L2_CID_CODEC_CLASS, V4L2_CID_MPEG_STREAM_TYPE, V4L2_CID_MPEG_STREAM_VBI_FMT, V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ, V4L2_CID_MPEG_AUDIO_ENCODING, V4L2_CID_MPEG_AUDIO_L2_BITRATE, V4L2_CID_MPEG_AUDIO_MODE, V4L2_CID_MPEG_AUDIO_MODE_EXTENSION, V4L2_CID_MPEG_AUDIO_EMPHASIS, V4L2_CID_MPEG_AUDIO_CRC, V4L2_CID_MPEG_AUDIO_MUTE, V4L2_CID_MPEG_AUDIO_AC3_BITRATE, V4L2_CID_MPEG_VIDEO_ENCODING, V4L2_CID_MPEG_VIDEO_ASPECT, V4L2_CID_MPEG_VIDEO_B_FRAMES, V4L2_CID_MPEG_VIDEO_GOP_SIZE, V4L2_CID_MPEG_VIDEO_GOP_CLOSURE, V4L2_CID_MPEG_VIDEO_BITRATE_MODE, V4L2_CID_MPEG_VIDEO_BITRATE, V4L2_CID_MPEG_VIDEO_BITRATE_PEAK, V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION, V4L2_CID_MPEG_VIDEO_MUTE, V4L2_CID_MPEG_VIDEO_MUTE_YUV, V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE, V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE, V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE, V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER, V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP, V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS, 0 }; EXPORT_SYMBOL(cx2341x_mpeg_ctrls); static const struct cx2341x_mpeg_params default_params = { /* misc */ .capabilities = 0, .port = CX2341X_PORT_MEMORY, .width = 720, .height = 480, .is_50hz = 0, /* stream */ .stream_type = V4L2_MPEG_STREAM_TYPE_MPEG2_PS, .stream_vbi_fmt = V4L2_MPEG_STREAM_VBI_FMT_NONE, .stream_insert_nav_packets = 0, /* audio */ .audio_sampling_freq = V4L2_MPEG_AUDIO_SAMPLING_FREQ_48000, .audio_encoding = V4L2_MPEG_AUDIO_ENCODING_LAYER_2, .audio_l2_bitrate = V4L2_MPEG_AUDIO_L2_BITRATE_224K, .audio_ac3_bitrate = V4L2_MPEG_AUDIO_AC3_BITRATE_224K, .audio_mode = V4L2_MPEG_AUDIO_MODE_STEREO, .audio_mode_extension = V4L2_MPEG_AUDIO_MODE_EXTENSION_BOUND_4, .audio_emphasis = V4L2_MPEG_AUDIO_EMPHASIS_NONE, .audio_crc = V4L2_MPEG_AUDIO_CRC_NONE, .audio_mute = 0, /* video */ .video_encoding = V4L2_MPEG_VIDEO_ENCODING_MPEG_2, .video_aspect = V4L2_MPEG_VIDEO_ASPECT_4x3, .video_b_frames = 2, .video_gop_size = 12, .video_gop_closure = 1, .video_bitrate_mode = V4L2_MPEG_VIDEO_BITRATE_MODE_VBR, .video_bitrate = 6000000, .video_bitrate_peak = 8000000, .video_temporal_decimation = 0, .video_mute = 0, .video_mute_yuv = 0x008080, /* YCbCr value for black */ /* encoding filters */ .video_spatial_filter_mode = V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_MANUAL, .video_spatial_filter = 0, .video_luma_spatial_filter_type = V4L2_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE_1D_HOR, .video_chroma_spatial_filter_type = V4L2_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE_1D_HOR, .video_temporal_filter_mode = V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_MANUAL, .video_temporal_filter = 8, .video_median_filter_type = V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF, .video_luma_median_filter_top = 255, .video_luma_median_filter_bottom = 0, .video_chroma_median_filter_top = 255, .video_chroma_median_filter_bottom = 0, }; /* Map the control ID to the correct field in the cx2341x_mpeg_params struct. Return -EINVAL if the ID is unknown, else return 0. */ static int cx2341x_get_ctrl(const struct cx2341x_mpeg_params *params, struct v4l2_ext_control *ctrl) { switch (ctrl->id) { case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ: ctrl->value = params->audio_sampling_freq; break; case V4L2_CID_MPEG_AUDIO_ENCODING: ctrl->value = params->audio_encoding; break; case V4L2_CID_MPEG_AUDIO_L2_BITRATE: ctrl->value = params->audio_l2_bitrate; break; case V4L2_CID_MPEG_AUDIO_AC3_BITRATE: ctrl->value = params->audio_ac3_bitrate; break; case V4L2_CID_MPEG_AUDIO_MODE: ctrl->value = params->audio_mode; break; case V4L2_CID_MPEG_AUDIO_MODE_EXTENSION: ctrl->value = params->audio_mode_extension; break; case V4L2_CID_MPEG_AUDIO_EMPHASIS: ctrl->value = params->audio_emphasis; break; case V4L2_CID_MPEG_AUDIO_CRC: ctrl->value = params->audio_crc; break; case V4L2_CID_MPEG_AUDIO_MUTE: ctrl->value = params->audio_mute; break; case V4L2_CID_MPEG_VIDEO_ENCODING: ctrl->value = params->video_encoding; break; case V4L2_CID_MPEG_VIDEO_ASPECT: ctrl->value = params->video_aspect; break; case V4L2_CID_MPEG_VIDEO_B_FRAMES: ctrl->value = params->video_b_frames; break; case V4L2_CID_MPEG_VIDEO_GOP_SIZE: ctrl->value = params->video_gop_size; break; case V4L2_CID_MPEG_VIDEO_GOP_CLOSURE: ctrl->value = params->video_gop_closure; break; case V4L2_CID_MPEG_VIDEO_BITRATE_MODE: ctrl->value = params->video_bitrate_mode; break; case V4L2_CID_MPEG_VIDEO_BITRATE: ctrl->value = params->video_bitrate; break; case V4L2_CID_MPEG_VIDEO_BITRATE_PEAK: ctrl->value = params->video_bitrate_peak; break; case V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION: ctrl->value = params->video_temporal_decimation; break; case V4L2_CID_MPEG_VIDEO_MUTE: ctrl->value = params->video_mute; break; case V4L2_CID_MPEG_VIDEO_MUTE_YUV: ctrl->value = params->video_mute_yuv; break; case V4L2_CID_MPEG_STREAM_TYPE: ctrl->value = params->stream_type; break; case V4L2_CID_MPEG_STREAM_VBI_FMT: ctrl->value = params->stream_vbi_fmt; break; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: ctrl->value = params->video_spatial_filter_mode; break; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: ctrl->value = params->video_spatial_filter; break; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: ctrl->value = params->video_luma_spatial_filter_type; break; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: ctrl->value = params->video_chroma_spatial_filter_type; break; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: ctrl->value = params->video_temporal_filter_mode; break; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER: ctrl->value = params->video_temporal_filter; break; case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: ctrl->value = params->video_median_filter_type; break; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: ctrl->value = params->video_luma_median_filter_top; break; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM: ctrl->value = params->video_luma_median_filter_bottom; break; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP: ctrl->value = params->video_chroma_median_filter_top; break; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM: ctrl->value = params->video_chroma_median_filter_bottom; break; case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: ctrl->value = params->stream_insert_nav_packets; break; default: return -EINVAL; } return 0; } /* Map the control ID to the correct field in the cx2341x_mpeg_params struct. Return -EINVAL if the ID is unknown, else return 0. */ static int cx2341x_set_ctrl(struct cx2341x_mpeg_params *params, int busy, struct v4l2_ext_control *ctrl) { switch (ctrl->id) { case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ: if (busy) return -EBUSY; params->audio_sampling_freq = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_ENCODING: if (busy) return -EBUSY; if (params->capabilities & CX2341X_CAP_HAS_AC3) if (ctrl->value != V4L2_MPEG_AUDIO_ENCODING_LAYER_2 && ctrl->value != V4L2_MPEG_AUDIO_ENCODING_AC3) return -ERANGE; params->audio_encoding = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_L2_BITRATE: if (busy) return -EBUSY; params->audio_l2_bitrate = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_AC3_BITRATE: if (busy) return -EBUSY; if (!(params->capabilities & CX2341X_CAP_HAS_AC3)) return -EINVAL; params->audio_ac3_bitrate = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_MODE: params->audio_mode = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_MODE_EXTENSION: params->audio_mode_extension = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_EMPHASIS: params->audio_emphasis = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_CRC: params->audio_crc = ctrl->value; break; case V4L2_CID_MPEG_AUDIO_MUTE: params->audio_mute = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_ASPECT: params->video_aspect = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_B_FRAMES: { int b = ctrl->value + 1; int gop = params->video_gop_size; params->video_b_frames = ctrl->value; params->video_gop_size = b * ((gop + b - 1) / b); /* Max GOP size = 34 */ while (params->video_gop_size > 34) params->video_gop_size -= b; break; } case V4L2_CID_MPEG_VIDEO_GOP_SIZE: { int b = params->video_b_frames + 1; int gop = ctrl->value; params->video_gop_size = b * ((gop + b - 1) / b); /* Max GOP size = 34 */ while (params->video_gop_size > 34) params->video_gop_size -= b; ctrl->value = params->video_gop_size; break; } case V4L2_CID_MPEG_VIDEO_GOP_CLOSURE: params->video_gop_closure = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_BITRATE_MODE: if (busy) return -EBUSY; /* MPEG-1 only allows CBR */ if (params->video_encoding == V4L2_MPEG_VIDEO_ENCODING_MPEG_1 && ctrl->value != V4L2_MPEG_VIDEO_BITRATE_MODE_CBR) return -EINVAL; params->video_bitrate_mode = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_BITRATE: if (busy) return -EBUSY; params->video_bitrate = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_BITRATE_PEAK: if (busy) return -EBUSY; params->video_bitrate_peak = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION: params->video_temporal_decimation = ctrl->value; break; case V4L2_CID_MPEG_VIDEO_MUTE: params->video_mute = (ctrl->value != 0); break; case V4L2_CID_MPEG_VIDEO_MUTE_YUV: params->video_mute_yuv = ctrl->value; break; case V4L2_CID_MPEG_STREAM_TYPE: if (busy) return -EBUSY; params->stream_type = ctrl->value; params->video_encoding = (params->stream_type == V4L2_MPEG_STREAM_TYPE_MPEG1_SS || params->stream_type == V4L2_MPEG_STREAM_TYPE_MPEG1_VCD) ? V4L2_MPEG_VIDEO_ENCODING_MPEG_1 : V4L2_MPEG_VIDEO_ENCODING_MPEG_2; if (params->video_encoding == V4L2_MPEG_VIDEO_ENCODING_MPEG_1) /* MPEG-1 implies CBR */ params->video_bitrate_mode = V4L2_MPEG_VIDEO_BITRATE_MODE_CBR; break; case V4L2_CID_MPEG_STREAM_VBI_FMT: params->stream_vbi_fmt = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: params->video_spatial_filter_mode = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: params->video_spatial_filter = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: params->video_luma_spatial_filter_type = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: params->video_chroma_spatial_filter_type = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: params->video_temporal_filter_mode = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER: params->video_temporal_filter = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: params->video_median_filter_type = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: params->video_luma_median_filter_top = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM: params->video_luma_median_filter_bottom = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP: params->video_chroma_median_filter_top = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM: params->video_chroma_median_filter_bottom = ctrl->value; break; case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: params->stream_insert_nav_packets = ctrl->value; break; default: return -EINVAL; } return 0; } static int cx2341x_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def) { const char *name; switch (qctrl->id) { /* MPEG controls */ case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER: case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM: case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: cx2341x_ctrl_fill(qctrl->id, &name, &qctrl->type, &min, &max, &step, &def, &qctrl->flags); qctrl->minimum = min; qctrl->maximum = max; qctrl->step = step; qctrl->default_value = def; qctrl->reserved[0] = qctrl->reserved[1] = 0; strscpy(qctrl->name, name, sizeof(qctrl->name)); return 0; default: return v4l2_ctrl_query_fill(qctrl, min, max, step, def); } } int cx2341x_ctrl_query(const struct cx2341x_mpeg_params *params, struct v4l2_queryctrl *qctrl) { int err; switch (qctrl->id) { case V4L2_CID_CODEC_CLASS: return v4l2_ctrl_query_fill(qctrl, 0, 0, 0, 0); case V4L2_CID_MPEG_STREAM_TYPE: return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_STREAM_TYPE_MPEG2_PS, V4L2_MPEG_STREAM_TYPE_MPEG2_SVCD, 1, V4L2_MPEG_STREAM_TYPE_MPEG2_PS); case V4L2_CID_MPEG_STREAM_VBI_FMT: if (params->capabilities & CX2341X_CAP_HAS_SLICED_VBI) return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_STREAM_VBI_FMT_NONE, V4L2_MPEG_STREAM_VBI_FMT_IVTV, 1, V4L2_MPEG_STREAM_VBI_FMT_NONE); return cx2341x_ctrl_query_fill(qctrl, V4L2_MPEG_STREAM_VBI_FMT_NONE, V4L2_MPEG_STREAM_VBI_FMT_NONE, 1, default_params.stream_vbi_fmt); case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ: return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_SAMPLING_FREQ_44100, V4L2_MPEG_AUDIO_SAMPLING_FREQ_32000, 1, V4L2_MPEG_AUDIO_SAMPLING_FREQ_48000); case V4L2_CID_MPEG_AUDIO_ENCODING: if (params->capabilities & CX2341X_CAP_HAS_AC3) { /* * The state of L2 & AC3 bitrate controls can change * when this control changes, but v4l2_ctrl_query_fill() * already sets V4L2_CTRL_FLAG_UPDATE for * V4L2_CID_MPEG_AUDIO_ENCODING, so we don't here. */ return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_ENCODING_LAYER_2, V4L2_MPEG_AUDIO_ENCODING_AC3, 1, default_params.audio_encoding); } return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_ENCODING_LAYER_2, V4L2_MPEG_AUDIO_ENCODING_LAYER_2, 1, default_params.audio_encoding); case V4L2_CID_MPEG_AUDIO_L2_BITRATE: err = v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_L2_BITRATE_192K, V4L2_MPEG_AUDIO_L2_BITRATE_384K, 1, default_params.audio_l2_bitrate); if (err) return err; if (params->capabilities & CX2341X_CAP_HAS_AC3 && params->audio_encoding != V4L2_MPEG_AUDIO_ENCODING_LAYER_2) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_AUDIO_MODE: return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_MODE_STEREO, V4L2_MPEG_AUDIO_MODE_MONO, 1, V4L2_MPEG_AUDIO_MODE_STEREO); case V4L2_CID_MPEG_AUDIO_MODE_EXTENSION: err = v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_MODE_EXTENSION_BOUND_4, V4L2_MPEG_AUDIO_MODE_EXTENSION_BOUND_16, 1, V4L2_MPEG_AUDIO_MODE_EXTENSION_BOUND_4); if (err == 0 && params->audio_mode != V4L2_MPEG_AUDIO_MODE_JOINT_STEREO) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return err; case V4L2_CID_MPEG_AUDIO_EMPHASIS: return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_EMPHASIS_NONE, V4L2_MPEG_AUDIO_EMPHASIS_CCITT_J17, 1, V4L2_MPEG_AUDIO_EMPHASIS_NONE); case V4L2_CID_MPEG_AUDIO_CRC: return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_CRC_NONE, V4L2_MPEG_AUDIO_CRC_CRC16, 1, V4L2_MPEG_AUDIO_CRC_NONE); case V4L2_CID_MPEG_AUDIO_MUTE: return v4l2_ctrl_query_fill(qctrl, 0, 1, 1, 0); case V4L2_CID_MPEG_AUDIO_AC3_BITRATE: err = v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_AUDIO_AC3_BITRATE_48K, V4L2_MPEG_AUDIO_AC3_BITRATE_448K, 1, default_params.audio_ac3_bitrate); if (err) return err; if (params->capabilities & CX2341X_CAP_HAS_AC3) { if (params->audio_encoding != V4L2_MPEG_AUDIO_ENCODING_AC3) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; } else qctrl->flags |= V4L2_CTRL_FLAG_DISABLED; return 0; case V4L2_CID_MPEG_VIDEO_ENCODING: /* this setting is read-only for the cx2341x since the V4L2_CID_MPEG_STREAM_TYPE really determines the MPEG-1/2 setting */ err = v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_VIDEO_ENCODING_MPEG_1, V4L2_MPEG_VIDEO_ENCODING_MPEG_2, 1, V4L2_MPEG_VIDEO_ENCODING_MPEG_2); if (err == 0) qctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY; return err; case V4L2_CID_MPEG_VIDEO_ASPECT: return v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_VIDEO_ASPECT_1x1, V4L2_MPEG_VIDEO_ASPECT_221x100, 1, V4L2_MPEG_VIDEO_ASPECT_4x3); case V4L2_CID_MPEG_VIDEO_B_FRAMES: return v4l2_ctrl_query_fill(qctrl, 0, 33, 1, 2); case V4L2_CID_MPEG_VIDEO_GOP_SIZE: return v4l2_ctrl_query_fill(qctrl, 1, 34, 1, params->is_50hz ? 12 : 15); case V4L2_CID_MPEG_VIDEO_GOP_CLOSURE: return v4l2_ctrl_query_fill(qctrl, 0, 1, 1, 1); case V4L2_CID_MPEG_VIDEO_BITRATE_MODE: err = v4l2_ctrl_query_fill(qctrl, V4L2_MPEG_VIDEO_BITRATE_MODE_VBR, V4L2_MPEG_VIDEO_BITRATE_MODE_CBR, 1, V4L2_MPEG_VIDEO_BITRATE_MODE_VBR); if (err == 0 && params->video_encoding == V4L2_MPEG_VIDEO_ENCODING_MPEG_1) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return err; case V4L2_CID_MPEG_VIDEO_BITRATE: return v4l2_ctrl_query_fill(qctrl, 0, 27000000, 1, 6000000); case V4L2_CID_MPEG_VIDEO_BITRATE_PEAK: err = v4l2_ctrl_query_fill(qctrl, 0, 27000000, 1, 8000000); if (err == 0 && params->video_bitrate_mode == V4L2_MPEG_VIDEO_BITRATE_MODE_CBR) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return err; case V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION: return v4l2_ctrl_query_fill(qctrl, 0, 255, 1, 0); case V4L2_CID_MPEG_VIDEO_MUTE: return v4l2_ctrl_query_fill(qctrl, 0, 1, 1, 0); case V4L2_CID_MPEG_VIDEO_MUTE_YUV: /* Init YUV (really YCbCr) to black */ return v4l2_ctrl_query_fill(qctrl, 0, 0xffffff, 1, 0x008080); /* CX23415/6 specific */ case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: return cx2341x_ctrl_query_fill(qctrl, V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_MANUAL, V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_AUTO, 1, default_params.video_spatial_filter_mode); case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: cx2341x_ctrl_query_fill(qctrl, 0, 15, 1, default_params.video_spatial_filter); qctrl->flags |= V4L2_CTRL_FLAG_SLIDER; if (params->video_spatial_filter_mode == V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_AUTO) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: cx2341x_ctrl_query_fill(qctrl, V4L2_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE_OFF, V4L2_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE_2D_SYM_NON_SEPARABLE, 1, default_params.video_luma_spatial_filter_type); if (params->video_spatial_filter_mode == V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_AUTO) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: cx2341x_ctrl_query_fill(qctrl, V4L2_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE_OFF, V4L2_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE_1D_HOR, 1, default_params.video_chroma_spatial_filter_type); if (params->video_spatial_filter_mode == V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_AUTO) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: return cx2341x_ctrl_query_fill(qctrl, V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_MANUAL, V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_AUTO, 1, default_params.video_temporal_filter_mode); case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER: cx2341x_ctrl_query_fill(qctrl, 0, 31, 1, default_params.video_temporal_filter); qctrl->flags |= V4L2_CTRL_FLAG_SLIDER; if (params->video_temporal_filter_mode == V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_AUTO) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: return cx2341x_ctrl_query_fill(qctrl, V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF, V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_DIAG, 1, default_params.video_median_filter_type); case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: cx2341x_ctrl_query_fill(qctrl, 0, 255, 1, default_params.video_luma_median_filter_top); qctrl->flags |= V4L2_CTRL_FLAG_SLIDER; if (params->video_median_filter_type == V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM: cx2341x_ctrl_query_fill(qctrl, 0, 255, 1, default_params.video_luma_median_filter_bottom); qctrl->flags |= V4L2_CTRL_FLAG_SLIDER; if (params->video_median_filter_type == V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP: cx2341x_ctrl_query_fill(qctrl, 0, 255, 1, default_params.video_chroma_median_filter_top); qctrl->flags |= V4L2_CTRL_FLAG_SLIDER; if (params->video_median_filter_type == V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM: cx2341x_ctrl_query_fill(qctrl, 0, 255, 1, default_params.video_chroma_median_filter_bottom); qctrl->flags |= V4L2_CTRL_FLAG_SLIDER; if (params->video_median_filter_type == V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF) qctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; return 0; case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: return cx2341x_ctrl_query_fill(qctrl, 0, 1, 1, default_params.stream_insert_nav_packets); default: return -EINVAL; } } EXPORT_SYMBOL(cx2341x_ctrl_query); const char * const *cx2341x_ctrl_get_menu(const struct cx2341x_mpeg_params *p, u32 id) { static const char * const mpeg_stream_type_without_ts[] = { "MPEG-2 Program Stream", "", "MPEG-1 System Stream", "MPEG-2 DVD-compatible Stream", "MPEG-1 VCD-compatible Stream", "MPEG-2 SVCD-compatible Stream", NULL }; static const char *mpeg_stream_type_with_ts[] = { "MPEG-2 Program Stream", "MPEG-2 Transport Stream", "MPEG-1 System Stream", "MPEG-2 DVD-compatible Stream", "MPEG-1 VCD-compatible Stream", "MPEG-2 SVCD-compatible Stream", NULL }; static const char *mpeg_audio_encoding_l2_ac3[] = { "", "MPEG-1/2 Layer II", "", "", "AC-3", NULL }; switch (id) { case V4L2_CID_MPEG_STREAM_TYPE: return (p->capabilities & CX2341X_CAP_HAS_TS) ? mpeg_stream_type_with_ts : mpeg_stream_type_without_ts; case V4L2_CID_MPEG_AUDIO_ENCODING: return (p->capabilities & CX2341X_CAP_HAS_AC3) ? mpeg_audio_encoding_l2_ac3 : v4l2_ctrl_get_menu(id); case V4L2_CID_MPEG_AUDIO_L1_BITRATE: case V4L2_CID_MPEG_AUDIO_L3_BITRATE: return NULL; case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE: case V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE: case V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE: return cx2341x_get_menu(id); default: return v4l2_ctrl_get_menu(id); } } EXPORT_SYMBOL(cx2341x_ctrl_get_menu); static void cx2341x_calc_audio_properties(struct cx2341x_mpeg_params *params) { params->audio_properties = (params->audio_sampling_freq << 0) | (params->audio_mode << 8) | (params->audio_mode_extension << 10) | (((params->audio_emphasis == V4L2_MPEG_AUDIO_EMPHASIS_CCITT_J17) ? 3 : params->audio_emphasis) << 12) | (params->audio_crc << 14); if ((params->capabilities & CX2341X_CAP_HAS_AC3) && params->audio_encoding == V4L2_MPEG_AUDIO_ENCODING_AC3) { params->audio_properties |= /* Not sure if this MPEG Layer II setting is required */ ((3 - V4L2_MPEG_AUDIO_ENCODING_LAYER_2) << 2) | (params->audio_ac3_bitrate << 4) | (CX2341X_AUDIO_ENCODING_METHOD_AC3 << 28); } else { /* Assuming MPEG Layer II */ params->audio_properties |= ((3 - params->audio_encoding) << 2) | ((1 + params->audio_l2_bitrate) << 4); } } /* Check for correctness of the ctrl's value based on the data from struct v4l2_queryctrl and the available menu items. Note that menu_items may be NULL, in that case it is ignored. */ static int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl, const char * const *menu_items) { if (qctrl->flags & V4L2_CTRL_FLAG_DISABLED) return -EINVAL; if (qctrl->flags & V4L2_CTRL_FLAG_GRABBED) return -EBUSY; if (qctrl->type == V4L2_CTRL_TYPE_STRING) return 0; if (qctrl->type == V4L2_CTRL_TYPE_BUTTON || qctrl->type == V4L2_CTRL_TYPE_INTEGER64 || qctrl->type == V4L2_CTRL_TYPE_CTRL_CLASS) return 0; if (ctrl->value < qctrl->minimum || ctrl->value > qctrl->maximum) return -ERANGE; if (qctrl->type == V4L2_CTRL_TYPE_MENU && menu_items != NULL) { if (menu_items[ctrl->value] == NULL || menu_items[ctrl->value][0] == '\0') return -EINVAL; } if (qctrl->type == V4L2_CTRL_TYPE_BITMASK && (ctrl->value & ~qctrl->maximum)) return -ERANGE; return 0; } int cx2341x_ext_ctrls(struct cx2341x_mpeg_params *params, int busy, struct v4l2_ext_controls *ctrls, unsigned int cmd) { int err = 0; int i; if (cmd == VIDIOC_G_EXT_CTRLS) { for (i = 0; i < ctrls->count; i++) { struct v4l2_ext_control *ctrl = ctrls->controls + i; err = cx2341x_get_ctrl(params, ctrl); if (err) { ctrls->error_idx = i; break; } } return err; } for (i = 0; i < ctrls->count; i++) { struct v4l2_ext_control *ctrl = ctrls->controls + i; struct v4l2_queryctrl qctrl; const char * const *menu_items = NULL; qctrl.id = ctrl->id; err = cx2341x_ctrl_query(params, &qctrl); if (err) break; if (qctrl.type == V4L2_CTRL_TYPE_MENU) menu_items = cx2341x_ctrl_get_menu(params, qctrl.id); err = v4l2_ctrl_check(ctrl, &qctrl, menu_items); if (err) break; err = cx2341x_set_ctrl(params, busy, ctrl); if (err) break; } if (err == 0 && params->video_bitrate_mode == V4L2_MPEG_VIDEO_BITRATE_MODE_VBR && params->video_bitrate_peak < params->video_bitrate) { err = -ERANGE; ctrls->error_idx = ctrls->count; } if (err) ctrls->error_idx = i; else cx2341x_calc_audio_properties(params); return err; } EXPORT_SYMBOL(cx2341x_ext_ctrls); void cx2341x_fill_defaults(struct cx2341x_mpeg_params *p) { *p = default_params; cx2341x_calc_audio_properties(p); } EXPORT_SYMBOL(cx2341x_fill_defaults); static int cx2341x_api(void *priv, cx2341x_mbox_func func, u32 cmd, int args, ...) { u32 data[CX2341X_MBOX_MAX_DATA]; va_list vargs; int i; va_start(vargs, args); for (i = 0; i < args; i++) data[i] = va_arg(vargs, int); va_end(vargs); return func(priv, cmd, args, 0, data); } #define CMP_FIELD(__old, __new, __field) (__old->__field != __new->__field) int cx2341x_update(void *priv, cx2341x_mbox_func func, const struct cx2341x_mpeg_params *old, const struct cx2341x_mpeg_params *new) { static int mpeg_stream_type[] = { 0, /* MPEG-2 PS */ 1, /* MPEG-2 TS */ 2, /* MPEG-1 SS */ 14, /* DVD */ 11, /* VCD */ 12, /* SVCD */ }; int err; cx2341x_api(priv, func, CX2341X_ENC_SET_OUTPUT_PORT, 2, new->port, 0); if (!old || CMP_FIELD(old, new, is_50hz)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_FRAME_RATE, 1, new->is_50hz); if (err) return err; } if (!old || CMP_FIELD(old, new, width) || CMP_FIELD(old, new, height) || CMP_FIELD(old, new, video_encoding)) { u16 w = new->width; u16 h = new->height; if (new->video_encoding == V4L2_MPEG_VIDEO_ENCODING_MPEG_1) { w /= 2; h /= 2; } err = cx2341x_api(priv, func, CX2341X_ENC_SET_FRAME_SIZE, 2, h, w); if (err) return err; } if (!old || CMP_FIELD(old, new, stream_type)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_STREAM_TYPE, 1, mpeg_stream_type[new->stream_type]); if (err) return err; } if (!old || CMP_FIELD(old, new, video_aspect)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_ASPECT_RATIO, 1, 1 + new->video_aspect); if (err) return err; } if (!old || CMP_FIELD(old, new, video_b_frames) || CMP_FIELD(old, new, video_gop_size)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_GOP_PROPERTIES, 2, new->video_gop_size, new->video_b_frames + 1); if (err) return err; } if (!old || CMP_FIELD(old, new, video_gop_closure)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_GOP_CLOSURE, 1, new->video_gop_closure); if (err) return err; } if (!old || CMP_FIELD(old, new, audio_properties)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_AUDIO_PROPERTIES, 1, new->audio_properties); if (err) return err; } if (!old || CMP_FIELD(old, new, audio_mute)) { err = cx2341x_api(priv, func, CX2341X_ENC_MUTE_AUDIO, 1, new->audio_mute); if (err) return err; } if (!old || CMP_FIELD(old, new, video_bitrate_mode) || CMP_FIELD(old, new, video_bitrate) || CMP_FIELD(old, new, video_bitrate_peak)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_BIT_RATE, 5, new->video_bitrate_mode, new->video_bitrate, new->video_bitrate_peak / 400, 0, 0); if (err) return err; } if (!old || CMP_FIELD(old, new, video_spatial_filter_mode) || CMP_FIELD(old, new, video_temporal_filter_mode) || CMP_FIELD(old, new, video_median_filter_type)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_DNR_FILTER_MODE, 2, new->video_spatial_filter_mode | (new->video_temporal_filter_mode << 1), new->video_median_filter_type); if (err) return err; } if (!old || CMP_FIELD(old, new, video_luma_median_filter_bottom) || CMP_FIELD(old, new, video_luma_median_filter_top) || CMP_FIELD(old, new, video_chroma_median_filter_bottom) || CMP_FIELD(old, new, video_chroma_median_filter_top)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_CORING_LEVELS, 4, new->video_luma_median_filter_bottom, new->video_luma_median_filter_top, new->video_chroma_median_filter_bottom, new->video_chroma_median_filter_top); if (err) return err; } if (!old || CMP_FIELD(old, new, video_luma_spatial_filter_type) || CMP_FIELD(old, new, video_chroma_spatial_filter_type)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_SPATIAL_FILTER_TYPE, 2, new->video_luma_spatial_filter_type, new->video_chroma_spatial_filter_type); if (err) return err; } if (!old || CMP_FIELD(old, new, video_spatial_filter) || CMP_FIELD(old, new, video_temporal_filter)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_DNR_FILTER_PROPS, 2, new->video_spatial_filter, new->video_temporal_filter); if (err) return err; } if (!old || CMP_FIELD(old, new, video_temporal_decimation)) { err = cx2341x_api(priv, func, CX2341X_ENC_SET_FRAME_DROP_RATE, 1, new->video_temporal_decimation); if (err) return err; } if (!old || CMP_FIELD(old, new, video_mute) || (new->video_mute && CMP_FIELD(old, new, video_mute_yuv))) { err = cx2341x_api(priv, func, CX2341X_ENC_MUTE_VIDEO, 1, new->video_mute | (new->video_mute_yuv << 8)); if (err) return err; } if (!old || CMP_FIELD(old, new, stream_insert_nav_packets)) { err = cx2341x_api(priv, func, CX2341X_ENC_MISC, 2, 7, new->stream_insert_nav_packets); if (err) return err; } return 0; } EXPORT_SYMBOL(cx2341x_update); static const char *cx2341x_menu_item(const struct cx2341x_mpeg_params *p, u32 id) { const char * const *menu = cx2341x_ctrl_get_menu(p, id); struct v4l2_ext_control ctrl; if (menu == NULL) goto invalid; ctrl.id = id; if (cx2341x_get_ctrl(p, &ctrl)) goto invalid; while (ctrl.value-- && *menu) menu++; if (*menu == NULL) goto invalid; return *menu; invalid: return "<invalid>"; } void cx2341x_log_status(const struct cx2341x_mpeg_params *p, const char *prefix) { int is_mpeg1 = p->video_encoding == V4L2_MPEG_VIDEO_ENCODING_MPEG_1; /* Stream */ printk(KERN_INFO "%s: Stream: %s", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_STREAM_TYPE)); if (p->stream_insert_nav_packets) printk(KERN_CONT " (with navigation packets)"); printk(KERN_CONT "\n"); printk(KERN_INFO "%s: VBI Format: %s\n", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_STREAM_VBI_FMT)); /* Video */ printk(KERN_INFO "%s: Video: %dx%d, %d fps%s\n", prefix, p->width / (is_mpeg1 ? 2 : 1), p->height / (is_mpeg1 ? 2 : 1), p->is_50hz ? 25 : 30, (p->video_mute) ? " (muted)" : ""); printk(KERN_INFO "%s: Video: %s, %s, %s, %d", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_VIDEO_ENCODING), cx2341x_menu_item(p, V4L2_CID_MPEG_VIDEO_ASPECT), cx2341x_menu_item(p, V4L2_CID_MPEG_VIDEO_BITRATE_MODE), p->video_bitrate); if (p->video_bitrate_mode == V4L2_MPEG_VIDEO_BITRATE_MODE_VBR) printk(KERN_CONT ", Peak %d", p->video_bitrate_peak); printk(KERN_CONT "\n"); printk(KERN_INFO "%s: Video: GOP Size %d, %d B-Frames, %sGOP Closure\n", prefix, p->video_gop_size, p->video_b_frames, p->video_gop_closure ? "" : "No "); if (p->video_temporal_decimation) printk(KERN_INFO "%s: Video: Temporal Decimation %d\n", prefix, p->video_temporal_decimation); /* Audio */ printk(KERN_INFO "%s: Audio: %s, %s, %s, %s%s", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ), cx2341x_menu_item(p, V4L2_CID_MPEG_AUDIO_ENCODING), cx2341x_menu_item(p, p->audio_encoding == V4L2_MPEG_AUDIO_ENCODING_AC3 ? V4L2_CID_MPEG_AUDIO_AC3_BITRATE : V4L2_CID_MPEG_AUDIO_L2_BITRATE), cx2341x_menu_item(p, V4L2_CID_MPEG_AUDIO_MODE), p->audio_mute ? " (muted)" : ""); if (p->audio_mode == V4L2_MPEG_AUDIO_MODE_JOINT_STEREO) printk(KERN_CONT ", %s", cx2341x_menu_item(p, V4L2_CID_MPEG_AUDIO_MODE_EXTENSION)); printk(KERN_CONT ", %s, %s\n", cx2341x_menu_item(p, V4L2_CID_MPEG_AUDIO_EMPHASIS), cx2341x_menu_item(p, V4L2_CID_MPEG_AUDIO_CRC)); /* Encoding filters */ printk(KERN_INFO "%s: Spatial Filter: %s, Luma %s, Chroma %s, %d\n", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE), cx2341x_menu_item(p, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE), cx2341x_menu_item(p, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE), p->video_spatial_filter); printk(KERN_INFO "%s: Temporal Filter: %s, %d\n", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE), p->video_temporal_filter); printk(KERN_INFO "%s: Median Filter: %s, Luma [%d, %d], Chroma [%d, %d]\n", prefix, cx2341x_menu_item(p, V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE), p->video_luma_median_filter_bottom, p->video_luma_median_filter_top, p->video_chroma_median_filter_bottom, p->video_chroma_median_filter_top); } EXPORT_SYMBOL(cx2341x_log_status); /********************** NEW CODE *********************/ static inline struct cx2341x_handler *to_cxhdl(struct v4l2_ctrl *ctrl) { return container_of(ctrl->handler, struct cx2341x_handler, hdl); } static int cx2341x_hdl_api(struct cx2341x_handler *hdl, u32 cmd, int args, ...) { u32 data[CX2341X_MBOX_MAX_DATA]; va_list vargs; int i; va_start(vargs, args); for (i = 0; i < args; i++) data[i] = va_arg(vargs, int); va_end(vargs); return hdl->func(hdl->priv, cmd, args, 0, data); } /* ctrl->handler->lock is held, so it is safe to access cur.val */ static inline int cx2341x_neq(struct v4l2_ctrl *ctrl) { return ctrl && ctrl->val != ctrl->cur.val; } static int cx2341x_try_ctrl(struct v4l2_ctrl *ctrl) { struct cx2341x_handler *hdl = to_cxhdl(ctrl); s32 val = ctrl->val; switch (ctrl->id) { case V4L2_CID_MPEG_VIDEO_B_FRAMES: { /* video gop cluster */ int b = val + 1; int gop = hdl->video_gop_size->val; gop = b * ((gop + b - 1) / b); /* Max GOP size = 34 */ while (gop > 34) gop -= b; hdl->video_gop_size->val = gop; break; } case V4L2_CID_MPEG_STREAM_TYPE: /* stream type cluster */ hdl->video_encoding->val = (hdl->stream_type->val == V4L2_MPEG_STREAM_TYPE_MPEG1_SS || hdl->stream_type->val == V4L2_MPEG_STREAM_TYPE_MPEG1_VCD) ? V4L2_MPEG_VIDEO_ENCODING_MPEG_1 : V4L2_MPEG_VIDEO_ENCODING_MPEG_2; if (hdl->video_encoding->val == V4L2_MPEG_VIDEO_ENCODING_MPEG_1) /* MPEG-1 implies CBR */ hdl->video_bitrate_mode->val = V4L2_MPEG_VIDEO_BITRATE_MODE_CBR; /* peak bitrate shall be >= normal bitrate */ if (hdl->video_bitrate_mode->val == V4L2_MPEG_VIDEO_BITRATE_MODE_VBR && hdl->video_bitrate_peak->val < hdl->video_bitrate->val) hdl->video_bitrate_peak->val = hdl->video_bitrate->val; break; } return 0; } static int cx2341x_s_ctrl(struct v4l2_ctrl *ctrl) { static const int mpeg_stream_type[] = { 0, /* MPEG-2 PS */ 1, /* MPEG-2 TS */ 2, /* MPEG-1 SS */ 14, /* DVD */ 11, /* VCD */ 12, /* SVCD */ }; struct cx2341x_handler *hdl = to_cxhdl(ctrl); s32 val = ctrl->val; u32 props; int err; switch (ctrl->id) { case V4L2_CID_MPEG_STREAM_VBI_FMT: if (hdl->ops && hdl->ops->s_stream_vbi_fmt) return hdl->ops->s_stream_vbi_fmt(hdl, val); return 0; case V4L2_CID_MPEG_VIDEO_ASPECT: return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_ASPECT_RATIO, 1, val + 1); case V4L2_CID_MPEG_VIDEO_GOP_CLOSURE: return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_GOP_CLOSURE, 1, val); case V4L2_CID_MPEG_AUDIO_MUTE: return cx2341x_hdl_api(hdl, CX2341X_ENC_MUTE_AUDIO, 1, val); case V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION: return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_FRAME_DROP_RATE, 1, val); case V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS: return cx2341x_hdl_api(hdl, CX2341X_ENC_MISC, 2, 7, val); case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ: /* audio properties cluster */ props = (hdl->audio_sampling_freq->val << 0) | (hdl->audio_mode->val << 8) | (hdl->audio_mode_extension->val << 10) | (hdl->audio_crc->val << 14); if (hdl->audio_emphasis->val == V4L2_MPEG_AUDIO_EMPHASIS_CCITT_J17) props |= 3 << 12; else props |= hdl->audio_emphasis->val << 12; if (hdl->audio_encoding->val == V4L2_MPEG_AUDIO_ENCODING_AC3) { props |= #if 1 /* Not sure if this MPEG Layer II setting is required */ ((3 - V4L2_MPEG_AUDIO_ENCODING_LAYER_2) << 2) | #endif (hdl->audio_ac3_bitrate->val << 4) | (CX2341X_AUDIO_ENCODING_METHOD_AC3 << 28); } else { /* Assuming MPEG Layer II */ props |= ((3 - hdl->audio_encoding->val) << 2) | ((1 + hdl->audio_l2_bitrate->val) << 4); } err = cx2341x_hdl_api(hdl, CX2341X_ENC_SET_AUDIO_PROPERTIES, 1, props); if (err) return err; hdl->audio_properties = props; if (hdl->audio_ac3_bitrate) { int is_ac3 = hdl->audio_encoding->val == V4L2_MPEG_AUDIO_ENCODING_AC3; v4l2_ctrl_activate(hdl->audio_ac3_bitrate, is_ac3); v4l2_ctrl_activate(hdl->audio_l2_bitrate, !is_ac3); } v4l2_ctrl_activate(hdl->audio_mode_extension, hdl->audio_mode->val == V4L2_MPEG_AUDIO_MODE_JOINT_STEREO); if (cx2341x_neq(hdl->audio_sampling_freq) && hdl->ops && hdl->ops->s_audio_sampling_freq) return hdl->ops->s_audio_sampling_freq(hdl, hdl->audio_sampling_freq->val); if (cx2341x_neq(hdl->audio_mode) && hdl->ops && hdl->ops->s_audio_mode) return hdl->ops->s_audio_mode(hdl, hdl->audio_mode->val); return 0; case V4L2_CID_MPEG_VIDEO_B_FRAMES: /* video gop cluster */ return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_GOP_PROPERTIES, 2, hdl->video_gop_size->val, hdl->video_b_frames->val + 1); case V4L2_CID_MPEG_STREAM_TYPE: /* stream type cluster */ err = cx2341x_hdl_api(hdl, CX2341X_ENC_SET_STREAM_TYPE, 1, mpeg_stream_type[val]); if (err) return err; err = cx2341x_hdl_api(hdl, CX2341X_ENC_SET_BIT_RATE, 5, hdl->video_bitrate_mode->val, hdl->video_bitrate->val, hdl->video_bitrate_peak->val / 400, 0, 0); if (err) return err; v4l2_ctrl_activate(hdl->video_bitrate_mode, hdl->video_encoding->val != V4L2_MPEG_VIDEO_ENCODING_MPEG_1); v4l2_ctrl_activate(hdl->video_bitrate_peak, hdl->video_bitrate_mode->val != V4L2_MPEG_VIDEO_BITRATE_MODE_CBR); if (cx2341x_neq(hdl->video_encoding) && hdl->ops && hdl->ops->s_video_encoding) return hdl->ops->s_video_encoding(hdl, hdl->video_encoding->val); return 0; case V4L2_CID_MPEG_VIDEO_MUTE: /* video mute cluster */ return cx2341x_hdl_api(hdl, CX2341X_ENC_MUTE_VIDEO, 1, hdl->video_mute->val | (hdl->video_mute_yuv->val << 8)); case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE: { int active_filter; /* video filter mode */ err = cx2341x_hdl_api(hdl, CX2341X_ENC_SET_DNR_FILTER_MODE, 2, hdl->video_spatial_filter_mode->val | (hdl->video_temporal_filter_mode->val << 1), hdl->video_median_filter_type->val); if (err) return err; active_filter = hdl->video_spatial_filter_mode->val != V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_AUTO; v4l2_ctrl_activate(hdl->video_spatial_filter, active_filter); v4l2_ctrl_activate(hdl->video_luma_spatial_filter_type, active_filter); v4l2_ctrl_activate(hdl->video_chroma_spatial_filter_type, active_filter); active_filter = hdl->video_temporal_filter_mode->val != V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_AUTO; v4l2_ctrl_activate(hdl->video_temporal_filter, active_filter); active_filter = hdl->video_median_filter_type->val != V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF; v4l2_ctrl_activate(hdl->video_luma_median_filter_bottom, active_filter); v4l2_ctrl_activate(hdl->video_luma_median_filter_top, active_filter); v4l2_ctrl_activate(hdl->video_chroma_median_filter_bottom, active_filter); v4l2_ctrl_activate(hdl->video_chroma_median_filter_top, active_filter); return 0; } case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE: /* video filter type cluster */ return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_SPATIAL_FILTER_TYPE, 2, hdl->video_luma_spatial_filter_type->val, hdl->video_chroma_spatial_filter_type->val); case V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER: /* video filter cluster */ return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_DNR_FILTER_PROPS, 2, hdl->video_spatial_filter->val, hdl->video_temporal_filter->val); case V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP: /* video median cluster */ return cx2341x_hdl_api(hdl, CX2341X_ENC_SET_CORING_LEVELS, 4, hdl->video_luma_median_filter_bottom->val, hdl->video_luma_median_filter_top->val, hdl->video_chroma_median_filter_bottom->val, hdl->video_chroma_median_filter_top->val); } return -EINVAL; } static const struct v4l2_ctrl_ops cx2341x_ops = { .try_ctrl = cx2341x_try_ctrl, .s_ctrl = cx2341x_s_ctrl, }; static struct v4l2_ctrl *cx2341x_ctrl_new_custom(struct v4l2_ctrl_handler *hdl, u32 id, s32 min, s32 max, s32 step, s32 def) { struct v4l2_ctrl_config cfg; memset(&cfg, 0, sizeof(cfg)); cx2341x_ctrl_fill(id, &cfg.name, &cfg.type, &min, &max, &step, &def, &cfg.flags); cfg.ops = &cx2341x_ops; cfg.id = id; cfg.min = min; cfg.max = max; cfg.def = def; if (cfg.type == V4L2_CTRL_TYPE_MENU) { cfg.step = 0; cfg.menu_skip_mask = step; cfg.qmenu = cx2341x_get_menu(id); } else { cfg.step = step; cfg.menu_skip_mask = 0; } return v4l2_ctrl_new_custom(hdl, &cfg, NULL); } static struct v4l2_ctrl *cx2341x_ctrl_new_std(struct v4l2_ctrl_handler *hdl, u32 id, s32 min, s32 max, s32 step, s32 def) { return v4l2_ctrl_new_std(hdl, &cx2341x_ops, id, min, max, step, def); } static struct v4l2_ctrl *cx2341x_ctrl_new_menu(struct v4l2_ctrl_handler *hdl, u32 id, s32 max, s32 mask, s32 def) { return v4l2_ctrl_new_std_menu(hdl, &cx2341x_ops, id, max, mask, def); } int cx2341x_handler_init(struct cx2341x_handler *cxhdl, unsigned nr_of_controls_hint) { struct v4l2_ctrl_handler *hdl = &cxhdl->hdl; u32 caps = cxhdl->capabilities; int has_sliced_vbi = caps & CX2341X_CAP_HAS_SLICED_VBI; int has_ac3 = caps & CX2341X_CAP_HAS_AC3; int has_ts = caps & CX2341X_CAP_HAS_TS; cxhdl->width = 720; cxhdl->height = 480; v4l2_ctrl_handler_init(hdl, nr_of_controls_hint); /* Add controls in ascending control ID order for fastest insertion time. */ cxhdl->stream_type = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_STREAM_TYPE, V4L2_MPEG_STREAM_TYPE_MPEG2_SVCD, has_ts ? 0 : 2, V4L2_MPEG_STREAM_TYPE_MPEG2_PS); cxhdl->stream_vbi_fmt = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_STREAM_VBI_FMT, V4L2_MPEG_STREAM_VBI_FMT_IVTV, has_sliced_vbi ? 0 : 2, V4L2_MPEG_STREAM_VBI_FMT_NONE); cxhdl->audio_sampling_freq = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ, V4L2_MPEG_AUDIO_SAMPLING_FREQ_32000, 0, V4L2_MPEG_AUDIO_SAMPLING_FREQ_48000); cxhdl->audio_encoding = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_ENCODING, V4L2_MPEG_AUDIO_ENCODING_AC3, has_ac3 ? ~0x12 : ~0x2, V4L2_MPEG_AUDIO_ENCODING_LAYER_2); cxhdl->audio_l2_bitrate = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_L2_BITRATE, V4L2_MPEG_AUDIO_L2_BITRATE_384K, 0x1ff, V4L2_MPEG_AUDIO_L2_BITRATE_224K); cxhdl->audio_mode = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_MODE, V4L2_MPEG_AUDIO_MODE_MONO, 0, V4L2_MPEG_AUDIO_MODE_STEREO); cxhdl->audio_mode_extension = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_MODE_EXTENSION, V4L2_MPEG_AUDIO_MODE_EXTENSION_BOUND_16, 0, V4L2_MPEG_AUDIO_MODE_EXTENSION_BOUND_4); cxhdl->audio_emphasis = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_EMPHASIS, V4L2_MPEG_AUDIO_EMPHASIS_CCITT_J17, 0, V4L2_MPEG_AUDIO_EMPHASIS_NONE); cxhdl->audio_crc = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_CRC, V4L2_MPEG_AUDIO_CRC_CRC16, 0, V4L2_MPEG_AUDIO_CRC_NONE); cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_AUDIO_MUTE, 0, 1, 1, 0); if (has_ac3) cxhdl->audio_ac3_bitrate = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_AUDIO_AC3_BITRATE, V4L2_MPEG_AUDIO_AC3_BITRATE_448K, 0x03, V4L2_MPEG_AUDIO_AC3_BITRATE_224K); cxhdl->video_encoding = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_VIDEO_ENCODING, V4L2_MPEG_VIDEO_ENCODING_MPEG_2, 0, V4L2_MPEG_VIDEO_ENCODING_MPEG_2); cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_VIDEO_ASPECT, V4L2_MPEG_VIDEO_ASPECT_221x100, 0, V4L2_MPEG_VIDEO_ASPECT_4x3); cxhdl->video_b_frames = cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_B_FRAMES, 0, 33, 1, 2); cxhdl->video_gop_size = cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_GOP_SIZE, 1, 34, 1, cxhdl->is_50hz ? 12 : 15); cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_GOP_CLOSURE, 0, 1, 1, 1); cxhdl->video_bitrate_mode = cx2341x_ctrl_new_menu(hdl, V4L2_CID_MPEG_VIDEO_BITRATE_MODE, V4L2_MPEG_VIDEO_BITRATE_MODE_CBR, 0, V4L2_MPEG_VIDEO_BITRATE_MODE_VBR); cxhdl->video_bitrate = cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_BITRATE, 0, 27000000, 1, 6000000); cxhdl->video_bitrate_peak = cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_BITRATE_PEAK, 0, 27000000, 1, 8000000); cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION, 0, 255, 1, 0); cxhdl->video_mute = cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_MUTE, 0, 1, 1, 0); cxhdl->video_mute_yuv = cx2341x_ctrl_new_std(hdl, V4L2_CID_MPEG_VIDEO_MUTE_YUV, 0, 0xffffff, 1, 0x008080); /* CX23415/6 specific */ cxhdl->video_spatial_filter_mode = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE, V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_MANUAL, V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_AUTO, 0, V4L2_MPEG_CX2341X_VIDEO_SPATIAL_FILTER_MODE_MANUAL); cxhdl->video_spatial_filter = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_SPATIAL_FILTER, 0, 15, 1, 0); cxhdl->video_luma_spatial_filter_type = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE, V4L2_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE_OFF, V4L2_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE_2D_SYM_NON_SEPARABLE, 0, V4L2_MPEG_CX2341X_VIDEO_LUMA_SPATIAL_FILTER_TYPE_1D_HOR); cxhdl->video_chroma_spatial_filter_type = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE, V4L2_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE_OFF, V4L2_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE_1D_HOR, 0, V4L2_MPEG_CX2341X_VIDEO_CHROMA_SPATIAL_FILTER_TYPE_1D_HOR); cxhdl->video_temporal_filter_mode = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE, V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_MANUAL, V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_AUTO, 0, V4L2_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER_MODE_MANUAL); cxhdl->video_temporal_filter = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_TEMPORAL_FILTER, 0, 31, 1, 8); cxhdl->video_median_filter_type = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE, V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF, V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_DIAG, 0, V4L2_MPEG_CX2341X_VIDEO_MEDIAN_FILTER_TYPE_OFF); cxhdl->video_luma_median_filter_bottom = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_BOTTOM, 0, 255, 1, 0); cxhdl->video_luma_median_filter_top = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_LUMA_MEDIAN_FILTER_TOP, 0, 255, 1, 255); cxhdl->video_chroma_median_filter_bottom = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_BOTTOM, 0, 255, 1, 0); cxhdl->video_chroma_median_filter_top = cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_VIDEO_CHROMA_MEDIAN_FILTER_TOP, 0, 255, 1, 255); cx2341x_ctrl_new_custom(hdl, V4L2_CID_MPEG_CX2341X_STREAM_INSERT_NAV_PACKETS, 0, 1, 1, 0); if (hdl->error) { int err = hdl->error; v4l2_ctrl_handler_free(hdl); return err; } v4l2_ctrl_cluster(8, &cxhdl->audio_sampling_freq); v4l2_ctrl_cluster(2, &cxhdl->video_b_frames); v4l2_ctrl_cluster(5, &cxhdl->stream_type); v4l2_ctrl_cluster(2, &cxhdl->video_mute); v4l2_ctrl_cluster(3, &cxhdl->video_spatial_filter_mode); v4l2_ctrl_cluster(2, &cxhdl->video_luma_spatial_filter_type); v4l2_ctrl_cluster(2, &cxhdl->video_spatial_filter); v4l2_ctrl_cluster(4, &cxhdl->video_luma_median_filter_top); return 0; } EXPORT_SYMBOL(cx2341x_handler_init); void cx2341x_handler_set_50hz(struct cx2341x_handler *cxhdl, int is_50hz) { cxhdl->is_50hz = is_50hz; cxhdl->video_gop_size->default_value = cxhdl->is_50hz ? 12 : 15; } EXPORT_SYMBOL(cx2341x_handler_set_50hz); int cx2341x_handler_setup(struct cx2341x_handler *cxhdl) { int h = cxhdl->height; int w = cxhdl->width; int err; err = cx2341x_hdl_api(cxhdl, CX2341X_ENC_SET_OUTPUT_PORT, 2, cxhdl->port, 0); if (err) return err; err = cx2341x_hdl_api(cxhdl, CX2341X_ENC_SET_FRAME_RATE, 1, cxhdl->is_50hz); if (err) return err; if (v4l2_ctrl_g_ctrl(cxhdl->video_encoding) == V4L2_MPEG_VIDEO_ENCODING_MPEG_1) { w /= 2; h /= 2; } err = cx2341x_hdl_api(cxhdl, CX2341X_ENC_SET_FRAME_SIZE, 2, h, w); if (err) return err; return v4l2_ctrl_handler_setup(&cxhdl->hdl); } EXPORT_SYMBOL(cx2341x_handler_setup); void cx2341x_handler_set_busy(struct cx2341x_handler *cxhdl, int busy) { v4l2_ctrl_grab(cxhdl->audio_sampling_freq, busy); v4l2_ctrl_grab(cxhdl->audio_encoding, busy); v4l2_ctrl_grab(cxhdl->audio_l2_bitrate, busy); v4l2_ctrl_grab(cxhdl->audio_ac3_bitrate, busy); v4l2_ctrl_grab(cxhdl->stream_vbi_fmt, busy); v4l2_ctrl_grab(cxhdl->stream_type, busy); v4l2_ctrl_grab(cxhdl->video_bitrate_mode, busy); v4l2_ctrl_grab(cxhdl->video_bitrate, busy); v4l2_ctrl_grab(cxhdl->video_bitrate_peak, busy); } EXPORT_SYMBOL(cx2341x_handler_set_busy); |
| 707 279 15 371 371 304 84 280 261 20 280 20 261 6 6 280 280 15 213 124 280 280 15 15 20 261 280 15 4 125 9 268 280 707 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2002 International Business Machines, Corp. * * This file is part of the SCTP kernel implementation * * These functions are the methods for accessing the SCTP inqueue. * * An SCTP inqueue is a queue into which you push SCTP packets * (which might be bundles or fragments of chunks) and out of which you * pop SCTP whole chunks. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <linux/interrupt.h> #include <linux/slab.h> /* Initialize an SCTP inqueue. */ void sctp_inq_init(struct sctp_inq *queue) { INIT_LIST_HEAD(&queue->in_chunk_list); queue->in_progress = NULL; /* Create a task for delivering data. */ INIT_WORK(&queue->immediate, NULL); } /* Properly release the chunk which is being worked on. */ static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk) { if (chunk->head_skb) chunk->skb = chunk->head_skb; sctp_chunk_free(chunk); } /* Release the memory associated with an SCTP inqueue. */ void sctp_inq_free(struct sctp_inq *queue) { struct sctp_chunk *chunk, *tmp; /* Empty the queue. */ list_for_each_entry_safe(chunk, tmp, &queue->in_chunk_list, list) { list_del_init(&chunk->list); sctp_chunk_free(chunk); } /* If there is a packet which is currently being worked on, * free it as well. */ if (queue->in_progress) { sctp_inq_chunk_free(queue->in_progress); queue->in_progress = NULL; } } /* Put a new packet in an SCTP inqueue. * We assume that packet->sctp_hdr is set and in host byte order. */ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) { /* Directly call the packet handling routine. Drop the chunk if the * receiver or the transport it was looked up on is gone. */ if (chunk->rcvr->dead || (chunk->transport && chunk->transport->dead)) { sctp_chunk_free(chunk); return; } /* We are now calling this either from the soft interrupt * or from the backlog processing. * Eventually, we should clean up inqueue to not rely * on the BH related data structures. */ list_add_tail(&chunk->list, &q->in_chunk_list); if (chunk->asoc) chunk->asoc->stats.ipackets++; q->immediate.func(&q->immediate); } /* Peek at the next chunk on the inqeue. */ struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) { struct sctp_chunk *chunk; struct sctp_chunkhdr *ch = NULL; chunk = queue->in_progress; /* If there is no more chunks in this packet, say so */ if (chunk->singleton || chunk->end_of_packet || chunk->pdiscard) return NULL; ch = (struct sctp_chunkhdr *)chunk->chunk_end; return ch; } /* Extract a chunk from an SCTP inqueue. * * WARNING: If you need to put the chunk on another queue, you need to * make a shallow copy (clone) of it. */ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) { struct sctp_chunk *chunk; struct sctp_chunkhdr *ch = NULL; /* The assumption is that we are safe to process the chunks * at this time. */ chunk = queue->in_progress; if (chunk) { /* There is a packet that we have been working on. * Any post processing work to do before we move on? */ if (chunk->singleton || chunk->end_of_packet || chunk->pdiscard) { if (chunk->head_skb == chunk->skb) { chunk->skb = skb_shinfo(chunk->skb)->frag_list; goto new_skb; } if (chunk->skb->next) { chunk->skb = chunk->skb->next; goto new_skb; } sctp_inq_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ ch = (struct sctp_chunkhdr *)chunk->chunk_end; /* Force chunk->skb->data to chunk->chunk_end. */ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); /* We are guaranteed to pull a SCTP header. */ } } /* Do we need to take the next packet out of the queue to process? */ if (!chunk) { struct list_head *entry; next_chunk: /* Is the queue empty? */ entry = sctp_list_dequeue(&queue->in_chunk_list); if (!entry) return NULL; chunk = list_entry(entry, struct sctp_chunk, list); if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) { /* GSO-marked skbs but without frags, handle * them normally */ if (skb_shinfo(chunk->skb)->frag_list) chunk->head_skb = chunk->skb; /* skbs with "cover letter" */ if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) { if (WARN_ON(!skb_shinfo(chunk->skb)->frag_list)) { __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); sctp_chunk_free(chunk); goto next_chunk; } chunk->skb = skb_shinfo(chunk->skb)->frag_list; } } if (chunk->asoc) sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb); queue->in_progress = chunk; new_skb: /* This is the first chunk in the packet. */ ch = (struct sctp_chunkhdr *)chunk->skb->data; chunk->singleton = 1; chunk->data_accepted = 0; chunk->pdiscard = 0; chunk->auth = 0; chunk->has_asconf = 0; chunk->end_of_packet = 0; if (chunk->head_skb) { struct sctp_input_cb *cb = SCTP_INPUT_CB(chunk->skb), *head_cb = SCTP_INPUT_CB(chunk->head_skb); cb->chunk = head_cb->chunk; cb->af = head_cb->af; cb->encap_port = head_cb->encap_port; } } chunk->chunk_hdr = ch; chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ if (unlikely(ntohs(ch->length) < sizeof(*ch))) { chunk->pdiscard = 1; } else if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { /* Discard inside state machine. */ chunk->pdiscard = 1; chunk->chunk_end = skb_tail_pointer(chunk->skb); } else { /* We are at the end of the packet, so mark the chunk * in case we need to send a SACK. */ chunk->end_of_packet = 1; } pr_debug("+++sctp_inq_pop+++ chunk:%p[%s], length:%d, skb->len:%d\n", chunk, sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)), ntohs(chunk->chunk_hdr->length), chunk->skb->len); return chunk; } /* Set a top-half handler. * * Originally, we the top-half handler was scheduled as a BH. We now * call the handler directly in sctp_inq_push() at a time that * we know we are lock safe. * The intent is that this routine will pull stuff out of the * inqueue and process it. */ void sctp_inq_set_th_handler(struct sctp_inq *q, work_func_t callback) { INIT_WORK(&q->immediate, callback); } |
| 3294 3294 3294 3294 3294 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * netprio_cgroup.h Control Group Priority set * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #ifndef _NETPRIO_CGROUP_H #define _NETPRIO_CGROUP_H #include <linux/cgroup.h> #include <linux/hardirq.h> #include <linux/rcupdate.h> #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map { struct rcu_head rcu; u32 priomap_len; u32 priomap[]; }; static inline u32 task_netprioidx(struct task_struct *p) { struct cgroup_subsys_state *css; u32 idx; rcu_read_lock(); css = task_css(p, net_prio_cgrp_id); idx = css->id; rcu_read_unlock(); return idx; } static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) { if (in_interrupt()) return; sock_cgroup_set_prioidx(skcd, task_netprioidx(current)); } #else /* !CONFIG_CGROUP_NET_PRIO */ static inline u32 task_netprioidx(struct task_struct *p) { return 0; } static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) { } #endif /* CONFIG_CGROUP_NET_PRIO */ #endif /* _NET_CLS_CGROUP_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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * HID driver for some a4tech "special" devices * * Copyright (c) 1999 Andreas Gal * Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz> * Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc * Copyright (c) 2006-2007 Jiri Kosina * Copyright (c) 2008 Jiri Slaby */ /* */ #include <linux/device.h> #include <linux/input.h> #include <linux/hid.h> #include <linux/module.h> #include <linux/slab.h> #include "hid-ids.h" #define A4_2WHEEL_MOUSE_HACK_7 0x01 #define A4_2WHEEL_MOUSE_HACK_B8 0x02 #define A4_WHEEL_ORIENTATION (HID_UP_GENDESK | 0x000000b8) struct a4tech_sc { unsigned long quirks; unsigned int hw_wheel; __s32 delayed_value; }; static int a4_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { struct a4tech_sc *a4 = hid_get_drvdata(hdev); if (a4->quirks & A4_2WHEEL_MOUSE_HACK_B8 && usage->hid == A4_WHEEL_ORIENTATION) { /* * We do not want to have this usage mapped to anything as it's * nonstandard and doesn't really behave like an HID report. * It's only selecting the orientation (vertical/horizontal) of * the previous mouse wheel report. The input_events will be * generated once both reports are recorded in a4_event(). */ return -1; } return 0; } static int a4_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { struct a4tech_sc *a4 = hid_get_drvdata(hdev); if (usage->type == EV_REL && usage->code == REL_WHEEL_HI_RES) { set_bit(REL_HWHEEL, *bit); set_bit(REL_HWHEEL_HI_RES, *bit); } if ((a4->quirks & A4_2WHEEL_MOUSE_HACK_7) && usage->hid == 0x00090007) return -1; return 0; } static int a4_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { struct a4tech_sc *a4 = hid_get_drvdata(hdev); struct input_dev *input; if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput) return 0; input = field->hidinput->input; if (a4->quirks & A4_2WHEEL_MOUSE_HACK_B8) { if (usage->type == EV_REL && usage->code == REL_WHEEL_HI_RES) { a4->delayed_value = value; return 1; } if (usage->hid == A4_WHEEL_ORIENTATION) { input_event(input, EV_REL, value ? REL_HWHEEL : REL_WHEEL, a4->delayed_value); input_event(input, EV_REL, value ? REL_HWHEEL_HI_RES : REL_WHEEL_HI_RES, a4->delayed_value * 120); return 1; } } if ((a4->quirks & A4_2WHEEL_MOUSE_HACK_7) && usage->hid == 0x00090007) { a4->hw_wheel = !!value; return 1; } if (usage->code == REL_WHEEL_HI_RES && a4->hw_wheel) { input_event(input, usage->type, REL_HWHEEL, value); input_event(input, usage->type, REL_HWHEEL_HI_RES, value * 120); return 1; } return 0; } static int a4_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct a4tech_sc *a4; int ret; a4 = devm_kzalloc(&hdev->dev, sizeof(*a4), GFP_KERNEL); if (a4 == NULL) { hid_err(hdev, "can't alloc device descriptor\n"); return -ENOMEM; } a4->quirks = id->driver_data; hid_set_drvdata(hdev, a4); ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); return ret; } ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "hw start failed\n"); return ret; } return 0; } static const struct hid_device_id a4_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_WCP32PU), .driver_data = A4_2WHEEL_MOUSE_HACK_7 }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_X5_005D), .driver_data = A4_2WHEEL_MOUSE_HACK_B8 }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_RP_649), .driver_data = A4_2WHEEL_MOUSE_HACK_B8 }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_NB_95), .driver_data = A4_2WHEEL_MOUSE_HACK_B8 }, { } }; MODULE_DEVICE_TABLE(hid, a4_devices); static struct hid_driver a4_driver = { .name = "a4tech", .id_table = a4_devices, .input_mapping = a4_input_mapping, .input_mapped = a4_input_mapped, .event = a4_event, .probe = a4_probe, }; module_hid_driver(a4_driver); MODULE_DESCRIPTION("HID driver for some a4tech \"special\" devices"); MODULE_LICENSE("GPL"); |
| 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NVMe over Fabrics common host code. * Copyright (c) 2015-2016 HGST, a Western Digital Company. */ #ifndef _NVME_FABRICS_H #define _NVME_FABRICS_H 1 #include <linux/in.h> #include <linux/inet.h> #define NVMF_MIN_QUEUE_SIZE 16 #define NVMF_MAX_QUEUE_SIZE 1024 #define NVMF_DEF_QUEUE_SIZE 128 #define NVMF_DEF_RECONNECT_DELAY 10 /* default to 600 seconds of reconnect attempts before giving up */ #define NVMF_DEF_CTRL_LOSS_TMO 600 /* default is -1: the fail fast mechanism is disabled */ #define NVMF_DEF_FAIL_FAST_TMO -1 /* * Define a host as seen by the target. We allocate one at boot, but also * allow the override it when creating controllers. This is both to provide * persistence of the Host NQN over multiple boots, and to allow using * multiple ones, for example in a container scenario. Because we must not * use different Host NQNs with the same Host ID we generate a Host ID and * use this structure to keep track of the relation between the two. */ struct nvmf_host { struct kref ref; struct list_head list; char nqn[NVMF_NQN_SIZE]; uuid_t id; }; /** * enum nvmf_parsing_opts - used to define the sysfs parsing options used. */ enum { NVMF_OPT_ERR = 0, NVMF_OPT_TRANSPORT = 1 << 0, NVMF_OPT_NQN = 1 << 1, NVMF_OPT_TRADDR = 1 << 2, NVMF_OPT_TRSVCID = 1 << 3, NVMF_OPT_QUEUE_SIZE = 1 << 4, NVMF_OPT_NR_IO_QUEUES = 1 << 5, NVMF_OPT_TL_RETRY_COUNT = 1 << 6, NVMF_OPT_KATO = 1 << 7, NVMF_OPT_HOSTNQN = 1 << 8, NVMF_OPT_RECONNECT_DELAY = 1 << 9, NVMF_OPT_HOST_TRADDR = 1 << 10, NVMF_OPT_CTRL_LOSS_TMO = 1 << 11, NVMF_OPT_HOST_ID = 1 << 12, NVMF_OPT_DUP_CONNECT = 1 << 13, NVMF_OPT_DISABLE_SQFLOW = 1 << 14, NVMF_OPT_HDR_DIGEST = 1 << 15, NVMF_OPT_DATA_DIGEST = 1 << 16, NVMF_OPT_NR_WRITE_QUEUES = 1 << 17, NVMF_OPT_NR_POLL_QUEUES = 1 << 18, NVMF_OPT_TOS = 1 << 19, NVMF_OPT_FAIL_FAST_TMO = 1 << 20, NVMF_OPT_HOST_IFACE = 1 << 21, NVMF_OPT_DISCOVERY = 1 << 22, NVMF_OPT_DHCHAP_SECRET = 1 << 23, NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24, NVMF_OPT_TLS = 1 << 25, NVMF_OPT_KEYRING = 1 << 26, NVMF_OPT_TLS_KEY = 1 << 27, NVMF_OPT_CONCAT = 1 << 28, }; /** * struct nvmf_ctrl_options - Used to hold the options specified * with the parsing opts enum. * @mask: Used by the fabrics library to parse through sysfs options * on adding a NVMe controller. * @max_reconnects: maximum number of allowed reconnect attempts before removing * the controller, (-1) means reconnect forever, zero means remove * immediately; * @transport: Holds the fabric transport "technology name" (for a lack of * better description) that will be used by an NVMe controller * being added. * @subsysnqn: Hold the fully qualified NQN subsystem name (format defined * in the NVMe specification, "NVMe Qualified Names"). * @traddr: The transport-specific TRADDR field for a port on the * subsystem which is adding a controller. * @trsvcid: The transport-specific TRSVCID field for a port on the * subsystem which is adding a controller. * @host_traddr: A transport-specific field identifying the NVME host port * to use for the connection to the controller. * @host_iface: A transport-specific field identifying the NVME host * interface to use for the connection to the controller. * @queue_size: Number of IO queue elements. * @nr_io_queues: Number of controller IO queues that will be established. * @reconnect_delay: Time between two consecutive reconnect attempts. * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN. * @kato: Keep-alive timeout. * @host: Virtual NVMe host, contains the NQN and Host ID. * @dhchap_secret: DH-HMAC-CHAP secret * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional * authentication * @keyring: Keyring to use for key lookups * @tls_key: TLS key for encrypted connections (TCP) * @tls: Start TLS encrypted connections (TCP) * @concat: Enabled Secure channel concatenation (TCP) * @disable_sqflow: disable controller sq flow control * @hdr_digest: generate/verify header digest (TCP) * @data_digest: generate/verify data digest (TCP) * @nr_write_queues: number of queues for write I/O * @nr_poll_queues: number of queues for polling I/O * @tos: type of service * @fast_io_fail_tmo: Fast I/O fail timeout in seconds */ struct nvmf_ctrl_options { unsigned mask; int max_reconnects; char *transport; char *subsysnqn; char *traddr; char *trsvcid; char *host_traddr; char *host_iface; size_t queue_size; unsigned int nr_io_queues; unsigned int reconnect_delay; bool discovery_nqn; bool duplicate_connect; unsigned int kato; struct nvmf_host *host; char *dhchap_secret; char *dhchap_ctrl_secret; struct key *keyring; struct key *tls_key; bool tls; bool concat; bool disable_sqflow; bool hdr_digest; bool data_digest; unsigned int nr_write_queues; unsigned int nr_poll_queues; int tos; int fast_io_fail_tmo; }; /* * struct nvmf_transport_ops - used to register a specific * fabric implementation of NVMe fabrics. * @entry: Used by the fabrics library to add the new * registration entry to its linked-list internal tree. * @module: Transport module reference * @name: Name of the NVMe fabric driver implementation. * @required_opts: sysfs command-line options that must be specified * when adding a new NVMe controller. * @allowed_opts: sysfs command-line options that can be specified * when adding a new NVMe controller. * @create_ctrl(): function pointer that points to a non-NVMe * implementation-specific fabric technology * that would go into starting up that fabric * for the purpose of connection to an NVMe controller * using that fabric technology. * * Notes: * 1. At minimum, 'required_opts' and 'allowed_opts' should * be set to the same enum parsing options defined earlier. * 2. create_ctrl() must be defined (even if it does nothing) * 3. struct nvmf_transport_ops must be statically allocated in the * modules .bss section so that a pure module_get on @module * prevents the memory from being freed. */ struct nvmf_transport_ops { struct list_head entry; struct module *module; const char *name; int required_opts; int allowed_opts; struct nvme_ctrl *(*create_ctrl)(struct device *dev, struct nvmf_ctrl_options *opts); }; static inline bool nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts) { enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); if (state == NVME_CTRL_DELETING || state == NVME_CTRL_DELETING_NOIO || state == NVME_CTRL_DEAD || strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) || strcmp(opts->host->nqn, ctrl->opts->host->nqn) || !uuid_equal(&opts->host->id, &ctrl->opts->host->id)) return false; return true; } static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl) { if (!ctrl->subsys || !strcmp(ctrl->opts->subsysnqn, NVME_DISC_SUBSYS_NAME)) return ctrl->opts->subsysnqn; return ctrl->subsys->subnqn; } static inline void nvmf_complete_timed_out_request(struct request *rq) { if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(rq); } } static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts) { return min(opts->nr_io_queues, num_online_cpus()) + min(opts->nr_write_queues, num_online_cpus()) + min(opts->nr_poll_queues, num_online_cpus()); } static inline unsigned long nvmf_get_virt_boundary(struct nvme_ctrl *ctrl, bool is_admin) { return 0; } int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); int nvmf_subsystem_reset(struct nvme_ctrl *ctrl); int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl); int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid); int nvmf_register_transport(struct nvmf_transport_ops *ops); void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status); bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts); void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues, u32 io_queues[HCTX_MAX_TYPES]); void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl, u32 io_queues[HCTX_MAX_TYPES]); #endif /* _NVME_FABRICS_H */ |
| 6855 20573 1374 | 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason); DEFINE_DROP_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SKB_DROP_REASON_##reason, #reason }, #define FNe(reason) { SKB_DROP_REASON_##reason, #reason } /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk), TP_ARGS(skb, location, reason, rx_sk), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) __field(const void *, rx_sk) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->rx_sk = rx_sk; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->rx_sk, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); #undef FN #undef FNe TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr) __field( void *, location) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; ), TP_printk("skbaddr=%p location=%pS", __entry->skbaddr, __entry->location) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 47 47 2 2 6 6 26 26 26 25 1 26 1 1 22 2 2 2 2 2 6 6 6 6 6 6 6 6 13 13 13 13 13 1 13 1 13 13 13 22 22 22 22 21 5 4 2 21 6 6 24 10 16 15 2 16 10 10 10 10 5 5 5 5 1 6 6 6 6 6 6 6 6 1 5 6 6 4 4 4 3 1 4 33 22 13 33 32 8 8 1 7 8 8 1 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 | // SPDX-License-Identifier: GPL-2.0-only /* * Fence mechanism for dma-buf and to allow for asynchronous dma access * * Copyright (C) 2012 Canonical Ltd * Copyright (C) 2012 Texas Instruments * * Authors: * Rob Clark <robdclark@gmail.com> * Maarten Lankhorst <maarten.lankhorst@canonical.com> */ #include <linux/slab.h> #include <linux/export.h> #include <linux/atomic.h> #include <linux/dma-fence.h> #include <linux/sched/signal.h> #include <linux/seq_file.h> #define CREATE_TRACE_POINTS #include <trace/events/dma_fence.h> EXPORT_TRACEPOINT_SYMBOL(dma_fence_emit); EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal); EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled); static struct dma_fence dma_fence_stub; /* * fence context counter: each execution context should have its own * fence context, this allows checking if fences belong to the same * context or not. One device can have multiple separate contexts, * and they're used if some engine can run independently of another. */ static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(1); /** * DOC: DMA fences overview * * DMA fences, represented by &struct dma_fence, are the kernel internal * synchronization primitive for DMA operations like GPU rendering, video * encoding/decoding, or displaying buffers on a screen. * * A fence is initialized using dma_fence_init() and completed using * dma_fence_signal(). Fences are associated with a context, allocated through * dma_fence_context_alloc(), and all fences on the same context are * fully ordered. * * Since the purposes of fences is to facilitate cross-device and * cross-application synchronization, there's multiple ways to use one: * * - Individual fences can be exposed as a &sync_file, accessed as a file * descriptor from userspace, created by calling sync_file_create(). This is * called explicit fencing, since userspace passes around explicit * synchronization points. * * - Some subsystems also have their own explicit fencing primitives, like * &drm_syncobj. Compared to &sync_file, a &drm_syncobj allows the underlying * fence to be updated. * * - Then there's also implicit fencing, where the synchronization points are * implicitly passed around as part of shared &dma_buf instances. Such * implicit fences are stored in &struct dma_resv through the * &dma_buf.resv pointer. */ /** * DOC: fence cross-driver contract * * Since &dma_fence provide a cross driver contract, all drivers must follow the * same rules: * * * Fences must complete in a reasonable time. Fences which represent kernels * and shaders submitted by userspace, which could run forever, must be backed * up by timeout and gpu hang recovery code. Minimally that code must prevent * further command submission and force complete all in-flight fences, e.g. * when the driver or hardware do not support gpu reset, or if the gpu reset * failed for some reason. Ideally the driver supports gpu recovery which only * affects the offending userspace context, and no other userspace * submissions. * * * Drivers may have different ideas of what completion within a reasonable * time means. Some hang recovery code uses a fixed timeout, others a mix * between observing forward progress and increasingly strict timeouts. * Drivers should not try to second guess timeout handling of fences from * other drivers. * * * To ensure there's no deadlocks of dma_fence_wait() against other locks * drivers should annotate all code required to reach dma_fence_signal(), * which completes the fences, with dma_fence_begin_signalling() and * dma_fence_end_signalling(). * * * Drivers are allowed to call dma_fence_wait() while holding dma_resv_lock(). * This means any code required for fence completion cannot acquire a * &dma_resv lock. Note that this also pulls in the entire established * locking hierarchy around dma_resv_lock() and dma_resv_unlock(). * * * Drivers are allowed to call dma_fence_wait() from their &shrinker * callbacks. This means any code required for fence completion cannot * allocate memory with GFP_KERNEL. * * * Drivers are allowed to call dma_fence_wait() from their &mmu_notifier * respectively &mmu_interval_notifier callbacks. This means any code required * for fence completion cannot allocate memory with GFP_NOFS or GFP_NOIO. * Only GFP_ATOMIC is permissible, which might fail. * * Note that only GPU drivers have a reasonable excuse for both requiring * &mmu_interval_notifier and &shrinker callbacks at the same time as having to * track asynchronous compute work using &dma_fence. No driver outside of * drivers/gpu should ever call dma_fence_wait() in such contexts. */ static const char *dma_fence_stub_get_name(struct dma_fence *fence) { return "stub"; } static const struct dma_fence_ops dma_fence_stub_ops = { .get_driver_name = dma_fence_stub_get_name, .get_timeline_name = dma_fence_stub_get_name, }; static int __init dma_fence_init_stub(void) { dma_fence_init(&dma_fence_stub, &dma_fence_stub_ops, NULL, 0, 0); set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &dma_fence_stub.flags); dma_fence_signal(&dma_fence_stub); return 0; } subsys_initcall(dma_fence_init_stub); /** * dma_fence_get_stub - return a signaled fence * * Return a stub fence which is already signaled. The fence's timestamp * corresponds to the initialisation time of the linux kernel. */ struct dma_fence *dma_fence_get_stub(void) { return dma_fence_get(&dma_fence_stub); } EXPORT_SYMBOL(dma_fence_get_stub); /** * dma_fence_allocate_private_stub - return a private, signaled fence * @timestamp: timestamp when the fence was signaled * * Return a newly allocated and signaled stub fence. */ struct dma_fence *dma_fence_allocate_private_stub(ktime_t timestamp) { struct dma_fence *fence; fence = kzalloc_obj(*fence); if (fence == NULL) return NULL; dma_fence_init(fence, &dma_fence_stub_ops, NULL, 0, 0); set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); dma_fence_signal_timestamp(fence, timestamp); return fence; } EXPORT_SYMBOL(dma_fence_allocate_private_stub); /** * dma_fence_context_alloc - allocate an array of fence contexts * @num: amount of contexts to allocate * * This function will return the first index of the number of fence contexts * allocated. The fence context is used for setting &dma_fence.context to a * unique number by passing the context to dma_fence_init(). */ u64 dma_fence_context_alloc(unsigned num) { WARN_ON(!num); return atomic64_fetch_add(num, &dma_fence_context_counter); } EXPORT_SYMBOL(dma_fence_context_alloc); /** * DOC: fence signalling annotation * * Proving correctness of all the kernel code around &dma_fence through code * review and testing is tricky for a few reasons: * * * It is a cross-driver contract, and therefore all drivers must follow the * same rules for lock nesting order, calling contexts for various functions * and anything else significant for in-kernel interfaces. But it is also * impossible to test all drivers in a single machine, hence brute-force N vs. * N testing of all combinations is impossible. Even just limiting to the * possible combinations is infeasible. * * * There is an enormous amount of driver code involved. For render drivers * there's the tail of command submission, after fences are published, * scheduler code, interrupt and workers to process job completion, * and timeout, gpu reset and gpu hang recovery code. Plus for integration * with core mm with have &mmu_notifier, respectively &mmu_interval_notifier, * and &shrinker. For modesetting drivers there's the commit tail functions * between when fences for an atomic modeset are published, and when the * corresponding vblank completes, including any interrupt processing and * related workers. Auditing all that code, across all drivers, is not * feasible. * * * Due to how many other subsystems are involved and the locking hierarchies * this pulls in there is extremely thin wiggle-room for driver-specific * differences. &dma_fence interacts with almost all of the core memory * handling through page fault handlers via &dma_resv, dma_resv_lock() and * dma_resv_unlock(). On the other side it also interacts through all * allocation sites through &mmu_notifier and &shrinker. * * Furthermore lockdep does not handle cross-release dependencies, which means * any deadlocks between dma_fence_wait() and dma_fence_signal() can't be caught * at runtime with some quick testing. The simplest example is one thread * waiting on a &dma_fence while holding a lock:: * * lock(A); * dma_fence_wait(B); * unlock(A); * * while the other thread is stuck trying to acquire the same lock, which * prevents it from signalling the fence the previous thread is stuck waiting * on:: * * lock(A); * unlock(A); * dma_fence_signal(B); * * By manually annotating all code relevant to signalling a &dma_fence we can * teach lockdep about these dependencies, which also helps with the validation * headache since now lockdep can check all the rules for us:: * * cookie = dma_fence_begin_signalling(); * lock(A); * unlock(A); * dma_fence_signal(B); * dma_fence_end_signalling(cookie); * * For using dma_fence_begin_signalling() and dma_fence_end_signalling() to * annotate critical sections the following rules need to be observed: * * * All code necessary to complete a &dma_fence must be annotated, from the * point where a fence is accessible to other threads, to the point where * dma_fence_signal() is called. Un-annotated code can contain deadlock issues, * and due to the very strict rules and many corner cases it is infeasible to * catch these just with review or normal stress testing. * * * &struct dma_resv deserves a special note, since the readers are only * protected by rcu. This means the signalling critical section starts as soon * as the new fences are installed, even before dma_resv_unlock() is called. * * * The only exception are fast paths and opportunistic signalling code, which * calls dma_fence_signal() purely as an optimization, but is not required to * guarantee completion of a &dma_fence. The usual example is a wait IOCTL * which calls dma_fence_signal(), while the mandatory completion path goes * through a hardware interrupt and possible job completion worker. * * * To aid composability of code, the annotations can be freely nested, as long * as the overall locking hierarchy is consistent. The annotations also work * both in interrupt and process context. Due to implementation details this * requires that callers pass an opaque cookie from * dma_fence_begin_signalling() to dma_fence_end_signalling(). * * * Validation against the cross driver contract is implemented by priming * lockdep with the relevant hierarchy at boot-up. This means even just * testing with a single device is enough to validate a driver, at least as * far as deadlocks with dma_fence_wait() against dma_fence_signal() are * concerned. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map dma_fence_lockdep_map = { .name = "dma_fence_map" }; /** * dma_fence_begin_signalling - begin a critical DMA fence signalling section * * Drivers should use this to annotate the beginning of any code section * required to eventually complete &dma_fence by calling dma_fence_signal(). * * The end of these critical sections are annotated with * dma_fence_end_signalling(). * * Returns: * * Opaque cookie needed by the implementation, which needs to be passed to * dma_fence_end_signalling(). */ bool dma_fence_begin_signalling(void) { /* explicitly nesting ... */ if (lock_is_held_type(&dma_fence_lockdep_map, 1)) return true; /* rely on might_sleep check for soft/hardirq locks */ if (in_atomic()) return true; /* ... and non-recursive successful read_trylock */ lock_acquire(&dma_fence_lockdep_map, 0, 1, 1, 1, NULL, _RET_IP_); return false; } EXPORT_SYMBOL(dma_fence_begin_signalling); /** * dma_fence_end_signalling - end a critical DMA fence signalling section * @cookie: opaque cookie from dma_fence_begin_signalling() * * Closes a critical section annotation opened by dma_fence_begin_signalling(). */ void dma_fence_end_signalling(bool cookie) { if (cookie) return; lock_release(&dma_fence_lockdep_map, _RET_IP_); } EXPORT_SYMBOL(dma_fence_end_signalling); void __dma_fence_might_wait(void) { bool tmp; tmp = lock_is_held_type(&dma_fence_lockdep_map, 1); if (tmp) lock_release(&dma_fence_lockdep_map, _THIS_IP_); lock_map_acquire(&dma_fence_lockdep_map); lock_map_release(&dma_fence_lockdep_map); if (tmp) lock_acquire(&dma_fence_lockdep_map, 0, 1, 1, 1, NULL, _THIS_IP_); } #endif /** * dma_fence_signal_timestamp_locked - signal completion of a fence * @fence: the fence to signal * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain * * Signal completion for software callbacks on a fence, this will unblock * dma_fence_wait() calls and run all the callbacks added with * dma_fence_add_callback(). Can be called multiple times, but since a fence * can only go from the unsignaled to the signaled state and not back, it will * only be effective the first time. Set the timestamp provided as the fence * signal timestamp. * * Unlike dma_fence_signal_timestamp(), this function must be called with * &dma_fence.lock held. */ void dma_fence_signal_timestamp_locked(struct dma_fence *fence, ktime_t timestamp) { const struct dma_fence_ops *ops; struct dma_fence_cb *cur, *tmp; struct list_head cb_list; dma_fence_assert_held(fence); if (unlikely(test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))) return; trace_dma_fence_signaled(fence); /* * When neither a release nor a wait operation is specified set the ops * pointer to NULL to allow the fence structure to become independent * from who originally issued it. */ ops = rcu_dereference_protected(fence->ops, true); if (!ops->release && !ops->wait) RCU_INIT_POINTER(fence->ops, NULL); /* Stash the cb_list before replacing it with the timestamp */ list_replace(&fence->cb_list, &cb_list); fence->timestamp = timestamp; set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); list_for_each_entry_safe(cur, tmp, &cb_list, node) { INIT_LIST_HEAD(&cur->node); cur->func(fence, cur); } } EXPORT_SYMBOL(dma_fence_signal_timestamp_locked); /** * dma_fence_signal_timestamp - signal completion of a fence * @fence: the fence to signal * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain * * Signal completion for software callbacks on a fence, this will unblock * dma_fence_wait() calls and run all the callbacks added with * dma_fence_add_callback(). Can be called multiple times, but since a fence * can only go from the unsignaled to the signaled state and not back, it will * only be effective the first time. Set the timestamp provided as the fence * signal timestamp. */ void dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp) { unsigned long flags; if (WARN_ON(!fence)) return; dma_fence_lock_irqsave(fence, flags); dma_fence_signal_timestamp_locked(fence, timestamp); dma_fence_unlock_irqrestore(fence, flags); } EXPORT_SYMBOL(dma_fence_signal_timestamp); /** * dma_fence_signal_locked - signal completion of a fence * @fence: the fence to signal * * Signal completion for software callbacks on a fence, this will unblock * dma_fence_wait() calls and run all the callbacks added with * dma_fence_add_callback(). Can be called multiple times, but since a fence * can only go from the unsignaled to the signaled state and not back, it will * only be effective the first time. * * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock * held. */ void dma_fence_signal_locked(struct dma_fence *fence) { dma_fence_signal_timestamp_locked(fence, ktime_get()); } EXPORT_SYMBOL(dma_fence_signal_locked); /** * dma_fence_check_and_signal_locked - signal the fence if it's not yet signaled * @fence: the fence to check and signal * * Checks whether a fence was signaled and signals it if it was not yet signaled. * * Unlike dma_fence_check_and_signal(), this function must be called with * &struct dma_fence.lock being held. * * Return: true if fence has been signaled already, false otherwise. */ bool dma_fence_check_and_signal_locked(struct dma_fence *fence) { bool ret; ret = dma_fence_test_signaled_flag(fence); dma_fence_signal_locked(fence); return ret; } EXPORT_SYMBOL(dma_fence_check_and_signal_locked); /** * dma_fence_check_and_signal - signal the fence if it's not yet signaled * @fence: the fence to check and signal * * Checks whether a fence was signaled and signals it if it was not yet signaled. * All this is done in a race-free manner. * * Return: true if fence has been signaled already, false otherwise. */ bool dma_fence_check_and_signal(struct dma_fence *fence) { unsigned long flags; bool ret; dma_fence_lock_irqsave(fence, flags); ret = dma_fence_check_and_signal_locked(fence); dma_fence_unlock_irqrestore(fence, flags); return ret; } EXPORT_SYMBOL(dma_fence_check_and_signal); /** * dma_fence_signal - signal completion of a fence * @fence: the fence to signal * * Signal completion for software callbacks on a fence, this will unblock * dma_fence_wait() calls and run all the callbacks added with * dma_fence_add_callback(). Can be called multiple times, but since a fence * can only go from the unsignaled to the signaled state and not back, it will * only be effective the first time. */ void dma_fence_signal(struct dma_fence *fence) { unsigned long flags; bool tmp; if (WARN_ON(!fence)) return; tmp = dma_fence_begin_signalling(); dma_fence_lock_irqsave(fence, flags); dma_fence_signal_timestamp_locked(fence, ktime_get()); dma_fence_unlock_irqrestore(fence, flags); dma_fence_end_signalling(tmp); } EXPORT_SYMBOL(dma_fence_signal); /** * dma_fence_wait_timeout - sleep until the fence gets signaled * or until timeout elapses * @fence: the fence to wait on * @intr: if true, do an interruptible wait * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT * * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the * remaining timeout in jiffies on success. Other error values may be * returned on custom implementations. * * Performs a synchronous wait on this fence. It is assumed the caller * directly or indirectly (buf-mgr between reservation and committing) * holds a reference to the fence, otherwise the fence might be * freed before return, resulting in undefined behavior. * * See also dma_fence_wait() and dma_fence_wait_any_timeout(). */ signed long dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) { const struct dma_fence_ops *ops; signed long ret; if (WARN_ON(timeout < 0)) return -EINVAL; might_sleep(); __dma_fence_might_wait(); dma_fence_enable_signaling(fence); rcu_read_lock(); ops = rcu_dereference(fence->ops); trace_dma_fence_wait_start(fence); if (ops && ops->wait) { /* * Implementing the wait ops is deprecated and not supported for * issuers of fences who need their lifetime to be independent * of their module after they signal, so it is ok to use the * ops outside the RCU protected section. */ rcu_read_unlock(); ret = ops->wait(fence, intr, timeout); } else { rcu_read_unlock(); ret = dma_fence_default_wait(fence, intr, timeout); } if (trace_dma_fence_wait_end_enabled()) { rcu_read_lock(); trace_dma_fence_wait_end(fence); rcu_read_unlock(); } return ret; } EXPORT_SYMBOL(dma_fence_wait_timeout); /** * dma_fence_release - default release function for fences * @kref: &dma_fence.recfount * * This is the default release functions for &dma_fence. Drivers shouldn't call * this directly, but instead call dma_fence_put(). */ void dma_fence_release(struct kref *kref) { struct dma_fence *fence = container_of(kref, struct dma_fence, refcount); const struct dma_fence_ops *ops; rcu_read_lock(); trace_dma_fence_destroy(fence); if (!list_empty(&fence->cb_list) && !dma_fence_test_signaled_flag(fence)) { const char __rcu *timeline; const char __rcu *driver; unsigned long flags; driver = dma_fence_driver_name(fence); timeline = dma_fence_timeline_name(fence); WARN(1, "Fence %s:%s:%llx:%llx released with pending signals!\n", rcu_dereference(driver), rcu_dereference(timeline), fence->context, fence->seqno); /* * Failed to signal before release, likely a refcounting issue. * * This should never happen, but if it does make sure that we * don't leave chains dangling. We set the error flag first * so that the callbacks know this signal is due to an error. */ dma_fence_lock_irqsave(fence, flags); fence->error = -EDEADLK; dma_fence_signal_locked(fence); dma_fence_unlock_irqrestore(fence, flags); } ops = rcu_dereference(fence->ops); if (ops && ops->release) ops->release(fence); else dma_fence_free(fence); rcu_read_unlock(); } EXPORT_SYMBOL(dma_fence_release); /** * dma_fence_free - default release function for &dma_fence. * @fence: fence to release * * This is the default implementation for &dma_fence_ops.release. It calls * kfree_rcu() on @fence. */ void dma_fence_free(struct dma_fence *fence) { kfree_rcu(fence, rcu); } EXPORT_SYMBOL(dma_fence_free); static bool __dma_fence_enable_signaling(struct dma_fence *fence) { const struct dma_fence_ops *ops; bool was_set; dma_fence_assert_held(fence); was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); if (dma_fence_test_signaled_flag(fence)) return false; rcu_read_lock(); ops = rcu_dereference(fence->ops); if (!was_set && ops && ops->enable_signaling) { trace_dma_fence_enable_signal(fence); if (!ops->enable_signaling(fence)) { rcu_read_unlock(); dma_fence_signal_locked(fence); return false; } } rcu_read_unlock(); return true; } /** * dma_fence_enable_signaling - enable signaling on fence * @fence: the fence to enable * * This will request for sw signaling to be enabled, to make the fence * complete as soon as possible. This calls &dma_fence_ops.enable_signaling * internally. */ void dma_fence_enable_signaling(struct dma_fence *fence) { unsigned long flags; dma_fence_lock_irqsave(fence, flags); __dma_fence_enable_signaling(fence); dma_fence_unlock_irqrestore(fence, flags); } EXPORT_SYMBOL(dma_fence_enable_signaling); /** * dma_fence_add_callback - add a callback to be called when the fence * is signaled * @fence: the fence to wait on * @cb: the callback to register * @func: the function to call * * Add a software callback to the fence. The caller should keep a reference to * the fence. * * @cb will be initialized by dma_fence_add_callback(), no initialization * by the caller is required. Any number of callbacks can be registered * to a fence, but a callback can only be registered to one fence at a time. * * If fence is already signaled, this function will return -ENOENT (and * *not* call the callback). * * Note that the callback can be called from an atomic context or irq context. * * Returns 0 in case of success, -ENOENT if the fence is already signaled * and -EINVAL in case of error. */ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, dma_fence_func_t func) { unsigned long flags; int ret = 0; if (WARN_ON(!fence || !func)) return -EINVAL; if (dma_fence_test_signaled_flag(fence)) { INIT_LIST_HEAD(&cb->node); return -ENOENT; } dma_fence_lock_irqsave(fence, flags); if (__dma_fence_enable_signaling(fence)) { cb->func = func; list_add_tail(&cb->node, &fence->cb_list); } else { INIT_LIST_HEAD(&cb->node); ret = -ENOENT; } dma_fence_unlock_irqrestore(fence, flags); return ret; } EXPORT_SYMBOL(dma_fence_add_callback); /** * dma_fence_get_status - returns the status upon completion * @fence: the dma_fence to query * * This wraps dma_fence_get_status_locked() to return the error status * condition on a signaled fence. See dma_fence_get_status_locked() for more * details. * * Returns 0 if the fence has not yet been signaled, 1 if the fence has * been signaled without an error condition, or a negative error code * if the fence has been completed in err. */ int dma_fence_get_status(struct dma_fence *fence) { unsigned long flags; int status; dma_fence_lock_irqsave(fence, flags); status = dma_fence_get_status_locked(fence); dma_fence_unlock_irqrestore(fence, flags); return status; } EXPORT_SYMBOL(dma_fence_get_status); /** * dma_fence_remove_callback - remove a callback from the signaling list * @fence: the fence to wait on * @cb: the callback to remove * * Remove a previously queued callback from the fence. This function returns * true if the callback is successfully removed, or false if the fence has * already been signaled. * * *WARNING*: * Cancelling a callback should only be done if you really know what you're * doing, since deadlocks and race conditions could occur all too easily. For * this reason, it should only ever be done on hardware lockup recovery, * with a reference held to the fence. * * Behaviour is undefined if @cb has not been added to @fence using * dma_fence_add_callback() beforehand. */ bool dma_fence_remove_callback(struct dma_fence *fence, struct dma_fence_cb *cb) { unsigned long flags; bool ret; dma_fence_lock_irqsave(fence, flags); ret = !list_empty(&cb->node); if (ret) list_del_init(&cb->node); dma_fence_unlock_irqrestore(fence, flags); return ret; } EXPORT_SYMBOL(dma_fence_remove_callback); struct default_wait_cb { struct dma_fence_cb base; struct task_struct *task; }; static void dma_fence_default_wait_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { struct default_wait_cb *wait = container_of(cb, struct default_wait_cb, base); wake_up_state(wait->task, TASK_NORMAL); } /** * dma_fence_default_wait - default sleep until the fence gets signaled * or until timeout elapses * @fence: the fence to wait on * @intr: if true, do an interruptible wait * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT * * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the * remaining timeout in jiffies on success. If timeout is zero the value one is * returned if the fence is already signaled for consistency with other * functions taking a jiffies timeout. */ signed long dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) { struct default_wait_cb cb; unsigned long flags; signed long ret = timeout ? timeout : 1; dma_fence_lock_irqsave(fence, flags); if (dma_fence_test_signaled_flag(fence)) goto out; if (intr && signal_pending(current)) { ret = -ERESTARTSYS; goto out; } if (!timeout) { ret = 0; goto out; } cb.base.func = dma_fence_default_wait_cb; cb.task = current; list_add(&cb.base.node, &fence->cb_list); while (!dma_fence_test_signaled_flag(fence) && ret > 0) { if (intr) __set_current_state(TASK_INTERRUPTIBLE); else __set_current_state(TASK_UNINTERRUPTIBLE); dma_fence_unlock_irqrestore(fence, flags); ret = schedule_timeout(ret); dma_fence_lock_irqsave(fence, flags); if (ret > 0 && intr && signal_pending(current)) ret = -ERESTARTSYS; } if (!list_empty(&cb.base.node)) list_del(&cb.base.node); __set_current_state(TASK_RUNNING); out: dma_fence_unlock_irqrestore(fence, flags); return ret; } EXPORT_SYMBOL(dma_fence_default_wait); static bool dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count, uint32_t *idx) { int i; for (i = 0; i < count; ++i) { struct dma_fence *fence = fences[i]; if (dma_fence_test_signaled_flag(fence)) { if (idx) *idx = i; return true; } } return false; } /** * dma_fence_wait_any_timeout - sleep until any fence gets signaled * or until timeout elapses * @fences: array of fences to wait on * @count: number of fences to wait on * @intr: if true, do an interruptible wait * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT * @idx: used to store the first signaled fence index, meaningful only on * positive return * * Returns -EINVAL on custom fence wait implementation, -ERESTARTSYS if * interrupted, 0 if the wait timed out, or the remaining timeout in jiffies * on success. * * Synchronous waits for the first fence in the array to be signaled. The * caller needs to hold a reference to all fences in the array, otherwise a * fence might be freed before return, resulting in undefined behavior. * * See also dma_fence_wait() and dma_fence_wait_timeout(). */ signed long dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count, bool intr, signed long timeout, uint32_t *idx) { struct default_wait_cb *cb; signed long ret = timeout; unsigned i; if (WARN_ON(!fences || !count || timeout < 0)) return -EINVAL; if (timeout == 0) { for (i = 0; i < count; ++i) if (dma_fence_is_signaled(fences[i])) { if (idx) *idx = i; return 1; } return 0; } cb = kzalloc_objs(struct default_wait_cb, count); if (cb == NULL) { ret = -ENOMEM; goto err_free_cb; } for (i = 0; i < count; ++i) { struct dma_fence *fence = fences[i]; cb[i].task = current; if (dma_fence_add_callback(fence, &cb[i].base, dma_fence_default_wait_cb)) { /* This fence is already signaled */ if (idx) *idx = i; goto fence_rm_cb; } } while (ret > 0) { if (intr) set_current_state(TASK_INTERRUPTIBLE); else set_current_state(TASK_UNINTERRUPTIBLE); if (dma_fence_test_signaled_any(fences, count, idx)) break; ret = schedule_timeout(ret); if (ret > 0 && intr && signal_pending(current)) ret = -ERESTARTSYS; } __set_current_state(TASK_RUNNING); fence_rm_cb: while (i-- > 0) dma_fence_remove_callback(fences[i], &cb[i].base); err_free_cb: kfree(cb); return ret; } EXPORT_SYMBOL(dma_fence_wait_any_timeout); /** * DOC: deadline hints * * In an ideal world, it would be possible to pipeline a workload sufficiently * that a utilization based device frequency governor could arrive at a minimum * frequency that meets the requirements of the use-case, in order to minimize * power consumption. But in the real world there are many workloads which * defy this ideal. For example, but not limited to: * * * Workloads that ping-pong between device and CPU, with alternating periods * of CPU waiting for device, and device waiting on CPU. This can result in * devfreq and cpufreq seeing idle time in their respective domains and in * result reduce frequency. * * * Workloads that interact with a periodic time based deadline, such as double * buffered GPU rendering vs vblank sync'd page flipping. In this scenario, * missing a vblank deadline results in an *increase* in idle time on the GPU * (since it has to wait an additional vblank period), sending a signal to * the GPU's devfreq to reduce frequency, when in fact the opposite is what is * needed. * * To this end, deadline hint(s) can be set on a &dma_fence via &dma_fence_set_deadline * (or indirectly via userspace facing ioctls like &sync_set_deadline). * The deadline hint provides a way for the waiting driver, or userspace, to * convey an appropriate sense of urgency to the signaling driver. * * A deadline hint is given in absolute ktime (CLOCK_MONOTONIC for userspace * facing APIs). The time could either be some point in the future (such as * the vblank based deadline for page-flipping, or the start of a compositor's * composition cycle), or the current time to indicate an immediate deadline * hint (Ie. forward progress cannot be made until this fence is signaled). * * Multiple deadlines may be set on a given fence, even in parallel. See the * documentation for &dma_fence_ops.set_deadline. * * The deadline hint is just that, a hint. The driver that created the fence * may react by increasing frequency, making different scheduling choices, etc. * Or doing nothing at all. */ /** * dma_fence_set_deadline - set desired fence-wait deadline hint * @fence: the fence that is to be waited on * @deadline: the time by which the waiter hopes for the fence to be * signaled * * Give the fence signaler a hint about an upcoming deadline, such as * vblank, by which point the waiter would prefer the fence to be * signaled by. This is intended to give feedback to the fence signaler * to aid in power management decisions, such as boosting GPU frequency * if a periodic vblank deadline is approaching but the fence is not * yet signaled.. */ void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) { const struct dma_fence_ops *ops; rcu_read_lock(); ops = rcu_dereference(fence->ops); if (ops && ops->set_deadline && !dma_fence_is_signaled(fence)) ops->set_deadline(fence, deadline); rcu_read_unlock(); } EXPORT_SYMBOL(dma_fence_set_deadline); /** * dma_fence_describe - Dump fence description into seq_file * @fence: the fence to describe * @seq: the seq_file to put the textual description into * * Dump a textual description of the fence and it's state into the seq_file. */ void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq) { const char __rcu *timeline = (const char __rcu *)""; const char __rcu *driver = (const char __rcu *)""; const char *signaled = ""; rcu_read_lock(); if (!dma_fence_is_signaled(fence)) { timeline = dma_fence_timeline_name(fence); driver = dma_fence_driver_name(fence); signaled = "un"; } seq_printf(seq, "%llu:%llu %s %s %ssignalled\n", fence->context, fence->seqno, timeline, driver, signaled); rcu_read_unlock(); } EXPORT_SYMBOL(dma_fence_describe); static void __dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, u64 seqno, unsigned long flags) { BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name); kref_init(&fence->refcount); /* * While it is counter intuitive to protect a constant function pointer * table by RCU it allows modules to wait for an RCU grace period * before they unload, to make sure that nobody is executing their * functions any more. */ RCU_INIT_POINTER(fence->ops, ops); INIT_LIST_HEAD(&fence->cb_list); fence->context = context; fence->seqno = seqno; fence->flags = flags | BIT(DMA_FENCE_FLAG_INITIALIZED_BIT); if (lock) { fence->extern_lock = lock; } else { spin_lock_init(&fence->inline_lock); fence->flags |= BIT(DMA_FENCE_FLAG_INLINE_LOCK_BIT); } fence->error = 0; trace_dma_fence_init(fence); } /** * dma_fence_init - Initialize a custom fence. * @fence: the fence to initialize * @ops: the dma_fence_ops for operations on this fence * @lock: optional irqsafe spinlock to use for locking this fence * @context: the execution context this fence is run on * @seqno: a linear increasing sequence number for this context * * Initializes an allocated fence, the caller doesn't have to keep its * refcount after committing with this fence, but it will need to hold a * refcount again if &dma_fence_ops.enable_signaling gets called. * * context and seqno are used for easy comparison between fences, allowing * to check which fence is later by simply using dma_fence_later(). * * External locks are a relic of legacy use cases that needed a shared lock * to serialize signaling when no out-of-order signaling was possible through * &dma_fence_ops.signaled. Drivers have abandoned this concept since the * introduction of the callback, but the external lock is still around. New * users MUST NOT use external locks, as they force the issuer to outlive all * fences that reference the lock. */ void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, u64 seqno) { __dma_fence_init(fence, ops, lock, context, seqno, 0UL); } EXPORT_SYMBOL(dma_fence_init); /** * dma_fence_init64 - Initialize a custom fence with 64-bit seqno support. * @fence: the fence to initialize * @ops: the dma_fence_ops for operations on this fence * @lock: optional irqsafe spinlock to use for locking this fence * @context: the execution context this fence is run on * @seqno: a linear increasing sequence number for this context * * Initializes an allocated fence, the caller doesn't have to keep its * refcount after committing with this fence, but it will need to hold a * refcount again if &dma_fence_ops.enable_signaling gets called. * * Context and seqno are used for easy comparison between fences, allowing * to check which fence is later by simply using dma_fence_later(). * * New users MUST NOT use external locks. Check the documentation in * dma_fence_init() to understand the motives behind the legacy use cases. */ void dma_fence_init64(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, u64 seqno) { __dma_fence_init(fence, ops, lock, context, seqno, BIT(DMA_FENCE_FLAG_SEQNO64_BIT)); } EXPORT_SYMBOL(dma_fence_init64); /** * dma_fence_driver_name - Access the driver name * @fence: the fence to query * * Returns a driver name backing the dma-fence implementation. * * IMPORTANT CONSIDERATION: * Dma-fence contract stipulates that access to driver provided data (data not * directly embedded into the object itself), such as the &dma_fence.lock and * memory potentially accessed by the &dma_fence.ops functions, is forbidden * after the fence has been signalled. Drivers are allowed to free that data, * and some do. * * To allow safe access drivers are mandated to guarantee a RCU grace period * between signalling the fence and freeing said data. * * As such access to the driver name is only valid inside a RCU locked section. * The pointer MUST be both queried and USED ONLY WITHIN a SINGLE block guarded * by the &rcu_read_lock and &rcu_read_unlock pair. */ const char __rcu *dma_fence_driver_name(struct dma_fence *fence) { const struct dma_fence_ops *ops; /* RCU protection is required for safe access to returned string */ ops = rcu_dereference(fence->ops); if (ops) return (const char __rcu *)ops->get_driver_name(fence); else return (const char __rcu *)"detached-driver"; } EXPORT_SYMBOL(dma_fence_driver_name); /** * dma_fence_timeline_name - Access the timeline name * @fence: the fence to query * * Returns a timeline name provided by the dma-fence implementation. * * IMPORTANT CONSIDERATION: * Dma-fence contract stipulates that access to driver provided data (data not * directly embedded into the object itself), such as the &dma_fence.lock and * memory potentially accessed by the &dma_fence.ops functions, is forbidden * after the fence has been signalled. Drivers are allowed to free that data, * and some do. * * To allow safe access drivers are mandated to guarantee a RCU grace period * between signalling the fence and freeing said data. * * As such access to the driver name is only valid inside a RCU locked section. * The pointer MUST be both queried and USED ONLY WITHIN a SINGLE block guarded * by the &rcu_read_lock and &rcu_read_unlock pair. */ const char __rcu *dma_fence_timeline_name(struct dma_fence *fence) { const struct dma_fence_ops *ops; /* RCU protection is required for safe access to returned string */ ops = rcu_dereference(fence->ops); if (ops) return (const char __rcu *)ops->get_timeline_name(fence); else return (const char __rcu *)"signaled-timeline"; } EXPORT_SYMBOL(dma_fence_timeline_name); |
| 6 5 4 2 25 1 2 23 1 2 6 6 5 6 3 3 6 2 1 3 1 2 3 3 1 2 1 1 6 6 2 1 1 2 149 1 1 1 2 1 1 2 2 1 1 1 6 1 1 1 5 3 1 3 2 2 1 1 36 26 1 1 8 4 1 2 1 2 1 5 1 5 14 1 1 5 1 1 1 2 2 2 2 1 2 2 2 2 2 2 2 1 2 16 1 11 4 6 3 1 5 6 2 2 4 3 6 6 9 5 4 6 4 338 338 221 108 31 30 54 1 1 1 2 1 1 1 1 1 1 1 1 1 5 1 1 3 1 1 2 2 1 5 5 5 7 1 16 1 1 1 2 2 6 1 22 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992 obz under the linux copyright * * Dynamic diacritical handling - aeb@cwi.nl - Dec 1993 * Dynamic keymap and string allocation - aeb@cwi.nl - May 1994 * Restrict VT switching via ioctl() - grif@cs.ucr.edu - Dec 1995 * Some code moved for less code duplication - Andi Kleen - Mar 1997 * Check put/get_user, cleanups - acme@conectiva.com.br - Jun 2001 */ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/tty.h> #include <linux/timer.h> #include <linux/kernel.h> #include <linux/compat.h> #include <linux/module.h> #include <linux/kd.h> #include <linux/vt.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/console.h> #include <linux/consolemap.h> #include <linux/signal.h> #include <linux/suspend.h> #include <linux/timex.h> #include <asm/io.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include <linux/kbd_kern.h> #include <linux/vt_kern.h> #include <linux/kbd_diacr.h> #include <linux/selection.h> bool vt_dont_switch; static inline bool vt_in_use(unsigned int i) { const struct vc_data *vc = vc_cons[i].d; /* * console_lock must be held to prevent the vc from being deallocated * while we're checking whether it's in-use. */ WARN_CONSOLE_UNLOCKED(); return vc && kref_read(&vc->port.kref) > 1; } static inline bool vt_busy(int i) { if (vt_in_use(i)) return true; if (i == fg_console) return true; if (vc_is_sel(vc_cons[i].d)) return true; return false; } /* * Console (vt and kd) routines, as defined by USL SVR4 manual, and by * experimentation and study of X386 SYSV handling. * * One point of difference: SYSV vt's are /dev/vtX, which X >= 0, and * /dev/console is a separate ttyp. Under Linux, /dev/tty0 is /dev/console, * and the vc start at /dev/ttyX, X >= 1. We maintain that here, so we will * always treat our set of vt as numbered 1..MAX_NR_CONSOLES (corresponding to * ttys 0..MAX_NR_CONSOLES-1). Explicitly naming VT 0 is illegal, but using * /dev/tty0 (fg_console) as a target is legal, since an implicit aliasing * to the current console is done by the main ioctl code. */ #ifdef CONFIG_X86 #include <asm/syscalls.h> #endif static void complete_change_console(struct vc_data *vc); /* * User space VT_EVENT handlers */ struct vt_event_wait { struct list_head list; struct vt_event event; int done; }; static LIST_HEAD(vt_events); static DEFINE_SPINLOCK(vt_event_lock); static DECLARE_WAIT_QUEUE_HEAD(vt_event_waitqueue); /** * vt_event_post * @event: the event that occurred * @old: old console * @new: new console * * Post an VT event to interested VT handlers */ void vt_event_post(unsigned int event, unsigned int old, unsigned int new) { struct list_head *pos, *head; unsigned long flags; int wake = 0; spin_lock_irqsave(&vt_event_lock, flags); head = &vt_events; list_for_each(pos, head) { struct vt_event_wait *ve = list_entry(pos, struct vt_event_wait, list); if (!(ve->event.event & event)) continue; ve->event.event = event; /* kernel view is consoles 0..n-1, user space view is console 1..n with 0 meaning current, so we must bias */ ve->event.oldev = old + 1; ve->event.newev = new + 1; wake = 1; ve->done = 1; } spin_unlock_irqrestore(&vt_event_lock, flags); if (wake) wake_up_interruptible(&vt_event_waitqueue); } static void __vt_event_queue(struct vt_event_wait *vw) { unsigned long flags; /* Prepare the event */ INIT_LIST_HEAD(&vw->list); vw->done = 0; /* Queue our event */ spin_lock_irqsave(&vt_event_lock, flags); list_add(&vw->list, &vt_events); spin_unlock_irqrestore(&vt_event_lock, flags); } static void __vt_event_wait(struct vt_event_wait *vw) { /* Wait for it to pass */ wait_event_interruptible(vt_event_waitqueue, vw->done); } static void __vt_event_dequeue(struct vt_event_wait *vw) { unsigned long flags; /* Dequeue it */ spin_lock_irqsave(&vt_event_lock, flags); list_del(&vw->list); spin_unlock_irqrestore(&vt_event_lock, flags); } /** * vt_event_wait - wait for an event * @vw: our event * * Waits for an event to occur which completes our vt_event_wait * structure. On return the structure has wv->done set to 1 for success * or 0 if some event such as a signal ended the wait. */ static void vt_event_wait(struct vt_event_wait *vw) { __vt_event_queue(vw); __vt_event_wait(vw); __vt_event_dequeue(vw); } /** * vt_event_wait_ioctl - event ioctl handler * @event: argument to ioctl (the event) * * Implement the VT_WAITEVENT ioctl using the VT event interface */ static int vt_event_wait_ioctl(struct vt_event __user *event) { struct vt_event_wait vw; if (copy_from_user(&vw.event, event, sizeof(struct vt_event))) return -EFAULT; /* Highest supported event for now */ if (vw.event.event & ~VT_MAX_EVENT) return -EINVAL; vt_event_wait(&vw); /* If it occurred report it */ if (vw.done) { if (copy_to_user(event, &vw.event, sizeof(struct vt_event))) return -EFAULT; return 0; } return -EINTR; } /** * vt_waitactive - active console wait * @n: new console * * Helper for event waits. Used to implement the legacy * event waiting ioctls in terms of events */ int vt_waitactive(int n) { struct vt_event_wait vw; do { vw.event.event = VT_EVENT_SWITCH; __vt_event_queue(&vw); if (n == fg_console + 1) { __vt_event_dequeue(&vw); break; } __vt_event_wait(&vw); __vt_event_dequeue(&vw); if (vw.done == 0) return -EINTR; } while (vw.event.newev != n); return 0; } /* * these are the valid i/o ports we're allowed to change. they map all the * video ports */ #define GPFIRST 0x3b4 #define GPLAST 0x3df #define GPNUM (GPLAST - GPFIRST + 1) /* * currently, setting the mode from KD_TEXT to KD_GRAPHICS doesn't do a whole * lot. i'm not sure if it should do any restoration of modes or what... * * XXX It should at least call into the driver, fbdev's definitely need to * restore their engine state. --BenH * * Called with the console lock held. */ static int vt_kdsetmode(struct vc_data *vc, unsigned long mode) { switch (mode) { case KD_GRAPHICS: break; case KD_TEXT0: case KD_TEXT1: mode = KD_TEXT; fallthrough; case KD_TEXT: break; default: return -EINVAL; } if (vc->vc_mode == mode) return 0; vc->vc_mode = mode; if (vc->vc_num != fg_console) return 0; /* explicitly blank/unblank the screen if switching modes */ if (mode == KD_TEXT) do_unblank_screen(1); else do_blank_screen(1); return 0; } static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg, bool perm) { struct vc_data *vc = tty->driver_data; void __user *up = (void __user *)arg; unsigned int console = vc->vc_num; int ret; switch (cmd) { case KIOCSOUND: if (!perm) return -EPERM; /* * The use of PIT_TICK_RATE is historic, it used to be * the platform-dependent CLOCK_TICK_RATE between 2.6.12 * and 2.6.36, which was a minor but unfortunate ABI * change. kd_mksound is locked by the input layer. */ if (arg) arg = PIT_TICK_RATE / arg; kd_mksound(arg, 0); break; case KDMKTONE: if (!perm) return -EPERM; { unsigned int ticks, count; /* * Generate the tone for the appropriate number of ticks. * If the time is zero, turn off sound ourselves. */ ticks = msecs_to_jiffies((arg >> 16) & 0xffff); count = ticks ? (arg & 0xffff) : 0; if (count) count = PIT_TICK_RATE / count; kd_mksound(count, ticks); break; } case KDGKBTYPE: /* * this is naïve. */ return put_user(KB_101, (char __user *)arg); /* * These cannot be implemented on any machine that implements * ioperm() in user level (such as Alpha PCs) or not at all. * * XXX: you should never use these, just call ioperm directly.. */ #ifdef CONFIG_X86 case KDADDIO: case KDDELIO: /* * KDADDIO and KDDELIO may be able to add ports beyond what * we reject here, but to be safe... * * These are locked internally via sys_ioperm */ if (arg < GPFIRST || arg > GPLAST) return -EINVAL; return ksys_ioperm(arg, 1, (cmd == KDADDIO)) ? -ENXIO : 0; case KDENABIO: case KDDISABIO: return ksys_ioperm(GPFIRST, GPNUM, (cmd == KDENABIO)) ? -ENXIO : 0; #endif /* Linux m68k/i386 interface for setting the keyboard delay/repeat rate */ case KDKBDREP: { struct kbd_repeat kbrep; if (!capable(CAP_SYS_TTY_CONFIG)) return -EPERM; if (copy_from_user(&kbrep, up, sizeof(struct kbd_repeat))) return -EFAULT; ret = kbd_rate(&kbrep); if (ret) return ret; if (copy_to_user(up, &kbrep, sizeof(struct kbd_repeat))) return -EFAULT; break; } case KDSETMODE: { if (!perm) return -EPERM; guard(console_lock)(); return vt_kdsetmode(vc, arg); } case KDGETMODE: return put_user(vc->vc_mode, (int __user *)arg); case KDMAPDISP: case KDUNMAPDISP: /* * these work like a combination of mmap and KDENABIO. * this could be easily finished. */ return -EINVAL; case KDSKBMODE: if (!perm) return -EPERM; ret = vt_do_kdskbmode(console, arg); if (ret) return ret; tty_ldisc_flush(tty); break; case KDGKBMODE: return put_user(vt_do_kdgkbmode(console), (int __user *)arg); /* this could be folded into KDSKBMODE, but for compatibility reasons it is not so easy to fold KDGKBMETA into KDGKBMODE */ case KDSKBMETA: if (!perm) return -EPERM; return vt_do_kdskbmeta(console, arg); case KDGKBMETA: /* FIXME: should review whether this is worth locking */ return put_user(vt_do_kdgkbmeta(console), (int __user *)arg); case KDGETKEYCODE: case KDSETKEYCODE: if(!capable(CAP_SYS_TTY_CONFIG)) perm = 0; return vt_do_kbkeycode_ioctl(cmd, up, perm); case KDGKBENT: case KDSKBENT: return vt_do_kdsk_ioctl(cmd, up, perm, console); case KDGKBSENT: case KDSKBSENT: return vt_do_kdgkb_ioctl(cmd, up, perm); /* Diacritical processing. Handled in keyboard.c as it has to operate on the keyboard locks and structures */ case KDGKBDIACR: case KDGKBDIACRUC: case KDSKBDIACR: case KDSKBDIACRUC: return vt_do_diacrit(cmd, up, perm); /* the ioctls below read/set the flags usually shown in the leds */ /* don't use them - they will go away without warning */ case KDGKBLED: case KDSKBLED: case KDGETLED: case KDSETLED: return vt_do_kdskled(console, cmd, arg, perm); /* * A process can indicate its willingness to accept signals * generated by pressing an appropriate key combination. * Thus, one can have a daemon that e.g. spawns a new console * upon a keypress and then changes to it. * See also the kbrequest field of inittab(5). */ case KDSIGACCEPT: if (!perm || !capable(CAP_KILL)) return -EPERM; if (!valid_signal(arg) || arg < 1 || arg == SIGKILL) return -EINVAL; spin_lock_irq(&vt_spawn_con.lock); put_pid(vt_spawn_con.pid); vt_spawn_con.pid = get_pid(task_pid(current)); vt_spawn_con.sig = arg; spin_unlock_irq(&vt_spawn_con.lock); break; case KDFONTOP: { struct console_font_op op; if (copy_from_user(&op, up, sizeof(op))) return -EFAULT; if (!perm && op.op != KD_FONT_OP_GET) return -EPERM; ret = con_font_op(vc, &op); if (ret) return ret; if (copy_to_user(up, &op, sizeof(op))) return -EFAULT; break; } default: return -ENOIOCTLCMD; } return 0; } static inline int do_unimap_ioctl(int cmd, struct unimapdesc __user *user_ud, bool perm, struct vc_data *vc) { struct unimapdesc tmp; if (copy_from_user(&tmp, user_ud, sizeof tmp)) return -EFAULT; switch (cmd) { case PIO_UNIMAP: if (!perm) return -EPERM; return con_set_unimap(vc, tmp.entry_ct, tmp.entries); case GIO_UNIMAP: if (!perm && fg_console != vc->vc_num) return -EPERM; return con_get_unimap(vc, tmp.entry_ct, &(user_ud->entry_ct), tmp.entries); } return 0; } static int vt_io_ioctl(struct vc_data *vc, unsigned int cmd, void __user *up, bool perm) { switch (cmd) { case PIO_CMAP: if (!perm) return -EPERM; return con_set_cmap(up); case GIO_CMAP: return con_get_cmap(up); case PIO_SCRNMAP: if (!perm) return -EPERM; return con_set_trans_old(up); case GIO_SCRNMAP: return con_get_trans_old(up); case PIO_UNISCRNMAP: if (!perm) return -EPERM; return con_set_trans_new(up); case GIO_UNISCRNMAP: return con_get_trans_new(up); case PIO_UNIMAPCLR: if (!perm) return -EPERM; con_clear_unimap(vc); break; case PIO_UNIMAP: case GIO_UNIMAP: return do_unimap_ioctl(cmd, up, perm, vc); default: return -ENOIOCTLCMD; } return 0; } static int vt_reldisp(struct vc_data *vc, unsigned int swtch) { int newvt, ret; if (vc->vt_mode.mode != VT_PROCESS) return -EINVAL; /* Switched-to response */ if (vc->vt_newvt < 0) { /* If it's just an ACK, ignore it */ return swtch == VT_ACKACQ ? 0 : -EINVAL; } /* Switching-from response */ if (swtch == 0) { /* Switch disallowed, so forget we were trying to do it. */ vc->vt_newvt = -1; return 0; } /* The current vt has been released, so complete the switch. */ newvt = vc->vt_newvt; vc->vt_newvt = -1; ret = vc_allocate(newvt); if (ret) return ret; /* * When we actually do the console switch, make sure we are atomic with * respect to other console switches.. */ complete_change_console(vc_cons[newvt].d); return 0; } static int vt_setactivate(struct vt_setactivate __user *sa) { struct vt_setactivate vsa; struct vc_data *nvc; int ret; if (copy_from_user(&vsa, sa, sizeof(vsa))) return -EFAULT; if (vsa.console == 0 || vsa.console > MAX_NR_CONSOLES) return -ENXIO; if (vsa.mode.mode != VT_AUTO && vsa.mode.mode != VT_PROCESS) return -EINVAL; vsa.console--; vsa.console = array_index_nospec(vsa.console, MAX_NR_CONSOLES); scoped_guard(console_lock) { ret = vc_allocate(vsa.console); if (ret) return ret; /* * This is safe providing we don't drop the console sem between * vc_allocate and finishing referencing nvc. */ nvc = vc_cons[vsa.console].d; nvc->vt_mode = vsa.mode; nvc->vt_mode.frsig = 0; put_pid(nvc->vt_pid); nvc->vt_pid = get_pid(task_pid(current)); } /* Commence switch and lock */ /* Review set_console locks */ set_console(vsa.console); return 0; } /* deallocate a single console, if possible (leave 0) */ static int vt_disallocate(unsigned int vc_num) { struct vc_data *vc = NULL; scoped_guard(console_lock) { if (vt_busy(vc_num)) return -EBUSY; if (vc_num) vc = vc_deallocate(vc_num); } if (vc && vc_num >= MIN_NR_CONSOLES) tty_port_put(&vc->port); return 0; } /* deallocate all unused consoles, but leave 0 */ static void vt_disallocate_all(void) { struct vc_data *vc[MAX_NR_CONSOLES]; int i; scoped_guard(console_lock) for (i = 1; i < MAX_NR_CONSOLES; i++) if (!vt_busy(i)) vc[i] = vc_deallocate(i); else vc[i] = NULL; for (i = 1; i < MAX_NR_CONSOLES; i++) { if (vc[i] && i >= MIN_NR_CONSOLES) tty_port_put(&vc[i]->port); } } static int vt_resizex(struct vc_data *vc, struct vt_consize __user *cs) { struct vt_consize v; int i; if (copy_from_user(&v, cs, sizeof(struct vt_consize))) return -EFAULT; /* FIXME: Should check the copies properly */ if (!v.v_vlin) v.v_vlin = vc->vc_scan_lines; if (v.v_clin) { int rows = v.v_vlin / v.v_clin; if (v.v_rows != rows) { if (v.v_rows) /* Parameters don't add up */ return -EINVAL; v.v_rows = rows; } } if (v.v_vcol && v.v_ccol) { int cols = v.v_vcol / v.v_ccol; if (v.v_cols != cols) { if (v.v_cols) return -EINVAL; v.v_cols = cols; } } if (v.v_clin > 32) return -EINVAL; for (i = 0; i < MAX_NR_CONSOLES; i++) { struct vc_data *vcp; if (!vc_cons[i].d) continue; guard(console_lock)(); vcp = vc_cons[i].d; if (vcp) { int ret; int save_scan_lines = vcp->vc_scan_lines; int save_cell_height = vcp->vc_cell_height; if (v.v_vlin) vcp->vc_scan_lines = v.v_vlin; if (v.v_clin) vcp->vc_cell_height = v.v_clin; ret = __vc_resize(vcp, v.v_cols, v.v_rows, true); if (ret) { vcp->vc_scan_lines = save_scan_lines; vcp->vc_cell_height = save_cell_height; return ret; } } } return 0; } /* * We handle the console-specific ioctl's here. We allow the * capability to modify any console, not just the fg_console. */ int vt_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct vc_data *vc = tty->driver_data; void __user *up = (void __user *)arg; int i, perm; int ret; /* * To have permissions to do most of the vt ioctls, we either have * to be the owner of the tty, or have CAP_SYS_TTY_CONFIG. */ perm = 0; if (current->signal->tty == tty || capable(CAP_SYS_TTY_CONFIG)) perm = 1; ret = vt_k_ioctl(tty, cmd, arg, perm); if (ret != -ENOIOCTLCMD) return ret; ret = vt_io_ioctl(vc, cmd, up, perm); if (ret != -ENOIOCTLCMD) return ret; switch (cmd) { case TIOCLINUX: return tioclinux(tty, arg); case VT_SETMODE: { struct vt_mode tmp; if (!perm) return -EPERM; if (copy_from_user(&tmp, up, sizeof(struct vt_mode))) return -EFAULT; if (tmp.mode != VT_AUTO && tmp.mode != VT_PROCESS) return -EINVAL; guard(console_lock)(); vc->vt_mode = tmp; /* the frsig is ignored, so we set it to 0 */ vc->vt_mode.frsig = 0; put_pid(vc->vt_pid); vc->vt_pid = get_pid(task_pid(current)); /* no switch is required -- saw@shade.msu.ru */ vc->vt_newvt = -1; break; } case VT_GETMODE: { struct vt_mode tmp; int rc; scoped_guard(console_lock) memcpy(&tmp, &vc->vt_mode, sizeof(struct vt_mode)); rc = copy_to_user(up, &tmp, sizeof(struct vt_mode)); if (rc) return -EFAULT; break; } /* * Returns global vt state. Note that VT 0 is always open, since * it's an alias for the current VT, and people can't use it here. * We cannot return state for more than 16 VTs, since v_state is short. */ case VT_GETSTATE: { struct vt_stat __user *vtstat = up; unsigned short state, mask; if (put_user(fg_console + 1, &vtstat->v_active)) return -EFAULT; state = 1; /* /dev/tty0 is always open */ scoped_guard(console_lock) /* required by vt_in_use() */ for (i = 0, mask = 2; i < MAX_NR_CONSOLES && mask; ++i, mask <<= 1) if (vt_in_use(i)) state |= mask; return put_user(state, &vtstat->v_state); } /* * Returns the first available (non-opened) console. */ case VT_OPENQRY: scoped_guard(console_lock) /* required by vt_in_use() */ for (i = 0; i < MAX_NR_CONSOLES; ++i) if (!vt_in_use(i)) break; i = i < MAX_NR_CONSOLES ? (i+1) : -1; return put_user(i, (int __user *)arg); /* * ioctl(fd, VT_ACTIVATE, num) will cause us to switch to vt # num, * with num >= 1 (switches to vt 0, our console, are not allowed, just * to preserve sanity). */ case VT_ACTIVATE: if (!perm) return -EPERM; if (arg == 0 || arg > MAX_NR_CONSOLES) return -ENXIO; arg--; arg = array_index_nospec(arg, MAX_NR_CONSOLES); scoped_guard(console_lock) { ret = vc_allocate(arg); if (ret) return ret; } set_console(arg); break; case VT_SETACTIVATE: if (!perm) return -EPERM; return vt_setactivate(up); /* * wait until the specified VT has been activated */ case VT_WAITACTIVE: if (!perm) return -EPERM; if (arg == 0 || arg > MAX_NR_CONSOLES) return -ENXIO; return vt_waitactive(arg); /* * If a vt is under process control, the kernel will not switch to it * immediately, but postpone the operation until the process calls this * ioctl, allowing the switch to complete. * * According to the X sources this is the behavior: * 0: pending switch-from not OK * 1: pending switch-from OK * 2: completed switch-to OK */ case VT_RELDISP: { if (!perm) return -EPERM; guard(console_lock)(); return vt_reldisp(vc, arg); } /* * Disallocate memory associated to VT (but leave VT1) */ case VT_DISALLOCATE: if (arg > MAX_NR_CONSOLES) return -ENXIO; if (arg == 0) { vt_disallocate_all(); break; } arg = array_index_nospec(arg - 1, MAX_NR_CONSOLES); return vt_disallocate(arg); case VT_RESIZE: { struct vt_sizes __user *vtsizes = up; struct vc_data *vc; ushort ll,cc; if (!perm) return -EPERM; if (get_user(ll, &vtsizes->v_rows) || get_user(cc, &vtsizes->v_cols)) return -EFAULT; guard(console_lock)(); for (i = 0; i < MAX_NR_CONSOLES; i++) { vc = vc_cons[i].d; if (vc) { /* FIXME: review v tty lock */ ret = __vc_resize(vc_cons[i].d, cc, ll, true); if (ret) return ret; } } break; } case VT_RESIZEX: if (!perm) return -EPERM; return vt_resizex(vc, up); case VT_LOCKSWITCH: if (!capable(CAP_SYS_TTY_CONFIG)) return -EPERM; vt_dont_switch = true; break; case VT_UNLOCKSWITCH: if (!capable(CAP_SYS_TTY_CONFIG)) return -EPERM; vt_dont_switch = false; break; case VT_GETHIFONTMASK: return put_user(vc->vc_hi_font_mask, (unsigned short __user *)arg); case VT_WAITEVENT: return vt_event_wait_ioctl((struct vt_event __user *)arg); case VT_GETCONSIZECSRPOS: { struct vt_consizecsrpos concsr; console_lock(); concsr.con_cols = vc->vc_cols; concsr.con_rows = vc->vc_rows; concsr.csr_col = vc->state.x; concsr.csr_row = vc->state.y; console_unlock(); if (copy_to_user(up, &concsr, sizeof(concsr))) return -EFAULT; return 0; } default: return -ENOIOCTLCMD; } return 0; } void reset_vc(struct vc_data *vc) { vc->vc_mode = KD_TEXT; vt_reset_unicode(vc->vc_num); vc->vt_mode.mode = VT_AUTO; vc->vt_mode.waitv = 0; vc->vt_mode.relsig = 0; vc->vt_mode.acqsig = 0; vc->vt_mode.frsig = 0; put_pid(vc->vt_pid); vc->vt_pid = NULL; vc->vt_newvt = -1; reset_palette(vc); } void vc_SAK(struct work_struct *work) { struct vc *vc_con = container_of(work, struct vc, SAK_work); struct vc_data *vc; struct tty_struct *tty; guard(console_lock)(); vc = vc_con->d; if (!vc) return; /* FIXME: review tty ref counting */ tty = vc->port.tty; /* SAK should also work in all raw modes and reset them properly. */ if (tty) __do_SAK(tty); reset_vc(vc); } #ifdef CONFIG_COMPAT struct compat_console_font_op { compat_uint_t op; /* operation code KD_FONT_OP_* */ compat_uint_t flags; /* KD_FONT_FLAG_* */ compat_uint_t width, height; /* font size */ compat_uint_t charcount; compat_caddr_t data; /* font data with height fixed to 32 */ }; static inline int compat_kdfontop_ioctl(struct compat_console_font_op __user *fontop, int perm, struct console_font_op *op, struct vc_data *vc) { int i; if (copy_from_user(op, fontop, sizeof(struct compat_console_font_op))) return -EFAULT; if (!perm && op->op != KD_FONT_OP_GET) return -EPERM; op->data = compat_ptr(((struct compat_console_font_op *)op)->data); i = con_font_op(vc, op); if (i) return i; ((struct compat_console_font_op *)op)->data = (unsigned long)op->data; if (copy_to_user(fontop, op, sizeof(struct compat_console_font_op))) return -EFAULT; return 0; } struct compat_unimapdesc { unsigned short entry_ct; compat_caddr_t entries; }; static inline int compat_unimap_ioctl(unsigned int cmd, struct compat_unimapdesc __user *user_ud, int perm, struct vc_data *vc) { struct compat_unimapdesc tmp; struct unipair __user *tmp_entries; if (copy_from_user(&tmp, user_ud, sizeof tmp)) return -EFAULT; tmp_entries = compat_ptr(tmp.entries); switch (cmd) { case PIO_UNIMAP: if (!perm) return -EPERM; return con_set_unimap(vc, tmp.entry_ct, tmp_entries); case GIO_UNIMAP: if (!perm && fg_console != vc->vc_num) return -EPERM; return con_get_unimap(vc, tmp.entry_ct, &(user_ud->entry_ct), tmp_entries); } return 0; } long vt_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct vc_data *vc = tty->driver_data; struct console_font_op op; /* used in multiple places here */ void __user *up = compat_ptr(arg); int perm; /* * To have permissions to do most of the vt ioctls, we either have * to be the owner of the tty, or have CAP_SYS_TTY_CONFIG. */ perm = 0; if (current->signal->tty == tty || capable(CAP_SYS_TTY_CONFIG)) perm = 1; switch (cmd) { /* * these need special handlers for incompatible data structures */ case KDFONTOP: return compat_kdfontop_ioctl(up, perm, &op, vc); case PIO_UNIMAP: case GIO_UNIMAP: return compat_unimap_ioctl(cmd, up, perm, vc); /* * all these treat 'arg' as an integer */ case KIOCSOUND: case KDMKTONE: #ifdef CONFIG_X86 case KDADDIO: case KDDELIO: #endif case KDSETMODE: case KDMAPDISP: case KDUNMAPDISP: case KDSKBMODE: case KDSKBMETA: case KDSKBLED: case KDSETLED: case KDSIGACCEPT: case VT_ACTIVATE: case VT_WAITACTIVE: case VT_RELDISP: case VT_DISALLOCATE: return vt_ioctl(tty, cmd, arg); /* * the rest has a compatible data structure behind arg, * but we have to convert it to a proper 64 bit pointer. */ default: return vt_ioctl(tty, cmd, (unsigned long)up); } } #endif /* CONFIG_COMPAT */ /* * Performs the back end of a vt switch. Called under the console * semaphore. */ static void complete_change_console(struct vc_data *vc) { unsigned char old_vc_mode; int old = fg_console; last_console = fg_console; /* * If we're switching, we could be going from KD_GRAPHICS to * KD_TEXT mode or vice versa, which means we need to blank or * unblank the screen later. */ old_vc_mode = vc_cons[fg_console].d->vc_mode; switch_screen(vc); /* * This can't appear below a successful kill_pid(). If it did, * then the *blank_screen operation could occur while X, having * received acqsig, is waking up on another processor. This * condition can lead to overlapping accesses to the VGA range * and the framebuffer (causing system lockups). * * To account for this we duplicate this code below only if the * controlling process is gone and we've called reset_vc. */ if (old_vc_mode != vc->vc_mode) { if (vc->vc_mode == KD_TEXT) do_unblank_screen(1); else do_blank_screen(1); } /* * If this new console is under process control, send it a signal * telling it that it has acquired. Also check if it has died and * clean up (similar to logic employed in change_console()) */ if (vc->vt_mode.mode == VT_PROCESS) { /* * Send the signal as privileged - kill_pid() will * tell us if the process has gone or something else * is awry */ if (kill_pid(vc->vt_pid, vc->vt_mode.acqsig, 1) != 0) { /* * The controlling process has died, so we revert back to * normal operation. In this case, we'll also change back * to KD_TEXT mode. I'm not sure if this is strictly correct * but it saves the agony when the X server dies and the screen * remains blanked due to KD_GRAPHICS! It would be nice to do * this outside of VT_PROCESS but there is no single process * to account for and tracking tty count may be undesirable. */ reset_vc(vc); if (old_vc_mode != vc->vc_mode) { if (vc->vc_mode == KD_TEXT) do_unblank_screen(1); else do_blank_screen(1); } } } /* * Wake anyone waiting for their VT to activate */ vt_event_post(VT_EVENT_SWITCH, old, vc->vc_num); return; } /* * Performs the front-end of a vt switch */ void change_console(struct vc_data *new_vc) { struct vc_data *vc; if (!new_vc || new_vc->vc_num == fg_console || vt_dont_switch) return; /* * If this vt is in process mode, then we need to handshake with * that process before switching. Essentially, we store where that * vt wants to switch to and wait for it to tell us when it's done * (via VT_RELDISP ioctl). * * We also check to see if the controlling process still exists. * If it doesn't, we reset this vt to auto mode and continue. * This is a cheap way to track process control. The worst thing * that can happen is: we send a signal to a process, it dies, and * the switch gets "lost" waiting for a response; hopefully, the * user will try again, we'll detect the process is gone (unless * the user waits just the right amount of time :-) and revert the * vt to auto control. */ vc = vc_cons[fg_console].d; if (vc->vt_mode.mode == VT_PROCESS) { /* * Send the signal as privileged - kill_pid() will * tell us if the process has gone or something else * is awry. * * We need to set vt_newvt *before* sending the signal or we * have a race. */ vc->vt_newvt = new_vc->vc_num; if (kill_pid(vc->vt_pid, vc->vt_mode.relsig, 1) == 0) { /* * It worked. Mark the vt to switch to and * return. The process needs to send us a * VT_RELDISP ioctl to complete the switch. */ return; } /* * The controlling process has died, so we revert back to * normal operation. In this case, we'll also change back * to KD_TEXT mode. I'm not sure if this is strictly correct * but it saves the agony when the X server dies and the screen * remains blanked due to KD_GRAPHICS! It would be nice to do * this outside of VT_PROCESS but there is no single process * to account for and tracking tty count may be undesirable. */ reset_vc(vc); /* * Fall through to normal (VT_AUTO) handling of the switch... */ } /* * Ignore all switches in KD_GRAPHICS+VT_AUTO mode */ if (vc->vc_mode == KD_GRAPHICS) return; complete_change_console(new_vc); } /* Perform a kernel triggered VT switch for suspend/resume */ static int disable_vt_switch; int vt_move_to_console(unsigned int vt, int alloc) { int prev; scoped_guard(console_lock) { /* Graphics mode - up to X */ if (disable_vt_switch) return 0; prev = fg_console; if (alloc && vc_allocate(vt)) { /* * We can't have a free VC for now. Too bad, we don't want to mess the * screen for now. */ return -ENOSPC; } if (set_console(vt)) { /* * We're unable to switch to the SUSPEND_CONSOLE. Let the calling function * know so it can decide what to do. */ return -EIO; } } if (vt_waitactive(vt + 1)) { pr_debug("Suspend: Can't switch VCs."); return -EINTR; } return prev; } /* * Normally during a suspend, we allocate a new console and switch to it. * When we resume, we switch back to the original console. This switch * can be slow, so on systems where the framebuffer can handle restoration * of video registers anyways, there's little point in doing the console * switch. This function allows you to disable it by passing it '0'. */ void pm_set_vt_switch(int do_switch) { guard(console_lock)(); disable_vt_switch = !do_switch; } EXPORT_SYMBOL(pm_set_vt_switch); |
| 12 12 75 89 1 89 42 1 41 88 88 50 41 45 7 39 17 83 88 88 88 2 88 88 14 68 1 1 1 2 1 1 6 6 2 4 8 5 3 8 4 2 2 4 20 20 19 73 43 45 43 45 73 73 47 25 73 73 20 73 3 63 62 63 62 73 1 70 59 62 63 29 69 8 73 73 73 73 101 2 2 2 104 1 9 11 76 22 90 29 73 49 46 13 29 27 116 116 23 101 101 34 116 2 2 54 68 54 12 12 10 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 | // SPDX-License-Identifier: GPL-2.0+ /* * module/drivers.c * functions for manipulating drivers * * COMEDI - Linux Control and Measurement Device Interface * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> * Copyright (C) 2002 Frank Mori Hess <fmhess@users.sourceforge.net> */ #include <linux/device.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/ioport.h> #include <linux/slab.h> #include <linux/dma-direction.h> #include <linux/interrupt.h> #include <linux/firmware.h> #include <linux/comedi/comedidev.h> #include "comedi_internal.h" struct comedi_driver *comedi_drivers; /* protects access to comedi_drivers */ DEFINE_MUTEX(comedi_drivers_list_lock); /** * comedi_set_hw_dev() - Set hardware device associated with COMEDI device * @dev: COMEDI device. * @hw_dev: Hardware device. * * For automatically configured COMEDI devices (resulting from a call to * comedi_auto_config() or one of its wrappers from the low-level COMEDI * driver), comedi_set_hw_dev() is called automatically by the COMEDI core * to associate the COMEDI device with the hardware device. It can also be * called directly by "legacy" low-level COMEDI drivers that rely on the * %COMEDI_DEVCONFIG ioctl to configure the hardware as long as the hardware * has a &struct device. * * If @dev->hw_dev is NULL, it gets a reference to @hw_dev and sets * @dev->hw_dev, otherwise, it does nothing. Calling it multiple times * with the same hardware device is not considered an error. If it gets * a reference to the hardware device, it will be automatically 'put' when * the device is detached from COMEDI. * * Returns 0 if @dev->hw_dev was NULL or the same as @hw_dev, otherwise * returns -EEXIST. */ int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev) { if (hw_dev == dev->hw_dev) return 0; if (dev->hw_dev) return -EEXIST; dev->hw_dev = get_device(hw_dev); return 0; } EXPORT_SYMBOL_GPL(comedi_set_hw_dev); static void comedi_clear_hw_dev(struct comedi_device *dev) { put_device(dev->hw_dev); dev->hw_dev = NULL; } /** * comedi_alloc_devpriv() - Allocate memory for the device private data * @dev: COMEDI device. * @size: Size of the memory to allocate. * * The allocated memory is zero-filled. @dev->private points to it on * return. The memory will be automatically freed when the COMEDI device is * "detached". * * Returns a pointer to the allocated memory, or NULL on failure. */ void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size) { dev->private = kzalloc(size, GFP_KERNEL); return dev->private; } EXPORT_SYMBOL_GPL(comedi_alloc_devpriv); /** * comedi_alloc_subdevices() - Allocate subdevices for COMEDI device * @dev: COMEDI device. * @num_subdevices: Number of subdevices to allocate. * * Allocates and initializes an array of &struct comedi_subdevice for the * COMEDI device. If successful, sets @dev->subdevices to point to the * first one and @dev->n_subdevices to the number. * * Returns 0 on success, -EINVAL if @num_subdevices is < 1, or -ENOMEM if * failed to allocate the memory. */ int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices) { struct comedi_subdevice *s; int i; if (num_subdevices < 1) return -EINVAL; s = kzalloc_objs(*s, num_subdevices); if (!s) return -ENOMEM; dev->subdevices = s; dev->n_subdevices = num_subdevices; for (i = 0; i < num_subdevices; ++i) { s = &dev->subdevices[i]; s->device = dev; s->index = i; s->async_dma_dir = DMA_NONE; spin_lock_init(&s->spin_lock); s->minor = -1; } return 0; } EXPORT_SYMBOL_GPL(comedi_alloc_subdevices); /** * comedi_alloc_subdev_readback() - Allocate memory for the subdevice readback * @s: COMEDI subdevice. * * This is called by low-level COMEDI drivers to allocate an array to record * the last values written to a subdevice's analog output channels (at least * by the %INSN_WRITE instruction), to allow them to be read back by an * %INSN_READ instruction. It also provides a default handler for the * %INSN_READ instruction unless one has already been set. * * On success, @s->readback points to the first element of the array, which * is zero-filled. The low-level driver is responsible for updating its * contents. @s->insn_read will be set to comedi_readback_insn_read() * unless it is already non-NULL. * * Returns 0 on success, -EINVAL if the subdevice has no channels, or * -ENOMEM on allocation failure. */ int comedi_alloc_subdev_readback(struct comedi_subdevice *s) { if (!s->n_chan) return -EINVAL; s->readback = kcalloc(s->n_chan, sizeof(*s->readback), GFP_KERNEL); if (!s->readback) return -ENOMEM; if (!s->insn_read) s->insn_read = comedi_readback_insn_read; return 0; } EXPORT_SYMBOL_GPL(comedi_alloc_subdev_readback); static void comedi_device_detach_cleanup(struct comedi_device *dev) { int i; struct comedi_subdevice *s; lockdep_assert_held_write(&dev->attach_lock); lockdep_assert_held(&dev->mutex); if (dev->subdevices) { for (i = 0; i < dev->n_subdevices; i++) { s = &dev->subdevices[i]; if (comedi_can_auto_free_spriv(s)) kfree(s->private); comedi_free_subdevice_minor(s); if (s->async) { comedi_buf_alloc(dev, s, 0); kfree(s->async); } kfree(s->readback); } kfree(dev->subdevices); dev->subdevices = NULL; dev->n_subdevices = 0; } kfree(dev->private); if (!IS_ERR(dev->pacer)) kfree(dev->pacer); dev->private = NULL; dev->pacer = NULL; dev->driver = NULL; dev->board_name = NULL; dev->board_ptr = NULL; dev->mmio = NULL; dev->iobase = 0; dev->iolen = 0; dev->ioenabled = false; dev->irq = 0; dev->read_subdev = NULL; dev->write_subdev = NULL; dev->open = NULL; dev->close = NULL; comedi_clear_hw_dev(dev); } void comedi_device_detach_locked(struct comedi_device *dev) { lockdep_assert_held_write(&dev->attach_lock); lockdep_assert_held(&dev->mutex); comedi_device_cancel_all(dev); dev->attached = false; dev->detach_count++; if (dev->driver) dev->driver->detach(dev); comedi_device_detach_cleanup(dev); } void comedi_device_detach(struct comedi_device *dev) { lockdep_assert_held(&dev->mutex); down_write(&dev->attach_lock); comedi_device_detach_locked(dev); up_write(&dev->attach_lock); } static int poll_invalid(struct comedi_device *dev, struct comedi_subdevice *s) { return -EINVAL; } static int insn_device_inval(struct comedi_device *dev, struct comedi_insn *insn, unsigned int *data) { return -EINVAL; } static unsigned int get_zero_valid_routes(struct comedi_device *dev, unsigned int n_pairs, unsigned int *pair_data) { return 0; } int insn_inval(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_insn *insn, unsigned int *data) { return -EINVAL; } /** * comedi_readback_insn_read() - A generic (*insn_read) for subdevice readback. * @dev: COMEDI device. * @s: COMEDI subdevice. * @insn: COMEDI instruction. * @data: Pointer to return the readback data. * * Handles the %INSN_READ instruction for subdevices that use the readback * array allocated by comedi_alloc_subdev_readback(). It may be used * directly as the subdevice's handler (@s->insn_read) or called via a * wrapper. * * @insn->n is normally 1, which will read a single value. If higher, the * same element of the readback array will be read multiple times. * * Returns @insn->n on success, or -EINVAL if @s->readback is NULL. */ int comedi_readback_insn_read(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_insn *insn, unsigned int *data) { unsigned int chan = CR_CHAN(insn->chanspec); int i; if (!s->readback) return -EINVAL; for (i = 0; i < insn->n; i++) data[i] = s->readback[chan]; return insn->n; } EXPORT_SYMBOL_GPL(comedi_readback_insn_read); /** * comedi_timeout() - Busy-wait for a driver condition to occur * @dev: COMEDI device. * @s: COMEDI subdevice. * @insn: COMEDI instruction. * @cb: Callback to check for the condition. * @context: Private context from the driver. * * Busy-waits for up to a second (%COMEDI_TIMEOUT_MS) for the condition or * some error (other than -EBUSY) to occur. The parameters @dev, @s, @insn, * and @context are passed to the callback function, which returns -EBUSY to * continue waiting or some other value to stop waiting (generally 0 if the * condition occurred, or some error value). * * Returns -ETIMEDOUT if timed out, otherwise the return value from the * callback function. */ int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_insn *insn, int (*cb)(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_insn *insn, unsigned long context), unsigned long context) { unsigned long timeout = jiffies + msecs_to_jiffies(COMEDI_TIMEOUT_MS); int ret; while (time_before(jiffies, timeout)) { ret = cb(dev, s, insn, context); if (ret != -EBUSY) return ret; /* success (0) or non EBUSY errno */ cpu_relax(); } return -ETIMEDOUT; } EXPORT_SYMBOL_GPL(comedi_timeout); /** * comedi_dio_insn_config() - Boilerplate (*insn_config) for DIO subdevices * @dev: COMEDI device. * @s: COMEDI subdevice. * @insn: COMEDI instruction. * @data: Instruction parameters and return data. * @mask: io_bits mask for grouped channels, or 0 for single channel. * * If @mask is 0, it is replaced with a single-bit mask corresponding to the * channel number specified by @insn->chanspec. Otherwise, @mask * corresponds to a group of channels (which should include the specified * channel) that are always configured together as inputs or outputs. * * Partially handles the %INSN_CONFIG_DIO_INPUT, %INSN_CONFIG_DIO_OUTPUTS, * and %INSN_CONFIG_DIO_QUERY instructions. The first two update * @s->io_bits to record the directions of the masked channels. The last * one sets @data[1] to the current direction of the group of channels * (%COMEDI_INPUT) or %COMEDI_OUTPUT) as recorded in @s->io_bits. * * The caller is responsible for updating the DIO direction in the hardware * registers if this function returns 0. * * Returns 0 for a %INSN_CONFIG_DIO_INPUT or %INSN_CONFIG_DIO_OUTPUT * instruction, @insn->n (> 0) for a %INSN_CONFIG_DIO_QUERY instruction, or * -EINVAL for some other instruction. */ int comedi_dio_insn_config(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_insn *insn, unsigned int *data, unsigned int mask) { unsigned int chan = CR_CHAN(insn->chanspec); if (!mask && chan < 32) mask = 1U << chan; switch (data[0]) { case INSN_CONFIG_DIO_INPUT: s->io_bits &= ~mask; break; case INSN_CONFIG_DIO_OUTPUT: s->io_bits |= mask; break; case INSN_CONFIG_DIO_QUERY: data[1] = (s->io_bits & mask) ? COMEDI_OUTPUT : COMEDI_INPUT; return insn->n; default: return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(comedi_dio_insn_config); /** * comedi_dio_update_state() - Update the internal state of DIO subdevices * @s: COMEDI subdevice. * @data: The channel mask and bits to update. * * Updates @s->state which holds the internal state of the outputs for DIO * or DO subdevices (up to 32 channels). @data[0] contains a bit-mask of * the channels to be updated. @data[1] contains a bit-mask of those * channels to be set to '1'. The caller is responsible for updating the * outputs in hardware according to @s->state. As a minimum, the channels * in the returned bit-mask need to be updated. * * Returns @mask with non-existent channels removed. */ unsigned int comedi_dio_update_state(struct comedi_subdevice *s, unsigned int *data) { unsigned int chanmask = (s->n_chan < 32) ? ((1U << s->n_chan) - 1) : 0xffffffff; unsigned int mask = data[0] & chanmask; unsigned int bits = data[1]; if (mask) { s->state &= ~mask; s->state |= (bits & mask); } return mask; } EXPORT_SYMBOL_GPL(comedi_dio_update_state); /** * comedi_bytes_per_scan_cmd() - Get length of asynchronous command "scan" in * bytes * @s: COMEDI subdevice. * @cmd: COMEDI command. * * Determines the overall scan length according to the subdevice type and the * number of channels in the scan for the specified command. * * For digital input, output or input/output subdevices, samples for * multiple channels are assumed to be packed into one or more unsigned * short or unsigned int values according to the subdevice's %SDF_LSAMPL * flag. For other types of subdevice, samples are assumed to occupy a * whole unsigned short or unsigned int according to the %SDF_LSAMPL flag. * * Returns the overall scan length in bytes. */ unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, struct comedi_cmd *cmd) { unsigned int num_samples; unsigned int bits_per_sample; switch (s->type) { case COMEDI_SUBD_DI: case COMEDI_SUBD_DO: case COMEDI_SUBD_DIO: bits_per_sample = 8 * comedi_bytes_per_sample(s); num_samples = DIV_ROUND_UP(cmd->scan_end_arg, bits_per_sample); break; default: num_samples = cmd->scan_end_arg; break; } return comedi_samples_to_bytes(s, num_samples); } EXPORT_SYMBOL_GPL(comedi_bytes_per_scan_cmd); static unsigned int _comedi_bytes_per_scan(struct comedi_subdevice *s) { struct comedi_cmd *cmd = &s->async->cmd; return comedi_bytes_per_scan_cmd(s, cmd); } /** * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes * @s: COMEDI subdevice. * * Determines the overall scan length according to the subdevice type and the * number of channels in the scan for the current command. * * For digital input, output or input/output subdevices, samples for * multiple channels are assumed to be packed into one or more unsigned * short or unsigned int values according to the subdevice's %SDF_LSAMPL * flag. For other types of subdevice, samples are assumed to occupy a * whole unsigned short or unsigned int according to the %SDF_LSAMPL flag. * * Returns the overall scan length in bytes. */ unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s) { unsigned int num_bytes; if (comedi_get_is_subdevice_running(s)) { num_bytes = _comedi_bytes_per_scan(s); comedi_put_is_subdevice_running(s); } else { /* Use nomimal, single sample scan length. */ num_bytes = comedi_samples_to_bytes(s, 1); } return num_bytes; } EXPORT_SYMBOL_GPL(comedi_bytes_per_scan); static unsigned int __comedi_nscans_left(struct comedi_subdevice *s, unsigned int nscans) { struct comedi_async *async = s->async; struct comedi_cmd *cmd = &async->cmd; if (cmd->stop_src == TRIG_COUNT) { unsigned int scans_left = 0; if (async->scans_done < cmd->stop_arg) scans_left = cmd->stop_arg - async->scans_done; if (nscans > scans_left) nscans = scans_left; } return nscans; } static unsigned int _comedi_nscans_left(struct comedi_subdevice *s, unsigned int nscans) { if (nscans == 0) { unsigned int nbytes = _comedi_buf_read_n_available(s); nscans = nbytes / _comedi_bytes_per_scan(s); } return __comedi_nscans_left(s, nscans); } /** * comedi_nscans_left() - Return the number of scans left in the command * @s: COMEDI subdevice. * @nscans: The expected number of scans or 0 for all available scans. * * If @nscans is 0, it is set to the number of scans available in the * async buffer. * * If the async command has a stop_src of %TRIG_COUNT, the @nscans will be * checked against the number of scans remaining to complete the command. * * The return value will then be either the expected number of scans or the * number of scans remaining to complete the command, whichever is fewer. */ unsigned int comedi_nscans_left(struct comedi_subdevice *s, unsigned int nscans) { if (comedi_get_is_subdevice_running(s)) { nscans = _comedi_nscans_left(s, nscans); comedi_put_is_subdevice_running(s); } else { nscans = 0; } return nscans; } EXPORT_SYMBOL_GPL(comedi_nscans_left); static unsigned int _comedi_nsamples_left(struct comedi_subdevice *s, unsigned int nsamples) { struct comedi_async *async = s->async; struct comedi_cmd *cmd = &async->cmd; unsigned long long scans_left; unsigned long long samples_left; if (cmd->stop_src != TRIG_COUNT) return nsamples; scans_left = __comedi_nscans_left(s, cmd->stop_arg); if (!scans_left) return 0; samples_left = scans_left * cmd->scan_end_arg - comedi_bytes_to_samples(s, async->scan_progress); if (samples_left < nsamples) return samples_left; return nsamples; } /** * comedi_nsamples_left() - Return the number of samples left in the command * @s: COMEDI subdevice. * @nsamples: The expected number of samples. * * Returns the number of samples remaining to complete the command, or the * specified expected number of samples (@nsamples), whichever is fewer. */ unsigned int comedi_nsamples_left(struct comedi_subdevice *s, unsigned int nsamples) { if (comedi_get_is_subdevice_running(s)) { nsamples = _comedi_nsamples_left(s, nsamples); comedi_put_is_subdevice_running(s); } else { nsamples = 0; } return nsamples; } EXPORT_SYMBOL_GPL(comedi_nsamples_left); void _comedi_inc_scan_progress(struct comedi_subdevice *s, unsigned int num_bytes) { struct comedi_async *async = s->async; struct comedi_cmd *cmd = &async->cmd; unsigned int scan_length = _comedi_bytes_per_scan(s); /* track the 'cur_chan' for non-SDF_PACKED subdevices */ if (!(s->subdev_flags & SDF_PACKED)) { async->cur_chan += comedi_bytes_to_samples(s, num_bytes); async->cur_chan %= cmd->chanlist_len; } async->scan_progress += num_bytes; if (async->scan_progress >= scan_length) { unsigned int nscans = async->scan_progress / scan_length; if (async->scans_done < (UINT_MAX - nscans)) async->scans_done += nscans; else async->scans_done = UINT_MAX; async->scan_progress %= scan_length; async->events |= COMEDI_CB_EOS; } } /** * comedi_inc_scan_progress() - Update scan progress in asynchronous command * @s: COMEDI subdevice. * @num_bytes: Amount of data in bytes to increment scan progress. * * Increments the scan progress by the number of bytes specified by @num_bytes. * If the scan progress reaches or exceeds the scan length in bytes, reduce * it modulo the scan length in bytes and set the "end of scan" asynchronous * event flag (%COMEDI_CB_EOS) to be processed later. */ void comedi_inc_scan_progress(struct comedi_subdevice *s, unsigned int num_bytes) { if (comedi_get_is_subdevice_running(s)) { _comedi_inc_scan_progress(s, num_bytes); comedi_put_is_subdevice_running(s); } } EXPORT_SYMBOL_GPL(comedi_inc_scan_progress); static unsigned int _comedi_handle_events(struct comedi_device *dev, struct comedi_subdevice *s) { unsigned int events = s->async->events; if (events == 0) return events; if ((events & COMEDI_CB_CANCEL_MASK) && s->cancel) s->cancel(dev, s); _comedi_event(dev, s); return events; } /** * comedi_handle_events() - Handle events and possibly stop acquisition * @dev: COMEDI device. * @s: COMEDI subdevice. * * Handles outstanding asynchronous acquisition event flags associated * with the subdevice. Call the subdevice's @s->cancel() handler if the * "end of acquisition", "error" or "overflow" event flags are set in order * to stop the acquisition at the driver level. * * Calls comedi_event() to further process the event flags, which may mark * the asynchronous command as no longer running, possibly terminated with * an error, and may wake up tasks. * * Return a bit-mask of the handled events. */ unsigned int comedi_handle_events(struct comedi_device *dev, struct comedi_subdevice *s) { unsigned int events; if (comedi_get_is_subdevice_running(s)) { events = _comedi_handle_events(dev, s); comedi_put_is_subdevice_running(s); } else { events = 0; } return events; } EXPORT_SYMBOL_GPL(comedi_handle_events); static int insn_rw_emulate_bits(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_insn *insn, unsigned int *data) { struct comedi_insn _insn; unsigned int chan = CR_CHAN(insn->chanspec); unsigned int base_chan = (chan < 32) ? 0 : chan; unsigned int _data[2]; unsigned int i; int ret; memset(_data, 0, sizeof(_data)); memset(&_insn, 0, sizeof(_insn)); _insn.insn = INSN_BITS; _insn.chanspec = base_chan; _insn.n = 2; _insn.subdev = insn->subdev; if (insn->insn == INSN_WRITE) { if (!(s->subdev_flags & SDF_WRITABLE)) return -EINVAL; _data[0] = 1U << (chan - base_chan); /* mask */ } for (i = 0; i < insn->n; i++) { if (insn->insn == INSN_WRITE) _data[1] = data[i] ? _data[0] : 0; /* bits */ ret = s->insn_bits(dev, s, &_insn, _data); if (ret < 0) return ret; if (insn->insn == INSN_READ) data[i] = (_data[1] >> (chan - base_chan)) & 1; } return insn->n; } static int __comedi_device_postconfig_async(struct comedi_device *dev, struct comedi_subdevice *s) { struct comedi_async *async; unsigned int buf_size; int ret; lockdep_assert_held(&dev->mutex); if ((s->subdev_flags & (SDF_CMD_READ | SDF_CMD_WRITE)) == 0) { dev_warn(dev->class_dev, "async subdevices must support SDF_CMD_READ or SDF_CMD_WRITE\n"); return -EINVAL; } if (!s->do_cmdtest) { dev_warn(dev->class_dev, "async subdevices must have a do_cmdtest() function\n"); return -EINVAL; } if (!s->cancel) dev_warn(dev->class_dev, "async subdevices should have a cancel() function\n"); async = kzalloc_obj(*async); if (!async) return -ENOMEM; init_waitqueue_head(&async->wait_head); init_completion(&async->run_complete); s->async = async; async->max_bufsize = comedi_default_buf_maxsize_kb * 1024; buf_size = comedi_default_buf_size_kb * 1024; if (buf_size > async->max_bufsize) buf_size = async->max_bufsize; if (comedi_buf_alloc(dev, s, buf_size) < 0) { dev_warn(dev->class_dev, "Buffer allocation failed\n"); return -ENOMEM; } if (s->buf_change) { ret = s->buf_change(dev, s); if (ret < 0) return ret; } comedi_alloc_subdevice_minor(s); return 0; } static int __comedi_device_postconfig(struct comedi_device *dev) { struct comedi_subdevice *s; int ret; int i; lockdep_assert_held(&dev->mutex); if (!dev->insn_device_config) dev->insn_device_config = insn_device_inval; if (!dev->get_valid_routes) dev->get_valid_routes = get_zero_valid_routes; for (i = 0; i < dev->n_subdevices; i++) { s = &dev->subdevices[i]; if (s->type == COMEDI_SUBD_UNUSED) continue; if (s->type == COMEDI_SUBD_DO) { if (s->n_chan < 32) s->io_bits = (1U << s->n_chan) - 1; else s->io_bits = 0xffffffff; } if (s->len_chanlist == 0) s->len_chanlist = 1; if (s->do_cmd) { ret = __comedi_device_postconfig_async(dev, s); if (ret) return ret; } if (!s->range_table && !s->range_table_list) s->range_table = &range_unknown; if (!s->insn_read && s->insn_bits) s->insn_read = insn_rw_emulate_bits; if (!s->insn_write && s->insn_bits) s->insn_write = insn_rw_emulate_bits; if (!s->insn_read) s->insn_read = insn_inval; if (!s->insn_write) s->insn_write = insn_inval; if (!s->insn_bits) s->insn_bits = insn_inval; if (!s->insn_config) s->insn_config = insn_inval; if (!s->poll) s->poll = poll_invalid; } return 0; } /* do a little post-config cleanup */ static int comedi_device_postconfig(struct comedi_device *dev) { int ret; lockdep_assert_held(&dev->mutex); ret = __comedi_device_postconfig(dev); if (ret < 0) return ret; down_write(&dev->attach_lock); dev->attached = true; up_write(&dev->attach_lock); return 0; } /* * Generic recognize function for drivers that register their supported * board names. * * 'driv->board_name' points to a 'const char *' member within the * zeroth element of an array of some private board information * structure, say 'struct foo_board' containing a member 'const char * *board_name' that is initialized to point to a board name string that * is one of the candidates matched against this function's 'name' * parameter. * * 'driv->offset' is the size of the private board information * structure, say 'sizeof(struct foo_board)', and 'driv->num_names' is * the length of the array of private board information structures. * * If one of the board names in the array of private board information * structures matches the name supplied to this function, the function * returns a pointer to the pointer to the board name, otherwise it * returns NULL. The return value ends up in the 'board_ptr' member of * a 'struct comedi_device' that the low-level comedi driver's * 'attach()' hook can convert to a point to a particular element of its * array of private board information structures by subtracting the * offset of the member that points to the board name. (No subtraction * is required if the board name pointer is the first member of the * private board information structure, which is generally the case.) */ static void *comedi_recognize(struct comedi_driver *driv, const char *name) { char **name_ptr = (char **)driv->board_name; int i; for (i = 0; i < driv->num_names; i++) { if (strcmp(*name_ptr, name) == 0) return name_ptr; name_ptr = (void *)name_ptr + driv->offset; } return NULL; } static void comedi_report_boards(struct comedi_driver *driv) { unsigned int i; const char *const *name_ptr; pr_info("comedi: valid board names for %s driver are:\n", driv->driver_name); name_ptr = driv->board_name; for (i = 0; i < driv->num_names; i++) { pr_info(" %s\n", *name_ptr); name_ptr = (const char **)((char *)name_ptr + driv->offset); } if (driv->num_names == 0) pr_info(" %s\n", driv->driver_name); } /** * comedi_load_firmware() - Request and load firmware for a device * @dev: COMEDI device. * @device: Hardware device. * @name: The name of the firmware image. * @cb: Callback to the upload the firmware image. * @context: Private context from the driver. * * Sends a firmware request for the hardware device and waits for it. Calls * the callback function to upload the firmware to the device, them releases * the firmware. * * Returns 0 on success, -EINVAL if @cb is NULL, or a negative error number * from the firmware request or the callback function. */ int comedi_load_firmware(struct comedi_device *dev, struct device *device, const char *name, int (*cb)(struct comedi_device *dev, const u8 *data, size_t size, unsigned long context), unsigned long context) { const struct firmware *fw; int ret; if (!cb) return -EINVAL; ret = request_firmware(&fw, name, device); if (ret == 0) { ret = cb(dev, fw->data, fw->size, context); release_firmware(fw); } return min(ret, 0); } EXPORT_SYMBOL_GPL(comedi_load_firmware); /** * __comedi_check_request_region() - Request an I/O region for a legacy driver * @dev: COMEDI device. * @start: Base address of the I/O region. * @len: Length of the I/O region. * @minstart: Minimum allowed start address of region. * @maxend: Maximum allowed region end address of region. * @minalign: Required alignment for base address. * * Requests the specified I/O port region which must start at a non-zero * address, must fall within specified bounds, and must be correctly aligned. * * Returns 0 on success, -EINVAL if @start is 0, or -EIO if the request * fails. */ int __comedi_check_request_region(struct comedi_device *dev, unsigned long start, unsigned long len, unsigned long minstart, unsigned long maxend, unsigned long minalign) { if (!start) { dev_warn(dev->class_dev, "%s: a I/O base address must be specified\n", dev->board_name); return -EINVAL; } if (start < minstart || start > maxend || maxend - start < len - 1) { dev_warn(dev->class_dev, "%s: I/O base address or length out of range\n", dev->board_name); return -EINVAL; } if (!IS_ALIGNED(start, minalign)) { dev_warn(dev->class_dev, "%s: I/O base address not correctly aligned\n", dev->board_name); return -EINVAL; } if (!request_region(start, len, dev->board_name)) { dev_warn(dev->class_dev, "%s: I/O port conflict (%#lx,%lu)\n", dev->board_name, start, len); return -EIO; } return 0; } EXPORT_SYMBOL_GPL(__comedi_check_request_region); /** * comedi_check_request_region() - Request an I/O region for a legacy driver * @dev: COMEDI device. * @start: Base address of the I/O region. * @len: Length of the I/O region. * @minstart: Minimum allowed start address of region. * @maxend: Maximum allowed region end address of region. * @minalign: Required alignment for base address. * * Requests the specified I/O port region which must start at a non-zero * address, must fall within specified bounds, and must be correctly aligned. * * On success, @dev->iobase is set to the base address of the region and * @dev->iolen is set to its length. * * Returns 0 on success, -EINVAL if @start is 0, or -EIO if the request * fails. */ int comedi_check_request_region(struct comedi_device *dev, unsigned long start, unsigned long len, unsigned long minstart, unsigned long maxend, unsigned long minalign) { int ret; ret = __comedi_check_request_region(dev, start, len, minstart, maxend, minalign); if (ret == 0) { dev->iobase = start; dev->iolen = len; } return ret; } EXPORT_SYMBOL_GPL(comedi_check_request_region); /** * comedi_legacy_detach() - A generic (*detach) function for legacy drivers * @dev: COMEDI device. * * This is a simple, generic 'detach' handler for legacy COMEDI devices that * just use a single I/O port region and possibly an IRQ and that don't need * any special clean-up for their private device or subdevice storage. It * can also be called by a driver-specific 'detach' handler. * * If @dev->irq is non-zero, the IRQ will be freed. If @dev->iobase and * @dev->iolen are both non-zero, the I/O port region will be released. */ void comedi_legacy_detach(struct comedi_device *dev) { if (dev->irq) { free_irq(dev->irq, dev); dev->irq = 0; } if (dev->iobase && dev->iolen) { release_region(dev->iobase, dev->iolen); dev->iobase = 0; dev->iolen = 0; } } EXPORT_SYMBOL_GPL(comedi_legacy_detach); int comedi_device_attach(struct comedi_device *dev, struct comedi_devconfig *it) { struct comedi_driver *driv; int ret; lockdep_assert_held(&dev->mutex); if (dev->attached) return -EBUSY; mutex_lock(&comedi_drivers_list_lock); for (driv = comedi_drivers; driv; driv = driv->next) { if (!try_module_get(driv->module)) continue; if (driv->num_names) { dev->board_ptr = comedi_recognize(driv, it->board_name); if (dev->board_ptr) break; } else if (strcmp(driv->driver_name, it->board_name) == 0) { break; } module_put(driv->module); } if (!driv) { /* recognize has failed if we get here */ /* report valid board names before returning error */ for (driv = comedi_drivers; driv; driv = driv->next) { if (!try_module_get(driv->module)) continue; comedi_report_boards(driv); module_put(driv->module); } ret = -EIO; goto out; } if (!driv->attach) { /* driver does not support manual configuration */ dev_warn(dev->class_dev, "driver '%s' does not support attach using comedi_config\n", driv->driver_name); module_put(driv->module); ret = -EIO; goto out; } if (IS_ENABLED(CONFIG_LOCKDEP)) { /* * dev->spinlock is for private use by the attached low-level * driver. Reinitialize it to stop lock-dependency tracking * between attachments to different low-level drivers. */ spin_lock_init(&dev->spinlock); } dev->driver = driv; dev->board_name = dev->board_ptr ? *(const char **)dev->board_ptr : dev->driver->driver_name; ret = driv->attach(dev, it); if (ret >= 0) ret = comedi_device_postconfig(dev); if (ret < 0) { comedi_device_detach(dev); module_put(driv->module); } /* On success, the driver module count has been incremented. */ out: mutex_unlock(&comedi_drivers_list_lock); return ret; } /** * comedi_auto_config() - Create a COMEDI device for a hardware device * @hardware_device: Hardware device. * @driver: COMEDI low-level driver for the hardware device. * @context: Driver context for the auto_attach handler. * * Allocates a new COMEDI device for the hardware device and calls the * low-level driver's 'auto_attach' handler to set-up the hardware and * allocate the COMEDI subdevices. Additional "post-configuration" setting * up is performed on successful return from the 'auto_attach' handler. * If the 'auto_attach' handler fails, the low-level driver's 'detach' * handler will be called as part of the clean-up. * * This is usually called from a wrapper function in a bus-specific COMEDI * module, which in turn is usually called from a bus device 'probe' * function in the low-level driver. * * Returns 0 on success, -EINVAL if the parameters are invalid or the * post-configuration determines the driver has set the COMEDI device up * incorrectly, -ENOMEM if failed to allocate memory, -EBUSY if run out of * COMEDI minor device numbers, or some negative error number returned by * the driver's 'auto_attach' handler. */ int comedi_auto_config(struct device *hardware_device, struct comedi_driver *driver, unsigned long context) { struct comedi_device *dev; int ret; if (!hardware_device) { pr_warn("BUG! %s called with NULL hardware_device\n", __func__); return -EINVAL; } if (!driver) { dev_warn(hardware_device, "BUG! %s called with NULL comedi driver\n", __func__); return -EINVAL; } if (!driver->auto_attach) { dev_warn(hardware_device, "BUG! comedi driver '%s' has no auto_attach handler\n", driver->driver_name); return -EINVAL; } dev = comedi_alloc_board_minor(hardware_device); if (IS_ERR(dev)) { dev_warn(hardware_device, "driver '%s' could not create device.\n", driver->driver_name); return PTR_ERR(dev); } /* Note: comedi_alloc_board_minor() locked dev->mutex. */ lockdep_assert_held(&dev->mutex); dev->driver = driver; dev->board_name = dev->driver->driver_name; ret = driver->auto_attach(dev, context); if (ret >= 0) ret = comedi_device_postconfig(dev); if (ret < 0) { dev_warn(hardware_device, "driver '%s' failed to auto-configure device.\n", driver->driver_name); mutex_unlock(&dev->mutex); comedi_release_hardware_device(hardware_device); } else { /* * class_dev should be set properly here * after a successful auto config */ dev_info(dev->class_dev, "driver '%s' has successfully auto-configured '%s'.\n", driver->driver_name, dev->board_name); mutex_unlock(&dev->mutex); } return ret; } EXPORT_SYMBOL_GPL(comedi_auto_config); /** * comedi_auto_unconfig() - Unconfigure auto-allocated COMEDI device * @hardware_device: Hardware device previously passed to * comedi_auto_config(). * * Cleans up and eventually destroys the COMEDI device allocated by * comedi_auto_config() for the same hardware device. As part of this * clean-up, the low-level COMEDI driver's 'detach' handler will be called. * (The COMEDI device itself will persist in an unattached state if it is * still open, until it is released, and any mmapped buffers will persist * until they are munmapped.) * * This is usually called from a wrapper module in a bus-specific COMEDI * module, which in turn is usually set as the bus device 'remove' function * in the low-level COMEDI driver. */ void comedi_auto_unconfig(struct device *hardware_device) { if (!hardware_device) return; comedi_release_hardware_device(hardware_device); } EXPORT_SYMBOL_GPL(comedi_auto_unconfig); /** * comedi_driver_register() - Register a low-level COMEDI driver * @driver: Low-level COMEDI driver. * * The low-level COMEDI driver is added to the list of registered COMEDI * drivers. This is used by the handler for the "/proc/comedi" file and is * also used by the handler for the %COMEDI_DEVCONFIG ioctl to configure * "legacy" COMEDI devices (for those low-level drivers that support it). * * Returns 0. */ int comedi_driver_register(struct comedi_driver *driver) { mutex_lock(&comedi_drivers_list_lock); driver->next = comedi_drivers; comedi_drivers = driver; mutex_unlock(&comedi_drivers_list_lock); return 0; } EXPORT_SYMBOL_GPL(comedi_driver_register); /** * comedi_driver_unregister() - Unregister a low-level COMEDI driver * @driver: Low-level COMEDI driver. * * The low-level COMEDI driver is removed from the list of registered COMEDI * drivers. Detaches any COMEDI devices attached to the driver, which will * result in the low-level driver's 'detach' handler being called for those * devices before this function returns. */ void comedi_driver_unregister(struct comedi_driver *driver) { struct comedi_driver *prev; int i; /* unlink the driver */ mutex_lock(&comedi_drivers_list_lock); if (comedi_drivers == driver) { comedi_drivers = driver->next; } else { for (prev = comedi_drivers; prev->next; prev = prev->next) { if (prev->next == driver) { prev->next = driver->next; break; } } } mutex_unlock(&comedi_drivers_list_lock); /* check for devices using this driver */ for (i = 0; i < COMEDI_NUM_BOARD_MINORS; i++) { struct comedi_device *dev = comedi_dev_get_from_minor(i); if (!dev) continue; mutex_lock(&dev->mutex); if (dev->attached && dev->driver == driver) { if (dev->use_count) dev_warn(dev->class_dev, "BUG! detaching device with use_count=%d\n", dev->use_count); comedi_device_detach(dev); } mutex_unlock(&dev->mutex); comedi_dev_put(dev); } } EXPORT_SYMBOL_GPL(comedi_driver_unregister); |
| 48 7 53 4 141 152 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* AF_RXRPC internal definitions * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/atomic.h> #include <linux/seqlock.h> #include <linux/win_minmax.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> #include "protocol.h" #define FCRYPT_ROUNDS 16 struct fcrypt_key { __be32 sched[FCRYPT_ROUNDS]; }; #define FCRYPT_BSIZE 8 struct rxrpc_crypt { union { u8 x[FCRYPT_BSIZE]; __be32 n[2]; }; } __attribute__((aligned(8))); void fcrypt_preparekey(struct fcrypt_key *key, const u8 raw_key[FCRYPT_BSIZE]); void fcrypt_pcbc_encrypt(const struct fcrypt_key *key, const u8 iv[FCRYPT_BSIZE], const void *src, void *dst, size_t nblocks); void fcrypt_pcbc_decrypt(const struct fcrypt_key *key, const u8 iv[FCRYPT_BSIZE], const void *src, void *dst, size_t nblocks); #if IS_ENABLED(CONFIG_KUNIT) struct des_ctx; void des_pcbc_decrypt_inplace(const struct des_ctx *key, __le64 iv, u8 *data, size_t len); #endif #define rxrpc_queue_work(WS) queue_work(rxrpc_workqueue, (WS)) #define rxrpc_queue_delayed_work(WS,D) \ queue_delayed_work(rxrpc_workqueue, (WS), (D)) struct key_preparsed_payload; struct rxrpc_connection; struct rxrpc_txbuf; struct rxrpc_txqueue; struct rxgk_context; /* * Mark applied to socket buffers in skb->mark. skb->priority is used * to pass supplementary information. */ enum rxrpc_skb_mark { RXRPC_SKB_MARK_PACKET, /* Received packet */ RXRPC_SKB_MARK_ERROR, /* Error notification */ RXRPC_SKB_MARK_CHALLENGE, /* Challenge notification */ RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ RXRPC_SKB_MARK_REJECT_CONN_ABORT, /* Reject with connection ABORT (code in skb->priority) */ }; /* * sk_state for RxRPC sockets */ enum { RXRPC_UNBOUND = 0, RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */ RXRPC_CLIENT_BOUND, /* client local address bound */ RXRPC_SERVER_BOUND, /* server local address bound */ RXRPC_SERVER_BOUND2, /* second server local address bound */ RXRPC_SERVER_LISTENING, /* server listening for connections */ RXRPC_SERVER_LISTEN_DISABLED, /* server listening disabled */ RXRPC_CLOSE, /* socket is being closed */ }; /* * Per-network namespace data. */ struct rxrpc_net { struct proc_dir_entry *proc_net; /* Subdir in /proc/net */ u32 epoch; /* Local epoch for detecting local-end reset */ struct list_head calls; /* List of calls active in this namespace */ spinlock_t call_lock; /* Lock for ->calls */ atomic_t nr_calls; /* Count of allocated calls */ atomic_t nr_conns; struct list_head bundle_proc_list; /* List of bundles for proc */ struct list_head conn_proc_list; /* List of conns in this namespace for proc */ struct list_head service_conns; /* Service conns in this namespace */ rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */ struct work_struct service_conn_reaper; struct timer_list service_conn_reap_timer; bool live; atomic_t nr_client_conns; struct hlist_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ DECLARE_HASHTABLE (peer_hash, 10); spinlock_t peer_hash_lock; /* Lock for ->peer_hash */ #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */ u8 peer_keepalive_cursor; time64_t peer_keepalive_base; struct list_head peer_keepalive[32]; struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; atomic_t stat_tx_data; atomic_t stat_tx_data_retrans; atomic_t stat_tx_data_send; atomic_t stat_tx_data_send_frag; atomic_t stat_tx_data_send_fail; atomic_t stat_tx_data_send_msgsize; atomic_t stat_tx_data_underflow; atomic_t stat_tx_data_cwnd_reset; atomic_t stat_rx_data; atomic_t stat_rx_data_reqack; atomic_t stat_rx_data_jumbo; atomic_t stat_tx_ack_fill; atomic_t stat_tx_ack_send; atomic_t stat_tx_ack_skip; atomic_t stat_tx_acks[256]; atomic_t stat_rx_acks[256]; atomic_t stat_tx_jumbo[10]; atomic_t stat_rx_jumbo[10]; atomic_t stat_why_req_ack[9]; atomic_t stat_io_loop; }; /* * Service backlog preallocation. * * This contains circular buffers of preallocated peers, connections and calls * for incoming service calls and their head and tail pointers. This allows * calls to be set up in the data_ready handler, thereby avoiding the need to * shuffle packets around so much. */ struct rxrpc_backlog { unsigned short peer_backlog_head; unsigned short peer_backlog_tail; unsigned short conn_backlog_head; unsigned short conn_backlog_tail; unsigned short call_backlog_head; unsigned short call_backlog_tail; #define RXRPC_BACKLOG_MAX 32 struct rxrpc_peer *peer_backlog[RXRPC_BACKLOG_MAX]; struct rxrpc_connection *conn_backlog[RXRPC_BACKLOG_MAX]; struct rxrpc_call *call_backlog[RXRPC_BACKLOG_MAX]; }; /* * RxRPC socket definition */ struct rxrpc_sock { /* WARNING: sk has to be the first member */ struct sock sk; const struct rxrpc_kernel_ops *app_ops; /* Table of kernel app notification funcs */ struct rxrpc_local *local; /* local endpoint */ struct rxrpc_backlog *backlog; /* Preallocation for services */ struct sk_buff_head recvmsg_oobq; /* OOB messages for recvmsg to pick up */ struct rb_root pending_oobq; /* OOB messages awaiting userspace to respond to */ u64 oob_id_counter; /* OOB message ID counter */ spinlock_t incoming_lock; /* Incoming call vs service shutdown lock */ struct list_head sock_calls; /* List of calls owned by this socket */ struct list_head to_be_accepted; /* calls awaiting acceptance */ struct list_head recvmsg_q; /* Calls awaiting recvmsg's attention */ spinlock_t recvmsg_lock; /* Lock for recvmsg_q */ struct key *key; /* security for this socket */ struct key *securities; /* list of server security descriptors */ struct rb_root calls; /* User ID -> call mapping */ unsigned long flags; #define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ #define RXRPC_SOCK_MANAGE_RESPONSE 1 /* User wants to manage RESPONSE packets */ rwlock_t call_lock; /* lock for calls */ u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT bool exclusive; /* Exclusive connection for a client socket */ u16 second_service; /* Additional service bound to the endpoint */ struct { /* Service upgrade information */ u16 from; /* Service ID to upgrade (if not 0) */ u16 to; /* service ID to upgrade to */ } service_upgrade; sa_family_t family; /* Protocol family created with */ struct sockaddr_rxrpc srx; /* Primary Service/local addresses */ struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */ }; #define rxrpc_sk(__sk) container_of((__sk), struct rxrpc_sock, sk) /* * CPU-byteorder normalised Rx packet header. */ struct rxrpc_host_header { u32 epoch; /* client boot timestamp */ u32 cid; /* connection and channel ID */ u32 callNumber; /* call ID (0 for connection-level packets) */ u32 seq; /* sequence number of pkt in call stream */ u32 serial; /* serial number of pkt sent to network */ u8 type; /* packet type */ u8 flags; /* packet flags */ u8 userStatus; /* app-layer defined status */ u8 securityIndex; /* security protocol ID */ union { u16 _rsvd; /* reserved */ u16 cksum; /* kerberos security checksum */ }; u16 serviceId; /* service ID */ } __packed; /* * RxRPC socket buffer private variables * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { union { struct rxrpc_connection *poke_conn; /* Conn referred to (poke packet) */ struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ }; struct { rxrpc_seq_t first_ack; /* First packet in acks table */ rxrpc_seq_t prev_ack; /* Highest seq seen */ rxrpc_serial_t acked_serial; /* Packet in response to (or 0) */ u16 nr_acks; /* Number of acks+nacks */ u8 reason; /* Reason for ack */ } ack; struct { struct rxrpc_connection *conn; /* Connection referred to */ union { u32 rxkad_nonce; }; } chall; struct { rxrpc_serial_t challenge_serial; u32 kvno; u32 version; u16 len; u16 ticket_len; } resp; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) /* * RxRPC security module interface */ struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); /* Clean up a security service */ void (*exit)(void); /* Parse the information from a server key */ int (*preparse_server_key)(struct key_preparsed_payload *); /* Clean up the preparse buffer after parsing a server key */ void (*free_preparse_server_key)(struct key_preparsed_payload *); /* Destroy the payload of a server key */ void (*destroy_server_key)(struct key *); /* Describe a server key */ void (*describe_server_key)(const struct key *, struct seq_file *); /* initialise a connection's security */ int (*init_connection_security)(struct rxrpc_connection *, struct rxrpc_key_token *); /* Work out how much data we can store in a packet, given an estimate * of the amount of data remaining and allocate a data buffer. */ struct rxrpc_txbuf *(*alloc_txbuf)(struct rxrpc_call *call, size_t remaining, gfp_t gfp); /* impose security on a packet */ int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); /* verify the security on a received packet */ int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); /* Validate a challenge packet */ bool (*validate_challenge)(struct rxrpc_connection *conn, struct sk_buff *skb); /* Fill out the cmsg for recvmsg() to pass on a challenge to userspace. * The security class gets to add additional information. */ int (*challenge_to_recvmsg)(struct rxrpc_connection *conn, struct sk_buff *challenge, struct msghdr *msg); /* Parse sendmsg() control message and respond to challenge. */ int (*sendmsg_respond_to_challenge)(struct sk_buff *challenge, struct msghdr *msg); /* respond to a challenge */ int (*respond_to_challenge)(struct rxrpc_connection *conn, struct sk_buff *challenge); /* verify a response */ int (*verify_response)(struct rxrpc_connection *conn, struct sk_buff *response_skb, void *response, unsigned int len); /* clear connection security */ void (*clear)(struct rxrpc_connection *); /* Default ticket -> key decoder */ int (*default_decode_ticket)(struct rxrpc_connection *conn, struct sk_buff *skb, void *ticket, unsigned int ticket_len, struct key **_key); }; /* * RxRPC local transport endpoint description * - owned by a single AF_RXRPC socket * - pointed to by transport socket struct sk_user_data */ struct rxrpc_local { struct rcu_head rcu; atomic_t active_users; /* Number of users of the local endpoint */ refcount_t ref; /* Number of references to the structure */ struct net *net; /* The network namespace */ struct rxrpc_net *rxnet; /* Our bits in the network namespace */ struct hlist_node link; struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ struct page_frag_cache tx_alloc; /* Tx control packet allocation (I/O thread only) */ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY struct sk_buff_head rx_delay_queue; /* Delay injection queue */ #endif struct sk_buff_head rx_queue; /* Received packets */ struct list_head conn_attend_q; /* Conns requiring immediate attention */ struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ bool kill_all_client_conns; struct list_head idle_client_conns; struct timer_list client_conn_reap_timer; unsigned long client_conn_flags; #define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ bool dead; bool service_closed; /* Service socket closed */ struct idr conn_ids; /* List of connection IDs */ struct list_head new_client_calls; /* Newly created client calls need connection */ spinlock_t client_call_lock; /* Lock for ->new_client_calls */ struct sockaddr_rxrpc srx; /* local address */ union { /* Provide a kvec table sufficiently large to manage either a * DATA packet with a maximum set of jumbo subpackets or a PING * ACK padded out to 64K with zeropages for PMTUD. */ struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ? 1 + RXRPC_MAX_NR_JUMBO : 3 + 16]; struct bio_vec bvec[3 + 16]; }; }; /* * RxRPC remote transport endpoint definition * - matched by local endpoint, remote port, address and protocol type */ struct rxrpc_peer { struct rcu_head rcu; /* This must be first */ refcount_t ref; unsigned long hash_key; struct hlist_node hash_link; struct rxrpc_local *local; struct hlist_head error_targets; /* targets for net error distribution */ struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ unsigned long app_data; /* Application data (e.g. afs_server) */ unsigned int last_tx_at; /* Last time packet sent here (time64_t LSW) */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ int debug_id; /* debug ID for printks */ struct sockaddr_rxrpc srx; /* remote address */ /* Path MTU discovery [RFC8899] */ unsigned int pmtud_trial; /* Current MTU probe size */ unsigned int pmtud_good; /* Largest working MTU probe we've tried */ unsigned int pmtud_bad; /* Smallest non-working MTU probe we've tried */ bool pmtud_lost; /* T if MTU probe was lost */ bool pmtud_probing; /* T if we have an active probe outstanding */ bool pmtud_pending; /* T if a call to this peer should send a probe */ u8 pmtud_jumbo; /* Max jumbo packets for the MTU */ bool ackr_adv_pmtud; /* T if the peer advertises path-MTU */ unsigned int ackr_max_data; /* Maximum data advertised by peer */ unsigned int if_mtu; /* Local interface MTU (- hdrsize) for this peer */ unsigned int max_data; /* Maximum packet data capacity for this peer */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ unsigned short tx_seg_max; /* Maximum number of transmissable segments */ /* Calculated RTT cache */ unsigned int recent_srtt_us; unsigned int recent_rto_us; u8 cong_ssthresh; /* Congestion slow-start threshold */ }; /* * Keys for matching a connection. */ struct rxrpc_conn_proto { union { struct { u32 epoch; /* epoch of this connection */ u32 cid; /* connection ID */ }; u64 index_key; }; }; struct rxrpc_conn_parameters { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Representation of remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ u16 service_id; /* Service ID for this connection */ u32 security_level; /* Security level selected */ }; /* * Call completion condition (state == RXRPC_CALL_COMPLETE). */ enum rxrpc_call_completion { RXRPC_CALL_SUCCEEDED, /* - Normal termination */ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ NR__RXRPC_CALL_COMPLETIONS }; /* * Bits in the connection flags. */ enum rxrpc_conn_flag { RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ RXRPC_CONN_FINAL_ACK_0, /* Need final ACK for channel 0 */ RXRPC_CONN_FINAL_ACK_1, /* Need final ACK for channel 1 */ RXRPC_CONN_FINAL_ACK_2, /* Need final ACK for channel 2 */ RXRPC_CONN_FINAL_ACK_3, /* Need final ACK for channel 3 */ }; #define RXRPC_CONN_FINAL_ACK_MASK ((1UL << RXRPC_CONN_FINAL_ACK_0) | \ (1UL << RXRPC_CONN_FINAL_ACK_1) | \ (1UL << RXRPC_CONN_FINAL_ACK_2) | \ (1UL << RXRPC_CONN_FINAL_ACK_3)) /* * Events that can be raised upon a connection. */ enum rxrpc_conn_event { RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */ RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */ }; /* * The connection protocol state. */ enum rxrpc_conn_proto_state { RXRPC_CONN_UNUSED, /* Connection not yet attempted */ RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */ RXRPC_CONN_CLIENT, /* Client connection */ RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */ RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ RXRPC_CONN_SERVICE, /* Service secured connection */ RXRPC_CONN_ABORTED, /* Conn aborted */ RXRPC_CONN__NR_STATES }; /* * RxRPC client connection bundle. */ struct rxrpc_bundle { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ struct list_head proc_link; /* Link in net->bundle_proc_list */ const struct rxrpc_security *security; /* applied security module */ refcount_t ref; atomic_t active; /* Number of active users */ unsigned int debug_id; u32 security_level; /* Security level selected */ u16 service_id; /* Service ID for this connection */ bool try_upgrade; /* True if the bundle is attempting upgrade */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ unsigned short alloc_error; /* Error from last conn allocation */ struct rb_node local_node; /* Node in local->client_conns */ struct list_head waiting_calls; /* Calls waiting for channels */ unsigned long avail_chans; /* Mask of available channels */ unsigned int conn_ids[4]; /* Connection IDs. */ struct rxrpc_connection *conns[4]; /* The connections in the bundle (max 4) */ }; /* * RxRPC connection definition * - matched by { local, peer, epoch, conn_id, direction } * - each connection can only handle four simultaneous calls */ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ struct list_head attend_link; /* Link in local->conn_attend_q */ refcount_t ref; atomic_t active; /* Active count for service conns */ struct rcu_head rcu; struct list_head cache_link; unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call *call; /* Active call */ unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ u8 last_type; /* Type of last packet */ union { u32 last_seq; u32 last_abort; }; } channels[RXRPC_MAXCALLS]; struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ struct work_struct destructor; /* In-process-context destroyer */ struct rxrpc_bundle *bundle; /* Client connection bundle */ struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ struct page_frag_cache tx_data_alloc; /* Tx DATA packet allocation */ struct mutex tx_data_alloc_lock; struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ union { struct { struct fcrypt_key *cipher; /* encryption key */ struct rxrpc_crypt csum_iv; /* packet checksum base */ u32 nonce; /* response re-use preventer */ } rxkad; struct { struct rxgk_context *keys[4]; /* (Re-)keying buffer */ u64 start_time; /* The start time for TK derivation */ u8 nonce[20]; /* Response re-use preventer */ u32 enctype; /* Kerberos 5 encoding type */ u32 key_number; /* Current key number */ } rxgk; }; rwlock_t security_use_lock; /* Security use/modification lock */ struct sk_buff *tx_response; /* Response packet to be transmitted */ unsigned long flags; unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_proto_state state; /* current state of connection */ enum rxrpc_call_completion completion; /* Completion condition */ s32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ rxrpc_serial_t tx_serial; /* Outgoing packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ rxrpc_serial_t pmtud_probe; /* Serial of MTU probe (or 0) */ unsigned int pmtud_call; /* ID of call used for probe */ u32 service_id; /* Service ID, possibly upgraded */ u32 security_level; /* Security level selected */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ u8 bundle_shift; /* Index into bundle->avail_chans */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ u16 orig_service_id; /* Originally requested service ID */ short error; /* Local error code */ }; static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp) { return sp->hdr.flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp) { return !rxrpc_to_server(sp); } /* * Flags in call->flags. */ enum rxrpc_call_flag { RXRPC_CALL_RELEASED, /* call has been released - no more message to userspace */ RXRPC_CALL_HAS_USERID, /* has a user ID attached */ RXRPC_CALL_IS_SERVICE, /* Call is service call */ RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ RXRPC_CALL_TX_NO_MORE, /* No more data to transmit (MSG_MORE deasserted) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */ RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */ RXRPC_CALL_CONN_CHALLENGING, /* The connection is being challenged */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ RXRPC_CALL_EV_INITIAL_PING, /* Send initial ping for a new service call */ }; /* * The states that a call can be in. */ enum rxrpc_call_state { RXRPC_CALL_UNINITIALISED, RXRPC_CALL_CLIENT_AWAIT_CONN, /* - client waiting for connection to become available */ RXRPC_CALL_CLIENT_PRE_SEND, /* - client is connected, but hasn't sent anything yet */ RXRPC_CALL_CLIENT_SEND_REQUEST, /* - client sending request phase */ RXRPC_CALL_CLIENT_AWAIT_ACK, /* - client awaiting ACKs of request */ RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */ RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ RXRPC_CALL_SERVER_AWAIT_ACK, /* - server awaiting final ACK */ RXRPC_CALL_COMPLETE, /* - call complete */ NR__RXRPC_CALL_STATES }; /* * Call Tx congestion management modes. */ enum rxrpc_ca_state { RXRPC_CA_SLOW_START, RXRPC_CA_CONGEST_AVOIDANCE, RXRPC_CA_PACKET_LOSS, RXRPC_CA_FAST_RETRANSMIT, NR__RXRPC_CA_STATES } __mode(byte); /* * Current purpose of call RACK timer. According to the RACK-TLP protocol * [RFC8985], the transmission timer (call->rack_timo_at) may only be used for * one of these at once. */ enum rxrpc_rack_timer_mode { RXRPC_CALL_RACKTIMER_OFF, /* Timer not running */ RXRPC_CALL_RACKTIMER_RACK_REORDER, /* RACK reordering timer */ RXRPC_CALL_RACKTIMER_TLP_PTO, /* TLP timeout */ RXRPC_CALL_RACKTIMER_RTO, /* Retransmission timeout */ } __mode(byte); /* * RxRPC call definition * - matched by { connection, call_id } */ struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_bundle *bundle; /* Connection bundle to use */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ struct sockaddr_rxrpc dest_srx; /* Destination address */ ktime_t delay_ack_at; /* When DELAY ACK needs to happen */ ktime_t rack_timo_at; /* When ACK is figured as lost */ ktime_t ping_at; /* When next to send a ping */ ktime_t keepalive_at; /* When next to send a keepalive ping */ ktime_t expect_rx_by; /* When we expect to get a packet by */ ktime_t expect_req_by; /* When we expect to get a request DATA packet by */ ktime_t expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (ms) */ u32 next_req_timo; /* Timeout for next Rx request packet (ms) */ u32 hard_timo; /* Maximum lifetime or 0 (s) */ struct timer_list timer; /* Combined event timer */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ struct list_head wait_link; /* Link in local->new_client_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ struct list_head attend_link; /* Link in local->call_attend_q */ struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; unsigned long events; spinlock_t notify_lock; /* Kernel notification lock */ unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */ s32 send_abort; /* Abort code to be sent */ short send_abort_err; /* Error to be associated with the abort */ rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */ s32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ enum rxrpc_call_state _state; /* Current state of call (needs barrier) */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; u8 security_ix; /* Security type */ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ u32 security_level; /* Security level selected */ u32 security_enctype; /* Security-specific encoding type (or 0) */ int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ /* Sendmsg data tracking. */ rxrpc_seq_t send_top; /* Highest Tx slot filled by sendmsg. */ struct rxrpc_txqueue *send_queue; /* Queue that sendmsg is writing into */ /* Transmitted data tracking. */ struct rxrpc_txqueue *tx_queue; /* Start of transmission buffers */ struct rxrpc_txqueue *tx_qtail; /* End of transmission buffers */ rxrpc_seq_t tx_qbase; /* First slot in tx_queue */ rxrpc_seq_t tx_bottom; /* First packet in buffer */ rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ rxrpc_serial_t tx_last_serial; /* Serial of last DATA transmitted */ u16 tx_backoff; /* Delay to insert due to Tx failure (ms) */ u16 tx_nr_sent; /* Number of packets sent, but unacked */ u16 tx_nr_lost; /* Number of packets marked lost */ u16 tx_nr_resent; /* Number of packets resent, but unacked */ u16 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 u8 tx_jumbo_max; /* Maximum subpkts peer will accept */ ktime_t tx_last_sent; /* Last time a transmission occurred */ /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ struct sk_buff_head rx_queue; /* Queue of packets for this call to receive */ struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ void *rx_dec_buffer; /* Decryption buffer */ unsigned short rx_dec_bsize; /* rx_dec_buffer size */ unsigned short rx_dec_offset; /* Decrypted packet data offset */ unsigned short rx_dec_len; /* Decrypted packet data len */ rxrpc_seq_t rx_dec_seq; /* Packet in decryption buffer */ rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ rxrpc_seq_t rx_consumed; /* Highest packet consumed */ rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA * packets) rather than bytes. */ #define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN #define RXRPC_MIN_CWND 4 enum rxrpc_ca_state cong_ca_state; /* Congestion control state */ u8 cong_extra; /* Extra to send for congestion management */ u16 cong_cwnd; /* Congestion window size */ u16 cong_ssthresh; /* Slow-start threshold */ u16 cong_dup_acks; /* Count of ACKs showing missing packets */ u16 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ /* RACK-TLP [RFC8985] state. */ ktime_t rack_xmit_ts; /* Latest transmission timestamp */ ktime_t rack_rtt; /* RTT of most recently ACK'd segment */ ktime_t rack_rtt_ts; /* Timestamp of rack_rtt */ ktime_t rack_reo_wnd; /* Reordering window */ unsigned int rack_reo_wnd_mult; /* Multiplier applied to rack_reo_wnd */ int rack_reo_wnd_persist; /* Num loss recoveries before reset reo_wnd */ rxrpc_seq_t rack_fack; /* Highest sequence so far ACK'd */ rxrpc_seq_t rack_end_seq; /* Highest sequence seen */ rxrpc_seq_t rack_dsack_round; /* DSACK opt recv'd in latest roundtrip */ bool rack_dsack_round_none; /* T if dsack_round is "None" */ bool rack_reordering_seen; /* T if detected reordering event */ enum rxrpc_rack_timer_mode rack_timer_mode; /* Current mode of RACK timer */ bool tlp_is_retrans; /* T if unacked TLP retransmission */ rxrpc_serial_t tlp_serial; /* Serial of TLP probe (or 0 if none in progress) */ rxrpc_seq_t tlp_seq; /* Sequence of TLP probe */ unsigned int tlp_rtt_taken; /* Last time RTT taken */ ktime_t tlp_max_ack_delay; /* Sender budget for max delayed ACK interval */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ u16 ackr_sack_base; /* Starting slot in SACK table ring */ rxrpc_seq_t ackr_window; /* Base of SACK window */ rxrpc_seq_t ackr_wtop; /* Base of SACK window */ unsigned int ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ struct { #define RXRPC_SACK_SIZE 256 /* SACK table for soft-acked packets */ u8 ackr_sack_table[RXRPC_SACK_SIZE]; } __aligned(8); /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ ktime_t rtt_sent_at[4]; /* Time packet sent */ unsigned long rtt_avail; /* Mask of available slots in bits 0-3, * Mask of pending samples in 8-11 */ #define RXRPC_CALL_RTT_AVAIL_MASK 0xf #define RXRPC_CALL_RTT_PEND_SHIFT 8 /* Transmission-phase ACK management (ACKs we've received). */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_hard_ack; /* Highest sequence hard acked */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ unsigned short acks_nr_sacks; /* Number of soft acks recorded */ unsigned short acks_nr_snacks; /* Number of soft nacks recorded */ /* Calculated RTT cache */ ktime_t rtt_last_req; /* Time of last RTT request */ unsigned int rtt_count; /* Number of samples we've got */ unsigned int rtt_taken; /* Number of samples taken (wrapping) */ struct minmax min_rtt; /* Estimated minimum RTT */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rto_us; /* Retransmission timeout in usec */ u8 backoff; /* Backoff timeout (as shift) */ }; /* * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { rxrpc_serial_t ack_serial; /* Serial number of ACK */ rxrpc_serial_t acked_serial; /* Serial number ACK'd */ u16 in_flight; /* Number of unreceived transmissions */ u16 nr_new_hacks; /* Number of rotated new ACKs */ u16 nr_new_sacks; /* Number of new soft ACKs in packet */ u16 nr_new_snacks; /* Number of new soft nacks in packet */ u8 ack_reason; bool new_low_snack:1; /* T if new low soft NACK found */ bool retrans_timeo:1; /* T if reTx due to timeout happened */ bool need_retransmit:1; /* T if we need transmission */ bool rtt_sample_avail:1; /* T if RTT sample available */ bool in_fast_or_rto_recovery:1; bool exiting_fast_or_rto_recovery:1; bool tlp_probe_acked:1; /* T if the TLP probe seq was acked */ u8 /*enum rxrpc_congest_change*/ change; }; /* * sendmsg() cmsg-specified parameters. */ enum rxrpc_command { RXRPC_CMD_SEND_DATA, /* send data message */ RXRPC_CMD_SEND_ABORT, /* request abort generation */ RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ RXRPC_CMD_CHARGE_ACCEPT, /* [server] charge accept preallocation */ }; struct rxrpc_call_params { s64 tx_total_len; /* Total Tx data length (if send data) */ unsigned long user_call_ID; /* User's call ID */ struct { u32 hard; /* Maximum lifetime (sec) */ u32 idle; /* Max time since last data packet (msec) */ u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ bool kernel; /* T if kernel is making the call */ enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; struct rxrpc_send_params { struct rxrpc_call_params call; u32 abort_code; /* Abort code to Tx (if abort) */ enum rxrpc_command command : 8; /* The command to implement */ bool exclusive; /* Shared or exclusive call */ bool upgrade; /* If the connection is upgradeable */ }; /* * Buffer of data to be output as a packet. */ struct rxrpc_txbuf { refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ rxrpc_serial_t serial; /* Last serial number transmitted with */ unsigned int call_debug_id; unsigned int debug_id; unsigned short len; /* Amount of data in buffer */ unsigned short space; /* Remaining data space */ unsigned short offset; /* Offset of fill point */ unsigned short crypto_header; /* Size of crypto header */ unsigned short sec_header; /* Size of security header */ unsigned short pkt_len; /* Size of packet content */ unsigned short alloc_size; /* Amount of bufferage allocated */ unsigned int flags; #define RXRPC_TXBUF_WIRE_FLAGS 0xff /* The wire protocol flags */ #define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ __be16 cksum; /* Checksum to go in header */ bool jumboable; /* Can be non-terminal jumbo subpacket */ void *data; /* Data with preceding jumbo header */ }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) { return txb->flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) { return !rxrpc_sending_to_server(txb); } /* * Transmit queue element, including RACK [RFC8985] per-segment metadata. The * transmission timestamp is in usec from the base. */ struct rxrpc_txqueue { /* Start with the members we want to prefetch. */ struct rxrpc_txqueue *next; ktime_t xmit_ts_base; rxrpc_seq_t qbase; u8 nr_reported_acks; /* Number of segments explicitly acked/nacked */ unsigned long segment_acked; /* Bit-per-buf: Set if ACK'd */ unsigned long segment_lost; /* Bit-per-buf: Set if declared lost */ unsigned long segment_retransmitted; /* Bit-per-buf: Set if retransmitted */ unsigned long rtt_samples; /* Bit-per-buf: Set if available for RTT */ unsigned long ever_retransmitted; /* Bit-per-buf: Set if ever retransmitted */ /* The arrays we want to pack into as few cache lines as possible. */ struct { #define RXRPC_NR_TXQUEUE BITS_PER_LONG #define RXRPC_TXQ_MASK (RXRPC_NR_TXQUEUE - 1) struct rxrpc_txbuf *bufs[RXRPC_NR_TXQUEUE]; unsigned int segment_serial[RXRPC_NR_TXQUEUE]; unsigned int segment_xmit_ts[RXRPC_NR_TXQUEUE]; } ____cacheline_aligned; }; /* * Data transmission request. */ struct rxrpc_send_data_req { ktime_t now; /* Current time */ struct rxrpc_txqueue *tq; /* Tx queue segment holding first DATA */ rxrpc_seq_t seq; /* Sequence of first data */ int n; /* Number of DATA packets to glue into jumbo */ bool retrans; /* T if this is a retransmission */ bool did_send; /* T if did actually send */ bool tlp_probe; /* T if this is a TLP probe */ int /* enum rxrpc_txdata_trace */ trace; }; #include <trace/events/rxrpc.h> /* * Allocate the next serial number on a connection. 0 must be skipped. */ static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn) { rxrpc_serial_t serial; serial = conn->tx_serial; if (serial == 0) serial = 1; conn->tx_serial = serial + 1; return serial; } /* * Allocate the next serial n numbers on a connection. 0 must be skipped. */ static inline rxrpc_serial_t rxrpc_get_next_serials(struct rxrpc_connection *conn, unsigned int n) { rxrpc_serial_t serial; serial = conn->tx_serial; if (serial + n <= n) serial = 1; conn->tx_serial = serial + n; return serial; } /* * af_rxrpc.c */ extern atomic_t rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* * call_accept.c */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); bool rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_resend_tlp(struct rxrpc_call *call); void rxrpc_transmit_some_data(struct rxrpc_call *call, unsigned int limit, enum rxrpc_txdata_trace trace); bool rxrpc_input_call_event(struct rxrpc_call *call); /* * call_object.c */ extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern struct kmem_cache *rxrpc_call_jar; void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what); struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, struct rxrpc_call_params *, gfp_t, unsigned int) __releases(&rx->sk.sk_lock) __acquires(&call->user_mutex); void rxrpc_start_call_timer(struct rxrpc_call *call); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); void rxrpc_destroy_all_calls(struct rxrpc_net *); static inline bool rxrpc_is_service_call(const struct rxrpc_call *call) { return test_bit(RXRPC_CALL_IS_SERVICE, &call->flags); } static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) { return !rxrpc_is_service_call(call); } /* * call_state.c */ bool rxrpc_set_call_completion(struct rxrpc_call *call, enum rxrpc_call_completion compl, u32 abort_code, int error); bool rxrpc_call_completed(struct rxrpc_call *call); bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, u32 abort_code, int error, enum rxrpc_abort_reason why); void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl, int error); static inline void rxrpc_set_call_state(struct rxrpc_call *call, enum rxrpc_call_state state) { /* Order write of completion info before write of ->state. */ smp_store_release(&call->_state, state); wake_up(&call->waitq); } static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call) { return call->_state; /* Only inside I/O thread */ } static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call) { return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; } static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call) { /* Order read ->state before read of completion info. */ return smp_load_acquire(&call->_state); } static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call) { return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; } static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call) { return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED; } /* * conn_client.c */ extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; void rxrpc_purge_client_connections(struct rxrpc_local *local); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp); void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c */ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb, unsigned int channel); int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, s32 abort_code, int err, enum rxrpc_abort_reason why); void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb); static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn) { /* Order reading the abort info after the state check. */ return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED; } /* * conn_object.c */ extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why); struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *, struct sockaddr_rxrpc *, struct sk_buff *); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_client_conn(struct rxrpc_connection *); void rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_see_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_put_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) { return conn->out_clientflag; } static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) { return !rxrpc_conn_is_client(conn); } static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, unsigned long expire_at) { timer_reduce(&conn->timer, expire_at); } /* * conn_service.c */ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, const struct rxrpc_security *, struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ void rxrpc_congestion_degrade(struct rxrpc_call *); void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); /* * input_rack.c */ void rxrpc_input_rack_one(struct rxrpc_call *call, struct rxrpc_ack_summary *summary, struct rxrpc_txqueue *tq, unsigned int ix); void rxrpc_input_rack(struct rxrpc_call *call, struct rxrpc_ack_summary *summary, struct rxrpc_txqueue *tq, unsigned long new_acks); void rxrpc_rack_detect_loss_and_arm_timer(struct rxrpc_call *call, struct rxrpc_ack_summary *summary); ktime_t rxrpc_tlp_calc_pto(struct rxrpc_call *call, ktime_t now); void rxrpc_tlp_send_probe(struct rxrpc_call *call); void rxrpc_tlp_process_ack(struct rxrpc_call *call, struct rxrpc_ack_summary *summary); void rxrpc_rack_timer_expired(struct rxrpc_call *call, ktime_t overran_by); /* Initialise TLP state [RFC8958 7.1]. */ static inline void rxrpc_tlp_init(struct rxrpc_call *call) { call->tlp_serial = 0; call->tlp_seq = call->acks_hard_ack; call->tlp_is_retrans = false; } /* * io_thread.c */ int rxrpc_encap_rcv(struct sock *, struct sk_buff *); void rxrpc_error_report(struct sock *); bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, s32 abort_code, int err); bool rxrpc_direct_conn_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, s32 abort_code, int err); int rxrpc_io_thread(void *data); void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) { struct task_struct *io_thread = READ_ONCE(local->io_thread); if (!io_thread) return; wake_up_process(io_thread); } static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why) { return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO); } /* * insecure.c */ extern const struct rxrpc_security rxrpc_no_security; /* * key.c */ extern struct key_type key_type_rxrpc; int rxrpc_request_key(struct rxrpc_sock *, sockptr_t , int); int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, u32); /* * local_event.c */ void rxrpc_gen_version_string(void); void rxrpc_send_version_request(struct rxrpc_local *local, struct rxrpc_host_header *hdr, struct sk_buff *skb); /* * local_object.c */ void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set); struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_put_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_unuse_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_destroy_local(struct rxrpc_local *local); void rxrpc_destroy_all_locals(struct rxrpc_net *); static inline bool __rxrpc_use_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { int r, u; r = refcount_read(&local->ref); u = atomic_fetch_add_unless(&local->active_users, 1, 0); trace_rxrpc_local(local->debug_id, why, r, u); return u != 0; } static inline void rxrpc_see_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { int r, u; r = refcount_read(&local->ref); u = atomic_read(&local->active_users); trace_rxrpc_local(local->debug_id, why, r, u); } /* * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY extern unsigned long rxrpc_inject_rx_delay; #endif /* * net_ns.c */ extern unsigned int rxrpc_net_id; extern struct pernet_operations rxrpc_net_ops; static inline struct rxrpc_net *rxrpc_net(struct net *net) { return net_generic(net, rxrpc_net_id); } /* * oob.c */ bool rxrpc_notify_socket_oob(struct rxrpc_call *call, struct sk_buff *skb); void rxrpc_add_pending_oob(struct rxrpc_sock *rx, struct sk_buff *skb); int rxrpc_sendmsg_oob(struct rxrpc_sock *rx, struct msghdr *msg, size_t len); /* * output.c */ ssize_t do_udp_sendmsg(struct socket *socket, struct msghdr *msg, size_t len); void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why); void rxrpc_send_probe_for_pmtud(struct rxrpc_call *call); int rxrpc_send_abort_packet(struct rxrpc_call *); void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req *req); void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *skb); /* * peer_event.c */ void rxrpc_input_error(struct rxrpc_local *, struct sk_buff *); void rxrpc_peer_keepalive_worker(struct work_struct *); void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial, bool sendmsg_fail); /* Update the last transmission time on a peer for keepalive purposes. */ static inline void rxrpc_peer_mark_tx(struct rxrpc_peer *peer) { /* To avoid tearing on 32-bit systems, we only keep the LSW. */ WRITE_ONCE(peer->last_tx_at, ktime_get_seconds()); } /* * peer_object.c */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp); void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, enum rxrpc_peer_trace); void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace); void rxrpc_put_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); /* * proc.c */ extern const struct seq_operations rxrpc_call_seq_ops; extern const struct seq_operations rxrpc_connection_seq_ops; extern const struct seq_operations rxrpc_bundle_seq_ops; extern const struct seq_operations rxrpc_peer_seq_ops; extern const struct seq_operations rxrpc_local_seq_ops; /* * recvmsg.c */ void rxrpc_notify_socket(struct rxrpc_call *); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * Abort a call due to a protocol error. */ static inline int rxrpc_abort_eproto(struct rxrpc_call *call, struct sk_buff *skb, s32 abort_code, enum rxrpc_abort_reason why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why); return -EPROTO; } /* * rtt.c */ void rxrpc_call_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time); ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans); void rxrpc_call_init_rtt(struct rxrpc_call *call); /* * rxgk.c */ extern const struct rxrpc_security rxgk_yfs; /* * rxkad.c */ #ifdef CONFIG_RXKAD extern const struct rxrpc_security rxkad; #endif /* * security.c */ int __init rxrpc_init_security(void); const struct rxrpc_security *rxrpc_security_lookup(u8); void rxrpc_exit_security(void); int rxrpc_init_client_call_security(struct rxrpc_call *); int rxrpc_init_client_conn_security(struct rxrpc_connection *); const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *, struct sk_buff *); struct key *rxrpc_look_up_server_security(struct rxrpc_connection *, struct sk_buff *, u32, u32); /* * sendmsg.c */ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, enum rxrpc_abort_reason why); int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* * server_key.c */ extern struct key_type key_type_rxrpc_s; int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int); /* * skbuff.c */ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* * stats.c */ int rxrpc_stats_show(struct seq_file *seq, void *v); int rxrpc_stats_clear(struct file *file, char *buf, size_t size); #define rxrpc_inc_stat(rxnet, s) atomic_inc(&(rxnet)->s) #define rxrpc_dec_stat(rxnet, s) atomic_dec(&(rxnet)->s) /* * sysctl.c */ #ifdef CONFIG_SYSCTL extern int __init rxrpc_sysctl_init(void); extern void rxrpc_sysctl_exit(void); #else static inline int __init rxrpc_sysctl_init(void) { return 0; } static inline void rxrpc_sysctl_exit(void) {} #endif /* * txbuf.c */ extern atomic_t rxrpc_nr_txbuf; struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, size_t data_align, gfp_t gfp); void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); /* * utils.c */ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); static inline bool before(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) < 0; } static inline bool before_eq(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) <= 0; } static inline bool after(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) > 0; } static inline bool after_eq(u32 seq1, u32 seq2) { return (s32)(seq1 - seq2) >= 0; } static inline u32 earliest(u32 seq1, u32 seq2) { return before(seq1, seq2) ? seq1 : seq2; } static inline u32 latest(u32 seq1, u32 seq2) { return after(seq1, seq2) ? seq1 : seq2; } static inline bool rxrpc_seq_in_txq(const struct rxrpc_txqueue *tq, rxrpc_seq_t seq) { return (seq & (RXRPC_NR_TXQUEUE - 1)) == tq->qbase; } static inline void rxrpc_queue_rx_call_packet(struct rxrpc_call *call, struct sk_buff *skb) { rxrpc_get_skb(skb, rxrpc_skb_get_call_rx); __skb_queue_tail(&call->rx_queue, skb); rxrpc_poke_call(call, rxrpc_call_poke_rx_packet); } /* * Calculate how much space there is for transmitting more DATA packets. */ static inline unsigned int rxrpc_tx_window_space(const struct rxrpc_call *call) { int winsize = umin(call->tx_winsize, call->cong_cwnd + call->cong_extra); int transmitted = call->tx_top - call->tx_bottom; return max(winsize - transmitted, 0); } static inline unsigned int rxrpc_left_out(const struct rxrpc_call *call) { return call->acks_nr_sacks + call->tx_nr_lost; } /* * Calculate the number of transmitted DATA packets assumed to be in flight * [approx RFC6675]. */ static inline unsigned int rxrpc_tx_in_flight(const struct rxrpc_call *call) { return call->tx_nr_sent - rxrpc_left_out(call) + call->tx_nr_resent; } /* * debug tracing */ extern unsigned int rxrpc_debug; #define dbgprintk(FMT,...) \ printk("[%-6.6s] "FMT"\n", current->comm ,##__VA_ARGS__) #define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__) #if defined(__KDEBUG) #define _enter(FMT,...) kenter(FMT,##__VA_ARGS__) #define _leave(FMT,...) kleave(FMT,##__VA_ARGS__) #define _debug(FMT,...) kdebug(FMT,##__VA_ARGS__) #elif defined(CONFIG_AF_RXRPC_DEBUG) #define RXRPC_DEBUG_KENTER 0x01 #define RXRPC_DEBUG_KLEAVE 0x02 #define RXRPC_DEBUG_KDEBUG 0x04 #define _enter(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KENTER)) \ kenter(FMT,##__VA_ARGS__); \ } while (0) #define _leave(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KLEAVE)) \ kleave(FMT,##__VA_ARGS__); \ } while (0) #define _debug(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KDEBUG)) \ kdebug(FMT,##__VA_ARGS__); \ } while (0) #else #define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__) #endif /* * debug assertion checking */ #if 1 // defined(__KDEBUGALL) #define ASSERT(X) \ do { \ if (unlikely(!(X))) { \ pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ __typeof__(X) _x = (X); \ __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely(!(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ (unsigned long)_x, (unsigned long)_x, #OP, \ (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) #define ASSERTIF(C, X) \ do { \ if (unlikely((C) && !(X))) { \ pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ __typeof__(X) _x = (X); \ __typeof__(Y) _y = (__typeof__(X))(Y); \ if (unlikely((C) && !(_x OP _y))) { \ pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ (unsigned long)_x, (unsigned long)_x, #OP, \ (unsigned long)_y, (unsigned long)_y); \ BUG(); \ } \ } while (0) #else #define ASSERT(X) \ do { \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ } while (0) #define ASSERTIF(C, X) \ do { \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ } while (0) #endif /* __KDEBUGALL */ |
| 7 8 8 8 8 8 1 1 7 7 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | // SPDX-License-Identifier: GPL-2.0-only /* * spectrum management * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2008, Intel Corporation * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2018, 2020, 2022-2024, 2026 Intel Corporation */ #include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "sta_info.h" #include "wme.h" static bool wbcs_elem_to_chandef(const struct ieee80211_wide_bw_chansw_ie *wbcs_elem, struct cfg80211_chan_def *chandef) { u8 ccfs0 = wbcs_elem->new_center_freq_seg0; u8 ccfs1 = wbcs_elem->new_center_freq_seg1; u32 cf0 = ieee80211_channel_to_frequency(ccfs0, chandef->chan->band); u32 cf1 = ieee80211_channel_to_frequency(ccfs1, chandef->chan->band); switch (wbcs_elem->new_channel_width) { case IEEE80211_VHT_CHANWIDTH_160MHZ: /* deprecated encoding */ chandef->width = NL80211_CHAN_WIDTH_160; chandef->center_freq1 = cf0; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: /* deprecated encoding */ chandef->width = NL80211_CHAN_WIDTH_80P80; chandef->center_freq1 = cf0; chandef->center_freq2 = cf1; break; case IEEE80211_VHT_CHANWIDTH_80MHZ: chandef->width = NL80211_CHAN_WIDTH_80; chandef->center_freq1 = cf0; if (ccfs1) { u8 diff = abs(ccfs0 - ccfs1); if (diff == 8) { chandef->width = NL80211_CHAN_WIDTH_160; chandef->center_freq1 = cf1; } else if (diff > 8) { chandef->width = NL80211_CHAN_WIDTH_80P80; chandef->center_freq2 = cf1; } } break; case IEEE80211_VHT_CHANWIDTH_USE_HT: default: /* If the WBCS Element is present, new channel bandwidth is * at least 40 MHz. */ chandef->width = NL80211_CHAN_WIDTH_40; chandef->center_freq1 = cf0; break; } return cfg80211_chandef_valid(chandef); } static void validate_chandef_by_ht_vht_oper(struct ieee80211_sub_if_data *sdata, struct ieee80211_conn_settings *conn, u32 vht_cap_info, struct cfg80211_chan_def *chandef) { u32 control_freq, center_freq1, center_freq2; enum nl80211_chan_width chan_width; struct ieee80211_ht_operation ht_oper; struct ieee80211_vht_operation vht_oper; if (conn->mode < IEEE80211_CONN_MODE_HT || conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { chandef->chan = NULL; return; } control_freq = chandef->chan->center_freq; center_freq1 = chandef->center_freq1; center_freq2 = chandef->center_freq2; chan_width = chandef->width; ht_oper.primary_chan = ieee80211_frequency_to_channel(control_freq); if (control_freq != center_freq1) ht_oper.ht_param = control_freq > center_freq1 ? IEEE80211_HT_PARAM_CHA_SEC_BELOW : IEEE80211_HT_PARAM_CHA_SEC_ABOVE; else ht_oper.ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; ieee80211_chandef_ht_oper(&ht_oper, chandef); if (conn->mode < IEEE80211_CONN_MODE_VHT) return; vht_oper.center_freq_seg0_idx = ieee80211_frequency_to_channel(center_freq1); vht_oper.center_freq_seg1_idx = center_freq2 ? ieee80211_frequency_to_channel(center_freq2) : 0; switch (chan_width) { case NL80211_CHAN_WIDTH_320: WARN_ON(1); break; case NL80211_CHAN_WIDTH_160: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; vht_oper.center_freq_seg1_idx = vht_oper.center_freq_seg0_idx; vht_oper.center_freq_seg0_idx += control_freq < center_freq1 ? -8 : 8; break; case NL80211_CHAN_WIDTH_80P80: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_80: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; break; default: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_USE_HT; break; } ht_oper.operation_mode = le16_encode_bits(vht_oper.center_freq_seg1_idx, IEEE80211_HT_OP_MODE_CCFS2_MASK); if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_cap_info, &vht_oper, &ht_oper, chandef)) chandef->chan = NULL; } static void validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata, struct ieee80211_conn_settings *conn, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = sdata->local; u32 control_freq, center_freq1, center_freq2; enum nl80211_chan_width chan_width; DEFINE_RAW_FLEX(struct ieee80211_he_operation, he, optional, sizeof(struct ieee80211_he_6ghz_oper)); struct ieee80211_he_6ghz_oper *_6ghz_oper = (struct ieee80211_he_6ghz_oper *)he->optional; DEFINE_RAW_FLEX(struct ieee80211_eht_operation, eht, optional, sizeof(struct ieee80211_eht_operation_info)); struct ieee80211_eht_operation_info *_oper_info = (struct ieee80211_eht_operation_info *)eht->optional; const struct ieee80211_eht_operation *eht_oper; if (conn->mode < IEEE80211_CONN_MODE_HE) { chandef->chan = NULL; return; } control_freq = chandef->chan->center_freq; center_freq1 = chandef->center_freq1; center_freq2 = chandef->center_freq2; chan_width = chandef->width; he->he_oper_params = le32_encode_bits(1, IEEE80211_HE_OPERATION_6GHZ_OP_INFO); _6ghz_oper->primary = ieee80211_frequency_to_channel(control_freq); _6ghz_oper->ccfs0 = ieee80211_frequency_to_channel(center_freq1); _6ghz_oper->ccfs1 = center_freq2 ? ieee80211_frequency_to_channel(center_freq2) : 0; switch (chan_width) { case NL80211_CHAN_WIDTH_320: _6ghz_oper->ccfs1 = _6ghz_oper->ccfs0; _6ghz_oper->ccfs0 += control_freq < center_freq1 ? -16 : 16; _6ghz_oper->control = IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ; break; case NL80211_CHAN_WIDTH_160: _6ghz_oper->ccfs1 = _6ghz_oper->ccfs0; _6ghz_oper->ccfs0 += control_freq < center_freq1 ? -8 : 8; fallthrough; case NL80211_CHAN_WIDTH_80P80: _6ghz_oper->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ; break; case NL80211_CHAN_WIDTH_80: _6ghz_oper->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_40: _6ghz_oper->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ; break; default: _6ghz_oper->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ; break; } if (conn->mode < IEEE80211_CONN_MODE_EHT) { eht_oper = NULL; } else { eht->params = IEEE80211_EHT_OPER_INFO_PRESENT; _oper_info->control = _6ghz_oper->control; _oper_info->ccfs0 = _6ghz_oper->ccfs0; _oper_info->ccfs1 = _6ghz_oper->ccfs1; eht_oper = eht; } if (!ieee80211_chandef_he_6ghz_oper(local, he, eht_oper, chandef)) chandef->chan = NULL; } int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band current_band, u32 vht_cap_info, struct ieee80211_conn_settings *conn, u8 *bssid, bool unprot_action, struct ieee80211_csa_ie *csa_ie) { enum nl80211_band new_band = current_band; int new_freq; int new_chan_no = -1, new_op_class = -1; struct ieee80211_channel *new_chan; struct cfg80211_chan_def new_chandef = {}; const struct ieee80211_sec_chan_offs_ie *sec_chan_offs; const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie; const struct ieee80211_bandwidth_indication *bwi; const struct ieee80211_ext_chansw_ie *ext_chansw_elem; int secondary_channel_offset = -1; memset(csa_ie, 0, sizeof(*csa_ie)); sec_chan_offs = elems->sec_chan_offs; wide_bw_chansw_ie = elems->wide_bw_chansw_ie; bwi = elems->bandwidth_indication; ext_chansw_elem = elems->ext_chansw_ie; if (conn->mode < IEEE80211_CONN_MODE_HT || conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { sec_chan_offs = NULL; wide_bw_chansw_ie = NULL; } if (conn->mode < IEEE80211_CONN_MODE_VHT) wide_bw_chansw_ie = NULL; if (ext_chansw_elem) { new_op_class = ext_chansw_elem->new_operating_class; if (!ieee80211_operating_class_to_band(new_op_class, &new_band)) { new_op_class = -1; if (!unprot_action) sdata_info(sdata, "cannot understand ECSA IE operating class, %d, ignoring\n", ext_chansw_elem->new_operating_class); } else { new_chan_no = ext_chansw_elem->new_ch_num; csa_ie->count = ext_chansw_elem->count; csa_ie->mode = ext_chansw_elem->mode; } } if (new_op_class < 0 && elems->ch_switch_ie) { new_chan_no = elems->ch_switch_ie->new_ch_num; csa_ie->count = elems->ch_switch_ie->count; csa_ie->mode = elems->ch_switch_ie->mode; } /* nothing here we understand */ if (new_chan_no < 0) return 1; /* Mesh Channel Switch Parameters Element */ if (elems->mesh_chansw_params_ie) { csa_ie->ttl = elems->mesh_chansw_params_ie->mesh_ttl; csa_ie->mode = elems->mesh_chansw_params_ie->mesh_flags; csa_ie->pre_value = le16_to_cpu( elems->mesh_chansw_params_ie->mesh_pre_value); if (elems->mesh_chansw_params_ie->mesh_flags & WLAN_EID_CHAN_SWITCH_PARAM_REASON) csa_ie->reason_code = le16_to_cpu( elems->mesh_chansw_params_ie->mesh_reason); } new_freq = ieee80211_channel_to_frequency(new_chan_no, new_band); new_chan = ieee80211_get_channel(sdata->local->hw.wiphy, new_freq); if (!new_chan || new_chan->flags & IEEE80211_CHAN_DISABLED) { if (!unprot_action) sdata_info(sdata, "BSS %pM switches to unsupported channel (%d MHz), disconnecting\n", bssid, new_freq); return -EINVAL; } if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; } else if (conn->mode >= IEEE80211_CONN_MODE_HT) { /* If the secondary channel offset IE is not present, * we can't know what's the post-CSA offset, so the * best we can do is use 20MHz. */ secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE; } switch (secondary_channel_offset) { default: /* secondary_channel_offset was present but is invalid */ case IEEE80211_HT_PARAM_CHA_SEC_NONE: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT20); break; case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT40PLUS); break; case IEEE80211_HT_PARAM_CHA_SEC_BELOW: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT40MINUS); break; case -1: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_NO_HT); break; } /* capture the AP configuration */ csa_ie->chanreq.ap = csa_ie->chanreq.oper; /* parse one of the Elements to build a new chandef */ memset(&new_chandef, 0, sizeof(new_chandef)); new_chandef.chan = new_chan; if (bwi) { /* start with the CSA one */ new_chandef = csa_ie->chanreq.oper; /* and update the width accordingly */ ieee80211_chandef_eht_oper(&bwi->info, &new_chandef); if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT) new_chandef.punctured = get_unaligned_le16(bwi->info.optional); } else if (!wide_bw_chansw_ie || !wbcs_elem_to_chandef(wide_bw_chansw_ie, &new_chandef)) { if (new_op_class < 0 || !ieee80211_operating_class_to_chandef(new_op_class, new_chan, &new_chandef)) new_chandef = csa_ie->chanreq.oper; } /* check if the new chandef fits the capabilities */ if (new_band == NL80211_BAND_6GHZ) validate_chandef_by_6ghz_he_eht_oper(sdata, conn, &new_chandef); else validate_chandef_by_ht_vht_oper(sdata, conn, vht_cap_info, &new_chandef); /* if data is there validate the bandwidth & use it */ if (new_chandef.chan) { /* capture the AP chandef before (potential) downgrading */ csa_ie->chanreq.ap = new_chandef; while (conn->bw_limit < ieee80211_min_bw_limit_from_chandef(&new_chandef)) ieee80211_chandef_downgrade(&new_chandef, NULL); if (!cfg80211_chandef_compatible(&new_chandef, &csa_ie->chanreq.oper)) { sdata_info(sdata, "BSS %pM: CSA has inconsistent channel data, disconnecting\n", bssid); return -EINVAL; } csa_ie->chanreq.oper = new_chandef; } if (elems->max_channel_switch_time) csa_ie->max_switch_time = (elems->max_channel_switch_time[0] << 0) | (elems->max_channel_switch_time[1] << 8) | (elems->max_channel_switch_time[2] << 16); return 0; } static void ieee80211_send_refuse_measurement_request(struct ieee80211_sub_if_data *sdata, struct ieee80211_msrment_ie *request_ie, const u8 *da, const u8 *bssid, u8 dialog_token) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *msr_report; skb = dev_alloc_skb(IEEE80211_MIN_ACTION_SIZE(measurement) + local->hw.extra_tx_headroom); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); msr_report = skb_put_zero(skb, IEEE80211_MIN_ACTION_SIZE(measurement)); memcpy(msr_report->da, da, ETH_ALEN); memcpy(msr_report->sa, sdata->vif.addr, ETH_ALEN); memcpy(msr_report->bssid, bssid, ETH_ALEN); msr_report->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); msr_report->u.action.category = WLAN_CATEGORY_SPECTRUM_MGMT; msr_report->u.action.action_code = WLAN_ACTION_SPCT_MSR_RPRT; msr_report->u.action.measurement.dialog_token = dialog_token; msr_report->u.action.measurement.element_id = WLAN_EID_MEASURE_REPORT; msr_report->u.action.measurement.length = sizeof(struct ieee80211_msrment_ie); msr_report->u.action.measurement.msr_elem.token = request_ie->token; msr_report->u.action.measurement.msr_elem.mode |= IEEE80211_SPCT_MSR_RPRT_MODE_REFUSED; msr_report->u.action.measurement.msr_elem.type = request_ie->type; ieee80211_tx_skb(sdata, skb); } void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) { /* * Ignoring measurement request is spec violation. * Mandatory measurements must be reported optional * measurements might be refused or reported incapable * For now just refuse * TODO: Answer basic measurement as unmeasured */ ieee80211_send_refuse_measurement_request(sdata, &mgmt->u.action.measurement.msr_elem, mgmt->sa, mgmt->bssid, mgmt->u.action.measurement.dialog_token); } |
| 428 428 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_STATE_H #define _LINUX_CONTEXT_TRACKING_STATE_H #include <linux/percpu.h> #include <linux/static_key.h> #include <linux/context_tracking_irq.h> /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ #define CT_NESTING_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { CT_STATE_DISABLED = -1, /* returned by ct_state() if unknown */ CT_STATE_KERNEL = 0, CT_STATE_IDLE = 1, CT_STATE_USER = 2, CT_STATE_GUEST = 3, CT_STATE_MAX = 4, }; struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING_USER /* * When active is false, probes are unset in order * to minimize overhead: TIF flags are cleared * and calls to user_enter/exit are ignored. This * may be further optimized using static keys. */ bool active; int recursion; #endif #ifdef CONFIG_CONTEXT_TRACKING atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE long nesting; /* Track process nesting level. */ long nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; /* * We cram two different things within the same atomic variable: * * CT_RCU_WATCHING_START CT_STATE_START * | | * v v * MSB [ RCU watching counter ][ context_state ] LSB * ^ ^ * | | * CT_RCU_WATCHING_END CT_STATE_END * * Bits are used from the LSB upwards, so unused bits (if any) will always be in * upper bits of the variable. */ #ifdef CONFIG_CONTEXT_TRACKING #define CT_SIZE (sizeof(((struct context_tracking *)0)->state) * BITS_PER_BYTE) #define CT_STATE_WIDTH bits_per(CT_STATE_MAX - 1) #define CT_STATE_START 0 #define CT_STATE_END (CT_STATE_START + CT_STATE_WIDTH - 1) #define CT_RCU_WATCHING_MAX_WIDTH (CT_SIZE - CT_STATE_WIDTH) #define CT_RCU_WATCHING_WIDTH (IS_ENABLED(CONFIG_RCU_DYNTICKS_TORTURE) ? 2 : CT_RCU_WATCHING_MAX_WIDTH) #define CT_RCU_WATCHING_START (CT_STATE_END + 1) #define CT_RCU_WATCHING_END (CT_RCU_WATCHING_START + CT_RCU_WATCHING_WIDTH - 1) #define CT_RCU_WATCHING BIT(CT_RCU_WATCHING_START) #define CT_STATE_MASK GENMASK(CT_STATE_END, CT_STATE_START) #define CT_RCU_WATCHING_MASK GENMASK(CT_RCU_WATCHING_END, CT_RCU_WATCHING_START) #define CT_UNUSED_WIDTH (CT_RCU_WATCHING_MAX_WIDTH - CT_RCU_WATCHING_WIDTH) static_assert(CT_STATE_WIDTH + CT_RCU_WATCHING_WIDTH + CT_UNUSED_WIDTH == CT_SIZE); DECLARE_PER_CPU(struct context_tracking, context_tracking); #endif /* CONFIG_CONTEXT_TRACKING */ #ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; } #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE static __always_inline int ct_rcu_watching(void) { return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK; } static __always_inline int ct_rcu_watching_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read(&ct->state) & CT_RCU_WATCHING_MASK; } static __always_inline int ct_rcu_watching_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read_acquire(&ct->state) & CT_RCU_WATCHING_MASK; } static __always_inline long ct_nesting(void) { return __this_cpu_read(context_tracking.nesting); } static __always_inline long ct_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->nesting; } static __always_inline long ct_nmi_nesting(void) { return __this_cpu_read(context_tracking.nmi_nesting); } static __always_inline long ct_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->nmi_nesting; } #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ #ifdef CONFIG_CONTEXT_TRACKING_USER extern struct static_key_false context_tracking_key; static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } static __always_inline bool context_tracking_enabled_this_cpu(void) { return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } /** * ct_state() - return the current context tracking state if known * * Returns the current cpu's context tracking state if context tracking * is enabled. If context tracking is disabled, returns * CT_STATE_DISABLED. This should be used primarily for debugging. */ static __always_inline int ct_state(void) { int ret; if (!context_tracking_enabled()) return CT_STATE_DISABLED; preempt_disable(); ret = __ct_state(); preempt_enable(); return ret; } #else static __always_inline bool context_tracking_enabled(void) { return false; } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING_USER */ #endif |
| 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Universal MIDI Packet (UMP) support */ #include <linux/list.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/export.h> #include <linux/mm.h> #include <sound/core.h> #include <sound/rawmidi.h> #include <sound/ump.h> #include <sound/ump_convert.h> #define ump_err(ump, fmt, args...) dev_err((ump)->core.dev, fmt, ##args) #define ump_warn(ump, fmt, args...) dev_warn((ump)->core.dev, fmt, ##args) #define ump_info(ump, fmt, args...) dev_info((ump)->core.dev, fmt, ##args) #define ump_dbg(ump, fmt, args...) dev_dbg((ump)->core.dev, fmt, ##args) static int snd_ump_dev_register(struct snd_rawmidi *rmidi); static int snd_ump_dev_unregister(struct snd_rawmidi *rmidi); static long snd_ump_ioctl(struct snd_rawmidi *rmidi, unsigned int cmd, void __user *argp); static void snd_ump_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer); static int snd_ump_rawmidi_open(struct snd_rawmidi_substream *substream); static int snd_ump_rawmidi_close(struct snd_rawmidi_substream *substream); static void snd_ump_rawmidi_trigger(struct snd_rawmidi_substream *substream, int up); static void snd_ump_rawmidi_drain(struct snd_rawmidi_substream *substream); static void ump_handle_stream_msg(struct snd_ump_endpoint *ump, const u32 *buf, int size); #if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) static int process_legacy_output(struct snd_ump_endpoint *ump, u32 *buffer, int count); static void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words); static void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump); static void update_legacy_names(struct snd_ump_endpoint *ump); #else static inline int process_legacy_output(struct snd_ump_endpoint *ump, u32 *buffer, int count) { return 0; } static inline void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words) { } static inline void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump) { } static inline void update_legacy_names(struct snd_ump_endpoint *ump) { } #endif /* copy a string safely with stripping non-printable letters */ static void safe_copy_string(void *dst, size_t max_dst_size, const void *src, size_t max_src_size) { const unsigned char *s = src; unsigned char *d = dst; if (!max_dst_size--) return; for (s = src; max_dst_size && *s && max_src_size--; s++) { if (!isascii(*s) || !isprint(*s)) continue; *d++ = *s; max_dst_size--; } *d = 0; } /* append a string safely with stripping non-printable letters */ static void safe_append_string(void *dst, size_t max_dst_size, const void *src, size_t max_src_size) { unsigned char *d = dst; size_t len = strlen(d); safe_copy_string(d + len, max_dst_size - len, src, max_src_size); } static const struct snd_rawmidi_global_ops snd_ump_rawmidi_ops = { .dev_register = snd_ump_dev_register, .dev_unregister = snd_ump_dev_unregister, .ioctl = snd_ump_ioctl, .proc_read = snd_ump_proc_read, }; static const struct snd_rawmidi_ops snd_ump_rawmidi_input_ops = { .open = snd_ump_rawmidi_open, .close = snd_ump_rawmidi_close, .trigger = snd_ump_rawmidi_trigger, }; static const struct snd_rawmidi_ops snd_ump_rawmidi_output_ops = { .open = snd_ump_rawmidi_open, .close = snd_ump_rawmidi_close, .trigger = snd_ump_rawmidi_trigger, .drain = snd_ump_rawmidi_drain, }; static void snd_ump_endpoint_free(struct snd_rawmidi *rmidi) { struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); struct snd_ump_block *fb; while (!list_empty(&ump->block_list)) { fb = list_first_entry(&ump->block_list, struct snd_ump_block, list); list_del(&fb->list); if (fb->private_free) fb->private_free(fb); kfree(fb); } if (ump->private_free) ump->private_free(ump); #if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) kfree(ump->out_cvts); #endif } /** * snd_ump_endpoint_new - create a UMP Endpoint object * @card: the card instance * @id: the id string for rawmidi * @device: the device index for rawmidi * @output: 1 for enabling output * @input: 1 for enabling input * @ump_ret: the pointer to store the new UMP instance * * Creates a new UMP Endpoint object. A UMP Endpoint is tied with one rawmidi * instance with one input and/or one output rawmidi stream (either uni- * or bi-directional). A UMP Endpoint may contain one or multiple UMP Blocks * that consist of one or multiple UMP Groups. * * Use snd_rawmidi_set_ops() to set the operators to the new instance. * Unlike snd_rawmidi_new(), this function sets up the info_flags by itself * depending on the given @output and @input. * * The device has SNDRV_RAWMIDI_INFO_UMP flag set and a different device * file ("umpCxDx") than a standard MIDI 1.x device ("midiCxDx") is * created. * * Return: Zero if successful, or a negative error code on failure. */ int snd_ump_endpoint_new(struct snd_card *card, char *id, int device, int output, int input, struct snd_ump_endpoint **ump_ret) { unsigned int info_flags = SNDRV_RAWMIDI_INFO_UMP; struct snd_ump_endpoint *ump; int err; if (input) info_flags |= SNDRV_RAWMIDI_INFO_INPUT; if (output) info_flags |= SNDRV_RAWMIDI_INFO_OUTPUT; if (input && output) info_flags |= SNDRV_RAWMIDI_INFO_DUPLEX; ump = kzalloc_obj(*ump); if (!ump) return -ENOMEM; INIT_LIST_HEAD(&ump->block_list); mutex_init(&ump->open_mutex); init_waitqueue_head(&ump->stream_wait); #if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) spin_lock_init(&ump->legacy_locks[0]); spin_lock_init(&ump->legacy_locks[1]); #endif err = snd_rawmidi_init(&ump->core, card, id, device, output, input, info_flags); if (err < 0) { snd_rawmidi_free(&ump->core); return err; } ump->info.card = card->number; ump->info.device = device; ump->core.private_free = snd_ump_endpoint_free; ump->core.ops = &snd_ump_rawmidi_ops; if (input) snd_rawmidi_set_ops(&ump->core, SNDRV_RAWMIDI_STREAM_INPUT, &snd_ump_rawmidi_input_ops); if (output) snd_rawmidi_set_ops(&ump->core, SNDRV_RAWMIDI_STREAM_OUTPUT, &snd_ump_rawmidi_output_ops); ump_dbg(ump, "Created a UMP EP #%d (%s)\n", device, id); *ump_ret = ump; return 0; } EXPORT_SYMBOL_GPL(snd_ump_endpoint_new); /* * Device register / unregister hooks; * do nothing, placeholders for avoiding the default rawmidi handling */ #if IS_ENABLED(CONFIG_SND_SEQUENCER) static void snd_ump_dev_seq_free(struct snd_seq_device *device) { struct snd_ump_endpoint *ump = device->private_data; ump->seq_dev = NULL; } #endif static int snd_ump_dev_register(struct snd_rawmidi *rmidi) { #if IS_ENABLED(CONFIG_SND_SEQUENCER) struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); int err; err = snd_seq_device_new(ump->core.card, ump->core.device, SNDRV_SEQ_DEV_ID_UMP, 0, &ump->seq_dev); if (err < 0) return err; ump->seq_dev->private_data = ump; ump->seq_dev->private_free = snd_ump_dev_seq_free; snd_device_register(ump->core.card, ump->seq_dev); #endif return 0; } static int snd_ump_dev_unregister(struct snd_rawmidi *rmidi) { return 0; } static struct snd_ump_block * snd_ump_get_block(struct snd_ump_endpoint *ump, unsigned char id) { struct snd_ump_block *fb; list_for_each_entry(fb, &ump->block_list, list) { if (fb->info.block_id == id) return fb; } return NULL; } /* * rawmidi ops for UMP endpoint */ static int snd_ump_rawmidi_open(struct snd_rawmidi_substream *substream) { struct snd_ump_endpoint *ump = rawmidi_to_ump(substream->rmidi); int dir = substream->stream; int err; if (ump->substreams[dir]) return -EBUSY; err = ump->ops->open(ump, dir); if (err < 0) return err; ump->substreams[dir] = substream; return 0; } static int snd_ump_rawmidi_close(struct snd_rawmidi_substream *substream) { struct snd_ump_endpoint *ump = rawmidi_to_ump(substream->rmidi); int dir = substream->stream; ump->substreams[dir] = NULL; ump->ops->close(ump, dir); return 0; } static void snd_ump_rawmidi_trigger(struct snd_rawmidi_substream *substream, int up) { struct snd_ump_endpoint *ump = rawmidi_to_ump(substream->rmidi); int dir = substream->stream; ump->ops->trigger(ump, dir, up); } static void snd_ump_rawmidi_drain(struct snd_rawmidi_substream *substream) { struct snd_ump_endpoint *ump = rawmidi_to_ump(substream->rmidi); if (ump->ops->drain) ump->ops->drain(ump, SNDRV_RAWMIDI_STREAM_OUTPUT); } /* number of 32bit words per message type */ static unsigned char ump_packet_words[0x10] = { 1, 1, 1, 2, 2, 4, 1, 1, 2, 2, 2, 3, 3, 4, 4, 4 }; /** * snd_ump_receive_ump_val - parse the UMP packet data * @ump: UMP endpoint * @val: UMP packet data * * The data is copied onto ump->input_buf[]. * When a full packet is completed, returns the number of words (from 1 to 4). * OTOH, if the packet is incomplete, returns 0. */ int snd_ump_receive_ump_val(struct snd_ump_endpoint *ump, u32 val) { int words; if (!ump->input_pending) ump->input_pending = ump_packet_words[ump_message_type(val)]; ump->input_buf[ump->input_buf_head++] = val; ump->input_pending--; if (!ump->input_pending) { words = ump->input_buf_head; ump->input_buf_head = 0; return words; } return 0; } EXPORT_SYMBOL_GPL(snd_ump_receive_ump_val); /** * snd_ump_receive - transfer UMP packets from the device * @ump: the UMP endpoint * @buffer: the buffer pointer to transfer * @count: byte size to transfer * * Called from the driver to submit the received UMP packets from the device * to user-space. It's essentially a wrapper of rawmidi_receive(). * The data to receive is in CPU-native endianness. */ int snd_ump_receive(struct snd_ump_endpoint *ump, const u32 *buffer, int count) { struct snd_rawmidi_substream *substream; const u32 *p = buffer; int n, words = count >> 2; while (words--) { n = snd_ump_receive_ump_val(ump, *p++); if (!n) continue; ump_handle_stream_msg(ump, ump->input_buf, n); #if IS_ENABLED(CONFIG_SND_SEQUENCER) if (ump->seq_ops) ump->seq_ops->input_receive(ump, ump->input_buf, n); #endif process_legacy_input(ump, ump->input_buf, n); } substream = ump->substreams[SNDRV_RAWMIDI_STREAM_INPUT]; if (!substream) return 0; return snd_rawmidi_receive(substream, (const char *)buffer, count); } EXPORT_SYMBOL_GPL(snd_ump_receive); /** * snd_ump_transmit - transmit UMP packets * @ump: the UMP endpoint * @buffer: the buffer pointer to transfer * @count: byte size to transfer * * Called from the driver to obtain the UMP packets from user-space to the * device. It's essentially a wrapper of rawmidi_transmit(). * The data to transmit is in CPU-native endianness. */ int snd_ump_transmit(struct snd_ump_endpoint *ump, u32 *buffer, int count) { struct snd_rawmidi_substream *substream = ump->substreams[SNDRV_RAWMIDI_STREAM_OUTPUT]; int err; if (!substream) return -ENODEV; err = snd_rawmidi_transmit(substream, (char *)buffer, count); /* received either data or an error? */ if (err) return err; return process_legacy_output(ump, buffer, count); } EXPORT_SYMBOL_GPL(snd_ump_transmit); /** * snd_ump_block_new - Create a UMP block * @ump: UMP object * @blk: block ID number to create * @direction: direction (in/out/bidirection) * @first_group: the first group ID (0-based) * @num_groups: the number of groups in this block * @blk_ret: the pointer to store the resultant block object */ int snd_ump_block_new(struct snd_ump_endpoint *ump, unsigned int blk, unsigned int direction, unsigned int first_group, unsigned int num_groups, struct snd_ump_block **blk_ret) { struct snd_ump_block *fb, *p; if (blk >= SNDRV_UMP_MAX_BLOCKS) return -EINVAL; if (snd_ump_get_block(ump, blk)) return -EBUSY; fb = kzalloc_obj(*fb); if (!fb) return -ENOMEM; fb->ump = ump; fb->info.card = ump->info.card; fb->info.device = ump->info.device; fb->info.block_id = blk; if (blk >= ump->info.num_blocks) ump->info.num_blocks = blk + 1; fb->info.direction = direction; fb->info.active = 1; fb->info.first_group = first_group; fb->info.num_groups = num_groups; /* fill the default name, may be overwritten to a better name */ snprintf(fb->info.name, sizeof(fb->info.name), "Group %u-%u", first_group + 1, first_group + num_groups); /* put the entry in the ordered list */ list_for_each_entry(p, &ump->block_list, list) { if (p->info.block_id > blk) { list_add_tail(&fb->list, &p->list); goto added; } } list_add_tail(&fb->list, &ump->block_list); added: ump_dbg(ump, "Created a UMP Block #%d (%s)\n", blk, fb->info.name); *blk_ret = fb; return 0; } EXPORT_SYMBOL_GPL(snd_ump_block_new); static int snd_ump_ioctl_block(struct snd_ump_endpoint *ump, struct snd_ump_block_info __user *argp) { struct snd_ump_block *fb; unsigned char id; if (get_user(id, &argp->block_id)) return -EFAULT; fb = snd_ump_get_block(ump, id); if (!fb) return -ENOENT; if (copy_to_user(argp, &fb->info, sizeof(fb->info))) return -EFAULT; return 0; } /* * Handle UMP-specific ioctls; called from snd_rawmidi_ioctl() */ static long snd_ump_ioctl(struct snd_rawmidi *rmidi, unsigned int cmd, void __user *argp) { struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); switch (cmd) { case SNDRV_UMP_IOCTL_ENDPOINT_INFO: if (copy_to_user(argp, &ump->info, sizeof(ump->info))) return -EFAULT; return 0; case SNDRV_UMP_IOCTL_BLOCK_INFO: return snd_ump_ioctl_block(ump, argp); default: ump_dbg(ump, "rawmidi: unknown command = 0x%x\n", cmd); return -ENOTTY; } } static const char *ump_direction_string(int dir) { switch (dir) { case SNDRV_UMP_DIR_INPUT: return "input"; case SNDRV_UMP_DIR_OUTPUT: return "output"; case SNDRV_UMP_DIR_BIDIRECTION: return "bidirection"; default: return "unknown"; } } static const char *ump_ui_hint_string(int dir) { switch (dir) { case SNDRV_UMP_BLOCK_UI_HINT_RECEIVER: return "receiver"; case SNDRV_UMP_BLOCK_UI_HINT_SENDER: return "sender"; case SNDRV_UMP_BLOCK_UI_HINT_BOTH: return "both"; default: return "unknown"; } } /* Additional proc file output */ static void snd_ump_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_rawmidi *rmidi = entry->private_data; struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); struct snd_ump_block *fb; snd_iprintf(buffer, "EP Name: %s\n", ump->info.name); snd_iprintf(buffer, "EP Product ID: %s\n", ump->info.product_id); snd_iprintf(buffer, "UMP Version: 0x%04x\n", ump->info.version); snd_iprintf(buffer, "Protocol Caps: 0x%08x\n", ump->info.protocol_caps); snd_iprintf(buffer, "Protocol: 0x%08x\n", ump->info.protocol); if (ump->info.version) { snd_iprintf(buffer, "Manufacturer ID: 0x%08x\n", ump->info.manufacturer_id); snd_iprintf(buffer, "Family ID: 0x%04x\n", ump->info.family_id); snd_iprintf(buffer, "Model ID: 0x%04x\n", ump->info.model_id); snd_iprintf(buffer, "SW Revision: 0x%4phN\n", ump->info.sw_revision); } snd_iprintf(buffer, "Static Blocks: %s\n", (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS) ? "Yes" : "No"); snd_iprintf(buffer, "Num Blocks: %d\n\n", ump->info.num_blocks); list_for_each_entry(fb, &ump->block_list, list) { snd_iprintf(buffer, "Block %d (%s)\n", fb->info.block_id, fb->info.name); snd_iprintf(buffer, " Direction: %s\n", ump_direction_string(fb->info.direction)); snd_iprintf(buffer, " Active: %s\n", fb->info.active ? "Yes" : "No"); snd_iprintf(buffer, " Groups: %d-%d\n", fb->info.first_group + 1, fb->info.first_group + fb->info.num_groups); snd_iprintf(buffer, " Is MIDI1: %s%s\n", (fb->info.flags & SNDRV_UMP_BLOCK_IS_MIDI1) ? "Yes" : "No", (fb->info.flags & SNDRV_UMP_BLOCK_IS_LOWSPEED) ? " (Low Speed)" : ""); if (ump->info.version) { snd_iprintf(buffer, " MIDI-CI Version: %d\n", fb->info.midi_ci_version); snd_iprintf(buffer, " Sysex8 Streams: %d\n", fb->info.sysex8_streams); snd_iprintf(buffer, " UI Hint: %s\n", ump_ui_hint_string(fb->info.ui_hint)); } snd_iprintf(buffer, "\n"); } } /* update dir_bits and active flag for all groups in the client */ void snd_ump_update_group_attrs(struct snd_ump_endpoint *ump) { struct snd_ump_block *fb; struct snd_ump_group *group; int i; for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) { group = &ump->groups[i]; *group->name = 0; group->dir_bits = 0; group->active = 0; group->group = i; group->valid = false; group->is_midi1 = false; } list_for_each_entry(fb, &ump->block_list, list) { if (fb->info.first_group + fb->info.num_groups > SNDRV_UMP_MAX_GROUPS) break; group = &ump->groups[fb->info.first_group]; for (i = 0; i < fb->info.num_groups; i++, group++) { group->valid = true; if (fb->info.active) group->active = 1; if (fb->info.flags & SNDRV_UMP_BLOCK_IS_MIDI1) group->is_midi1 = true; switch (fb->info.direction) { case SNDRV_UMP_DIR_INPUT: group->dir_bits |= (1 << SNDRV_RAWMIDI_STREAM_INPUT); break; case SNDRV_UMP_DIR_OUTPUT: group->dir_bits |= (1 << SNDRV_RAWMIDI_STREAM_OUTPUT); break; case SNDRV_UMP_DIR_BIDIRECTION: group->dir_bits |= (1 << SNDRV_RAWMIDI_STREAM_INPUT) | (1 << SNDRV_RAWMIDI_STREAM_OUTPUT); break; } if (!*fb->info.name) continue; if (*group->name) strlcat(group->name, ", ", sizeof(group->name)); safe_append_string(group->name, sizeof(group->name), fb->info.name, sizeof(fb->info.name)); } } } EXPORT_SYMBOL_GPL(snd_ump_update_group_attrs); /* * UMP endpoint and function block handling */ /* open / close UMP streams for the internal stream msg communication */ static int ump_request_open(struct snd_ump_endpoint *ump) { return snd_rawmidi_kernel_open(&ump->core, 0, SNDRV_RAWMIDI_LFLG_OUTPUT, &ump->stream_rfile); } static void ump_request_close(struct snd_ump_endpoint *ump) { snd_rawmidi_kernel_release(&ump->stream_rfile); } /* request a command and wait for the given response; * @req1 and @req2 are u32 commands * @reply is the expected UMP stream status */ static int ump_req_msg(struct snd_ump_endpoint *ump, u32 req1, u32 req2, u32 reply) { u32 buf[4]; ump_dbg(ump, "%s: request %08x %08x, wait-for %08x\n", __func__, req1, req2, reply); memset(buf, 0, sizeof(buf)); buf[0] = req1; buf[1] = req2; ump->stream_finished = 0; ump->stream_wait_for = reply; snd_rawmidi_kernel_write(ump->stream_rfile.output, (unsigned char *)&buf, 16); wait_event_timeout(ump->stream_wait, ump->stream_finished, msecs_to_jiffies(500)); if (!READ_ONCE(ump->stream_finished)) { ump_dbg(ump, "%s: request timed out\n", __func__); return -ETIMEDOUT; } ump->stream_finished = 0; ump_dbg(ump, "%s: reply: %08x %08x %08x %08x\n", __func__, buf[0], buf[1], buf[2], buf[3]); return 0; } /* append the received letters via UMP packet to the given string buffer; * return 1 if the full string is received or 0 to continue */ static int ump_append_string(struct snd_ump_endpoint *ump, char *dest, int maxsize, const u32 *buf, int offset) { unsigned char format; int c; format = ump_stream_message_format(buf[0]); if (format == UMP_STREAM_MSG_FORMAT_SINGLE || format == UMP_STREAM_MSG_FORMAT_START) { c = 0; } else { c = strlen(dest); if (c >= maxsize - 1) return 1; } for (; offset < 16; offset++) { dest[c] = buf[offset / 4] >> (3 - (offset % 4)) * 8; if (!dest[c]) break; if (++c >= maxsize - 1) break; } dest[c] = 0; return (format == UMP_STREAM_MSG_FORMAT_SINGLE || format == UMP_STREAM_MSG_FORMAT_END); } /* Choose the default protocol */ static void choose_default_protocol(struct snd_ump_endpoint *ump) { if (ump->info.protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK) return; if (ump->info.protocol_caps & SNDRV_UMP_EP_INFO_PROTO_MIDI2) ump->info.protocol |= SNDRV_UMP_EP_INFO_PROTO_MIDI2; else ump->info.protocol |= SNDRV_UMP_EP_INFO_PROTO_MIDI1; } /* notify the EP info/name change to sequencer */ static void seq_notify_ep_change(struct snd_ump_endpoint *ump) { #if IS_ENABLED(CONFIG_SND_SEQUENCER) if (ump->parsed && ump->seq_ops && ump->seq_ops->notify_ep_change) ump->seq_ops->notify_ep_change(ump); #endif } /* handle EP info stream message; update the UMP attributes */ static int ump_handle_ep_info_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { ump->info.version = (buf->ep_info.ump_version_major << 8) | buf->ep_info.ump_version_minor; ump->info.num_blocks = buf->ep_info.num_function_blocks; if (ump->info.num_blocks > SNDRV_UMP_MAX_BLOCKS) { ump_info(ump, "Invalid function blocks %d, fallback to 1\n", ump->info.num_blocks); ump->info.num_blocks = 1; } if (buf->ep_info.static_function_block) ump->info.flags |= SNDRV_UMP_EP_INFO_STATIC_BLOCKS; ump->info.protocol_caps = (buf->ep_info.protocol << 8) | buf->ep_info.jrts; ump_dbg(ump, "EP info: version=%x, num_blocks=%x, proto_caps=%x\n", ump->info.version, ump->info.num_blocks, ump->info.protocol_caps); ump->info.protocol &= ump->info.protocol_caps; choose_default_protocol(ump); seq_notify_ep_change(ump); return 1; /* finished */ } /* handle EP device info stream message; update the UMP attributes */ static int ump_handle_device_info_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { ump->info.manufacturer_id = buf->device_info.manufacture_id & 0x7f7f7f; ump->info.family_id = (buf->device_info.family_msb << 8) | buf->device_info.family_lsb; ump->info.model_id = (buf->device_info.model_msb << 8) | buf->device_info.model_lsb; ump->info.sw_revision[0] = (buf->device_info.sw_revision >> 24) & 0x7f; ump->info.sw_revision[1] = (buf->device_info.sw_revision >> 16) & 0x7f; ump->info.sw_revision[2] = (buf->device_info.sw_revision >> 8) & 0x7f; ump->info.sw_revision[3] = buf->device_info.sw_revision & 0x7f; ump_dbg(ump, "EP devinfo: manid=%08x, family=%04x, model=%04x, sw=%4phN\n", ump->info.manufacturer_id, ump->info.family_id, ump->info.model_id, ump->info.sw_revision); seq_notify_ep_change(ump); return 1; /* finished */ } /* set up the core rawmidi name from UMP EP name string */ static void ump_set_rawmidi_name(struct snd_ump_endpoint *ump) { safe_copy_string(ump->core.name, sizeof(ump->core.name), ump->info.name, sizeof(ump->info.name)); } /* handle EP name stream message; update the UMP name string */ static int ump_handle_ep_name_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { int ret; ret = ump_append_string(ump, ump->info.name, sizeof(ump->info.name), buf->raw, 2); if (ret && ump->parsed) { ump_set_rawmidi_name(ump); ump_legacy_set_rawmidi_name(ump); seq_notify_ep_change(ump); } return ret; } /* handle EP product id stream message; update the UMP product_id string */ static int ump_handle_product_id_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { int ret; ret = ump_append_string(ump, ump->info.product_id, sizeof(ump->info.product_id), buf->raw, 2); if (ret) seq_notify_ep_change(ump); return ret; } /* notify the protocol change to sequencer */ static void seq_notify_protocol(struct snd_ump_endpoint *ump) { #if IS_ENABLED(CONFIG_SND_SEQUENCER) if (ump->seq_ops && ump->seq_ops->switch_protocol) ump->seq_ops->switch_protocol(ump); #endif /* CONFIG_SND_SEQUENCER */ } /** * snd_ump_switch_protocol - switch MIDI protocol * @ump: UMP endpoint * @protocol: protocol to switch to * * Returns 1 if the protocol is actually switched, 0 if unchanged */ int snd_ump_switch_protocol(struct snd_ump_endpoint *ump, unsigned int protocol) { unsigned int type; protocol &= ump->info.protocol_caps; if (protocol == ump->info.protocol) return 0; type = protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK; if (type != SNDRV_UMP_EP_INFO_PROTO_MIDI1 && type != SNDRV_UMP_EP_INFO_PROTO_MIDI2) return 0; ump->info.protocol = protocol; ump_dbg(ump, "New protocol = %x (caps = %x)\n", protocol, ump->info.protocol_caps); seq_notify_protocol(ump); return 1; } EXPORT_SYMBOL_GPL(snd_ump_switch_protocol); /* handle EP stream config message; update the UMP protocol */ static int ump_handle_stream_cfg_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { unsigned int protocol = (buf->stream_cfg.protocol << 8) | buf->stream_cfg.jrts; snd_ump_switch_protocol(ump, protocol); return 1; /* finished */ } /* Extract Function Block info from UMP packet */ static void fill_fb_info(struct snd_ump_endpoint *ump, struct snd_ump_block_info *info, const union snd_ump_stream_msg *buf) { info->direction = buf->fb_info.direction; info->ui_hint = buf->fb_info.ui_hint; info->first_group = buf->fb_info.first_group; info->num_groups = buf->fb_info.num_groups; if (buf->fb_info.midi_10 < 2) info->flags = buf->fb_info.midi_10; else info->flags = SNDRV_UMP_BLOCK_IS_MIDI1 | SNDRV_UMP_BLOCK_IS_LOWSPEED; info->active = buf->fb_info.active; info->midi_ci_version = buf->fb_info.midi_ci_version; info->sysex8_streams = buf->fb_info.sysex8_streams; ump_dbg(ump, "FB %d: dir=%d, active=%d, first_gp=%d, num_gp=%d, midici=%d, sysex8=%d, flags=0x%x\n", info->block_id, info->direction, info->active, info->first_group, info->num_groups, info->midi_ci_version, info->sysex8_streams, info->flags); if ((info->flags & SNDRV_UMP_BLOCK_IS_MIDI1) && info->num_groups != 1) { info->num_groups = 1; ump_dbg(ump, "FB %d: corrected groups to 1 for MIDI1\n", info->block_id); } } /* check whether the FB info gets updated by the current message */ static bool is_fb_info_updated(struct snd_ump_endpoint *ump, struct snd_ump_block *fb, const union snd_ump_stream_msg *buf) { char tmpbuf[offsetof(struct snd_ump_block_info, name)]; if (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS) { ump_info(ump, "Skipping static FB info update (blk#%d)\n", fb->info.block_id); return 0; } memcpy(tmpbuf, &fb->info, sizeof(tmpbuf)); fill_fb_info(ump, (struct snd_ump_block_info *)tmpbuf, buf); return memcmp(&fb->info, tmpbuf, sizeof(tmpbuf)) != 0; } /* notify the FB info/name change to sequencer */ static void seq_notify_fb_change(struct snd_ump_endpoint *ump, struct snd_ump_block *fb) { #if IS_ENABLED(CONFIG_SND_SEQUENCER) if (ump->seq_ops && ump->seq_ops->notify_fb_change) ump->seq_ops->notify_fb_change(ump, fb); #endif } /* handle FB info message; update FB info if the block is present */ static int ump_handle_fb_info_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { unsigned char blk; struct snd_ump_block *fb; blk = buf->fb_info.function_block_id; fb = snd_ump_get_block(ump, blk); /* complain only if updated after parsing */ if (!fb && ump->parsed) { ump_info(ump, "Function Block Info Update for non-existing block %d\n", blk); return -ENODEV; } /* When updated after the initial parse, check the FB info update */ if (ump->parsed && !is_fb_info_updated(ump, fb, buf)) return 1; /* no content change */ if (fb) { fill_fb_info(ump, &fb->info, buf); if (ump->parsed) { snd_ump_update_group_attrs(ump); update_legacy_names(ump); seq_notify_fb_change(ump, fb); } } return 1; /* finished */ } /* handle FB name message; update the FB name string */ static int ump_handle_fb_name_msg(struct snd_ump_endpoint *ump, const union snd_ump_stream_msg *buf) { unsigned char blk; struct snd_ump_block *fb; int ret; blk = buf->fb_name.function_block_id; fb = snd_ump_get_block(ump, blk); if (!fb) return -ENODEV; if (ump->parsed && (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS)) { ump_dbg(ump, "Skipping static FB name update (blk#%d)\n", fb->info.block_id); return 0; } ret = ump_append_string(ump, fb->info.name, sizeof(fb->info.name), buf->raw, 3); /* notify the FB name update to sequencer, too */ if (ret > 0 && ump->parsed) { snd_ump_update_group_attrs(ump); update_legacy_names(ump); seq_notify_fb_change(ump, fb); } return ret; } static int create_block_from_fb_info(struct snd_ump_endpoint *ump, int blk) { struct snd_ump_block *fb; unsigned char direction, first_group, num_groups; const union snd_ump_stream_msg *buf = (const union snd_ump_stream_msg *)ump->input_buf; u32 msg; int err; /* query the FB info once */ msg = ump_stream_compose(UMP_STREAM_MSG_STATUS_FB_DISCOVERY, 0) | (blk << 8) | UMP_STREAM_MSG_REQUEST_FB_INFO; err = ump_req_msg(ump, msg, 0, UMP_STREAM_MSG_STATUS_FB_INFO); if (err < 0) { ump_dbg(ump, "Unable to get FB info for block %d\n", blk); return err; } /* the last input must be the FB info */ if (buf->fb_info.status != UMP_STREAM_MSG_STATUS_FB_INFO) { ump_dbg(ump, "Inconsistent input: 0x%x\n", *buf->raw); return -EINVAL; } direction = buf->fb_info.direction; first_group = buf->fb_info.first_group; num_groups = buf->fb_info.num_groups; err = snd_ump_block_new(ump, blk, direction, first_group, num_groups, &fb); if (err < 0) return err; fill_fb_info(ump, &fb->info, buf); msg = ump_stream_compose(UMP_STREAM_MSG_STATUS_FB_DISCOVERY, 0) | (blk << 8) | UMP_STREAM_MSG_REQUEST_FB_NAME; err = ump_req_msg(ump, msg, 0, UMP_STREAM_MSG_STATUS_FB_NAME); if (err) ump_dbg(ump, "Unable to get UMP FB name string #%d\n", blk); return 0; } /* handle stream messages, called from snd_ump_receive() */ static void ump_handle_stream_msg(struct snd_ump_endpoint *ump, const u32 *buf, int size) { const union snd_ump_stream_msg *msg; unsigned int status; int ret; /* UMP stream message suppressed (for gadget UMP)? */ if (ump->no_process_stream) return; BUILD_BUG_ON(sizeof(*msg) != 16); ump_dbg(ump, "Stream msg: %08x %08x %08x %08x\n", buf[0], buf[1], buf[2], buf[3]); if (size != 4 || ump_message_type(*buf) != UMP_MSG_TYPE_STREAM) return; msg = (const union snd_ump_stream_msg *)buf; status = ump_stream_message_status(*buf); switch (status) { case UMP_STREAM_MSG_STATUS_EP_INFO: ret = ump_handle_ep_info_msg(ump, msg); break; case UMP_STREAM_MSG_STATUS_DEVICE_INFO: ret = ump_handle_device_info_msg(ump, msg); break; case UMP_STREAM_MSG_STATUS_EP_NAME: ret = ump_handle_ep_name_msg(ump, msg); break; case UMP_STREAM_MSG_STATUS_PRODUCT_ID: ret = ump_handle_product_id_msg(ump, msg); break; case UMP_STREAM_MSG_STATUS_STREAM_CFG: ret = ump_handle_stream_cfg_msg(ump, msg); break; case UMP_STREAM_MSG_STATUS_FB_INFO: ret = ump_handle_fb_info_msg(ump, msg); break; case UMP_STREAM_MSG_STATUS_FB_NAME: ret = ump_handle_fb_name_msg(ump, msg); break; default: return; } /* when the message has been processed fully, wake up */ if (ret > 0 && ump->stream_wait_for == status) { WRITE_ONCE(ump->stream_finished, 1); wake_up(&ump->stream_wait); } } /** * snd_ump_parse_endpoint - parse endpoint and create function blocks * @ump: UMP object * * Returns 0 for successful parse, -ENODEV if device doesn't respond * (or the query is unsupported), or other error code for serious errors. */ int snd_ump_parse_endpoint(struct snd_ump_endpoint *ump) { int blk, err; u32 msg; if (!(ump->core.info_flags & SNDRV_RAWMIDI_INFO_DUPLEX)) return -ENODEV; err = ump_request_open(ump); if (err < 0) { ump_dbg(ump, "Unable to open rawmidi device: %d\n", err); return err; } /* Check Endpoint Information */ msg = ump_stream_compose(UMP_STREAM_MSG_STATUS_EP_DISCOVERY, 0) | 0x0101; /* UMP version 1.1 */ err = ump_req_msg(ump, msg, UMP_STREAM_MSG_REQUEST_EP_INFO, UMP_STREAM_MSG_STATUS_EP_INFO); if (err < 0) { ump_dbg(ump, "Unable to get UMP EP info\n"); goto error; } /* Request Endpoint Device Info */ err = ump_req_msg(ump, msg, UMP_STREAM_MSG_REQUEST_DEVICE_INFO, UMP_STREAM_MSG_STATUS_DEVICE_INFO); if (err < 0) ump_dbg(ump, "Unable to get UMP EP device info\n"); /* Request Endpoint Name */ err = ump_req_msg(ump, msg, UMP_STREAM_MSG_REQUEST_EP_NAME, UMP_STREAM_MSG_STATUS_EP_NAME); if (err < 0) ump_dbg(ump, "Unable to get UMP EP name string\n"); ump_set_rawmidi_name(ump); /* Request Endpoint Product ID */ err = ump_req_msg(ump, msg, UMP_STREAM_MSG_REQUEST_PRODUCT_ID, UMP_STREAM_MSG_STATUS_PRODUCT_ID); if (err < 0) ump_dbg(ump, "Unable to get UMP EP product ID string\n"); /* Get the current stream configuration */ err = ump_req_msg(ump, msg, UMP_STREAM_MSG_REQUEST_STREAM_CFG, UMP_STREAM_MSG_STATUS_STREAM_CFG); if (err < 0) ump_dbg(ump, "Unable to get UMP EP stream config\n"); /* If no protocol is set by some reason, assume the valid one */ choose_default_protocol(ump); /* Query and create blocks from Function Blocks */ for (blk = 0; blk < ump->info.num_blocks; blk++) { err = create_block_from_fb_info(ump, blk); if (err < 0) continue; } /* initialize group attributions */ snd_ump_update_group_attrs(ump); error: ump->parsed = true; ump_request_close(ump); if (err == -ETIMEDOUT) err = -ENODEV; return err; } EXPORT_SYMBOL_GPL(snd_ump_parse_endpoint); #if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) /* * Legacy rawmidi support */ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream) { struct snd_ump_endpoint *ump = substream->rmidi->private_data; int dir = substream->stream; int group = ump->legacy_mapping[substream->number]; int err; guard(mutex)(&ump->open_mutex); if (ump->legacy_substreams[dir][group]) return -EBUSY; if (!ump->groups[group].active) return -ENODEV; if (dir == SNDRV_RAWMIDI_STREAM_OUTPUT) { if (!ump->legacy_out_opens) { err = snd_rawmidi_kernel_open_nested(&ump->core, 0, SNDRV_RAWMIDI_LFLG_OUTPUT | SNDRV_RAWMIDI_LFLG_APPEND, &ump->legacy_out_rfile, SINGLE_DEPTH_NESTING); if (err < 0) return err; } ump->legacy_out_opens++; snd_ump_convert_reset(&ump->out_cvts[group]); } guard(spinlock_irq)(&ump->legacy_locks[dir]); ump->legacy_substreams[dir][group] = substream; return 0; } static int snd_ump_legacy_close(struct snd_rawmidi_substream *substream) { struct snd_ump_endpoint *ump = substream->rmidi->private_data; int dir = substream->stream; int group = ump->legacy_mapping[substream->number]; guard(mutex)(&ump->open_mutex); scoped_guard(spinlock_irq, &ump->legacy_locks[dir]) ump->legacy_substreams[dir][group] = NULL; if (dir == SNDRV_RAWMIDI_STREAM_OUTPUT) { if (!--ump->legacy_out_opens) snd_rawmidi_kernel_release_nested(&ump->legacy_out_rfile, SINGLE_DEPTH_NESTING); } return 0; } static void snd_ump_legacy_trigger(struct snd_rawmidi_substream *substream, int up) { struct snd_ump_endpoint *ump = substream->rmidi->private_data; int dir = substream->stream; ump->ops->trigger(ump, dir, up); } static void snd_ump_legacy_drain(struct snd_rawmidi_substream *substream) { struct snd_ump_endpoint *ump = substream->rmidi->private_data; if (ump->ops->drain) ump->ops->drain(ump, SNDRV_RAWMIDI_STREAM_OUTPUT); } static int snd_ump_legacy_dev_register(struct snd_rawmidi *rmidi) { /* dummy, just for avoiding create superfluous seq clients */ return 0; } static const struct snd_rawmidi_ops snd_ump_legacy_input_ops = { .open = snd_ump_legacy_open, .close = snd_ump_legacy_close, .trigger = snd_ump_legacy_trigger, }; static const struct snd_rawmidi_ops snd_ump_legacy_output_ops = { .open = snd_ump_legacy_open, .close = snd_ump_legacy_close, .trigger = snd_ump_legacy_trigger, .drain = snd_ump_legacy_drain, }; static const struct snd_rawmidi_global_ops snd_ump_legacy_ops = { .dev_register = snd_ump_legacy_dev_register, }; static int process_legacy_output(struct snd_ump_endpoint *ump, u32 *buffer, int count) { struct snd_rawmidi_substream *substream; struct ump_cvt_to_ump *ctx; const int dir = SNDRV_RAWMIDI_STREAM_OUTPUT; unsigned int protocol; unsigned char c; int group, size = 0; if (!ump->out_cvts || !ump->legacy_out_opens) return 0; guard(spinlock_irqsave)(&ump->legacy_locks[dir]); for (group = 0; group < SNDRV_UMP_MAX_GROUPS; group++) { substream = ump->legacy_substreams[dir][group]; if (!substream) continue; ctx = &ump->out_cvts[group]; protocol = ump->info.protocol; if ((protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI2) && ump->groups[group].is_midi1) protocol = SNDRV_UMP_EP_INFO_PROTO_MIDI1; while (!ctx->ump_bytes && snd_rawmidi_transmit(substream, &c, 1) > 0) snd_ump_convert_to_ump(ctx, group, protocol, c); if (ctx->ump_bytes && ctx->ump_bytes <= count) { size = ctx->ump_bytes; memcpy(buffer, ctx->ump, size); ctx->ump_bytes = 0; break; } } return size; } static void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words) { struct snd_rawmidi_substream *substream; unsigned char buf[16]; unsigned char group; const int dir = SNDRV_RAWMIDI_STREAM_INPUT; int size; size = snd_ump_convert_from_ump(src, buf, &group); if (size <= 0) return; guard(spinlock_irqsave)(&ump->legacy_locks[dir]); substream = ump->legacy_substreams[dir][group]; if (substream) snd_rawmidi_receive(substream, buf, size); } /* Fill ump->legacy_mapping[] for groups to be used for legacy rawmidi */ static int fill_legacy_mapping(struct snd_ump_endpoint *ump) { struct snd_ump_block *fb; unsigned int group_maps = 0; int i, num; if (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS) { list_for_each_entry(fb, &ump->block_list, list) { for (i = 0; i < fb->info.num_groups; i++) group_maps |= 1U << (fb->info.first_group + i); } if (!group_maps) ump_info(ump, "No UMP Group is found in FB\n"); } /* use all groups for non-static case */ if (!group_maps) group_maps = (1U << SNDRV_UMP_MAX_GROUPS) - 1; num = 0; for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) if (group_maps & (1U << i)) ump->legacy_mapping[num++] = i; return num; } static void update_legacy_substreams(struct snd_ump_endpoint *ump, struct snd_rawmidi *rmidi, int dir) { struct snd_rawmidi_substream *s; const char *name; int idx; list_for_each_entry(s, &rmidi->streams[dir].substreams, list) { idx = ump->legacy_mapping[s->number]; name = ump->groups[idx].name; if (!*name) name = ump->core.name; scnprintf(s->name, sizeof(s->name), "Group %d (%.16s)%s", idx + 1, name, ump->groups[idx].active ? "" : " [Inactive]"); s->inactive = !ump->groups[idx].active; } } static void update_legacy_names(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; if (!rmidi) return; update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); } static void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; if (!rmidi) return; snprintf(rmidi->name, sizeof(rmidi->name), "%.68s (MIDI 1.0)", ump->core.name); } int snd_ump_attach_legacy_rawmidi(struct snd_ump_endpoint *ump, char *id, int device) { struct snd_rawmidi *rmidi; bool input, output; int err, num; ump->out_cvts = kzalloc_objs(*ump->out_cvts, SNDRV_UMP_MAX_GROUPS); if (!ump->out_cvts) return -ENOMEM; num = fill_legacy_mapping(ump); input = ump->core.info_flags & SNDRV_RAWMIDI_INFO_INPUT; output = ump->core.info_flags & SNDRV_RAWMIDI_INFO_OUTPUT; err = snd_rawmidi_new(ump->core.card, id, device, output ? num : 0, input ? num : 0, &rmidi); if (err < 0) { kfree(ump->out_cvts); ump->out_cvts = NULL; return err; } if (input) snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_INPUT, &snd_ump_legacy_input_ops); if (output) snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT, &snd_ump_legacy_output_ops); rmidi->info_flags = ump->core.info_flags & ~SNDRV_RAWMIDI_INFO_UMP; rmidi->ops = &snd_ump_legacy_ops; rmidi->private_data = ump; ump->legacy_rmidi = rmidi; ump_legacy_set_rawmidi_name(ump); update_legacy_names(ump); snd_rawmidi_tie_devices(rmidi, &ump->core); ump_dbg(ump, "Created a legacy rawmidi #%d (%s)\n", device, id); return 0; } EXPORT_SYMBOL_GPL(snd_ump_attach_legacy_rawmidi); #endif /* CONFIG_SND_UMP_LEGACY_RAWMIDI */ MODULE_DESCRIPTION("Universal MIDI Packet (UMP) Core Driver"); MODULE_LICENSE("GPL"); |
| 6 47 72 5 79 79 69 2 79 66 13 80 66 76 13 1 1 1 4 4 4 3 2 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/tcp.h> #include <net/tcp.h> static u32 tcp_rack_reo_wnd(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (!tp->reord_seen) { /* If reordering has not been observed, be aggressive during * the recovery or starting the recovery by DUPACK threshold. */ if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery) return 0; if (tp->sacked_out >= tp->reordering && !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & TCP_RACK_NO_DUPTHRESH)) return 0; } /* To be more reordering resilient, allow min_rtt/4 settling delay. * Use min_rtt instead of the smoothed RTT because reordering is * often a path property and less related to queuing or delayed ACKs. * Upon receiving DSACKs, linearly increase the window up to the * smoothed RTT. */ return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps, tp->srtt_us >> 3); } s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd) { return tp->rack.rtt_us + reo_wnd - tcp_stamp_us_delta(tp->tcp_mstamp, tcp_skb_timestamp_us(skb)); } /* RACK loss detection (IETF RFC8985): * * Marks a packet lost, if some packet sent later has been (s)acked. * The underlying idea is similar to the traditional dupthresh and FACK * but they look at different metrics: * * dupthresh: 3 OOO packets delivered (packet count) * FACK: sequence delta to highest sacked sequence (sequence space) * RACK: sent time delta to the latest delivered packet (time domain) * * The advantage of RACK is it applies to both original and retransmitted * packet and therefore is robust against tail losses. Another advantage * is being more resilient to reordering by simply allowing some * "settling delay", instead of tweaking the dupthresh. * * When tcp_rack_detect_loss() detects some packets are lost and we * are not already in the CA_Recovery state, either tcp_rack_reo_timeout() * or tcp_time_to_recover()'s "Trick#1: the loss is proven" code path will * make us enter the CA_Recovery state. */ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *n; u32 reo_wnd; *reo_timeout = 0; reo_wnd = tcp_rack_reo_wnd(sk); list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); s32 remaining; /* Skip ones marked lost but not yet retransmitted */ if ((scb->sacked & TCPCB_LOST) && !(scb->sacked & TCPCB_SACKED_RETRANS)) continue; if (!tcp_skb_sent_after(tp->rack.mstamp, tcp_skb_timestamp_us(skb), tp->rack.end_seq, scb->end_seq)) break; /* A packet is lost if it has not been s/acked beyond * the recent RTT plus the reordering window. */ remaining = tcp_rack_skb_timeout(tp, skb, reo_wnd); if (remaining <= 0) { tcp_mark_skb_lost(sk, skb); list_del_init(&skb->tcp_tsorted_anchor); } else { /* Record maximum wait time */ *reo_timeout = max_t(u32, *reo_timeout, remaining); } } } bool tcp_rack_mark_lost(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 timeout; if (!tp->rack.advanced) return false; /* Reset the advanced flag to avoid unnecessary queue scanning */ tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } return !!timeout; } /* We have waited long enough to accommodate reordering. Mark the expired * packets lost and retransmit them. */ void tcp_rack_reo_timeout(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 timeout, prior_inflight; u32 lost = tp->lost; prior_inflight = tcp_packets_in_flight(tp); tcp_rack_detect_loss(sk, &timeout); if (prior_inflight != tcp_packets_in_flight(tp)) { if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) { tcp_enter_recovery(sk, false); if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_cwnd_reduction(sk, 1, tp->lost - lost, 0); } tcp_xmit_retransmit_queue(sk); } if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS) tcp_rearm_rto(sk); } /* RFC6582 NewReno recovery for non-SACK connection. It simply retransmits * the next unacked packet upon receiving * a) three or more DUPACKs to start the fast recovery * b) an ACK acknowledging new data during the fast recovery. */ void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced) { const u8 state = inet_csk(sk)->icsk_ca_state; struct tcp_sock *tp = tcp_sk(sk); if ((state < TCP_CA_Recovery && tp->sacked_out >= tp->reordering) || (state == TCP_CA_Recovery && snd_una_advanced)) { struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 mss; if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) return; mss = tcp_skb_mss(skb); if (tcp_skb_pcount(skb) > 1 && skb->len > mss) tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, mss, mss, GFP_ATOMIC); tcp_mark_skb_lost(sk, skb); } } |
| 6 151 3 204 20 654 106 81 25 107 1 106 25 81 100 100 23 77 107 1 106 104 104 22 22 22 22 2 20 17 22 129 107 22 540 152 388 2 539 539 538 538 251 272 2 505 3 3 8 1 7 1 6 6 1 6 191 26 188 191 146 45 37 37 29 8 8 37 37 20 22 196 1 195 195 195 45 41 133 78 91 5 160 40 189 2 41 164 191 141 50 15 15 37 29 8 3556 3556 3556 3556 3556 7 7 7 7 7 7 16 16 16 18 18 3 5 12 4 4 4 3041 3041 3041 3041 3041 1247 3040 4567 11 2765 4567 2807 4567 4567 2 4491 77 4567 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/uio.h> #include "kernfs-internal.h" struct kernfs_open_node { struct rcu_head rcu_head; atomic_t event; wait_queue_head_t poll; struct list_head files; /* goes through kernfs_open_file.list */ unsigned int nr_mmapped; unsigned int nr_to_release; }; /* * kernfs_notify() may be called from any context and bounces notifications * through a work item. To minimize space overhead in kernfs_node, the * pending queue is implemented as a singly linked list of kernfs_nodes. * The list is terminated with the self pointer so that whether a * kernfs_node is on the list or not can be determined by testing the next * pointer for %NULL. */ #define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) static DEFINE_SPINLOCK(kernfs_notify_lock); static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; /* Compatibility wrappers - use the common hashed node lock */ static inline struct mutex *kernfs_open_file_mutex_ptr(struct kernfs_node *kn) { return kernfs_node_lock_ptr(kn); } static inline struct mutex *kernfs_open_file_mutex_lock(struct kernfs_node *kn) { return kernfs_node_lock(kn); } /** * of_on - Get the kernfs_open_node of the specified kernfs_open_file * @of: target kernfs_open_file * * Return: the kernfs_open_node of the kernfs_open_file */ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) { return rcu_dereference_protected(of->kn->attr.open, !list_empty(&of->list)); } /* Get active reference to kernfs node for an open file */ static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) { /* Skip if file was already released */ if (unlikely(of->released)) return NULL; if (!kernfs_get_active(of->kn)) return NULL; return of; } static void kernfs_put_active_of(struct kernfs_open_file *of) { return kernfs_put_active(of->kn); } /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * * @kn: target kernfs_node. * * Fetch and return ->attr.open of @kn when caller holds the * kernfs_open_file_mutex_ptr(kn). * * Update of ->attr.open happens under kernfs_open_file_mutex_ptr(kn). So when * the caller guarantees that this mutex is being held, other updaters can't * change ->attr.open and this means that we can safely deref ->attr.open * outside RCU read-side critical section. * * The caller needs to make sure that kernfs_open_file_mutex is held. * * Return: @kn->attr.open when kernfs_open_file_mutex is held. */ static struct kernfs_open_node * kernfs_deref_open_node_locked(struct kernfs_node *kn) { return rcu_dereference_protected(kn->attr.open, lockdep_is_held(kernfs_open_file_mutex_ptr(kn))); } static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; } /* * Determine the kernfs_ops for the given kernfs_node. This function must * be called while holding an active reference. */ static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) { if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kn->attr.ops; } /* * As kernfs_seq_stop() is also called after kernfs_seq_start() or * kernfs_seq_next() failure, it needs to distinguish whether it's stopping * a seq_file iteration which is fully initialized with an active reference * or an aborted kernfs_seq_start() due to get_active failure. The * position pointer is the only context for each seq_file iteration and * thus the stop condition should be encoded in it. As the return value is * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable * choice to indicate get_active failure. * * Unfortunately, this is complicated due to the optional custom seq_file * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or * custom seq_file operations and thus can't decide whether put_active * should be performed or not only on ERR_PTR(-ENODEV). * * This is worked around by factoring out the custom seq_stop() and * put_active part into kernfs_seq_stop_active(), skipping it from * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures * that kernfs_seq_stop_active() is skipped only after get_active failure. */ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_stop) ops->seq_stop(sf, v); kernfs_put_active_of(of); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); if (ops->seq_start) { void *next = ops->seq_start(sf, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } return single_start(sf, ppos); } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_next) { void *next = ops->seq_next(sf, v, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(), always * terminate after the initial read. */ ++*ppos; return NULL; } } static void kernfs_seq_stop(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; if (v != ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, v); mutex_unlock(&of->mutex); } static int kernfs_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; of->event = atomic_read(&of_on(of)->event); return of->kn->attr.ops->seq_show(sf, v); } static const struct seq_operations kernfs_seq_ops = { .start = kernfs_seq_start, .next = kernfs_seq_next, .stop = kernfs_seq_stop, .show = kernfs_seq_show, }; /* * As reading a bin file can have side-effects, the exact offset and bytes * specified in read(2) call should be passed to the read callback making * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; } of->event = atomic_read(&of_on(of)->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len < 0) goto out_free; if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) return seq_read_iter(iocb, iter); return kernfs_file_read_iter(iocb, iter); } /* * Copy data in from userland and pass it to the matching kernfs write * operation. * * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come on * the first write. Hint: if you're writing a value, first read the file, * modify only the value you're changing, then write entire buffer * back. */ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; char *buf; if (of->atomic_write_len) { if (len > of->atomic_write_len) return -E2BIG; } else { len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } buf[len] = '\0'; /* guarantee string termination */ /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; } ops = kernfs_ops(of->kn); if (ops->write) len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len > 0) iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static void kernfs_vma_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); if (!of->vm_ops) return; if (!kernfs_get_active_of(of)) return; if (of->vm_ops->open) of->vm_ops->open(vma); kernfs_put_active_of(of); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); kernfs_put_active_of(of); return ret; } static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = 0; if (of->vm_ops->page_mkwrite) ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); kernfs_put_active_of(of); return ret; } static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return -EINVAL; if (!kernfs_get_active_of(of)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); kernfs_put_active_of(of); return ret; } static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; int rc; /* * mmap path and of->mutex are prone to triggering spurious lockdep * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the * comment in kernfs_fop_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; mutex_lock(&of->mutex); rc = -ENODEV; if (!kernfs_get_active_of(of)) goto out_unlock; ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); if (rc) goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() * to satisfy versions of X which crash if the mmap fails: that * substitutes a new vm_file, and we don't then want bin_vm_ops. */ if (vma->vm_file != file) goto out_put; rc = -EINVAL; if (of->mmapped && of->vm_ops != vma->vm_ops) goto out_put; /* * It is not possible to successfully wrap close. * So error if someone is trying to use close. */ if (vma->vm_ops && vma->vm_ops->close) goto out_put; rc = 0; if (!of->mmapped) { of->mmapped = true; of_on(of)->nr_mmapped++; of->vm_ops = vma->vm_ops; } vma->vm_ops = &kernfs_vm_ops; out_put: kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex); return rc; } /** * kernfs_get_open_node - get or create kernfs_open_node * @kn: target kernfs_node * @of: kernfs_open_file for this instance of open * * If @kn->attr.open exists, increment its reference count; otherwise, * create one. @of is chained to the files list. * * Locking: * Kernel thread context (may sleep). * * Return: * %0 on success, -errno on failure. */ static int kernfs_get_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { /* not there, initialize a new one */ on = kzalloc_obj(*on); if (!on) { mutex_unlock(mutex); return -ENOMEM; } atomic_set(&on->event, 1); init_waitqueue_head(&on->poll); INIT_LIST_HEAD(&on->files); rcu_assign_pointer(kn->attr.open, on); } list_add_tail(&of->list, &on->files); if (kn->flags & KERNFS_HAS_RELEASE) on->nr_to_release++; mutex_unlock(mutex); return 0; } /** * kernfs_unlink_open_file - Unlink @of from @kn. * * @kn: target kernfs_node * @of: associated kernfs_open_file * @open_failed: ->open() failed, cancel ->release() * * Unlink @of from list of @kn's associated open files. If list of * associated open files becomes empty, disassociate and free * kernfs_open_node. * * LOCKING: * None. */ static void kernfs_unlink_open_file(struct kernfs_node *kn, struct kernfs_open_file *of, bool open_failed) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } if (of) { if (kn->flags & KERNFS_HAS_RELEASE) { WARN_ON_ONCE(of->released == open_failed); if (open_failed) on->nr_to_release--; } if (of->mmapped) on->nr_mmapped--; list_del(&of->list); } if (list_empty(&on->files)) { rcu_assign_pointer(kn->attr.open, NULL); kfree_rcu(on, rcu_head); } mutex_unlock(mutex); } static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; int error = -EACCES; if (!kernfs_get_active(kn)) return -ENODEV; ops = kernfs_ops(kn); has_read = ops->seq_show || ops->read || ops->mmap; has_write = ops->write || ops->mmap; has_mmap = ops->mmap; /* see the flag definition for details */ if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { if ((file->f_mode & FMODE_WRITE) && (!(inode->i_mode & S_IWUGO) || !has_write)) goto err_out; if ((file->f_mode & FMODE_READ) && (!(inode->i_mode & S_IRUGO) || !has_read)) goto err_out; } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; of = kzalloc_obj(struct kernfs_open_file); if (!of) goto err_out; /* * The following is done to give a different lockdep key to * @of->mutex for files which implement mmap. This is a rather * crude way to avoid false positive lockdep warning around * mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under * which mm->mmap_lock nests, while holding @of->mutex. As each * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * * For similar reasons, writable and readonly files are given different * lockdep key, because the writable file /sys/power/resume may call vfs * lookup helpers for arbitrary paths and readonly files can be read by * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. * * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); else if (file->f_mode & FMODE_WRITE) mutex_init(&of->mutex); else mutex_init(&of->mutex); of->kn = kn; of->file = file; /* * Write path needs to atomic_write_len outside active reference. * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; error = -EINVAL; /* * ->seq_show is incompatible with ->prealloc, * as seq_read does its own allocation. * ->read must be used instead. */ if (ops->prealloc && ops->seq_show) goto err_free; if (ops->prealloc) { int len = of->atomic_write_len ?: PAGE_SIZE; of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL); error = -ENOMEM; if (!of->prealloc_buf) goto err_free; mutex_init(&of->prealloc_mutex); } /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. */ if (ops->seq_show) error = seq_open(file, &kernfs_seq_ops); else error = seq_open(file, NULL); if (error) goto err_free; of->seq_file = file->private_data; of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) file->f_mode |= FMODE_PWRITE; /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) goto err_seq_release; if (ops->open) { /* nobody has access to @of yet, skip @of->mutex */ error = ops->open(of); if (error) goto err_put_node; } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; err_put_node: kernfs_unlink_open_file(kn, of, true); err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); kfree(of); err_out: kernfs_put_active(kn); return error; } /* used from release/drain to ensure that ->release() is called exactly once */ static void kernfs_release_file(struct kernfs_node *kn, struct kernfs_open_file *of) { /* * @of is guaranteed to have no other file operations in flight and * we just want to synchronize release and drain paths. * @kernfs_open_file_mutex_ptr(kn) is enough. @of->mutex can't be used * here because drain path may be called from places which can * cause circular dependency. */ lockdep_assert_held(kernfs_open_file_mutex_ptr(kn)); if (!of->released) { /* * A file is never detached without being released and we * need to be able to release files which are deactivated * and being drained. Don't use kernfs_ops(). */ kn->attr.ops->release(of); of->released = true; of_on(of)->nr_to_release--; } } static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); kernfs_release_file(kn, of); mutex_unlock(mutex); } kernfs_unlink_open_file(kn, of, false); seq_release(inode, filp); kfree(of->prealloc_buf); kfree(of); return 0; } bool kernfs_should_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; bool ret; /* * @kn being deactivated guarantees that @kn->attr.open can't change * beneath us making the lockless test below safe. * Callers post kernfs_unbreak_active_protection may be counted in * kn->active by now, do not WARN_ON because of them. */ rcu_read_lock(); on = rcu_dereference(kn->attr.open); ret = on && (on->nr_mmapped || on->nr_to_release); rcu_read_unlock(); return ret; } void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); if (of->mmapped) { unmap_mapping_range(inode->i_mapping, 0, 0, 1); of->mmapped = false; on->nr_mmapped--; } if (kn->flags & KERNFS_HAS_RELEASE) kernfs_release_file(kn, of); } WARN_ON_ONCE(on->nr_mmapped || on->nr_to_release); mutex_unlock(mutex); } /* * Kernfs attribute files are pollable. The idea is that you read * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. * Reminder: this only works for attributes which actively support * it, and it is not possible to test an attribute from userspace * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ __poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) { struct kernfs_open_node *on = of_on(of); poll_wait(of->file, &on->poll, wait); if (of->event != atomic_read(&on->event)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; return DEFAULT_POLLMASK; } static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) ret = kn->attr.ops->poll(of, wait); else ret = kernfs_generic_poll(of, wait); kernfs_put_active_of(of); return ret; } static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; loff_t ret; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); return -ENODEV; } ops = kernfs_ops(of->kn); if (ops->llseek) ret = ops->llseek(of, offset, whence); else ret = generic_file_llseek(file, offset, whence); kernfs_put_active_of(of); mutex_unlock(&of->mutex); return ret; } static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; struct kernfs_root *root; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); kn = kernfs_notify_list; if (kn == KERNFS_NOTIFY_EOL) { spin_unlock_irq(&kernfs_notify_lock); return; } kernfs_notify_list = kn->attr.notify_next; kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); root = kernfs_root(kn); /* kick fsnotify */ down_read(&root->kernfs_supers_rwsem); down_read(&root->kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; const char *kn_name; struct inode *inode; struct qstr name; /* * We want fsnotify_modify() on @kn but as the * modifications aren't originating from userland don't * have the matching @file available. Look up the inodes * and generate the events manually. */ inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; kn_name = kernfs_rcu_name(kn); name = QSTR(kn_name); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, p_inode, &name, inode, 0); iput(p_inode); } kernfs_put(parent); } if (!p_inode) fsnotify_inode(inode, FS_MODIFY); iput(inode); } up_read(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } /** * kernfs_notify - notify a kernfs file * @kn: file to notify * * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any * context. */ void kernfs_notify(struct kernfs_node *kn) { static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); unsigned long flags; struct kernfs_open_node *on; if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) return; /* kick poll immediately */ rcu_read_lock(); on = rcu_dereference(kn->attr.open); if (on) { atomic_inc(&on->event); wake_up_interruptible(&on->poll); } rcu_read_unlock(); /* schedule work to kick fsnotify */ spin_lock_irqsave(&kernfs_notify_lock, flags); if (!kn->attr.notify_next) { kernfs_get(kn); kn->attr.notify_next = kernfs_notify_list; kernfs_notify_list = kn; schedule_work(&kernfs_notify_work); } spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, .llseek = kernfs_fop_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /** * __kernfs_create_file - kernfs internal function to create a file * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file * @uid: uid of the file * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file * @ns: optional namespace tag of the file * @key: lockdep key for the file's active_ref, %NULL to disable lockdep * * Return: the created node on success, ERR_PTR() value on error. */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const struct ns_common *ns, struct lock_class_key *key) { struct kernfs_node *kn; unsigned flags; int rc; flags = KERNFS_FILE; kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); kn->attr.ops = ops; kn->attr.size = size; kn->ns = ns; kn->priv = priv; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { lockdep_init_map(&kn->dep_map, "kn->active", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif /* * kn->attr.ops is accessible only while holding active ref. We * need to know whether some ops are implemented outside active * ref. Cache their existence in flags. */ if (ops->seq_show) kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; if (ops->release) kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); } return kn; } |
| 4 4 4 19 19 19 19 19 19 19 3 3 3 1 1 55 13 31 2 1 15 15 10 46 46 13 33 31 15 46 46 46 23 55 23 19 19 19 19 19 19 13 1 3 19 3 19 88 88 38 38 6 2 1 6 1 80 79 1 4 4 4 4 4 4 16 16 1 14 11 11 52 37 29 29 52 52 29 7 7 7 4 4 4 4 4 4 4 3 3 3 3 3 4 4 4 31 31 6 26 4 4 4 32 32 32 32 12 12 11 10 2 6 1 1 2 3 2 4 4 2 1 1 2 1 1 36 36 36 20 20 20 19 19 3 3 3 19 1 18 17 1 18 3 3 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI connection handling. */ #include <linux/export.h> #include <linux/debugfs.h> #include <linux/errqueue.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/iso.h> #include <net/bluetooth/mgmt.h> #include "smp.h" #include "eir.h" struct sco_param { u16 pkt_type; u16 max_latency; u8 retrans_effort; }; struct conn_handle_t { struct hci_conn *conn; __u16 handle; }; static const struct sco_param esco_param_cvsd[] = { { EDR_ESCO_MASK & ~ESCO_2EV3, 0x000a, 0x01 }, /* S3 */ { EDR_ESCO_MASK & ~ESCO_2EV3, 0x0007, 0x01 }, /* S2 */ { EDR_ESCO_MASK | ESCO_EV3, 0x0007, 0x01 }, /* S1 */ { EDR_ESCO_MASK | ESCO_HV3, 0xffff, 0x01 }, /* D1 */ { EDR_ESCO_MASK | ESCO_HV1, 0xffff, 0x01 }, /* D0 */ }; static const struct sco_param sco_param_cvsd[] = { { EDR_ESCO_MASK | ESCO_HV3, 0xffff, 0xff }, /* D1 */ { EDR_ESCO_MASK | ESCO_HV1, 0xffff, 0xff }, /* D0 */ }; static const struct sco_param esco_param_msbc[] = { { EDR_ESCO_MASK & ~ESCO_2EV3, 0x000d, 0x02 }, /* T2 */ { EDR_ESCO_MASK | ESCO_EV3, 0x0008, 0x02 }, /* T1 */ }; /* This function requires the caller holds hdev->lock */ void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; struct smp_irk *irk; bdaddr_t *bdaddr; u8 bdaddr_type; bdaddr = &conn->dst; bdaddr_type = conn->dst_type; /* Check if we need to convert to identity address */ irk = hci_get_irk(hdev, bdaddr, bdaddr_type); if (irk) { bdaddr = &irk->bdaddr; bdaddr_type = irk->addr_type; } params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); if (!params) return; if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); params->conn = NULL; } if (!params->explicit_connect) return; /* If the status indicates successful cancellation of * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to * connect. The only exception is explicit connect requests * where a timeout + cancel does indicate an actual failure. */ if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) mgmt_connect_failed(hdev, conn, status); /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark * them as waiting for connection, by clearing explicit_connect field. */ params->explicit_connect = false; hci_pend_le_list_del_init(params); switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: hci_conn_params_del(hdev, bdaddr, bdaddr_type); /* return instead of break to avoid duplicate scan update */ return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; } hci_update_passive_scan(hdev); } static void hci_conn_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); if (test_and_clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags)) hci_remove_link_key(hdev, &conn->dst); hci_chan_list_flush(conn); if (HCI_CONN_HANDLE_UNSET(conn->handle)) ida_free(&hdev->unset_handle_ida, conn->handle); if (conn->cleanup) conn->cleanup(conn); if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: case SCO_AIRMODE_TRANSP: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_DISABLE_SCO); break; } } else { if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); } debugfs_remove_recursive(conn->debugfs); hci_conn_del_sysfs(conn); hci_dev_put(hdev); } int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); /* When we are central of an established connection and it enters * the disconnect timeout, then go ahead and try to read the * current clock offset. Processing of the result is done * within the event handling and hci_clock_offset_evt function. */ if (conn->type == ACL_LINK && conn->role == HCI_ROLE_MASTER && (conn->state == BT_CONNECTED || conn->state == BT_CONFIG)) { struct hci_dev *hdev = conn->hdev; struct hci_cp_read_clock_offset clkoff_cp; clkoff_cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_READ_CLOCK_OFFSET, sizeof(clkoff_cp), &clkoff_cp); } return hci_abort_conn(conn, reason); } static void hci_add_sco(struct hci_conn *conn, __u16 handle) { struct hci_dev *hdev = conn->hdev; struct hci_cp_add_sco cp; BT_DBG("hcon %p", conn); conn->state = BT_CONNECT; conn->out = true; conn->attempt++; cp.handle = cpu_to_le16(handle); cp.pkt_type = cpu_to_le16(conn->pkt_type); hci_send_cmd(hdev, HCI_OP_ADD_SCO, sizeof(cp), &cp); } static bool find_next_esco_param(struct hci_conn *conn, const struct sco_param *esco_param, int size) { if (!conn->parent) return false; for (; conn->attempt <= size; conn->attempt++) { if (lmp_esco_2m_capable(conn->parent) || (esco_param[conn->attempt - 1].pkt_type & ESCO_2EV3)) break; BT_DBG("hcon %p skipped attempt %d, eSCO 2M not supported", conn, conn->attempt); } return conn->attempt <= size; } static int configure_datapath_sync(struct hci_dev *hdev, struct bt_codec *codec) { int err; __u8 vnd_len, *vnd_data = NULL; struct hci_op_configure_data_path *cmd = NULL; /* Do not take below 2 checks as error since the 1st means user do not * want to use HFP offload mode and the 2nd means the vendor controller * do not need to send below HCI command for offload mode. */ if (!codec->data_path || !hdev->get_codec_config_data) return 0; err = hdev->get_codec_config_data(hdev, ESCO_LINK, codec, &vnd_len, &vnd_data); if (err < 0) goto error; cmd = kzalloc(sizeof(*cmd) + vnd_len, GFP_KERNEL); if (!cmd) { err = -ENOMEM; goto error; } err = hdev->get_data_path_id(hdev, &cmd->data_path_id); if (err < 0) goto error; cmd->vnd_len = vnd_len; memcpy(cmd->vnd_data, vnd_data, vnd_len); cmd->direction = 0x00; __hci_cmd_sync_status(hdev, HCI_CONFIGURE_DATA_PATH, sizeof(*cmd) + vnd_len, cmd, HCI_CMD_TIMEOUT); cmd->direction = 0x01; err = __hci_cmd_sync_status(hdev, HCI_CONFIGURE_DATA_PATH, sizeof(*cmd) + vnd_len, cmd, HCI_CMD_TIMEOUT); error: kfree(cmd); kfree(vnd_data); return err; } static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data) { struct conn_handle_t *conn_handle = data; struct hci_conn *conn = conn_handle->conn; __u16 handle = conn_handle->handle; struct hci_cp_enhanced_setup_sync_conn cp; const struct sco_param *param; if (!hci_conn_valid(hdev, conn)) return -ECANCELED; bt_dev_dbg(hdev, "hcon %p", conn); configure_datapath_sync(hdev, &conn->codec); conn->state = BT_CONNECT; conn->out = true; conn->attempt++; memset(&cp, 0x00, sizeof(cp)); cp.handle = cpu_to_le16(handle); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); switch (conn->codec.id) { case BT_CODEC_MSBC: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) return -EINVAL; param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x05; cp.rx_coding_format.id = 0x05; cp.tx_codec_frame_size = __cpu_to_le16(60); cp.rx_codec_frame_size = __cpu_to_le16(60); cp.in_bandwidth = __cpu_to_le32(32000); cp.out_bandwidth = __cpu_to_le32(32000); cp.in_coding_format.id = 0x04; cp.out_coding_format.id = 0x04; cp.in_coded_data_size = __cpu_to_le16(16); cp.out_coded_data_size = __cpu_to_le16(16); cp.in_pcm_data_format = 2; cp.out_pcm_data_format = 2; cp.in_pcm_sample_payload_msb_pos = 0; cp.out_pcm_sample_payload_msb_pos = 0; cp.in_data_path = conn->codec.data_path; cp.out_data_path = conn->codec.data_path; cp.in_transport_unit_size = 1; cp.out_transport_unit_size = 1; break; case BT_CODEC_TRANSPARENT: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) return -EINVAL; param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x03; cp.rx_coding_format.id = 0x03; cp.tx_codec_frame_size = __cpu_to_le16(60); cp.rx_codec_frame_size = __cpu_to_le16(60); cp.in_bandwidth = __cpu_to_le32(0x1f40); cp.out_bandwidth = __cpu_to_le32(0x1f40); cp.in_coding_format.id = 0x03; cp.out_coding_format.id = 0x03; cp.in_coded_data_size = __cpu_to_le16(16); cp.out_coded_data_size = __cpu_to_le16(16); cp.in_pcm_data_format = 2; cp.out_pcm_data_format = 2; cp.in_pcm_sample_payload_msb_pos = 0; cp.out_pcm_sample_payload_msb_pos = 0; cp.in_data_path = conn->codec.data_path; cp.out_data_path = conn->codec.data_path; cp.in_transport_unit_size = 1; cp.out_transport_unit_size = 1; break; case BT_CODEC_CVSD: if (conn->parent && lmp_esco_capable(conn->parent)) { if (!find_next_esco_param(conn, esco_param_cvsd, ARRAY_SIZE(esco_param_cvsd))) return -EINVAL; param = &esco_param_cvsd[conn->attempt - 1]; } else { if (conn->attempt > ARRAY_SIZE(sco_param_cvsd)) return -EINVAL; param = &sco_param_cvsd[conn->attempt - 1]; } cp.tx_coding_format.id = 2; cp.rx_coding_format.id = 2; cp.tx_codec_frame_size = __cpu_to_le16(60); cp.rx_codec_frame_size = __cpu_to_le16(60); cp.in_bandwidth = __cpu_to_le32(16000); cp.out_bandwidth = __cpu_to_le32(16000); cp.in_coding_format.id = 4; cp.out_coding_format.id = 4; cp.in_coded_data_size = __cpu_to_le16(16); cp.out_coded_data_size = __cpu_to_le16(16); cp.in_pcm_data_format = 2; cp.out_pcm_data_format = 2; cp.in_pcm_sample_payload_msb_pos = 0; cp.out_pcm_sample_payload_msb_pos = 0; cp.in_data_path = conn->codec.data_path; cp.out_data_path = conn->codec.data_path; cp.in_transport_unit_size = 16; cp.out_transport_unit_size = 16; break; default: return -EINVAL; } cp.retrans_effort = param->retrans_effort; cp.pkt_type = __cpu_to_le16(param->pkt_type); cp.max_latency = __cpu_to_le16(param->max_latency); if (hci_send_cmd(hdev, HCI_OP_ENHANCED_SETUP_SYNC_CONN, sizeof(cp), &cp) < 0) return -EIO; return 0; } static bool hci_setup_sync_conn(struct hci_conn *conn, __u16 handle) { struct hci_dev *hdev = conn->hdev; struct hci_cp_setup_sync_conn cp; const struct sco_param *param; bt_dev_dbg(hdev, "hcon %p", conn); conn->state = BT_CONNECT; conn->out = true; conn->attempt++; cp.handle = cpu_to_le16(handle); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.voice_setting = cpu_to_le16(conn->setting); switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) return false; param = &esco_param_msbc[conn->attempt - 1]; break; case SCO_AIRMODE_CVSD: if (conn->parent && lmp_esco_capable(conn->parent)) { if (!find_next_esco_param(conn, esco_param_cvsd, ARRAY_SIZE(esco_param_cvsd))) return false; param = &esco_param_cvsd[conn->attempt - 1]; } else { if (conn->attempt > ARRAY_SIZE(sco_param_cvsd)) return false; param = &sco_param_cvsd[conn->attempt - 1]; } break; default: return false; } cp.retrans_effort = param->retrans_effort; cp.pkt_type = __cpu_to_le16(param->pkt_type); cp.max_latency = __cpu_to_le16(param->max_latency); if (hci_send_cmd(hdev, HCI_OP_SETUP_SYNC_CONN, sizeof(cp), &cp) < 0) return false; return true; } static void hci_enhanced_setup_sync_destroy(struct hci_dev *hdev, void *data, int err) { struct conn_handle_t *conn_handle = data; hci_conn_put(conn_handle->conn); kfree(conn_handle); } bool hci_setup_sync(struct hci_conn *conn, __u16 handle) { int result; struct conn_handle_t *conn_handle; if (enhanced_sync_conn_capable(conn->hdev)) { conn_handle = kzalloc_obj(*conn_handle); if (!conn_handle) return false; conn_handle->conn = hci_conn_get(conn); conn_handle->handle = handle; result = hci_cmd_sync_queue(conn->hdev, hci_enhanced_setup_sync, conn_handle, hci_enhanced_setup_sync_destroy); if (result < 0) { hci_conn_put(conn); kfree(conn_handle); } return result == 0; } return hci_setup_sync_conn(conn, handle); } struct le_conn_update_data { struct hci_conn *conn; u16 min; u16 max; u16 latency; u16 to_multiplier; }; static int le_conn_update_sync(struct hci_dev *hdev, void *data) { struct le_conn_update_data *d = data; struct hci_conn *conn = d->conn; struct hci_conn_params *params; struct hci_cp_le_conn_update cp; u16 timeout; u8 store_hint; int err; /* Verify connection is still alive and read conn fields under * the same lock to prevent a concurrent disconnect from freeing * or reusing the connection while we build the HCI command. */ hci_dev_lock(hdev); if (!hci_conn_valid(hdev, conn)) { hci_dev_unlock(hdev); return -ECANCELED; } memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.conn_interval_min = cpu_to_le16(d->min); cp.conn_interval_max = cpu_to_le16(d->max); cp.conn_latency = cpu_to_le16(d->latency); cp.supervision_timeout = cpu_to_le16(d->to_multiplier); cp.min_ce_len = cpu_to_le16(0x0000); cp.max_ce_len = cpu_to_le16(0x0000); timeout = conn->conn_timeout; hci_dev_unlock(hdev); err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp, HCI_EV_LE_CONN_UPDATE_COMPLETE, timeout, NULL); if (err) return err; /* Update stored connection parameters after the controller has * confirmed the update via the LE Connection Update Complete event. */ hci_dev_lock(hdev); params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); if (params) { params->conn_min_interval = d->min; params->conn_max_interval = d->max; params->conn_latency = d->latency; params->supervision_timeout = d->to_multiplier; store_hint = 0x01; } else { store_hint = 0x00; } hci_dev_unlock(hdev); mgmt_new_conn_param(hdev, &conn->dst, conn->dst_type, store_hint, d->min, d->max, d->latency, d->to_multiplier); return 0; } static void le_conn_update_complete(struct hci_dev *hdev, void *data, int err) { struct le_conn_update_data *d = data; hci_conn_put(d->conn); kfree(d); } void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier) { struct le_conn_update_data *d; d = kzalloc_obj(*d); if (!d) return; hci_conn_get(conn); d->conn = conn; d->min = min; d->max = max; d->latency = latency; d->to_multiplier = to_multiplier; if (hci_cmd_sync_queue(conn->hdev, le_conn_update_sync, d, le_conn_update_complete) < 0) { hci_conn_put(conn); kfree(d); } } void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_start_enc cp; BT_DBG("hcon %p", conn); memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.rand = rand; cp.ediv = ediv; memcpy(cp.ltk, ltk, key_size); hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); } /* Device _must_ be locked */ void hci_sco_setup(struct hci_conn *conn, __u8 status) { struct hci_link *link; link = list_first_entry_or_null(&conn->link_list, struct hci_link, list); if (!link || !link->conn) return; BT_DBG("hcon %p", conn); if (!status) { if (lmp_esco_capable(conn->hdev)) hci_setup_sync(link->conn, conn->handle); else hci_add_sco(link->conn, conn->handle); } else { hci_connect_cfm(link->conn, status); hci_conn_del(link->conn); } } static void hci_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, disc_work.work); int refcnt = atomic_read(&conn->refcnt); BT_DBG("hcon %p state %s", conn, state_to_string(conn->state)); WARN_ON(refcnt < 0); /* FIXME: It was observed that in pairing failed scenario, refcnt * drops below 0. Probably this is because l2cap_conn_del calls * l2cap_chan_del for each channel, and inside l2cap_chan_del conn is * dropped. After that loop hci_chan_del is called which also drops * conn. For now make sure that ACL is alive if refcnt is higher then 0, * otherwise drop it. */ if (refcnt > 0) return; hci_abort_conn(conn, hci_proto_disconn_ind(conn)); } /* Enter sniff mode */ static void hci_conn_idle(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, idle_work.work); struct hci_dev *hdev = conn->hdev; BT_DBG("hcon %p mode %d", conn, conn->mode); if (!lmp_sniff_capable(hdev) || !lmp_sniff_capable(conn)) return; if (conn->mode != HCI_CM_ACTIVE || !(conn->link_policy & HCI_LP_SNIFF)) return; if (lmp_sniffsubr_capable(hdev) && lmp_sniffsubr_capable(conn)) { struct hci_cp_sniff_subrate cp; cp.handle = cpu_to_le16(conn->handle); cp.max_latency = cpu_to_le16(0); cp.min_remote_timeout = cpu_to_le16(0); cp.min_local_timeout = cpu_to_le16(0); hci_send_cmd(hdev, HCI_OP_SNIFF_SUBRATE, sizeof(cp), &cp); } if (!test_and_set_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags)) { struct hci_cp_sniff_mode cp; cp.handle = cpu_to_le16(conn->handle); cp.max_interval = cpu_to_le16(hdev->sniff_max_interval); cp.min_interval = cpu_to_le16(hdev->sniff_min_interval); cp.attempt = cpu_to_le16(4); cp.timeout = cpu_to_le16(1); hci_send_cmd(hdev, HCI_OP_SNIFF_MODE, sizeof(cp), &cp); } } static void hci_conn_auto_accept(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, auto_accept_work.work); hci_send_cmd(conn->hdev, HCI_OP_USER_CONFIRM_REPLY, sizeof(conn->dst), &conn->dst); } static void le_disable_advertising(struct hci_dev *hdev) { if (ext_adv_capable(hdev)) { struct hci_cp_le_set_ext_adv_enable cp; cp.enable = 0x00; cp.num_of_sets = 0x00; hci_send_cmd(hdev, HCI_OP_LE_SET_EXT_ADV_ENABLE, sizeof(cp), &cp); } else { u8 enable = 0x00; hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); } } static void le_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, le_conn_timeout.work); struct hci_dev *hdev = conn->hdev; BT_DBG(""); /* We could end up here due to having done directed advertising, * so clean up the state if necessary. This should however only * happen with broken hardware or if low duty cycle was used * (which doesn't have a timeout of its own). */ if (conn->role == HCI_ROLE_SLAVE) { /* Disable LE Advertising */ le_disable_advertising(hdev); hci_dev_lock(hdev); hci_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); hci_dev_unlock(hdev); return; } hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); } struct iso_list_data { union { u8 cig; u8 big; }; union { u8 cis; u8 bis; u16 sync_handle; }; int count; bool big_term; bool pa_sync_term; bool big_sync_term; }; static void bis_list(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Skip if not broadcast/ANY address */ if (bacmp(&conn->dst, BDADDR_ANY)) return; if (d->big != conn->iso_qos.bcast.big || d->bis == BT_ISO_QOS_BIS_UNSET || d->bis != conn->iso_qos.bcast.bis) return; d->count++; } static int terminate_big_sync(struct hci_dev *hdev, void *data) { struct iso_list_data *d = data; bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", d->big, d->bis); hci_disable_per_advertising_sync(hdev, d->bis); hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL); /* Only terminate BIG if it has been created */ if (!d->big_term) return 0; return hci_le_terminate_big_sync(hdev, d->big, HCI_ERROR_LOCAL_HOST_TERM); } static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err) { kfree(data); } static int hci_le_terminate_big(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", conn->iso_qos.bcast.big, conn->iso_qos.bcast.bis); d = kzalloc_obj(*d); if (!d) return -ENOMEM; d->big = conn->iso_qos.bcast.big; d->bis = conn->iso_qos.bcast.bis; d->big_term = test_and_clear_bit(HCI_CONN_BIG_CREATED, &conn->flags); ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d, terminate_big_destroy); if (ret) kfree(d); return ret; } static int big_terminate_sync(struct hci_dev *hdev, void *data) { struct iso_list_data *d = data; bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", d->big, d->sync_handle); if (d->big_sync_term) hci_le_big_terminate_sync(hdev, d->big); if (d->pa_sync_term) return hci_le_pa_terminate_sync(hdev, d->sync_handle); return 0; } static void find_bis(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Ignore if BIG doesn't match */ if (d->big != conn->iso_qos.bcast.big) return; d->count++; } static int hci_le_big_terminate(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; bt_dev_dbg(hdev, "hcon %p big 0x%2.2x sync_handle 0x%4.4x", conn, conn->iso_qos.bcast.big, conn->sync_handle); d = kzalloc_obj(*d); if (!d) return -ENOMEM; d->big = conn->iso_qos.bcast.big; d->sync_handle = conn->sync_handle; if (conn->type == PA_LINK && test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, PA_LINK, HCI_CONN_PA_SYNC, d); if (!d->count) d->pa_sync_term = true; d->count = 0; } if (test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, BIS_LINK, HCI_CONN_BIG_SYNC, d); if (!d->count) d->big_sync_term = true; } if (!d->pa_sync_term && !d->big_sync_term) { kfree(d); return 0; } ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); if (ret) kfree(d); return ret; } /* Cleanup BIS connection * * Detects if there any BIS left connected in a BIG * broadcaster: Remove advertising instance and terminate BIG. * broadcaster receiver: Terminate BIG sync and terminate PA sync. */ static void bis_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct hci_conn *bis; bt_dev_dbg(hdev, "conn %p", conn); if (conn->role == HCI_ROLE_MASTER) { if (!test_and_clear_bit(HCI_CONN_PER_ADV, &conn->flags)) return; /* Check if ISO connection is a BIS and terminate advertising * set and BIG if there are no other connections using it. */ bis = hci_conn_hash_lookup_big_state(hdev, conn->iso_qos.bcast.big, BT_CONNECTED, HCI_ROLE_MASTER); if (bis) return; bis = hci_conn_hash_lookup_big_state(hdev, conn->iso_qos.bcast.big, BT_CONNECT, HCI_ROLE_MASTER); if (bis) return; bis = hci_conn_hash_lookup_big_state(hdev, conn->iso_qos.bcast.big, BT_OPEN, HCI_ROLE_MASTER); if (bis) return; hci_le_terminate_big(hdev, conn); } else { hci_le_big_terminate(hdev, conn); } } static int remove_cig_sync(struct hci_dev *hdev, void *data) { u8 handle = PTR_UINT(data); return hci_le_remove_cig_sync(hdev, handle); } static int hci_le_remove_cig(struct hci_dev *hdev, u8 handle) { bt_dev_dbg(hdev, "handle 0x%2.2x", handle); return hci_cmd_sync_queue(hdev, remove_cig_sync, UINT_PTR(handle), NULL); } static void find_cis(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Ignore broadcast or if CIG don't match */ if (!bacmp(&conn->dst, BDADDR_ANY) || d->cig != conn->iso_qos.ucast.cig) return; d->count++; } /* Cleanup CIS connection: * * Detects if there any CIS left connected in a CIG and remove it. */ static void cis_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct iso_list_data d; if (conn->iso_qos.ucast.cig == BT_ISO_QOS_CIG_UNSET) return; memset(&d, 0, sizeof(d)); d.cig = conn->iso_qos.ucast.cig; /* Check if ISO connection is a CIS and remove CIG if there are * no other connections using it. */ hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_BOUND, &d); hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_CONNECT, &d); hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_CONNECTED, &d); if (d.count) return; hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig); } static int hci_conn_hash_alloc_unset(struct hci_dev *hdev) { return ida_alloc_range(&hdev->unset_handle_ida, HCI_CONN_HANDLE_MAX + 1, U16_MAX, GFP_ATOMIC); } static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role, u16 handle) { struct hci_conn *conn; struct smp_irk *irk = NULL; switch (type) { case ACL_LINK: if (!hdev->acl_mtu) return ERR_PTR(-ECONNREFUSED); break; case CIS_LINK: case BIS_LINK: case PA_LINK: if (!hdev->iso_mtu) return ERR_PTR(-ECONNREFUSED); irk = hci_get_irk(hdev, dst, dst_type); break; case LE_LINK: if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) return ERR_PTR(-ECONNREFUSED); if (!hdev->le_mtu && hdev->acl_mtu < HCI_MIN_LE_MTU) return ERR_PTR(-ECONNREFUSED); irk = hci_get_irk(hdev, dst, dst_type); break; case SCO_LINK: case ESCO_LINK: if (!hdev->sco_pkts) /* Controller does not support SCO or eSCO over HCI */ return ERR_PTR(-ECONNREFUSED); break; default: return ERR_PTR(-ECONNREFUSED); } bt_dev_dbg(hdev, "dst %pMR handle 0x%4.4x", dst, handle); conn = kzalloc_obj(*conn); if (!conn) return ERR_PTR(-ENOMEM); /* If and IRK exists use its identity address */ if (!irk) { bacpy(&conn->dst, dst); conn->dst_type = dst_type; } else { bacpy(&conn->dst, &irk->bdaddr); conn->dst_type = irk->addr_type; } bacpy(&conn->src, &hdev->bdaddr); conn->handle = handle; conn->hdev = hdev; conn->type = type; conn->role = role; conn->mode = HCI_CM_ACTIVE; conn->state = BT_OPEN; conn->auth_type = HCI_AT_GENERAL_BONDING; conn->io_capability = hdev->io_capability; conn->remote_auth = 0xff; conn->key_type = 0xff; conn->rssi = HCI_RSSI_INVALID; conn->tx_power = HCI_TX_POWER_INVALID; conn->max_tx_power = HCI_TX_POWER_INVALID; conn->sync_handle = HCI_SYNC_HANDLE_INVALID; conn->sid = HCI_SID_INVALID; set_bit(HCI_CONN_POWER_SAVE, &conn->flags); conn->disc_timeout = HCI_DISCONN_TIMEOUT; /* Set Default Authenticated payload timeout to 30s */ conn->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; if (conn->role == HCI_ROLE_MASTER) conn->out = true; switch (type) { case ACL_LINK: conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK; conn->link_policy = hdev->link_policy; conn->mtu = hdev->acl_mtu; break; case LE_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; /* Use the controller supported PHYS as default until the * remote features are resolved. */ conn->le_tx_def_phys = hdev->le_tx_def_phys; conn->le_rx_def_phys = hdev->le_tx_def_phys; break; case CIS_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); if (conn->role == HCI_ROLE_MASTER) conn->cleanup = cis_cleanup; conn->mtu = hdev->iso_mtu; break; case PA_LINK: case BIS_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); conn->cleanup = bis_cleanup; conn->mtu = hdev->iso_mtu; break; case SCO_LINK: if (lmp_esco_capable(hdev)) conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | (hdev->esco_type & EDR_ESCO_MASK); else conn->pkt_type = hdev->pkt_type & SCO_PTYPE_MASK; conn->mtu = hdev->sco_mtu; break; case ESCO_LINK: conn->pkt_type = hdev->esco_type & ~EDR_ESCO_MASK; conn->mtu = hdev->sco_mtu; break; } skb_queue_head_init(&conn->data_q); skb_queue_head_init(&conn->tx_q.queue); INIT_LIST_HEAD(&conn->chan_list); INIT_LIST_HEAD(&conn->link_list); INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout); INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); spin_lock_init(&conn->proto_lock); atomic_set(&conn->refcnt, 0); hci_dev_hold(hdev); hci_conn_hash_add(hdev, conn); /* The SCO and eSCO connections will only be notified when their * setup has been completed. This is different to ACL links which * can be notified right away. */ if (conn->type != SCO_LINK && conn->type != ESCO_LINK) { if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_ADD); } hci_conn_init_sysfs(conn); return conn; } struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role) { int handle; bt_dev_dbg(hdev, "dst %pMR", dst); handle = hci_conn_hash_alloc_unset(hdev); if (unlikely(handle < 0)) return ERR_PTR(-ECONNREFUSED); return __hci_conn_add(hdev, type, dst, dst_type, role, handle); } struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role, u16 handle) { if (handle > HCI_CONN_HANDLE_MAX) return ERR_PTR(-EINVAL); return __hci_conn_add(hdev, type, dst, dst_type, role, handle); } static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason) { if (!reason) reason = HCI_ERROR_REMOTE_USER_TERM; /* Due to race, SCO/ISO conn might be not established yet at this point, * and nothing else will clean it up. In other cases it is done via HCI * events. */ switch (conn->type) { case SCO_LINK: case ESCO_LINK: if (HCI_CONN_HANDLE_UNSET(conn->handle)) hci_conn_failed(conn, reason); break; case CIS_LINK: case BIS_LINK: case PA_LINK: if ((conn->state != BT_CONNECTED && !test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) || test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) hci_conn_failed(conn, reason); break; } } static void hci_conn_unlink(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "hcon %p", conn); if (!conn->parent) { struct hci_link *link, *t; list_for_each_entry_safe(link, t, &conn->link_list, list) { struct hci_conn *child = link->conn; hci_conn_unlink(child); /* If hdev is down it means * hci_dev_close_sync/hci_conn_hash_flush is in progress * and links don't need to be cleanup as all connections * would be cleanup. */ if (!test_bit(HCI_UP, &hdev->flags)) continue; hci_conn_cleanup_child(child, conn->abort_reason); } return; } if (!conn->link) return; list_del_rcu(&conn->link->list); synchronize_rcu(); hci_conn_drop(conn->parent); hci_conn_put(conn->parent); conn->parent = NULL; kfree(conn->link); conn->link = NULL; } void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); hci_conn_unlink(conn); disable_delayed_work_sync(&conn->disc_work); disable_delayed_work_sync(&conn->auto_accept_work); disable_delayed_work_sync(&conn->idle_work); /* Remove the connection from the list so unacked logic can detect when * a certain pool is not being utilized. */ hci_conn_hash_del(hdev, conn); /* Handle unacked frames: * * - In case there are no connection, or if restoring the buffers * considered in transist would overflow, restore all buffers to the * pool. * - Otherwise restore just the buffers considered in transit for the * hci_conn */ switch (conn->type) { case ACL_LINK: if (!hci_conn_num(hdev, ACL_LINK) || hdev->acl_cnt + conn->sent > hdev->acl_pkts) hdev->acl_cnt = hdev->acl_pkts; else hdev->acl_cnt += conn->sent; break; case LE_LINK: cancel_delayed_work(&conn->le_conn_timeout); if (hdev->le_pkts) { if (!hci_conn_num(hdev, LE_LINK) || hdev->le_cnt + conn->sent > hdev->le_pkts) hdev->le_cnt = hdev->le_pkts; else hdev->le_cnt += conn->sent; } else { if ((!hci_conn_num(hdev, LE_LINK) && !hci_conn_num(hdev, ACL_LINK)) || hdev->acl_cnt + conn->sent > hdev->acl_pkts) hdev->acl_cnt = hdev->acl_pkts; else hdev->acl_cnt += conn->sent; } break; case CIS_LINK: case BIS_LINK: case PA_LINK: if (!hci_iso_count(hdev) || hdev->iso_cnt + conn->sent > hdev->iso_pkts) hdev->iso_cnt = hdev->iso_pkts; else hdev->iso_cnt += conn->sent; break; } skb_queue_purge(&conn->data_q); skb_queue_purge(&conn->tx_q.queue); /* Remove the connection from the list and cleanup its remaining * state. This is a separate function since for some cases like * BT_CONNECT_SCAN we *only* want the cleanup part without the * rest of hci_conn_del. */ hci_conn_cleanup(conn); /* Dequeue callbacks using connection pointer as data */ hci_cmd_sync_dequeue(hdev, NULL, conn, NULL); } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) { int use_src = bacmp(src, BDADDR_ANY); struct hci_dev *hdev = NULL, *d; BT_DBG("%pMR -> %pMR", src, dst); read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { if (!test_bit(HCI_UP, &d->flags) || hci_dev_test_flag(d, HCI_USER_CHANNEL)) continue; /* Simple routing: * No source address - find interface with bdaddr != dst * Source address - find interface with bdaddr == src */ if (use_src) { bdaddr_t id_addr; u8 id_addr_type; if (src_type == BDADDR_BREDR) { if (!lmp_bredr_capable(d)) continue; bacpy(&id_addr, &d->bdaddr); id_addr_type = BDADDR_BREDR; } else { if (!lmp_le_capable(d)) continue; hci_copy_identity_address(d, &id_addr, &id_addr_type); /* Convert from HCI to three-value type */ if (id_addr_type == ADDR_LE_DEV_PUBLIC) id_addr_type = BDADDR_LE_PUBLIC; else id_addr_type = BDADDR_LE_RANDOM; } if (!bacmp(&id_addr, src) && id_addr_type == src_type) { hdev = d; break; } } else { if (bacmp(&d->bdaddr, dst)) { hdev = d; break; } } } if (hdev) hdev = hci_dev_hold(hdev); read_unlock(&hci_dev_list_lock); return hdev; } EXPORT_SYMBOL(hci_get_route); /* This function requires the caller holds hdev->lock */ static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. */ if (conn->role == HCI_ROLE_SLAVE) hci_enable_advertising(hdev); } /* This function requires the caller holds hdev->lock */ void hci_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "status 0x%2.2x", status); switch (conn->type) { case LE_LINK: hci_le_conn_failed(conn, status); break; case ACL_LINK: mgmt_connect_failed(hdev, conn, status); break; } /* In case of BIG/PA sync failed, clear conn flags so that * the conns will be correctly cleaned up by ISO layer */ test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags); test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags); conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); } /* This function requires the caller holds hdev->lock */ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "hcon %p handle 0x%4.4x", conn, handle); if (conn->handle == handle) return 0; if (handle > HCI_CONN_HANDLE_MAX) { bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, HCI_CONN_HANDLE_MAX); return HCI_ERROR_INVALID_PARAMETERS; } /* If abort_reason has been sent it means the connection is being * aborted and the handle shall not be changed. */ if (conn->abort_reason) return conn->abort_reason; if (HCI_CONN_HANDLE_UNSET(conn->handle)) ida_free(&hdev->unset_handle_ida, conn->handle); conn->handle = handle; return 0; } struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct smp_irk *irk; int err; /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } /* Since the controller supports only one LE connection attempt at a * time, we return -EBUSY if there is any connection attempt running. */ if (hci_lookup_le_connect(hdev)) return ERR_PTR(-EBUSY); /* If there's already a connection object but it's not in * scanning state it means it must already be established, in * which case we can't do anything else except report a failure * to connect. */ conn = hci_conn_hash_lookup_le(hdev, dst, dst_type); if (conn && !test_bit(HCI_CONN_SCANNING, &conn->flags)) { return ERR_PTR(-EBUSY); } /* Check if the destination address has been resolved by the controller * since if it did then the identity address shall be used. */ if (!dst_resolved) { /* When given an identity address with existing identity * resolving key, the connection needs to be established * to a resolvable random address. * * Storing the resolvable random address is required here * to handle connection failures. The address will later * be resolved back into the original identity address * from the connect request. */ irk = hci_find_irk_by_addr(hdev, dst, dst_type); if (irk && bacmp(&irk->rpa, BDADDR_ANY)) { dst = &irk->rpa; dst_type = ADDR_LE_DEV_RANDOM; } } if (conn) { bacpy(&conn->dst, dst); } else { conn = hci_conn_add_unset(hdev, LE_LINK, dst, dst_type, role); if (IS_ERR(conn)) return conn; hci_conn_hold(conn); conn->pending_sec_level = sec_level; } conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; conn->le_adv_phy = phy; conn->le_adv_sec_phy = sec_phy; err = hci_connect_le_sync(hdev, conn); if (err) { hci_conn_del(conn); return ERR_PTR(err); } return conn; } static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type) { struct hci_conn *conn; conn = hci_conn_hash_lookup_le(hdev, addr, type); if (!conn) return false; if (conn->state != BT_CONNECTED) return false; return true; } /* This function requires the caller holds hdev->lock */ static int hci_explicit_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; if (is_connected(hdev, addr, addr_type)) return -EISCONN; params = hci_conn_params_lookup(hdev, addr, addr_type); if (!params) { params = hci_conn_params_add(hdev, addr, addr_type); if (!params) return -ENOMEM; /* If we created new params, mark them to be deleted in * hci_connect_le_scan_cleanup. It's different case than * existing disabled params, those will stay after cleanup. */ params->auto_connect = HCI_AUTO_CONN_EXPLICIT; } /* We're trying to connect, so make sure params are at pend_le_conns */ if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { hci_pend_le_list_del_init(params); hci_pend_le_list_add(params, &hdev->pend_le_conns); } params->explicit_connect = true; BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type, params->auto_connect); return 0; } static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos) { struct hci_conn *conn; u8 big; /* Allocate a BIG if not set */ if (qos->bcast.big == BT_ISO_QOS_BIG_UNSET) { for (big = 0x00; big < 0xef; big++) { conn = hci_conn_hash_lookup_big(hdev, big); if (!conn) break; } if (big == 0xef) return -EADDRNOTAVAIL; /* Update BIG */ qos->bcast.big = big; } return 0; } static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) { struct hci_conn *conn; u8 bis; /* Allocate BIS if not set */ if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) { if (qos->bcast.big != BT_ISO_QOS_BIG_UNSET) { conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); if (conn) { /* If the BIG handle is already matched to an advertising * handle, do not allocate a new one. */ qos->bcast.bis = conn->iso_qos.bcast.bis; return 0; } } /* Find an unused adv set to advertise BIS, skip instance 0x00 * since it is reserved as general purpose set. */ for (bis = 0x01; bis < hdev->le_num_of_adv_sets; bis++) { conn = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, bis); if (!conn) break; } if (bis == hdev->le_num_of_adv_sets) return -EADDRNOTAVAIL; /* Update BIS */ qos->bcast.bis = bis; } return 0; } /* This function requires the caller holds hdev->lock */ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid, struct bt_iso_qos *qos, __u8 base_len, __u8 *base, u16 timeout) { struct hci_conn *conn; int err; /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } err = qos_set_big(hdev, qos); if (err) return ERR_PTR(err); err = qos_set_bis(hdev, qos); if (err) return ERR_PTR(err); /* Check if the LE Create BIG command has already been sent */ conn = hci_conn_hash_lookup_per_adv_bis(hdev, dst, qos->bcast.big, qos->bcast.big); if (conn) return ERR_PTR(-EADDRINUSE); /* Check BIS settings against other bound BISes, since all * BISes in a BIG must have the same value for all parameters */ conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) || base_len != conn->le_per_adv_data_len || memcmp(conn->le_per_adv_data, base, base_len))) return ERR_PTR(-EADDRINUSE); conn = hci_conn_add_unset(hdev, BIS_LINK, dst, 0, HCI_ROLE_MASTER); if (IS_ERR(conn)) return conn; conn->state = BT_CONNECT; conn->sid = sid; conn->conn_timeout = timeout; hci_conn_hold(conn); return conn; } /* This function requires the caller holds hdev->lock */ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, enum conn_reasons conn_reason) { struct hci_conn *conn; /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } /* Some devices send ATT messages as soon as the physical link is * established. To be able to handle these ATT messages, the user- * space first establishes the connection and then starts the pairing * process. * * So if a hci_conn object already exists for the following connection * attempt, we simply update pending_sec_level and auth_type fields * and return the object found. */ conn = hci_conn_hash_lookup_le(hdev, dst, dst_type); if (conn) { if (conn->pending_sec_level < sec_level) conn->pending_sec_level = sec_level; goto done; } BT_DBG("requesting refresh of dst_addr"); conn = hci_conn_add_unset(hdev, LE_LINK, dst, dst_type, HCI_ROLE_MASTER); if (IS_ERR(conn)) return conn; if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) { hci_conn_del(conn); return ERR_PTR(-EBUSY); } conn->state = BT_CONNECT; set_bit(HCI_CONN_SCANNING, &conn->flags); conn->sec_level = BT_SECURITY_LOW; conn->pending_sec_level = sec_level; conn->conn_timeout = conn_timeout; conn->conn_reason = conn_reason; hci_update_passive_scan(hdev); done: hci_conn_hold(conn); return conn; } struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason, u16 timeout) { struct hci_conn *acl; if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { if (lmp_bredr_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } /* Reject outgoing connection to device with same BD ADDR against * CVE-2020-26555 */ if (!bacmp(&hdev->bdaddr, dst)) { bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", dst); return ERR_PTR(-ECONNREFUSED); } acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { acl = hci_conn_add_unset(hdev, ACL_LINK, dst, 0, HCI_ROLE_MASTER); if (IS_ERR(acl)) return acl; } hci_conn_hold(acl); acl->conn_reason = conn_reason; if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { int err; acl->sec_level = BT_SECURITY_LOW; acl->pending_sec_level = sec_level; acl->auth_type = auth_type; acl->conn_timeout = timeout; err = hci_connect_acl_sync(hdev, acl); if (err) { hci_conn_del(acl); return ERR_PTR(err); } } return acl; } static struct hci_link *hci_conn_link(struct hci_conn *parent, struct hci_conn *conn) { struct hci_dev *hdev = parent->hdev; struct hci_link *link; bt_dev_dbg(hdev, "parent %p hcon %p", parent, conn); if (conn->link) return conn->link; if (conn->parent) return NULL; link = kzalloc_obj(*link); if (!link) return NULL; link->conn = hci_conn_hold(conn); conn->link = link; conn->parent = hci_conn_get(parent); /* Use list_add_tail_rcu append to the list */ list_add_tail_rcu(&link->list, &parent->link_list); return link; } struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec, u16 timeout) { struct hci_conn *acl; struct hci_conn *sco; struct hci_link *link; acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING, CONN_REASON_SCO_CONNECT, timeout); if (IS_ERR(acl)) return acl; sco = hci_conn_hash_lookup_ba(hdev, type, dst); if (!sco) { sco = hci_conn_add_unset(hdev, type, dst, 0, HCI_ROLE_MASTER); if (IS_ERR(sco)) { hci_conn_drop(acl); return sco; } } link = hci_conn_link(acl, sco); if (!link) { hci_conn_drop(acl); hci_conn_drop(sco); return ERR_PTR(-ENOLINK); } sco->setting = setting; sco->codec = *codec; if (acl->state == BT_CONNECTED && (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { set_bit(HCI_CONN_POWER_SAVE, &acl->flags); hci_conn_enter_active_mode(acl, BT_POWER_FORCE_ACTIVE_ON); if (test_bit(HCI_CONN_MODE_CHANGE_PEND, &acl->flags)) { /* defer SCO setup until mode change completed */ set_bit(HCI_CONN_SCO_SETUP_PEND, &acl->flags); return sco; } hci_sco_setup(acl, 0x00); } return sco; } static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_create_big cp; struct iso_list_data data; memset(&cp, 0, sizeof(cp)); data.big = qos->bcast.big; data.bis = qos->bcast.bis; data.count = 0; /* Create a BIS for each bound connection */ hci_conn_hash_list_state(hdev, bis_list, BIS_LINK, BT_BOUND, &data); cp.handle = qos->bcast.big; cp.adv_handle = qos->bcast.bis; cp.num_bis = data.count; hci_cpu_to_le24(qos->bcast.out.interval, cp.bis.sdu_interval); cp.bis.sdu = cpu_to_le16(qos->bcast.out.sdu); cp.bis.latency = cpu_to_le16(qos->bcast.out.latency); cp.bis.rtn = qos->bcast.out.rtn; cp.bis.phy = qos->bcast.out.phys; cp.bis.packing = qos->bcast.packing; cp.bis.framing = qos->bcast.framing; cp.bis.encryption = qos->bcast.encryption; memcpy(cp.bis.bcode, qos->bcast.bcode, sizeof(cp.bis.bcode)); return hci_send_cmd(hdev, HCI_OP_LE_CREATE_BIG, sizeof(cp), &cp); } static int set_cig_params_sync(struct hci_dev *hdev, void *data) { DEFINE_FLEX(struct hci_cp_le_set_cig_params, pdu, cis, num_cis, 0x1f); u8 cig_id = PTR_UINT(data); struct hci_conn *conn; struct bt_iso_qos *qos; u8 aux_num_cis = 0; u8 cis_id; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_cig(hdev, cig_id); if (!conn) { hci_dev_unlock(hdev); return 0; } qos = &conn->iso_qos; pdu->cig_id = cig_id; hci_cpu_to_le24(qos->ucast.out.interval, pdu->c_interval); hci_cpu_to_le24(qos->ucast.in.interval, pdu->p_interval); pdu->sca = qos->ucast.sca; pdu->packing = qos->ucast.packing; pdu->framing = qos->ucast.framing; pdu->c_latency = cpu_to_le16(qos->ucast.out.latency); pdu->p_latency = cpu_to_le16(qos->ucast.in.latency); /* Reprogram all CIS(s) with the same CIG, valid range are: * num_cis: 0x00 to 0x1F * cis_id: 0x00 to 0xEF */ for (cis_id = 0x00; cis_id < 0xf0 && aux_num_cis < pdu->num_cis; cis_id++) { struct hci_cis_params *cis; conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, cig_id, cis_id); if (!conn) continue; qos = &conn->iso_qos; cis = &pdu->cis[aux_num_cis++]; cis->cis_id = cis_id; cis->c_sdu = cpu_to_le16(conn->iso_qos.ucast.out.sdu); cis->p_sdu = cpu_to_le16(conn->iso_qos.ucast.in.sdu); cis->c_phys = qos->ucast.out.phys ? qos->ucast.out.phys : qos->ucast.in.phys; cis->p_phys = qos->ucast.in.phys ? qos->ucast.in.phys : qos->ucast.out.phys; cis->c_rtn = qos->ucast.out.rtn; cis->p_rtn = qos->ucast.in.rtn; } pdu->num_cis = aux_num_cis; hci_dev_unlock(hdev); if (!pdu->num_cis) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, struct_size(pdu, cis, pdu->num_cis), pdu, HCI_CMD_TIMEOUT); } static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct iso_list_data data; memset(&data, 0, sizeof(data)); /* Allocate first still reconfigurable CIG if not set */ if (qos->ucast.cig == BT_ISO_QOS_CIG_UNSET) { for (data.cig = 0x00; data.cig < 0xf0; data.cig++) { data.count = 0; hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_CONNECT, &data); if (data.count) continue; hci_conn_hash_list_state(hdev, find_cis, CIS_LINK, BT_CONNECTED, &data); if (!data.count) break; } if (data.cig == 0xf0) return false; /* Update CIG */ qos->ucast.cig = data.cig; } if (qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) { if (hci_conn_hash_lookup_cis(hdev, NULL, 0, qos->ucast.cig, qos->ucast.cis)) return false; goto done; } /* Allocate first available CIS if not set */ for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0xf0; data.cis++) { if (!hci_conn_hash_lookup_cis(hdev, NULL, 0, data.cig, data.cis)) { /* Update CIS */ qos->ucast.cis = data.cis; break; } } if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET) return false; done: conn->iso_qos = *qos; if (hci_cmd_sync_queue(hdev, set_cig_params_sync, UINT_PTR(qos->ucast.cig), NULL) < 0) return false; return true; } struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, u16 timeout) { struct hci_conn *cis; cis = hci_conn_hash_lookup_cis(hdev, dst, dst_type, qos->ucast.cig, qos->ucast.cis); if (!cis) { cis = hci_conn_add_unset(hdev, CIS_LINK, dst, dst_type, HCI_ROLE_MASTER); if (IS_ERR(cis)) return cis; cis->cleanup = cis_cleanup; cis->dst_type = dst_type; cis->iso_qos.ucast.cig = BT_ISO_QOS_CIG_UNSET; cis->iso_qos.ucast.cis = BT_ISO_QOS_CIS_UNSET; cis->conn_timeout = timeout; } if (cis->state == BT_CONNECTED) return cis; /* Check if CIS has been set and the settings matches */ if (cis->state == BT_BOUND && !memcmp(&cis->iso_qos, qos, sizeof(*qos))) return cis; /* Update LINK PHYs according to QoS preference */ cis->le_tx_phy = qos->ucast.out.phys; cis->le_rx_phy = qos->ucast.in.phys; /* If output interval is not set use the input interval as it cannot be * 0x000000. */ if (!qos->ucast.out.interval) qos->ucast.out.interval = qos->ucast.in.interval; /* If input interval is not set use the output interval as it cannot be * 0x000000. */ if (!qos->ucast.in.interval) qos->ucast.in.interval = qos->ucast.out.interval; /* If output latency is not set use the input latency as it cannot be * 0x0000. */ if (!qos->ucast.out.latency) qos->ucast.out.latency = qos->ucast.in.latency; /* If input latency is not set use the output latency as it cannot be * 0x0000. */ if (!qos->ucast.in.latency) qos->ucast.in.latency = qos->ucast.out.latency; if (!hci_le_set_cig_params(cis, qos)) { hci_conn_drop(cis); return ERR_PTR(-EINVAL); } hci_conn_hold(cis); cis->state = BT_BOUND; return cis; } bool hci_iso_setup_path(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_setup_iso_path cmd; memset(&cmd, 0, sizeof(cmd)); if (conn->iso_qos.ucast.out.sdu) { cmd.handle = cpu_to_le16(conn->handle); cmd.direction = 0x00; /* Input (Host to Controller) */ cmd.path = 0x00; /* HCI path if enabled */ cmd.codec = 0x03; /* Transparent Data */ if (hci_send_cmd(hdev, HCI_OP_LE_SETUP_ISO_PATH, sizeof(cmd), &cmd) < 0) return false; } if (conn->iso_qos.ucast.in.sdu) { cmd.handle = cpu_to_le16(conn->handle); cmd.direction = 0x01; /* Output (Controller to Host) */ cmd.path = 0x00; /* HCI path if enabled */ cmd.codec = 0x03; /* Transparent Data */ if (hci_send_cmd(hdev, HCI_OP_LE_SETUP_ISO_PATH, sizeof(cmd), &cmd) < 0) return false; } return true; } int hci_conn_check_create_cis(struct hci_conn *conn) { if (conn->type != CIS_LINK) return -EINVAL; if (!conn->parent || conn->parent->state != BT_CONNECTED || conn->state != BT_CONNECT || HCI_CONN_HANDLE_UNSET(conn->handle)) return 1; return 0; } static int hci_create_cis_sync(struct hci_dev *hdev, void *data) { return hci_le_create_cis_sync(hdev); } int hci_le_create_cis_pending(struct hci_dev *hdev) { struct hci_conn *conn; bool pending = false; rcu_read_lock(); list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) { rcu_read_unlock(); return -EBUSY; } if (!hci_conn_check_create_cis(conn)) pending = true; } rcu_read_unlock(); if (!pending) return 0; /* Queue Create CIS */ return hci_cmd_sync_queue(hdev, hci_create_cis_sync, NULL, NULL); } static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, struct bt_iso_io_qos *qos, __u8 phys) { /* Only set MTU if PHY is enabled */ if (!qos->sdu && qos->phys) qos->sdu = conn->mtu; /* Use the same PHY as ACL if set to any */ if (qos->phys == BT_ISO_PHY_ANY) qos->phys = phys; /* Use LE ACL connection interval if not set */ if (!qos->interval) /* ACL interval unit in 1.25 ms to us */ qos->interval = conn->le_conn_interval * 1250; /* Use LE ACL connection latency if not set */ if (!qos->latency) qos->latency = conn->le_conn_latency; } static int create_big_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn = data; struct bt_iso_qos *qos = &conn->iso_qos; u16 interval, sync_interval = 0; u32 flags = 0; int err; if (!hci_conn_valid(hdev, conn)) return -ECANCELED; if (qos->bcast.out.phys == BIT(1)) flags |= MGMT_ADV_FLAG_SEC_2M; /* Align intervals */ interval = (qos->bcast.out.interval / 1250) * qos->bcast.sync_factor; if (qos->bcast.bis) sync_interval = interval * 4; err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->sid, conn->le_per_adv_data_len, conn->le_per_adv_data, flags, interval, interval, sync_interval); if (err) return err; return hci_le_create_big(conn, &conn->iso_qos); } struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos) { struct hci_conn *conn; bt_dev_dbg(hdev, "dst %pMR type %d sid %d", dst, dst_type, sid); conn = hci_conn_add_unset(hdev, PA_LINK, dst, dst_type, HCI_ROLE_SLAVE); if (IS_ERR(conn)) return conn; conn->iso_qos = *qos; conn->sid = sid; conn->state = BT_LISTEN; conn->conn_timeout = msecs_to_jiffies(qos->bcast.sync_timeout * 10); hci_conn_hold(conn); hci_connect_pa_sync(hdev, conn); return conn; } int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]) { int err; if (num_bis < 0x01 || num_bis > ISO_MAX_NUM_BIS) return -EINVAL; err = qos_set_big(hdev, qos); if (err) return err; if (hcon) { /* Update hcon QoS */ hcon->iso_qos = *qos; hcon->num_bis = num_bis; memcpy(hcon->bis, bis, num_bis); hcon->conn_timeout = msecs_to_jiffies(qos->bcast.timeout * 10); } return hci_connect_big_sync(hdev, hcon); } static void create_big_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; bt_dev_dbg(hdev, "conn %p", conn); if (err == -ECANCELED) goto done; hci_dev_lock(hdev); if (!hci_conn_valid(hdev, conn)) goto unlock; if (err) { bt_dev_err(hdev, "Unable to create BIG: %d", err); hci_connect_cfm(conn, err); hci_conn_del(conn); } unlock: hci_dev_unlock(hdev); done: hci_conn_put(conn); } struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid, struct bt_iso_qos *qos, __u8 base_len, __u8 *base, u16 timeout) { struct hci_conn *conn; struct hci_conn *parent; __u8 eir[HCI_MAX_PER_AD_LENGTH]; struct hci_link *link; /* Look for any BIS that is open for rebinding */ conn = hci_conn_hash_lookup_big_state(hdev, qos->bcast.big, BT_OPEN, HCI_ROLE_MASTER); if (conn) { memcpy(qos, &conn->iso_qos, sizeof(*qos)); conn->state = BT_CONNECTED; return conn; } if (base_len && base) base_len = eir_append_service_data(eir, 0, 0x1851, base, base_len); /* We need hci_conn object using the BDADDR_ANY as dst */ conn = hci_add_bis(hdev, dst, sid, qos, base_len, eir, timeout); if (IS_ERR(conn)) return conn; /* Update LINK PHYs according to QoS preference */ conn->le_tx_def_phys = qos->bcast.out.phys; /* Add Basic Announcement into Peridic Adv Data if BASE is set */ if (base_len && base) { memcpy(conn->le_per_adv_data, eir, sizeof(eir)); conn->le_per_adv_data_len = base_len; } hci_iso_qos_setup(hdev, conn, &qos->bcast.out, conn->le_tx_def_phys ? conn->le_tx_def_phys : hdev->le_tx_def_phys); conn->iso_qos = *qos; conn->state = BT_BOUND; /* Link BISes together */ parent = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); if (parent && parent != conn) { link = hci_conn_link(parent, conn); hci_conn_drop(conn); if (!link) return ERR_PTR(-ENOLINK); } return conn; } int hci_past_bis(struct hci_conn *conn, bdaddr_t *dst, __u8 dst_type) { struct hci_conn *le; /* Lookup existing LE connection to rebind to */ le = hci_conn_hash_lookup_le(conn->hdev, dst, dst_type); if (!le) return -EINVAL; return hci_past_sync(conn, le); } static void bis_mark_per_adv(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Skip if not broadcast/ANY address */ if (bacmp(&conn->dst, BDADDR_ANY)) return; if (d->big != conn->iso_qos.bcast.big || d->bis == BT_ISO_QOS_BIS_UNSET || d->bis != conn->iso_qos.bcast.bis) return; set_bit(HCI_CONN_PER_ADV, &conn->flags); } struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos, __u8 base_len, __u8 *base, u16 timeout) { struct hci_conn *conn; int err; struct iso_list_data data; conn = hci_bind_bis(hdev, dst, sid, qos, base_len, base, timeout); if (IS_ERR(conn)) return conn; if (conn->state == BT_CONNECTED) return conn; /* Check if SID needs to be allocated then search for the first * available. */ if (conn->sid == HCI_SID_INVALID) { u8 sid; for (sid = 0; sid <= 0x0f; sid++) { if (!hci_find_adv_sid(hdev, sid)) { conn->sid = sid; break; } } } data.big = qos->bcast.big; data.bis = qos->bcast.bis; /* Set HCI_CONN_PER_ADV for all bound connections, to mark that * the start periodic advertising and create BIG commands have * been queued */ hci_conn_hash_list_state(hdev, bis_mark_per_adv, BIS_LINK, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ err = hci_cmd_sync_queue(hdev, create_big_sync, hci_conn_get(conn), create_big_complete); if (err < 0) { hci_conn_drop(conn); hci_conn_put(conn); return ERR_PTR(err); } return conn; } struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, u16 timeout) { struct hci_conn *le; struct hci_conn *cis; struct hci_link *link; if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, HCI_ROLE_SLAVE, 0, 0); else le = hci_connect_le_scan(hdev, dst, dst_type, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, CONN_REASON_ISO_CONNECT); if (IS_ERR(le)) return le; hci_iso_qos_setup(hdev, le, &qos->ucast.out, le->le_tx_def_phys ? le->le_tx_def_phys : hdev->le_tx_def_phys); hci_iso_qos_setup(hdev, le, &qos->ucast.in, le->le_rx_def_phys ? le->le_rx_def_phys : hdev->le_rx_def_phys); cis = hci_bind_cis(hdev, dst, dst_type, qos, timeout); if (IS_ERR(cis)) { hci_conn_drop(le); return cis; } link = hci_conn_link(le, cis); hci_conn_drop(cis); if (!link) { hci_conn_drop(le); return ERR_PTR(-ENOLINK); } cis->state = BT_CONNECT; hci_le_create_cis_pending(hdev); return cis; } /* Check link security requirement */ int hci_conn_check_link_mode(struct hci_conn *conn) { BT_DBG("hcon %p", conn); /* In Secure Connections Only mode, it is required that Secure * Connections is used and the link is encrypted with AES-CCM * using a P-256 authenticated combination key. */ if (hci_dev_test_flag(conn->hdev, HCI_SC_ONLY)) { if (!hci_conn_sc_enabled(conn) || !test_bit(HCI_CONN_AES_CCM, &conn->flags) || conn->key_type != HCI_LK_AUTH_COMBINATION_P256) return 0; } /* AES encryption is required for Level 4: * * BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 3, Part C * page 1319: * * 128-bit equivalent strength for link and encryption keys * required using FIPS approved algorithms (E0 not allowed, * SAFER+ not allowed, and P-192 not allowed; encryption key * not shortened) */ if (conn->sec_level == BT_SECURITY_FIPS && !test_bit(HCI_CONN_AES_CCM, &conn->flags)) { bt_dev_err(conn->hdev, "Invalid security: Missing AES-CCM usage"); return 0; } if (hci_conn_ssp_enabled(conn) && !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; return 1; } /* Authenticate remote device */ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) { BT_DBG("hcon %p", conn); if (conn->pending_sec_level > sec_level) sec_level = conn->pending_sec_level; if (sec_level > conn->sec_level) conn->pending_sec_level = sec_level; else if (test_bit(HCI_CONN_AUTH, &conn->flags)) return 1; /* Make sure we preserve an existing MITM requirement*/ auth_type |= (conn->auth_type & 0x01); conn->auth_type = auth_type; if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); /* Set the ENCRYPT_PEND to trigger encryption after * authentication. */ if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } return 0; } /* Encrypt the link */ static void hci_conn_encrypt(struct hci_conn *conn) { BT_DBG("hcon %p", conn); if (!test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) { struct hci_cp_set_conn_encrypt cp; cp.handle = cpu_to_le16(conn->handle); cp.encrypt = 0x01; hci_send_cmd(conn->hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), &cp); } } /* Enable security */ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, bool initiator) { BT_DBG("hcon %p", conn); if (conn->type == LE_LINK) return smp_conn_security(conn, sec_level); /* For sdp we don't need the link key. */ if (sec_level == BT_SECURITY_SDP) return 1; /* For non 2.1 devices and low security level we don't need the link key. */ if (sec_level == BT_SECURITY_LOW && !hci_conn_ssp_enabled(conn)) return 1; /* For other security levels we need the link key. */ if (!test_bit(HCI_CONN_AUTH, &conn->flags)) goto auth; switch (conn->key_type) { case HCI_LK_AUTH_COMBINATION_P256: /* An authenticated FIPS approved combination key has * sufficient security for security level 4 or lower. */ if (sec_level <= BT_SECURITY_FIPS) goto encrypt; break; case HCI_LK_AUTH_COMBINATION_P192: /* An authenticated combination key has sufficient security for * security level 3 or lower. */ if (sec_level <= BT_SECURITY_HIGH) goto encrypt; break; case HCI_LK_UNAUTH_COMBINATION_P192: case HCI_LK_UNAUTH_COMBINATION_P256: /* An unauthenticated combination key has sufficient security * for security level 2 or lower. */ if (sec_level <= BT_SECURITY_MEDIUM) goto encrypt; break; case HCI_LK_COMBINATION: /* A combination key has always sufficient security for the * security levels 2 or lower. High security level requires the * combination key is generated using maximum PIN code length * (16). For pre 2.1 units. */ if (sec_level <= BT_SECURITY_MEDIUM || conn->pin_length == 16) goto encrypt; break; default: break; } auth: if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return 0; if (initiator) set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); if (!hci_conn_auth(conn, sec_level, auth_type)) return 0; encrypt: if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) { /* Ensure that the encryption key size has been read, * otherwise stall the upper layer responses. */ if (!conn->enc_key_size) return 0; /* Nothing else needed, all requirements are met */ return 1; } hci_conn_encrypt(conn); return 0; } EXPORT_SYMBOL(hci_conn_security); /* Check secure link requirement */ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level) { BT_DBG("hcon %p", conn); /* Accept if non-secure or higher security level is required */ if (sec_level != BT_SECURITY_HIGH && sec_level != BT_SECURITY_FIPS) return 1; /* Accept if secure or higher security level is already present */ if (conn->sec_level == BT_SECURITY_HIGH || conn->sec_level == BT_SECURITY_FIPS) return 1; /* Reject not secure link */ return 0; } EXPORT_SYMBOL(hci_conn_check_secure); /* Switch role */ int hci_conn_switch_role(struct hci_conn *conn, __u8 role) { BT_DBG("hcon %p", conn); if (role == conn->role) return 1; if (!test_and_set_bit(HCI_CONN_RSWITCH_PEND, &conn->flags)) { struct hci_cp_switch_role cp; bacpy(&cp.bdaddr, &conn->dst); cp.role = role; hci_send_cmd(conn->hdev, HCI_OP_SWITCH_ROLE, sizeof(cp), &cp); } return 0; } EXPORT_SYMBOL(hci_conn_switch_role); /* Enter active mode */ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) { struct hci_dev *hdev = conn->hdev; BT_DBG("hcon %p mode %d", conn, conn->mode); if (conn->mode != HCI_CM_SNIFF) goto timer; if (!test_bit(HCI_CONN_POWER_SAVE, &conn->flags) && !force_active) goto timer; if (!test_and_set_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags)) { struct hci_cp_exit_sniff_mode cp; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_EXIT_SNIFF_MODE, sizeof(cp), &cp); } timer: if (hdev->idle_timeout > 0) mod_delayed_work(hdev->workqueue, &conn->idle_work, msecs_to_jiffies(hdev->idle_timeout)); } /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { struct list_head *head = &hdev->conn_hash.list; struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); /* We should not traverse the list here, because hci_conn_del * can remove extra links, which may cause the list traversal * to hit items that have already been released. */ while ((conn = list_first_entry_or_null(head, struct hci_conn, list)) != NULL) { conn->state = BT_CLOSED; hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); hci_conn_del(conn); } } static u32 get_link_mode(struct hci_conn *conn) { u32 link_mode = 0; if (conn->role == HCI_ROLE_MASTER) link_mode |= HCI_LM_MASTER; if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) link_mode |= HCI_LM_ENCRYPT; if (test_bit(HCI_CONN_AUTH, &conn->flags)) link_mode |= HCI_LM_AUTH; if (test_bit(HCI_CONN_SECURE, &conn->flags)) link_mode |= HCI_LM_SECURE; if (test_bit(HCI_CONN_FIPS, &conn->flags)) link_mode |= HCI_LM_FIPS; return link_mode; } int hci_get_conn_list(void __user *arg) { struct hci_conn *c; struct hci_conn_list_req req, *cl; struct hci_conn_info *ci; struct hci_dev *hdev; int n = 0, size, err; if (copy_from_user(&req, arg, sizeof(req))) return -EFAULT; if (!req.conn_num || req.conn_num > (PAGE_SIZE * 2) / sizeof(*ci)) return -EINVAL; size = sizeof(req) + req.conn_num * sizeof(*ci); cl = kmalloc(size, GFP_KERNEL); if (!cl) return -ENOMEM; hdev = hci_dev_get(req.dev_id); if (!hdev) { kfree(cl); return -ENODEV; } ci = cl->conn_info; hci_dev_lock(hdev); list_for_each_entry(c, &hdev->conn_hash.list, list) { bacpy(&(ci + n)->bdaddr, &c->dst); (ci + n)->handle = c->handle; (ci + n)->type = c->type; (ci + n)->out = c->out; (ci + n)->state = c->state; (ci + n)->link_mode = get_link_mode(c); if (++n >= req.conn_num) break; } hci_dev_unlock(hdev); cl->dev_id = hdev->id; cl->conn_num = n; size = sizeof(req) + n * sizeof(*ci); hci_dev_put(hdev); err = copy_to_user(arg, cl, size); kfree(cl); return err ? -EFAULT : 0; } int hci_get_conn_info(struct hci_dev *hdev, void __user *arg) { struct hci_conn_info_req req; struct hci_conn_info ci; struct hci_conn *conn; char __user *ptr = arg + sizeof(req); if (copy_from_user(&req, arg, sizeof(req))) return -EFAULT; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, req.type, &req.bdaddr); if (conn) { bacpy(&ci.bdaddr, &conn->dst); ci.handle = conn->handle; ci.type = conn->type; ci.out = conn->out; ci.state = conn->state; ci.link_mode = get_link_mode(conn); } hci_dev_unlock(hdev); if (!conn) return -ENOENT; return copy_to_user(ptr, &ci, sizeof(ci)) ? -EFAULT : 0; } int hci_get_auth_info(struct hci_dev *hdev, void __user *arg) { struct hci_auth_info_req req; struct hci_conn *conn; if (copy_from_user(&req, arg, sizeof(req))) return -EFAULT; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &req.bdaddr); if (conn) req.type = conn->auth_type; hci_dev_unlock(hdev); if (!conn) return -ENOENT; return copy_to_user(arg, &req, sizeof(req)) ? -EFAULT : 0; } struct hci_chan *hci_chan_create(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct hci_chan *chan; BT_DBG("%s hcon %p", hdev->name, conn); if (test_bit(HCI_CONN_DROP, &conn->flags)) { BT_DBG("Refusing to create new hci_chan"); return NULL; } chan = kzalloc_obj(*chan); if (!chan) return NULL; chan->conn = hci_conn_get(conn); skb_queue_head_init(&chan->data_q); chan->state = BT_CONNECTED; list_add_rcu(&chan->list, &conn->chan_list); return chan; } void hci_chan_del(struct hci_chan *chan) { struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p chan %p", hdev->name, conn, chan); list_del_rcu(&chan->list); synchronize_rcu(); /* Prevent new hci_chan's to be created for this hci_conn */ set_bit(HCI_CONN_DROP, &conn->flags); hci_conn_put(conn); skb_queue_purge(&chan->data_q); kfree(chan); } void hci_chan_list_flush(struct hci_conn *conn) { struct hci_chan *chan, *n; BT_DBG("hcon %p", conn); list_for_each_entry_safe(chan, n, &conn->chan_list, list) hci_chan_del(chan); } static struct hci_chan *__hci_chan_lookup_handle(struct hci_conn *hcon, __u16 handle) { struct hci_chan *hchan; list_for_each_entry(hchan, &hcon->chan_list, list) { if (hchan->handle == handle) return hchan; } return NULL; } struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *hcon; struct hci_chan *hchan = NULL; rcu_read_lock(); list_for_each_entry_rcu(hcon, &h->list, list) { hchan = __hci_chan_lookup_handle(hcon, handle); if (hchan) break; } rcu_read_unlock(); return hchan; } u32 hci_conn_get_phy(struct hci_conn *conn) { u32 phys = 0; /* BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 2, Part B page 471: * Table 6.2: Packets defined for synchronous, asynchronous, and * CPB logical transport types. */ switch (conn->type) { case SCO_LINK: /* SCO logical transport (1 Mb/s): * HV1, HV2, HV3 and DV. */ phys |= BT_PHY_BR_1M_1SLOT; break; case ACL_LINK: /* ACL logical transport (1 Mb/s) ptt=0: * DH1, DM3, DH3, DM5 and DH5. */ phys |= BT_PHY_BR_1M_1SLOT; if (conn->pkt_type & (HCI_DM3 | HCI_DH3)) phys |= BT_PHY_BR_1M_3SLOT; if (conn->pkt_type & (HCI_DM5 | HCI_DH5)) phys |= BT_PHY_BR_1M_5SLOT; /* ACL logical transport (2 Mb/s) ptt=1: * 2-DH1, 2-DH3 and 2-DH5. */ if (!(conn->pkt_type & HCI_2DH1)) phys |= BT_PHY_EDR_2M_1SLOT; if (!(conn->pkt_type & HCI_2DH3)) phys |= BT_PHY_EDR_2M_3SLOT; if (!(conn->pkt_type & HCI_2DH5)) phys |= BT_PHY_EDR_2M_5SLOT; /* ACL logical transport (3 Mb/s) ptt=1: * 3-DH1, 3-DH3 and 3-DH5. */ if (!(conn->pkt_type & HCI_3DH1)) phys |= BT_PHY_EDR_3M_1SLOT; if (!(conn->pkt_type & HCI_3DH3)) phys |= BT_PHY_EDR_3M_3SLOT; if (!(conn->pkt_type & HCI_3DH5)) phys |= BT_PHY_EDR_3M_5SLOT; break; case ESCO_LINK: /* eSCO logical transport (1 Mb/s): EV3, EV4 and EV5 */ phys |= BT_PHY_BR_1M_1SLOT; if (!(conn->pkt_type & (ESCO_EV4 | ESCO_EV5))) phys |= BT_PHY_BR_1M_3SLOT; /* eSCO logical transport (2 Mb/s): 2-EV3, 2-EV5 */ if (!(conn->pkt_type & ESCO_2EV3)) phys |= BT_PHY_EDR_2M_1SLOT; if (!(conn->pkt_type & ESCO_2EV5)) phys |= BT_PHY_EDR_2M_3SLOT; /* eSCO logical transport (3 Mb/s): 3-EV3, 3-EV5 */ if (!(conn->pkt_type & ESCO_3EV3)) phys |= BT_PHY_EDR_3M_1SLOT; if (!(conn->pkt_type & ESCO_3EV5)) phys |= BT_PHY_EDR_3M_3SLOT; break; case LE_LINK: if (conn->le_tx_def_phys & HCI_LE_SET_PHY_1M) phys |= BT_PHY_LE_1M_TX; if (conn->le_rx_def_phys & HCI_LE_SET_PHY_1M) phys |= BT_PHY_LE_1M_RX; if (conn->le_tx_def_phys & HCI_LE_SET_PHY_2M) phys |= BT_PHY_LE_2M_TX; if (conn->le_rx_def_phys & HCI_LE_SET_PHY_2M) phys |= BT_PHY_LE_2M_RX; if (conn->le_tx_def_phys & HCI_LE_SET_PHY_CODED) phys |= BT_PHY_LE_CODED_TX; if (conn->le_rx_def_phys & HCI_LE_SET_PHY_CODED) phys |= BT_PHY_LE_CODED_RX; break; } return phys; } static u16 bt_phy_pkt_type(struct hci_conn *conn, u32 phys) { u16 pkt_type = conn->pkt_type; if (phys & BT_PHY_BR_1M_3SLOT) pkt_type |= HCI_DM3 | HCI_DH3; else pkt_type &= ~(HCI_DM3 | HCI_DH3); if (phys & BT_PHY_BR_1M_5SLOT) pkt_type |= HCI_DM5 | HCI_DH5; else pkt_type &= ~(HCI_DM5 | HCI_DH5); if (phys & BT_PHY_EDR_2M_1SLOT) pkt_type &= ~HCI_2DH1; else pkt_type |= HCI_2DH1; if (phys & BT_PHY_EDR_2M_3SLOT) pkt_type &= ~HCI_2DH3; else pkt_type |= HCI_2DH3; if (phys & BT_PHY_EDR_2M_5SLOT) pkt_type &= ~HCI_2DH5; else pkt_type |= HCI_2DH5; if (phys & BT_PHY_EDR_3M_1SLOT) pkt_type &= ~HCI_3DH1; else pkt_type |= HCI_3DH1; if (phys & BT_PHY_EDR_3M_3SLOT) pkt_type &= ~HCI_3DH3; else pkt_type |= HCI_3DH3; if (phys & BT_PHY_EDR_3M_5SLOT) pkt_type &= ~HCI_3DH5; else pkt_type |= HCI_3DH5; return pkt_type; } static int bt_phy_le_phy(u32 phys, u8 *tx_phys, u8 *rx_phys) { if (!tx_phys || !rx_phys) return -EINVAL; *tx_phys = 0; *rx_phys = 0; if (phys & BT_PHY_LE_1M_TX) *tx_phys |= HCI_LE_SET_PHY_1M; if (phys & BT_PHY_LE_1M_RX) *rx_phys |= HCI_LE_SET_PHY_1M; if (phys & BT_PHY_LE_2M_TX) *tx_phys |= HCI_LE_SET_PHY_2M; if (phys & BT_PHY_LE_2M_RX) *rx_phys |= HCI_LE_SET_PHY_2M; if (phys & BT_PHY_LE_CODED_TX) *tx_phys |= HCI_LE_SET_PHY_CODED; if (phys & BT_PHY_LE_CODED_RX) *rx_phys |= HCI_LE_SET_PHY_CODED; return 0; } int hci_conn_set_phy(struct hci_conn *conn, u32 phys) { u8 tx_phys, rx_phys; switch (conn->type) { case SCO_LINK: case ESCO_LINK: return -EINVAL; case ACL_LINK: /* Only allow setting BR/EDR PHYs if link type is ACL */ if (phys & ~BT_PHY_BREDR_MASK) return -EINVAL; return hci_acl_change_pkt_type(conn, bt_phy_pkt_type(conn, phys)); case LE_LINK: /* Only allow setting LE PHYs if link type is LE */ if (phys & ~BT_PHY_LE_MASK) return -EINVAL; if (bt_phy_le_phy(phys, &tx_phys, &rx_phys)) return -EINVAL; return hci_le_set_phy(conn, tx_phys, rx_phys); default: return -EINVAL; } } static int abort_conn_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn = data; if (!hci_conn_valid(hdev, conn)) return -ECANCELED; return hci_abort_conn_sync(hdev, conn, conn->abort_reason); } static void abort_conn_destroy(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; hci_conn_put(conn); } int hci_abort_conn(struct hci_conn *conn, u8 reason) { struct hci_dev *hdev = conn->hdev; int err; /* If abort_reason has already been set it means the connection is * already being aborted so don't attempt to overwrite it. */ if (conn->abort_reason) return 0; bt_dev_dbg(hdev, "handle 0x%2.2x reason 0x%2.2x", conn->handle, reason); conn->abort_reason = reason; /* Cancel the connect attempt. A return of 0 means the create command * was still queued and got dequeued, so there is nothing to disconnect. */ if (!hci_cancel_connect_sync(hdev, conn)) return 0; /* Run immediately if on cmd_sync_work since this may be called * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does * already queue its callback on cmd_sync_work. */ err = hci_cmd_sync_run_once(hdev, abort_conn_sync, hci_conn_get(conn), abort_conn_destroy); if (err) hci_conn_put(conn); return (err == -EEXIST) ? 0 : err; } void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset, const struct sockcm_cookie *sockc) { struct sock *sk = skb ? skb->sk : NULL; int key; /* This shall be called on a single skb of those generated by user * sendmsg(), and only when the sendmsg() does not return error to * user. This is required for keeping the tskey that increments here in * sync with possible sendmsg() counting by user. * * Stream sockets shall set key_offset to sendmsg() length in bytes * and call with the last fragment, others to 1 and first fragment. */ if (!skb || !sockc || !sk || !key_offset) return; sock_tx_timestamp(sk, sockc, &skb_shinfo(skb)->tx_flags); if (sk->sk_type == SOCK_STREAM) key = atomic_add_return(key_offset, &sk->sk_tskey); if (sockc->tsflags & SOF_TIMESTAMPING_OPT_ID && sockc->tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { if (sockc->tsflags & SOCKCM_FLAG_TS_OPT_ID) { skb_shinfo(skb)->tskey = sockc->ts_opt_id; } else { if (sk->sk_type != SOCK_STREAM) key = atomic_inc_return(&sk->sk_tskey); skb_shinfo(skb)->tskey = key - 1; } } } void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb) { struct tx_queue *comp = &conn->tx_q; bool track = false; /* Emit SND now, ie. just before sending to driver */ if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SND); /* COMPLETION tstamp is emitted for tracked skb later in Number of * Completed Packets event. Available only for flow controlled cases. * * TODO: SCO support without flowctl (needs to be done in drivers) */ switch (conn->type) { case CIS_LINK: case BIS_LINK: case PA_LINK: case ACL_LINK: case LE_LINK: break; case SCO_LINK: case ESCO_LINK: if (!hci_dev_test_flag(conn->hdev, HCI_SCO_FLOWCTL)) return; break; default: return; } if (skb->sk && (skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP)) track = true; /* If nothing is tracked, just count extra skbs at the queue head */ if (!track && !comp->tracked) { comp->extra++; return; } if (track) { skb = skb_clone_sk(skb); if (!skb) goto count_only; comp->tracked++; } else { skb = skb_clone(skb, GFP_KERNEL); if (!skb) goto count_only; } skb_queue_tail(&comp->queue, skb); return; count_only: /* Stop tracking skbs, and only count. This will not emit timestamps for * the packets, but if we get here something is more seriously wrong. */ comp->tracked = 0; comp->extra += skb_queue_len(&comp->queue) + 1; skb_queue_purge(&comp->queue); } void hci_conn_tx_dequeue(struct hci_conn *conn) { struct tx_queue *comp = &conn->tx_q; struct sk_buff *skb; /* If there are tracked skbs, the counted extra go before dequeuing real * skbs, to keep ordering. When nothing is tracked, the ordering doesn't * matter so dequeue real skbs first to get rid of them ASAP. */ if (comp->extra && (comp->tracked || skb_queue_empty(&comp->queue))) { comp->extra--; return; } skb = skb_dequeue(&comp->queue); if (!skb) return; if (skb->sk) { comp->tracked--; __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_COMPLETION); } kfree_skb(skb); } u8 *hci_conn_key_enc_size(struct hci_conn *conn) { if (conn->type == ACL_LINK) { struct link_key *key; key = hci_find_link_key(conn->hdev, &conn->dst); if (!key) return NULL; return &key->pin_len; } else if (conn->type == LE_LINK) { struct smp_ltk *ltk; ltk = hci_find_ltk(conn->hdev, &conn->dst, conn->dst_type, conn->role); if (!ltk) return NULL; return <k->enc_size; } return NULL; } int hci_ethtool_ts_info(unsigned int index, int sk_proto, struct kernel_ethtool_ts_info *info) { struct hci_dev *hdev; hdev = hci_dev_get(index); if (!hdev) return -ENODEV; info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; info->phc_index = -1; info->tx_types = BIT(HWTSTAMP_TX_OFF); info->rx_filters = BIT(HWTSTAMP_FILTER_NONE); switch (sk_proto) { case BTPROTO_ISO: case BTPROTO_L2CAP: info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE; info->so_timestamping |= SOF_TIMESTAMPING_TX_COMPLETION; break; case BTPROTO_SCO: info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE; if (hci_dev_test_flag(hdev, HCI_SCO_FLOWCTL)) info->so_timestamping |= SOF_TIMESTAMPING_TX_COMPLETION; break; } hci_dev_put(hdev); return 0; } |
| 95 101 95 316 320 320 117 115 91 6 112 87 110 88 9 2 6 1 1 307 307 2 85 246 86 2 305 88 305 85 101 316 316 99 99 99 316 92 316 93 316 90 2 308 91 305 85 90 90 96 96 305 305 305 305 102 305 305 91 3 305 305 305 305 305 305 305 305 305 1 82 82 39 39 119 11 114 9 9 112 3 112 1 109 5 1 4 4 1 114 3 113 110 6 1 1 1 1 6 95 6 95 91 19 91 95 105 105 90 3 96 89 2 3 3 95 95 95 95 94 1 94 94 94 2 93 92 92 1 92 90 89 91 91 90 90 90 95 95 98 3 95 91 2 98 95 6 3 102 2 96 5 101 98 90 4 3 3 4 4 4 1 3 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * cpuid support routines * * derived from arch/x86/kvm/x86.c * * Copyright 2011 Red Hat, Inc. and/or its affiliates. * Copyright IBM Corporation, 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/lockdep.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> #include <linux/sched/stat.h> #include <asm/processor.h> #include <asm/user.h> #include <asm/fpu/xstate.h> #include <asm/sgx.h> #include <asm/cpuid/api.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" #include "trace.h" #include "pmu.h" #include "xen.h" #include "x86.h" /* * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be * aligned to sizeof(unsigned long) because it's not accessed via bitops. */ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_cpu_caps); bool kvm_is_configuring_cpu_caps __read_mostly; EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_is_configuring_cpu_caps); struct cpuid_xstate_sizes { u32 eax; u32 ebx; u32 ecx; }; static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init; void __init kvm_init_xstate_sizes(void) { u32 ign; int i; for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) { struct cpuid_xstate_sizes *xs = &xstate_sizes[i]; cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign); } } u32 xstate_required_size(u64 xstate_bv, bool compacted) { u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; int i; xstate_bv &= XFEATURE_MASK_EXTEND; for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes) && xstate_bv; i++) { struct cpuid_xstate_sizes *xs = &xstate_sizes[i]; u32 offset; if (!(xstate_bv & BIT_ULL(i))) continue; /* ECX[1]: 64B alignment in compacted form */ if (compacted) offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret; else offset = xs->ebx; ret = max(ret, offset + xs->eax); xstate_bv &= ~BIT_ULL(i); } return ret; } struct kvm_cpuid_entry2 *kvm_find_cpuid_entry2( struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index) { struct kvm_cpuid_entry2 *e; int i; /* * KVM has a semi-arbitrary rule that querying the guest's CPUID model * with IRQs disabled is disallowed. The CPUID model can legitimately * have over one hundred entries, i.e. the lookup is slow, and IRQs are * typically disabled in KVM only when KVM is in a performance critical * path, e.g. the core VM-Enter/VM-Exit run loop. Nothing will break * if this rule is violated, this assertion is purely to flag potential * performance issues. If this fires, consider moving the lookup out * of the hotpath, e.g. by caching information during CPUID updates. */ lockdep_assert_irqs_enabled(); for (i = 0; i < nent; i++) { e = &entries[i]; if (e->function != function) continue; /* * If the index isn't significant, use the first entry with a * matching function. It's userspace's responsibility to not * provide "duplicate" entries in all cases. */ if (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index) return e; /* * Similarly, use the first matching entry if KVM is doing a * lookup (as opposed to emulating CPUID) for a function that's * architecturally defined as not having a significant index. */ if (index == KVM_CPUID_INDEX_NOT_SIGNIFICANT) { /* * Direct lookups from KVM should not diverge from what * KVM defines internally (the architectural behavior). */ WARN_ON_ONCE(cpuid_function_is_indexed(function)); return e; } } return NULL; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_find_cpuid_entry2); static int kvm_check_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; u64 xfeatures; /* * The existing code assumes virtual address is 48-bit or 57-bit in the * canonical address checks; exit if it is ever changed. */ best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) { int vaddr_bits = (best->eax & 0xff00) >> 8; if (vaddr_bits != 48 && vaddr_bits != 57 && vaddr_bits != 0) return -EINVAL; } /* * Exposing dynamic xfeatures to the guest requires additional * enabling in the FPU, e.g. to expand the guest XSAVE state size. */ best = kvm_find_cpuid_entry_index(vcpu, 0xd, 0); if (!best) return 0; xfeatures = best->eax | ((u64)best->edx << 32); xfeatures &= XFEATURE_MASK_USER_DYNAMIC; if (!xfeatures) return 0; return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures); } static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu); static void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); /* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { struct kvm_cpuid_entry2 *orig; int i; /* * Apply runtime CPUID updates to the incoming CPUID entries to avoid * false positives due mismatches on KVM-owned feature flags. * * Note! @e2 and @nent track the _old_ CPUID entries! */ kvm_update_cpuid_runtime(vcpu); kvm_apply_cpuid_pv_features_quirk(vcpu); if (nent != vcpu->arch.cpuid_nent) return -EINVAL; for (i = 0; i < nent; i++) { orig = &vcpu->arch.cpuid_entries[i]; if (e2[i].function != orig->function || e2[i].index != orig->index || e2[i].flags != orig->flags || e2[i].eax != orig->eax || e2[i].ebx != orig->ebx || e2[i].ecx != orig->ecx || e2[i].edx != orig->edx) return -EINVAL; } return 0; } static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_cpuid_base_hypervisor(base) { entry = kvm_find_cpuid_entry(vcpu, base); if (entry) { u32 signature[3]; signature[0] = entry->ebx; signature[1] = entry->ecx; signature[2] = entry->edx; if (!memcmp(signature, sig, sizeof(signature))) { cpuid.base = base; cpuid.limit = entry->eax; break; } } } return cpuid; } static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu) { struct kvm_hypervisor_cpuid kvm_cpuid; struct kvm_cpuid_entry2 *best; kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); if (!kvm_cpuid.base) return 0; best = kvm_find_cpuid_entry(vcpu, kvm_cpuid.base | KVM_CPUID_FEATURES); if (!best) return 0; if (kvm_hlt_in_guest(vcpu->kvm)) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); return best->eax; } /* * Calculate guest's supported XCR0 taking into account guest CPUID data and * KVM's supported XCR0 (comprised of host's XCR0 and KVM_SUPPORTED_XCR0). */ static u64 cpuid_get_supported_xcr0(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry_index(vcpu, 0xd, 0); if (!best) return 0; return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0; } static u64 cpuid_get_supported_xss(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry_index(vcpu, 0xd, 1); if (!best) return 0; return (best->ecx | ((u64)best->edx << 32)) & kvm_caps.supported_xss; } static __always_inline void kvm_update_feature_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entry, unsigned int x86_feature, bool has_feature) { cpuid_entry_change(entry, x86_feature, has_feature); guest_cpu_cap_change(vcpu, x86_feature, has_feature); } static void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; vcpu->arch.cpuid_dynamic_bits_dirty = false; best = kvm_find_cpuid_entry(vcpu, 1); if (best) { kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSXSAVE, kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)); kvm_update_feature_runtime(vcpu, best, X86_FEATURE_APIC, vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) kvm_update_feature_runtime(vcpu, best, X86_FEATURE_MWAIT, vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } best = kvm_find_cpuid_entry_index(vcpu, 7, 0); if (best) kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSPKE, kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); best = kvm_find_cpuid_entry_index(vcpu, 0xD, 0); if (best) best->ebx = xstate_required_size(vcpu->arch.xcr0, false); best = kvm_find_cpuid_entry_index(vcpu, 0xD, 1); if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0 | vcpu->arch.ia32_xss, true); } static bool kvm_cpuid_has_hyperv(struct kvm_vcpu *vcpu) { #ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; #else return false; #endif } static bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; entry = kvm_find_cpuid_entry(vcpu, 0); if (!entry) return false; return is_guest_vendor_amd(entry->ebx, entry->ecx, entry->edx) || is_guest_vendor_hygon(entry->ebx, entry->ecx, entry->edx); } /* * This isn't truly "unsafe", but except for the cpu_caps initialization code, * all register lookups should use __cpuid_entry_get_reg(), which provides * compile-time validation of the input. */ static u32 cpuid_get_reg_unsafe(struct kvm_cpuid_entry2 *entry, u32 reg) { switch (reg) { case CPUID_EAX: return entry->eax; case CPUID_EBX: return entry->ebx; case CPUID_ECX: return entry->ecx; case CPUID_EDX: return entry->edx; default: WARN_ON_ONCE(1); return 0; } } static int cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, u32 func, u32 index, bool include_partially_emulated); void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; struct kvm_cpuid_entry2 *entry; bool allow_gbpages; int i; memset(vcpu->arch.cpu_caps, 0, sizeof(vcpu->arch.cpu_caps)); BUILD_BUG_ON(ARRAY_SIZE(reverse_cpuid) != NR_KVM_CPU_CAPS); /* * Reset guest capabilities to userspace's guest CPUID definition, i.e. * honor userspace's definition for features that don't require KVM or * hardware management/support (or that KVM simply doesn't care about). */ for (i = 0; i < NR_KVM_CPU_CAPS; i++) { const struct cpuid_reg cpuid = reverse_cpuid[i]; struct kvm_cpuid_entry2 emulated; if (!cpuid.function) continue; entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index); if (!entry) continue; cpuid_func_emulated(&emulated, cpuid.function, cpuid.index, true); /* * A vCPU has a feature if it's supported by KVM and is enabled * in guest CPUID. Note, this includes features that are * supported by KVM but aren't advertised to userspace! */ vcpu->arch.cpu_caps[i] = kvm_cpu_caps[i] | cpuid_get_reg_unsafe(&emulated, cpuid.reg); vcpu->arch.cpu_caps[i] &= cpuid_get_reg_unsafe(entry, cpuid.reg); } kvm_update_cpuid_runtime(vcpu); /* * If TDP is enabled, let the guest use GBPAGES if they're supported in * hardware. The hardware page walker doesn't let KVM disable GBPAGES, * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA * walk for performance and complexity reasons. Not to mention KVM * _can't_ solve the problem because GVA->GPA walks aren't visible to * KVM once a TDP translation is installed. Mimic hardware behavior so * that KVM's is at least consistent, i.e. doesn't randomly inject #PF. * If TDP is disabled, honor *only* guest CPUID as KVM has full control * and can install smaller shadow pages if the host lacks 1GiB support. */ allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES); guest_cpu_cap_change(vcpu, X86_FEATURE_GBPAGES, allow_gbpages); best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER)) apic->lapic_timer.timer_mode_mask = 3 << 17; else apic->lapic_timer.timer_mode_mask = 1 << 17; kvm_apic_set_version(vcpu); } vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu); vcpu->arch.guest_supported_xss = cpuid_get_supported_xss(vcpu); vcpu->arch.pv_cpuid.features = kvm_apply_cpuid_pv_features_quirk(vcpu); vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); kvm_pmu_refresh(vcpu); #define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_) | __cr4_reserved_bits(guest_cpu_cap_has, vcpu); #undef __kvm_cpu_cap_has kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu)); /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_call(vcpu_after_set_cpuid)(vcpu); /* * Except for the MMU, which needs to do its thing any vendor specific * adjustments to the reserved GPA bits. */ kvm_mmu_after_set_cpuid(vcpu); kvm_make_request(KVM_REQ_RECALC_INTERCEPTS, vcpu); } int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 0x80000000); if (!best || best->eax < 0x80000008) goto not_found; best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) return best->eax & 0xff; not_found: return 36; } int cpuid_query_maxguestphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 0x80000000); if (!best || best->eax < 0x80000008) goto not_found; best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) return (best->eax >> 16) & 0xff; not_found: return 0; } /* * This "raw" version returns the reserved GPA bits without any adjustments for * encryption technologies that usurp bits. The raw mask should be used if and * only if hardware does _not_ strip the usurped bits, e.g. in virtual MTRRs. */ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) { return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); } static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { u32 vcpu_caps[NR_KVM_CPU_CAPS]; int r; /* * Apply pending runtime CPUID updates to the current CPUID entries to * avoid false positives due to mismatches on KVM-owned feature flags. */ if (vcpu->arch.cpuid_dynamic_bits_dirty) kvm_update_cpuid_runtime(vcpu); /* * Swap the existing (old) entries with the incoming (new) entries in * order to massage the new entries, e.g. to account for dynamic bits * that KVM controls, without losing the current guest CPUID, which KVM * needs to preserve in order to unwind on failure. * * Similarly, save the vCPU's current cpu_caps so that the capabilities * can be updated alongside the CPUID entries when performing runtime * updates. Full initialization is done if and only if the vCPU hasn't * run, i.e. only if userspace is potentially changing CPUID features. */ swap(vcpu->arch.cpuid_entries, e2); swap(vcpu->arch.cpuid_nent, nent); memcpy(vcpu_caps, vcpu->arch.cpu_caps, sizeof(vcpu_caps)); BUILD_BUG_ON(sizeof(vcpu_caps) != sizeof(vcpu->arch.cpu_caps)); /* * KVM does not correctly handle changing guest CPUID after KVM_RUN or * while L2 is active, as MAXPHYADDR, GBPAGES support, AMD reserved bit * behavior, etc. aren't tracked in kvm_mmu_page_role, and L2 state * can't be adjusted (without breaking L2 in some way). As a result, * KVM may reuse SPs/SPTEs and/or run L2 with bad/misconfigured state. * * In practice, no sane VMM mucks with the core vCPU model on the fly. * It would've been better to forbid any KVM_SET_CPUID{,2} calls after * KVM_RUN or KVM_SET_NESTED_STATE altogether, but unfortunately some * VMMs (e.g. QEMU) reuse vCPU fds for CPU hotplug/unplug and do * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ if (!kvm_can_set_cpuid_and_feature_msrs(vcpu)) { r = kvm_cpuid_check_equal(vcpu, e2, nent); if (r) goto err; goto success; } #ifdef CONFIG_KVM_HYPERV if (kvm_cpuid_has_hyperv(vcpu)) { r = kvm_hv_vcpu_init(vcpu); if (r) goto err; } #endif r = kvm_check_cpuid(vcpu); if (r) goto err; #ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); #endif kvm_vcpu_after_set_cpuid(vcpu); success: kvfree(e2); return 0; err: memcpy(vcpu->arch.cpu_caps, vcpu_caps, sizeof(vcpu_caps)); swap(vcpu->arch.cpuid_entries, e2); swap(vcpu->arch.cpuid_nent, nent); return r; } /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, struct kvm_cpuid_entry __user *entries) { int r, i; struct kvm_cpuid_entry *e = NULL; struct kvm_cpuid_entry2 *e2 = NULL; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) return -E2BIG; if (cpuid->nent) { e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e)); if (IS_ERR(e)) return PTR_ERR(e); e2 = kvmalloc_objs(*e2, cpuid->nent, GFP_KERNEL_ACCOUNT); if (!e2) { r = -ENOMEM; goto out_free_cpuid; } } for (i = 0; i < cpuid->nent; i++) { e2[i].function = e[i].function; e2[i].eax = e[i].eax; e2[i].ebx = e[i].ebx; e2[i].ecx = e[i].ecx; e2[i].edx = e[i].edx; e2[i].index = 0; e2[i].flags = 0; e2[i].padding[0] = 0; e2[i].padding[1] = 0; e2[i].padding[2] = 0; } r = kvm_set_cpuid(vcpu, e2, cpuid->nent); if (r) kvfree(e2); out_free_cpuid: kvfree(e); return r; } int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *e2 = NULL; int r; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) return -E2BIG; if (cpuid->nent) { e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2)); if (IS_ERR(e2)) return PTR_ERR(e2); } r = kvm_set_cpuid(vcpu, e2, cpuid->nent); if (r) kvfree(e2); return r; } int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { if (cpuid->nent < vcpu->arch.cpuid_nent) return -E2BIG; if (vcpu->arch.cpuid_dynamic_bits_dirty) kvm_update_cpuid_runtime(vcpu); if (copy_to_user(entries, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) return -EFAULT; cpuid->nent = vcpu->arch.cpuid_nent; return 0; } static __always_inline u32 raw_cpuid_get(struct cpuid_reg cpuid) { struct kvm_cpuid_entry2 entry; u32 base; /* * KVM only supports features defined by Intel (0x0), AMD (0x80000000), * and Centaur (0xc0000000). WARN if a feature for new vendor base is * defined, as this and other code would need to be updated. */ base = cpuid.function & 0xffff0000; if (WARN_ON_ONCE(base && base != 0x80000000 && base != 0xc0000000)) return 0; if (cpuid_eax(base) < cpuid.function) return 0; cpuid_count(cpuid.function, cpuid.index, &entry.eax, &entry.ebx, &entry.ecx, &entry.edx); return *__cpuid_entry_get_reg(&entry, cpuid.reg); } /* * For kernel-defined leafs, mask KVM's supported feature set with the kernel's * capabilities as well as raw CPUID. For KVM-defined leafs, consult only raw * CPUID, as KVM is the one and only authority (in the kernel). */ #define kvm_cpu_cap_init(leaf, feature_initializers...) \ do { \ const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); \ const u32 __maybe_unused kvm_cpu_cap_init_in_progress = leaf; \ const u32 *kernel_cpu_caps = boot_cpu_data.x86_capability; \ u32 kvm_cpu_cap_passthrough = 0; \ u32 kvm_cpu_cap_synthesized = 0; \ u32 kvm_cpu_cap_emulated = 0; \ u32 kvm_cpu_cap_features = 0; \ \ feature_initializers \ \ kvm_cpu_caps[leaf] = kvm_cpu_cap_features; \ \ if (leaf < NCAPINTS) \ kvm_cpu_caps[leaf] &= kernel_cpu_caps[leaf]; \ \ kvm_cpu_caps[leaf] |= kvm_cpu_cap_passthrough; \ kvm_cpu_caps[leaf] &= (raw_cpuid_get(cpuid) | \ kvm_cpu_cap_synthesized); \ kvm_cpu_caps[leaf] |= kvm_cpu_cap_emulated; \ } while (0) /* * Assert that the feature bit being declared, e.g. via F(), is in the CPUID * word that's being initialized. Exempt 0x8000_0001.EDX usage of 0x1.EDX * features, as AMD duplicated many 0x1.EDX features into 0x8000_0001.EDX. */ #define KVM_VALIDATE_CPU_CAP_USAGE(name) \ do { \ u32 __leaf = __feature_leaf(X86_FEATURE_##name); \ \ BUILD_BUG_ON(__leaf != kvm_cpu_cap_init_in_progress); \ } while (0) #define F(name) \ ({ \ KVM_VALIDATE_CPU_CAP_USAGE(name); \ kvm_cpu_cap_features |= feature_bit(name); \ }) /* Scattered Flag - For features that are scattered by cpufeatures.h. */ #define SCATTERED_F(name) \ ({ \ BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ KVM_VALIDATE_CPU_CAP_USAGE(name); \ if (boot_cpu_has(X86_FEATURE_##name)) \ F(name); \ }) /* Features that KVM supports only on 64-bit kernels. */ #define X86_64_F(name) \ ({ \ KVM_VALIDATE_CPU_CAP_USAGE(name); \ if (IS_ENABLED(CONFIG_X86_64)) \ F(name); \ }) /* * Emulated Feature - For features that KVM emulates in software irrespective * of host CPU/kernel support. */ #define EMULATED_F(name) \ ({ \ kvm_cpu_cap_emulated |= feature_bit(name); \ F(name); \ }) /* * Synthesized Feature - For features that are synthesized into boot_cpu_data, * i.e. may not be present in the raw CPUID, but can still be advertised to * userspace. Primarily used for mitigation related feature flags. */ #define SYNTHESIZED_F(name) \ ({ \ kvm_cpu_cap_synthesized |= feature_bit(name); \ \ BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ if (boot_cpu_has(X86_FEATURE_##name)) \ F(name); \ }) /* * Passthrough Feature - For features that KVM supports based purely on raw * hardware CPUID, i.e. that KVM virtualizes even if the host kernel doesn't * use the feature. Simply force set the feature in KVM's capabilities, raw * CPUID support will be factored in by kvm_cpu_cap_mask(). */ #define PASSTHROUGH_F(name) \ ({ \ kvm_cpu_cap_passthrough |= feature_bit(name); \ F(name); \ }) /* * Aliased Features - For features in 0x8000_0001.EDX that are duplicates of * identical 0x1.EDX features, and thus are aliased from 0x1 to 0x8000_0001. */ #define ALIASED_1_EDX_F(name) \ ({ \ BUILD_BUG_ON(__feature_leaf(X86_FEATURE_##name) != CPUID_1_EDX); \ BUILD_BUG_ON(kvm_cpu_cap_init_in_progress != CPUID_8000_0001_EDX); \ kvm_cpu_cap_features |= feature_bit(name); \ }) /* * Vendor Features - For features that KVM supports, but are added in later * because they require additional vendor enabling. */ #define VENDOR_F(name) \ ({ \ KVM_VALIDATE_CPU_CAP_USAGE(name); \ }) /* * Runtime Features - For features that KVM dynamically sets/clears at runtime, * e.g. when CR4 changes, but which are never advertised to userspace. */ #define RUNTIME_F(name) \ ({ \ KVM_VALIDATE_CPU_CAP_USAGE(name); \ }) /* * Undefine the MSR bit macro to avoid token concatenation issues when * processing X86_FEATURE_SPEC_CTRL_SSBD. */ #undef SPEC_CTRL_SSBD /* DS is defined by ptrace-abi.h on 32-bit builds. */ #undef DS void kvm_initialize_cpu_caps(void) { memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps)); WARN_ON_ONCE(kvm_is_configuring_cpu_caps); kvm_is_configuring_cpu_caps = true; BUILD_BUG_ON(sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)) > sizeof(boot_cpu_data.x86_capability)); kvm_cpu_cap_init(CPUID_1_ECX, F(XMM3), F(PCLMULQDQ), VENDOR_F(DTES64), /* * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not* * advertised to guests via CPUID! MWAIT is also technically a * runtime flag thanks to IA32_MISC_ENABLES; mark it as such so * that KVM is aware that it's a known, unadvertised flag. */ RUNTIME_F(MWAIT), /* DS-CPL */ VENDOR_F(VMX), /* SMX, EST */ /* TM2 */ F(SSSE3), /* CNXT-ID */ /* Reserved */ F(FMA), F(CX16), /* xTPR Update */ F(PDCM), F(PCID), /* Reserved, DCA */ F(XMM4_1), F(XMM4_2), EMULATED_F(X2APIC), F(MOVBE), F(POPCNT), EMULATED_F(TSC_DEADLINE_TIMER), F(AES), F(XSAVE), RUNTIME_F(OSXSAVE), F(AVX), F(F16C), F(RDRAND), EMULATED_F(HYPERVISOR), ); kvm_cpu_cap_init(CPUID_1_EDX, F(FPU), F(VME), F(DE), F(PSE), F(TSC), F(MSR), F(PAE), F(MCE), F(CX8), F(APIC), /* Reserved */ F(SEP), F(MTRR), F(PGE), F(MCA), F(CMOV), F(PAT), F(PSE36), /* PSN */ F(CLFLUSH), /* Reserved */ VENDOR_F(DS), /* ACPI */ F(MMX), F(FXSR), F(XMM), F(XMM2), F(SELFSNOOP), /* HTT, TM, Reserved, PBE */ ); kvm_cpu_cap_init(CPUID_7_0_EBX, F(FSGSBASE), EMULATED_F(TSC_ADJUST), F(SGX), F(BMI1), F(HLE), F(AVX2), F(FDP_EXCPTN_ONLY), F(SMEP), F(BMI2), F(ERMS), F(INVPCID), F(RTM), F(ZERO_FCS_FDS), VENDOR_F(MPX), F(AVX512F), F(AVX512DQ), F(RDSEED), F(ADX), F(SMAP), F(AVX512IFMA), F(CLFLUSHOPT), F(CLWB), VENDOR_F(INTEL_PT), F(AVX512PF), F(AVX512ER), F(AVX512CD), F(SHA_NI), F(AVX512BW), F(AVX512VL), ); kvm_cpu_cap_init(CPUID_7_ECX, F(AVX512VBMI), PASSTHROUGH_F(LA57), F(PKU), RUNTIME_F(OSPKE), F(RDPID), F(AVX512_VPOPCNTDQ), F(UMIP), F(AVX512_VBMI2), F(GFNI), F(VAES), F(VPCLMULQDQ), F(AVX512_VNNI), F(AVX512_BITALG), F(CLDEMOTE), F(MOVDIRI), F(MOVDIR64B), VENDOR_F(WAITPKG), F(SGX_LC), F(BUS_LOCK_DETECT), X86_64_F(SHSTK), ); /* * PKU not yet implemented for shadow paging and requires OSPKE * to be set on the host. Clear it if that is not the case */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) kvm_cpu_cap_clear(X86_FEATURE_PKU); /* * Shadow Stacks aren't implemented in the Shadow MMU. Shadow Stack * accesses require "magic" Writable=0,Dirty=1 protection, which KVM * doesn't know how to emulate or map. */ if (!tdp_enabled) kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_init(CPUID_7_EDX, F(AVX512_4VNNIW), F(AVX512_4FMAPS), F(SPEC_CTRL), F(SPEC_CTRL_SSBD), EMULATED_F(ARCH_CAPABILITIES), F(INTEL_STIBP), F(MD_CLEAR), F(AVX512_VP2INTERSECT), F(FSRM), F(SERIALIZE), F(TSXLDTRK), F(AVX512_FP16), F(AMX_TILE), F(AMX_INT8), F(AMX_BF16), F(FLUSH_L1D), F(IBT), ); /* * Disable support for IBT and SHSTK if KVM is configured to emulate * accesses to reserved GPAs, as KVM's emulator doesn't support IBT or * SHSTK, nor does KVM handle Shadow Stack #PFs (see above). */ if (allow_smaller_maxphyaddr) { kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); } if (boot_cpu_has(X86_FEATURE_AMD_IBPB_RET) && boot_cpu_has(X86_FEATURE_AMD_IBPB) && boot_cpu_has(X86_FEATURE_AMD_IBRS)) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL); if (boot_cpu_has(X86_FEATURE_STIBP)) kvm_cpu_cap_set(X86_FEATURE_INTEL_STIBP); if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_init(CPUID_7_1_EAX, F(SHA512), F(SM3), F(SM4), F(AVX_VNNI), F(AVX512_BF16), F(CMPCCXADD), F(FZRM), F(FSRS), F(FSRC), F(WRMSRNS), X86_64_F(LKGS), F(AMX_FP16), F(AVX_IFMA), F(LAM), F(MOVRS), ); kvm_cpu_cap_init(CPUID_7_1_ECX, SCATTERED_F(MSR_IMM), ); kvm_cpu_cap_init(CPUID_7_1_EDX, F(AVX_VNNI_INT8), F(AVX_NE_CONVERT), F(AMX_COMPLEX), F(AVX_VNNI_INT16), F(PREFETCHITI), F(AVX10), ); kvm_cpu_cap_init(CPUID_7_2_EDX, F(INTEL_PSFD), F(IPRED_CTRL), F(RRSBA_CTRL), F(DDPD_U), F(BHI_CTRL), F(MCDT_NO), ); kvm_cpu_cap_init(CPUID_D_1_EAX, F(XSAVEOPT), F(XSAVEC), F(XGETBV1), F(XSAVES), X86_64_F(XFD), ); kvm_cpu_cap_init(CPUID_12_EAX, SCATTERED_F(SGX1), SCATTERED_F(SGX2), SCATTERED_F(SGX_EDECCSSA), ); kvm_cpu_cap_init(CPUID_1E_1_EAX, F(AMX_INT8_ALIAS), F(AMX_BF16_ALIAS), F(AMX_COMPLEX_ALIAS), F(AMX_FP16_ALIAS), F(AMX_FP8), F(AMX_TF32), F(AMX_AVX512), F(AMX_MOVRS), ); kvm_cpu_cap_init(CPUID_24_0_EBX, F(AVX10_128), F(AVX10_256), F(AVX10_512), ); kvm_cpu_cap_init(CPUID_24_1_ECX, F(AVX10_VNNI_INT), ); kvm_cpu_cap_init(CPUID_8000_0001_ECX, F(LAHF_LM), F(CMP_LEGACY), VENDOR_F(SVM), /* ExtApicSpace */ F(CR8_LEGACY), F(ABM), F(SSE4A), F(MISALIGNSSE), F(3DNOWPREFETCH), F(OSVW), /* IBS */ F(XOP), /* SKINIT, WDT, LWP */ F(FMA4), F(TBM), F(TOPOEXT), VENDOR_F(PERFCTR_CORE), ); kvm_cpu_cap_init(CPUID_8000_0001_EDX, ALIASED_1_EDX_F(FPU), ALIASED_1_EDX_F(VME), ALIASED_1_EDX_F(DE), ALIASED_1_EDX_F(PSE), ALIASED_1_EDX_F(TSC), ALIASED_1_EDX_F(MSR), ALIASED_1_EDX_F(PAE), ALIASED_1_EDX_F(MCE), ALIASED_1_EDX_F(CX8), ALIASED_1_EDX_F(APIC), /* Reserved */ F(SYSCALL), ALIASED_1_EDX_F(MTRR), ALIASED_1_EDX_F(PGE), ALIASED_1_EDX_F(MCA), ALIASED_1_EDX_F(CMOV), ALIASED_1_EDX_F(PAT), ALIASED_1_EDX_F(PSE36), /* Reserved */ F(NX), /* Reserved */ F(MMXEXT), ALIASED_1_EDX_F(MMX), ALIASED_1_EDX_F(FXSR), F(FXSR_OPT), X86_64_F(GBPAGES), F(RDTSCP), /* Reserved */ X86_64_F(LM), F(3DNOWEXT), F(3DNOW), ); if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); kvm_cpu_cap_init(CPUID_8000_0007_EDX, SCATTERED_F(CONSTANT_TSC), ); kvm_cpu_cap_init(CPUID_8000_0008_EBX, F(CLZERO), F(XSAVEERPTR), F(WBNOINVD), F(AMD_IBPB), F(AMD_IBRS), F(AMD_SSBD), F(VIRT_SSBD), F(AMD_SSB_NO), F(AMD_STIBP), F(AMD_STIBP_ALWAYS_ON), F(AMD_IBRS_SAME_MODE), PASSTHROUGH_F(EFER_LMSLE_MBZ), F(AMD_PSFD), F(AMD_IBPB_RET), ); /* * AMD has separate bits for each SPEC_CTRL bit. * arch/x86/kernel/cpu/bugs.c is kind enough to * record that in cpufeatures so use them. */ if (boot_cpu_has(X86_FEATURE_IBPB)) { kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB); if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) && !boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB_RET); } if (boot_cpu_has(X86_FEATURE_IBRS)) kvm_cpu_cap_set(X86_FEATURE_AMD_IBRS); if (boot_cpu_has(X86_FEATURE_STIBP)) kvm_cpu_cap_set(X86_FEATURE_AMD_STIBP); if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) kvm_cpu_cap_set(X86_FEATURE_AMD_SSBD); if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) kvm_cpu_cap_set(X86_FEATURE_AMD_SSB_NO); /* * The preference is to use SPEC CTRL MSR instead of the * VIRT_SPEC MSR. */ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && !boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); /* All SVM features required additional vendor module enabling. */ kvm_cpu_cap_init(CPUID_8000_000A_EDX, VENDOR_F(NPT), VENDOR_F(VMCBCLEAN), VENDOR_F(FLUSHBYASID), VENDOR_F(NRIPS), VENDOR_F(TSCRATEMSR), VENDOR_F(V_VMSAVE_VMLOAD), VENDOR_F(LBRV), VENDOR_F(PAUSEFILTER), VENDOR_F(PFTHRESHOLD), VENDOR_F(VGIF), VENDOR_F(VNMI), VENDOR_F(SVME_ADDR_CHK), ); kvm_cpu_cap_init(CPUID_8000_001F_EAX, VENDOR_F(SME), VENDOR_F(SEV), /* VM_PAGE_FLUSH */ VENDOR_F(SEV_ES), F(SME_COHERENT), ); kvm_cpu_cap_init(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP), F(WRMSR_XX_BASE_NS), /* * Synthesize "LFENCE is serializing" into the AMD-defined entry * in KVM's supported CPUID, i.e. if the feature is reported as * supported by the kernel. LFENCE_RDTSC was a Linux-defined * synthetic feature long before AMD joined the bandwagon, e.g. * LFENCE is serializing on most CPUs that support SSE2. On * CPUs that don't support AMD's leaf, ANDing with the raw host * CPUID will drop the flags, and reporting support in AMD's * leaf can make it easier for userspace to detect the feature. */ SYNTHESIZED_F(LFENCE_RDTSC), /* SmmPgCfgLock */ /* 4: Resv */ SYNTHESIZED_F(VERW_CLEAR), F(NULL_SEL_CLR_BASE), /* UpperAddressIgnore */ F(AUTOIBRS), EMULATED_F(NO_SMM_CTL_MSR), /* PrefetchCtlMsr */ EMULATED_F(GP_ON_USER_CPUID), /* EPSF */ F(PREFETCHI), F(AVX512_BMM), F(ERAPS), SYNTHESIZED_F(SBPB), SYNTHESIZED_F(IBPB_BRTYPE), SYNTHESIZED_F(SRSO_NO), F(SRSO_USER_KERNEL_NO), ); kvm_cpu_cap_init(CPUID_8000_0021_ECX, SYNTHESIZED_F(TSA_SQ_NO), SYNTHESIZED_F(TSA_L1_NO), ); kvm_cpu_cap_init(CPUID_8000_0022_EAX, F(PERFMON_V2), ); if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) kvm_cpu_cap_set(X86_FEATURE_NULL_SEL_CLR_BASE); kvm_cpu_cap_init(CPUID_C000_0001_EDX, F(SM2), F(SM2_EN), F(XSTORE), F(XSTORE_EN), F(CCS), F(CCS_EN), F(XCRYPT), F(XCRYPT_EN), F(ACE2), F(ACE2_EN), F(PHE), F(PHE_EN), F(PMM), F(PMM_EN), F(RNG2), F(RNG2_EN), F(PHE2), F(PHE2_EN), F(RSA), F(RSA_EN), ); /* * Hide RDTSCP and RDPID if either feature is reported as supported but * probing MSR_TSC_AUX failed. This is purely a sanity check and * should never happen, but the guest will likely crash if RDTSCP or * RDPID is misreported, and KVM has botched MSR_TSC_AUX emulation in * the past. For example, the sanity check may fire if this instance of * KVM is running as L1 on top of an older, broken KVM. */ if (WARN_ON((kvm_cpu_cap_has(X86_FEATURE_RDTSCP) || kvm_cpu_cap_has(X86_FEATURE_RDPID)) && !kvm_is_supported_user_return_msr(MSR_TSC_AUX))) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); kvm_cpu_cap_clear(X86_FEATURE_RDPID); } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_initialize_cpu_caps); #undef F #undef SCATTERED_F #undef X86_64_F #undef EMULATED_F #undef SYNTHESIZED_F #undef PASSTHROUGH_F #undef ALIASED_1_EDX_F #undef VENDOR_F #undef RUNTIME_F struct kvm_cpuid_array { struct kvm_cpuid_entry2 *entries; int maxnent; int nent; }; static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array) { if (array->nent >= array->maxnent) return NULL; return &array->entries[array->nent++]; } static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, u32 function, u32 index) { struct kvm_cpuid_entry2 *entry = get_next_cpuid(array); if (!entry) return NULL; memset(entry, 0, sizeof(*entry)); entry->function = function; entry->index = index; switch (function & 0xC0000000) { case 0x40000000: /* Hypervisor leaves are always synthesized by __do_cpuid_func. */ return entry; case 0x80000000: /* * 0x80000021 is sometimes synthesized by __do_cpuid_func, which * would result in out-of-bounds calls to do_host_cpuid. */ { static int max_cpuid_80000000; if (!READ_ONCE(max_cpuid_80000000)) WRITE_ONCE(max_cpuid_80000000, cpuid_eax(0x80000000)); if (function > READ_ONCE(max_cpuid_80000000)) return entry; } break; default: break; } cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); if (cpuid_function_is_indexed(function)) entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; return entry; } static int cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, u32 func, u32 index, bool include_partially_emulated) { memset(entry, 0, sizeof(*entry)); /* KVM doesn't currently emulate any non-zero indices. */ if (cpuid_function_is_indexed(func) && index) return 0; entry->function = func; entry->index = 0; entry->flags = 0; switch (func) { case 0: entry->eax = 7; return 1; case 1: entry->ecx = feature_bit(MOVBE); /* * KVM allows userspace to enumerate MONITOR+MWAIT support to * the guest, but the MWAIT feature flag is never advertised * to userspace because MONITOR+MWAIT aren't virtualized by * hardware, can't be faithfully emulated in software (KVM * emulates them as NOPs), and allowing the guest to execute * them natively requires enabling a per-VM capability. */ if (include_partially_emulated) entry->ecx |= feature_bit(MWAIT); return 1; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) entry->ecx = feature_bit(RDPID); return 1; default: return 0; } } static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) { if (array->nent >= array->maxnent) return -E2BIG; array->nent += cpuid_func_emulated(&array->entries[array->nent], func, 0, false); return 0; } static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) { struct kvm_cpuid_entry2 *entry; int r, i, max_idx; /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); r = -E2BIG; entry = do_host_cpuid(array, function, 0); if (!entry) goto out; switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ entry->eax = min(entry->eax, 0x24U); break; case 1: cpuid_entry_override(entry, CPUID_1_EDX); cpuid_entry_override(entry, CPUID_1_ECX); break; case 2: /* * On ancient CPUs, function 2 entries are STATEFUL. That is, * CPUID(function=2, index=0) may return different results each * time, with the least-significant byte in EAX enumerating the * number of times software should do CPUID(2, 0). * * Modern CPUs, i.e. every CPU KVM has *ever* run on are less * idiotic. Intel's SDM states that EAX & 0xff "will always * return 01H. Software should ignore this value and not * interpret it as an informational descriptor", while AMD's * APM states that CPUID(2) is reserved. * * WARN if a frankenstein CPU that supports virtualization and * a stateful CPUID.0x2 is encountered. */ WARN_ON_ONCE((entry->eax & 0xff) > 1); break; /* functions 4 and 0x8000001d have additional index. */ case 4: case 0x8000001d: /* * Read entries until the cache type in the previous entry is * zero, i.e. indicates an invalid entry. */ for (i = 1; entry->eax & 0x1f; ++i) { entry = do_host_cpuid(array, function, i); if (!entry) goto out; } break; case 6: /* Thermal management */ entry->eax = 0x4; /* allow ARAT */ entry->ebx = 0; entry->ecx = 0; entry->edx = 0; break; /* function 7 has additional index. */ case 7: max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); /* KVM only supports up to 0x7.2, capped above via min(). */ if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; cpuid_entry_override(entry, CPUID_7_1_EAX); cpuid_entry_override(entry, CPUID_7_1_ECX); cpuid_entry_override(entry, CPUID_7_1_EDX); entry->ebx = 0; } if (max_idx >= 2) { entry = do_host_cpuid(array, function, 2); if (!entry) goto out; cpuid_entry_override(entry, CPUID_7_2_EDX); entry->ecx = 0; entry->ebx = 0; entry->eax = 0; } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax = { }; union cpuid10_edx edx = { }; if (!enable_pmu || !cpu_feature_enabled(X86_FEATURE_ARCH_PERFMON)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } eax.split.version_id = kvm_pmu_cap.version; eax.split.num_counters = kvm_pmu_cap.num_counters_gp; eax.split.bit_width = kvm_pmu_cap.bit_width_gp; eax.split.mask_length = kvm_pmu_cap.events_mask_len; edx.split.num_counters_fixed = kvm_pmu_cap.num_counters_fixed; edx.split.bit_width_fixed = kvm_pmu_cap.bit_width_fixed; if (kvm_pmu_cap.version) edx.split.anythread_deprecated = 1; entry->eax = eax.full; entry->ebx = kvm_pmu_cap.events_mask; entry->ecx = 0; entry->edx = edx.full; break; } case 0x1f: case 0xb: /* * No topology; a valid topology is indicated by the presence * of subleaf 1. */ entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { u64 permitted_xcr0 = kvm_get_filtered_xcr0(); u64 permitted_xss = kvm_caps.supported_xss; entry->eax &= permitted_xcr0; entry->ebx = xstate_required_size(permitted_xcr0, false); entry->ecx = entry->ebx; entry->edx &= permitted_xcr0 >> 32; if (!permitted_xcr0) break; entry = do_host_cpuid(array, function, 1); if (!entry) goto out; cpuid_entry_override(entry, CPUID_D_1_EAX); if (entry->eax & (feature_bit(XSAVES) | feature_bit(XSAVEC))) entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { WARN_ON_ONCE(permitted_xss != 0); entry->ebx = 0; } entry->ecx &= permitted_xss; entry->edx &= permitted_xss >> 32; for (i = 2; i < 64; ++i) { bool s_state; if (permitted_xcr0 & BIT_ULL(i)) s_state = false; else if (permitted_xss & BIT_ULL(i)) s_state = true; else continue; entry = do_host_cpuid(array, function, i); if (!entry) goto out; /* * The supported check above should have filtered out * invalid sub-leafs. Only valid sub-leafs should * reach this point, and they should have a non-zero * save state size. Furthermore, check whether the * processor agrees with permitted_xcr0/permitted_xss * on whether this is an XCR0- or IA32_XSS-managed area. */ if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { --array->nent; continue; } if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) entry->ecx &= ~BIT_ULL(2); entry->edx = 0; } break; } case 0x12: /* Intel SGX */ if (!kvm_cpu_cap_has(X86_FEATURE_SGX)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } /* * Index 0: Sub-features, MISCSELECT (a.k.a extended features) * and max enclave sizes. The SGX sub-features and MISCSELECT * are restricted by kernel and KVM capabilities (like most * feature flags), while enclave size is unrestricted. */ cpuid_entry_override(entry, CPUID_12_EAX); entry->ebx &= SGX_MISC_EXINFO; entry = do_host_cpuid(array, function, 1); if (!entry) goto out; /* * Index 1: SECS.ATTRIBUTES. ATTRIBUTES are restricted a la * feature flags. Advertise all supported flags, including * privileged attributes that require explicit opt-in from * userspace. ATTRIBUTES.XFRM is not adjusted as userspace is * expected to derive it from supported XCR0. */ entry->eax &= SGX_ATTR_PRIV_MASK | SGX_ATTR_UNPRIV_MASK; entry->ebx &= 0; break; /* Intel PT */ case 0x14: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { if (!do_host_cpuid(array, function, i)) goto out; } break; /* Intel AMX TILE */ case 0x1d: if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } for (i = 1, max_idx = entry->eax; i <= max_idx; ++i) { if (!do_host_cpuid(array, function, i)) goto out; } break; case 0x1e: /* TMUL information */ if (!kvm_cpu_cap_has(X86_FEATURE_AMX_TILE)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } max_idx = entry->eax = min(entry->eax, 1u); /* KVM only supports up to 0x1e.0x1, capped above via min(). */ if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; cpuid_entry_override(entry, CPUID_1E_1_EAX); entry->ebx = 0; entry->ecx = 0; entry->edx = 0; } break; case 0x24: { u8 avx10_version; if (!kvm_cpu_cap_has(X86_FEATURE_AVX10)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } max_idx = entry->eax = min(entry->eax, 1u); /* * The AVX10 version is encoded in EBX[7:0]. Note, the version * is guaranteed to be >=1 if AVX10 is supported. Note #2, the * version needs to be captured before overriding EBX features! */ avx10_version = min_t(u8, entry->ebx & 0xff, 2); cpuid_entry_override(entry, CPUID_24_0_EBX); entry->ebx |= avx10_version; entry->ecx = 0; entry->edx = 0; /* KVM only supports up to 0x24.0x1, capped above via min(). */ if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; cpuid_entry_override(entry, CPUID_24_1_ECX); entry->eax = 0; entry->ebx = 0; entry->edx = 0; } break; } case KVM_CPUID_SIGNATURE: { const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; entry->ebx = sigptr[0]; entry->ecx = sigptr[1]; entry->edx = sigptr[2]; break; } case KVM_CPUID_FEATURES: entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | (1 << KVM_FEATURE_NOP_IO_DELAY) | (1 << KVM_FEATURE_CLOCKSOURCE2) | (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | (1 << KVM_FEATURE_PV_TLB_FLUSH) | (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) | (1 << KVM_FEATURE_PV_SEND_IPI) | (1 << KVM_FEATURE_POLL_CONTROL) | (1 << KVM_FEATURE_PV_SCHED_YIELD) | (1 << KVM_FEATURE_ASYNC_PF_INT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); entry->ebx = 0; entry->ecx = 0; entry->edx = 0; break; case 0x80000000: entry->eax = min(entry->eax, 0x80000022); /* * Serializing LFENCE is reported in a multitude of ways, and * NullSegClearsBase is not reported in CPUID on Zen2; help * userspace by providing the CPUID leaf ourselves. * * However, only do it if the host has CPUID leaf 0x8000001d. * QEMU thinks that it can query the host blindly for that * CPUID leaf if KVM reports that it supports 0x8000001d or * above. The processor merrily returns values from the * highest Intel leaf which QEMU tries to use as the guest's * 0x8000001d. Even worse, this can result in an infinite * loop if said highest leaf has no subleaves indexed by ECX. */ if (entry->eax >= 0x8000001d && (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC) || !static_cpu_has_bug(X86_BUG_NULL_SEG))) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000005: /* Pass host L1 cache and TLB info. */ break; case 0x80000006: /* Drop reserved bits, pass host L2 cache and TLB info. */ entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ cpuid_entry_override(entry, CPUID_8000_0007_EDX); /* mask against host */ entry->edx &= boot_cpu_data.x86_power; entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { /* * GuestPhysAddrSize (EAX[23:16]) is intended for software * use. * * KVM's ABI is to report the effective MAXPHYADDR for the * guest in PhysAddrSize (phys_as), and the maximum * *addressable* GPA in GuestPhysAddrSize (g_phys_as). * * GuestPhysAddrSize is valid if and only if TDP is enabled, * in which case the max GPA that can be addressed by KVM may * be less than the max GPA that can be legally generated by * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't * support 5-level TDP. */ unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); unsigned int phys_as, g_phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as * the guest operates in the same PA space as the host, i.e. * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * * If TDP is enabled, use the raw bare metal MAXPHYADDR as * reductions to the HPAs do not affect GPAs. The max * addressable GPA is the same as the max effective GPA, except * that it's capped at 48 bits if 5-level TDP isn't supported * (hardware processes bits 51:48 only when walking the fifth * level page table). */ if (!tdp_enabled) { phys_as = boot_cpu_data.x86_phys_bits; g_phys_as = 0; } else { phys_as = entry->eax & 0xff; g_phys_as = phys_as; if (kvm_mmu_get_max_tdp_level() < 5) g_phys_as = min(g_phys_as, 48U); } entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; } case 0x8000000A: if (!kvm_cpu_cap_has(X86_FEATURE_SVM)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } entry->eax = 1; /* SVM revision 1 */ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper ASID emulation to nested SVM */ entry->ecx = 0; /* Reserved */ cpuid_entry_override(entry, CPUID_8000_000A_EDX); break; case 0x80000019: entry->ecx = entry->edx = 0; break; case 0x8000001a: entry->eax &= GENMASK(2, 0); entry->ebx = entry->ecx = entry->edx = 0; break; case 0x8000001e: /* Do not return host topology information. */ entry->eax = entry->ebx = entry->ecx = 0; entry->edx = 0; /* reserved */ break; case 0x8000001F: if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); /* Clear NumVMPL since KVM does not support VMPL. */ entry->ebx &= ~GENMASK(31, 12); /* * Enumerate '0' for "PA bits reduction", the adjusted * MAXPHYADDR is enumerated directly (see 0x80000008). */ entry->ebx &= ~GENMASK(11, 6); } break; case 0x80000020: entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; case 0x80000021: entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0021_EAX); if (kvm_cpu_cap_has(X86_FEATURE_ERAPS)) entry->ebx &= GENMASK(23, 16); else entry->ebx = 0; cpuid_entry_override(entry, CPUID_8000_0021_ECX); break; /* AMD Extended Performance Monitoring and Debug */ case 0x80000022: { union cpuid_0x80000022_ebx ebx = { }; entry->ecx = entry->edx = 0; if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) { entry->eax = entry->ebx = 0; break; } cpuid_entry_override(entry, CPUID_8000_0022_EAX); ebx.split.num_core_pmc = kvm_pmu_cap.num_counters_gp; entry->ebx = ebx.full; break; } /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ entry->eax = min(entry->eax, 0xC0000004); break; case 0xC0000001: cpuid_entry_override(entry, CPUID_C000_0001_EDX); break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ case 0xC0000002: case 0xC0000003: case 0xC0000004: default: entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } r = 0; out: put_cpu(); return r; } static int do_cpuid_func(struct kvm_cpuid_array *array, u32 func, unsigned int type) { if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_func_emulated(array, func); return __do_cpuid_func(array, func); } #define CENTAUR_CPUID_SIGNATURE 0xC0000000 static int get_cpuid_func(struct kvm_cpuid_array *array, u32 func, unsigned int type) { u32 limit; int r; if (func == CENTAUR_CPUID_SIGNATURE && boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR && boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 0; r = do_cpuid_func(array, func, type); if (r) return r; limit = array->entries[array->nent - 1].eax; for (func = func + 1; func <= limit; ++func) { r = do_cpuid_func(array, func, type); if (r) break; } return r; } static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, __u32 num_entries, unsigned int ioctl_type) { int i; __u32 pad[3]; if (ioctl_type != KVM_GET_EMULATED_CPUID) return false; /* * We want to make sure that ->padding is being passed clean from * userspace in case we want to use it for something in the future. * * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we * have to give ourselves satisfied only with the emulated side. /me * sheds a tear. */ for (i = 0; i < num_entries; i++) { if (copy_from_user(pad, entries[i].padding, sizeof(pad))) return true; if (pad[0] || pad[1] || pad[2]) return true; } return false; } int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries, unsigned int type) { static const u32 funcs[] = { 0, 0x80000000, CENTAUR_CPUID_SIGNATURE, KVM_CPUID_SIGNATURE, }; struct kvm_cpuid_array array = { .nent = 0, }; int r, i; if (cpuid->nent < 1) return -E2BIG; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; array.entries = kvzalloc_objs(struct kvm_cpuid_entry2, cpuid->nent); if (!array.entries) return -ENOMEM; array.maxnent = cpuid->nent; for (i = 0; i < ARRAY_SIZE(funcs); i++) { r = get_cpuid_func(&array, funcs[i], type); if (r) goto out_free; } cpuid->nent = array.nent; if (copy_to_user(entries, array.entries, array.nent * sizeof(struct kvm_cpuid_entry2))) r = -EFAULT; out_free: kvfree(array.entries); return r; } /* * Intel CPUID semantics treats any query for an out-of-range leaf as if the * highest basic leaf (i.e. CPUID.0H:EAX) were requested. AMD CPUID semantics * returns all zeroes for any undefined leaf, whether or not the leaf is in * range. Centaur/VIA follows Intel semantics. * * A leaf is considered out-of-range if its function is higher than the maximum * supported leaf of its associated class or if its associated class does not * exist. * * There are three primary classes to be considered, with their respective * ranges described as "<base> - <top>[,<base2> - <top2>] inclusive. A primary * class exists if a guest CPUID entry for its <base> leaf exists. For a given * class, CPUID.<base>.EAX contains the max supported leaf for the class. * * - Basic: 0x00000000 - 0x3fffffff, 0x50000000 - 0x7fffffff * - Hypervisor: 0x40000000 - 0x4fffffff * - Extended: 0x80000000 - 0xbfffffff * - Centaur: 0xc0000000 - 0xcfffffff * * The Hypervisor class is further subdivided into sub-classes that each act as * their own independent class associated with a 0x100 byte range. E.g. if Qemu * is advertising support for both HyperV and KVM, the resulting Hypervisor * CPUID sub-classes are: * * - HyperV: 0x40000000 - 0x400000ff * - KVM: 0x40000100 - 0x400001ff */ static struct kvm_cpuid_entry2 * get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) { struct kvm_cpuid_entry2 *basic, *class; u32 function = *fn_ptr; basic = kvm_find_cpuid_entry(vcpu, 0); if (!basic) return NULL; if (is_guest_vendor_amd(basic->ebx, basic->ecx, basic->edx) || is_guest_vendor_hygon(basic->ebx, basic->ecx, basic->edx)) return NULL; if (function >= 0x40000000 && function <= 0x4fffffff) class = kvm_find_cpuid_entry(vcpu, function & 0xffffff00); else if (function >= 0xc0000000) class = kvm_find_cpuid_entry(vcpu, 0xc0000000); else class = kvm_find_cpuid_entry(vcpu, function & 0x80000000); if (class && function <= class->eax) return NULL; /* * Leaf specific adjustments are also applied when redirecting to the * max basic entry, e.g. if the max basic leaf is 0xb but there is no * entry for CPUID.0xb.index (see below), then the output value for EDX * needs to be pulled from CPUID.0xb.1. */ *fn_ptr = basic->eax; /* * The class does not exist or the requested function is out of range; * the effective CPUID entry is the max basic leaf. Note, the index of * the original requested leaf is observed! */ return kvm_find_cpuid_entry_index(vcpu, basic->eax, index); } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only) { u32 orig_function = *eax, function = *eax, index = *ecx; struct kvm_cpuid_entry2 *entry; bool exact, used_max_basic = false; if (vcpu->arch.cpuid_dynamic_bits_dirty) kvm_update_cpuid_runtime(vcpu); entry = kvm_find_cpuid_entry_index(vcpu, function, index); exact = !!entry; if (!entry && !exact_only) { entry = get_out_of_range_cpuid_entry(vcpu, &function, index); used_max_basic = !!entry; } if (entry) { *eax = entry->eax; *ebx = entry->ebx; *ecx = entry->ecx; *edx = entry->edx; if (function == 7 && index == 0) { u64 data; if ((*ebx & (feature_bit(RTM) | feature_bit(HLE))) && !kvm_msr_read(vcpu, MSR_IA32_TSX_CTRL, &data) && (data & TSX_CTRL_CPUID_CLEAR)) *ebx &= ~(feature_bit(RTM) | feature_bit(HLE)); } else if (function == 0x80000007) { if (kvm_hv_invtsc_suppressed(vcpu)) *edx &= ~feature_bit(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; /* * When leaf 0BH or 1FH is defined, CL is pass-through * and EDX is always the x2APIC ID, even for undefined * subleaves. Index 1 will exist iff the leaf is * implemented, so we pass through CL iff leaf 1 * exists. EDX can be copied from any existing index. */ if (function == 0xb || function == 0x1f) { entry = kvm_find_cpuid_entry_index(vcpu, function, 1); if (entry) { *ecx = index & 0xff; *edx = entry->edx; } } } trace_kvm_cpuid(orig_function, index, *eax, *ebx, *ecx, *edx, exact, used_max_basic); return exact; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_cpuid); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu) { u32 eax, ebx, ecx, edx; if (!kvm_is_cpuid_allowed(vcpu)) { kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return 1; } eax = kvm_eax_read(vcpu); ecx = kvm_ecx_read(vcpu); kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, false); kvm_eax_write(vcpu, eax); kvm_ebx_write(vcpu, ebx); kvm_ecx_write(vcpu, ecx); kvm_edx_write(vcpu, edx); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_cpuid); |
| 2787 33 923 2736 1860 1859 3398 2085 2866 576 1553 737 1218 2179 923 2034 4175 4177 3756 1873 949 1768 1942 | 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 */ |
| 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 | /* SPDX-License-Identifier: ISC */ /* * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018, The Linux Foundation. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef _HTT_H_ #define _HTT_H_ #include <linux/bug.h> #include <linux/interrupt.h> #include <linux/dmapool.h> #include <linux/hashtable.h> #include <linux/kfifo.h> #include <net/mac80211.h> #include "htc.h" #include "hw.h" #include "rx_desc.h" enum htt_dbg_stats_type { HTT_DBG_STATS_WAL_PDEV_TXRX = 1 << 0, HTT_DBG_STATS_RX_REORDER = 1 << 1, HTT_DBG_STATS_RX_RATE_INFO = 1 << 2, HTT_DBG_STATS_TX_PPDU_LOG = 1 << 3, HTT_DBG_STATS_TX_RATE_INFO = 1 << 4, /* bits 5-23 currently reserved */ HTT_DBG_NUM_STATS /* keep this last */ }; enum htt_h2t_msg_type { /* host-to-target */ HTT_H2T_MSG_TYPE_VERSION_REQ = 0, HTT_H2T_MSG_TYPE_TX_FRM = 1, HTT_H2T_MSG_TYPE_RX_RING_CFG = 2, HTT_H2T_MSG_TYPE_STATS_REQ = 3, HTT_H2T_MSG_TYPE_SYNC = 4, HTT_H2T_MSG_TYPE_AGGR_CFG = 5, HTT_H2T_MSG_TYPE_FRAG_DESC_BANK_CFG = 6, /* This command is used for sending management frames in HTT < 3.0. * HTT >= 3.0 uses TX_FRM for everything. */ HTT_H2T_MSG_TYPE_MGMT_TX = 7, HTT_H2T_MSG_TYPE_TX_FETCH_RESP = 11, HTT_H2T_NUM_MSGS /* keep this last */ }; struct htt_cmd_hdr { u8 msg_type; } __packed; struct htt_ver_req { u8 pad[sizeof(u32) - sizeof(struct htt_cmd_hdr)]; } __packed; /* * HTT tx MSDU descriptor * * The HTT tx MSDU descriptor is created by the host HTT SW for each * tx MSDU. The HTT tx MSDU descriptor contains the information that * the target firmware needs for the FW's tx processing, particularly * for creating the HW msdu descriptor. * The same HTT tx descriptor is used for HL and LL systems, though * a few fields within the tx descriptor are used only by LL or * only by HL. * The HTT tx descriptor is defined in two manners: by a struct with * bitfields, and by a series of [dword offset, bit mask, bit shift] * definitions. * The target should use the struct def, for simplicity and clarity, * but the host shall use the bit-mast + bit-shift defs, to be endian- * neutral. Specifically, the host shall use the get/set macros built * around the mask + shift defs. */ struct htt_data_tx_desc_frag { union { struct double_word_addr { __le32 paddr; __le32 len; } __packed dword_addr; struct triple_word_addr { __le32 paddr_lo; __le16 paddr_hi; __le16 len_16; } __packed tword_addr; } __packed; } __packed; struct htt_msdu_ext_desc { __le32 tso_flag[3]; __le16 ip_identification; u8 flags; u8 reserved; struct htt_data_tx_desc_frag frags[6]; }; struct htt_msdu_ext_desc_64 { __le32 tso_flag[5]; __le16 ip_identification; u8 flags; u8 reserved; struct htt_data_tx_desc_frag frags[6]; }; #define HTT_MSDU_EXT_DESC_FLAG_IPV4_CSUM_ENABLE BIT(0) #define HTT_MSDU_EXT_DESC_FLAG_UDP_IPV4_CSUM_ENABLE BIT(1) #define HTT_MSDU_EXT_DESC_FLAG_UDP_IPV6_CSUM_ENABLE BIT(2) #define HTT_MSDU_EXT_DESC_FLAG_TCP_IPV4_CSUM_ENABLE BIT(3) #define HTT_MSDU_EXT_DESC_FLAG_TCP_IPV6_CSUM_ENABLE BIT(4) #define HTT_MSDU_CHECKSUM_ENABLE (HTT_MSDU_EXT_DESC_FLAG_IPV4_CSUM_ENABLE \ | HTT_MSDU_EXT_DESC_FLAG_UDP_IPV4_CSUM_ENABLE \ | HTT_MSDU_EXT_DESC_FLAG_UDP_IPV6_CSUM_ENABLE \ | HTT_MSDU_EXT_DESC_FLAG_TCP_IPV4_CSUM_ENABLE \ | HTT_MSDU_EXT_DESC_FLAG_TCP_IPV6_CSUM_ENABLE) #define HTT_MSDU_EXT_DESC_FLAG_IPV4_CSUM_ENABLE_64 BIT(16) #define HTT_MSDU_EXT_DESC_FLAG_UDP_IPV4_CSUM_ENABLE_64 BIT(17) #define HTT_MSDU_EXT_DESC_FLAG_UDP_IPV6_CSUM_ENABLE_64 BIT(18) #define HTT_MSDU_EXT_DESC_FLAG_TCP_IPV4_CSUM_ENABLE_64 BIT(19) #define HTT_MSDU_EXT_DESC_FLAG_TCP_IPV6_CSUM_ENABLE_64 BIT(20) #define HTT_MSDU_EXT_DESC_FLAG_PARTIAL_CSUM_ENABLE_64 BIT(21) #define HTT_MSDU_CHECKSUM_ENABLE_64 (HTT_MSDU_EXT_DESC_FLAG_IPV4_CSUM_ENABLE_64 \ | HTT_MSDU_EXT_DESC_FLAG_UDP_IPV4_CSUM_ENABLE_64 \ | HTT_MSDU_EXT_DESC_FLAG_UDP_IPV6_CSUM_ENABLE_64 \ | HTT_MSDU_EXT_DESC_FLAG_TCP_IPV4_CSUM_ENABLE_64 \ | HTT_MSDU_EXT_DESC_FLAG_TCP_IPV6_CSUM_ENABLE_64) enum htt_data_tx_desc_flags0 { HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT = 1 << 0, HTT_DATA_TX_DESC_FLAGS0_NO_AGGR = 1 << 1, HTT_DATA_TX_DESC_FLAGS0_NO_ENCRYPT = 1 << 2, HTT_DATA_TX_DESC_FLAGS0_NO_CLASSIFY = 1 << 3, HTT_DATA_TX_DESC_FLAGS0_RSVD0 = 1 << 4 #define HTT_DATA_TX_DESC_FLAGS0_PKT_TYPE_MASK 0xE0 #define HTT_DATA_TX_DESC_FLAGS0_PKT_TYPE_LSB 5 }; enum htt_data_tx_desc_flags1 { #define HTT_DATA_TX_DESC_FLAGS1_VDEV_ID_BITS 6 #define HTT_DATA_TX_DESC_FLAGS1_VDEV_ID_MASK 0x003F #define HTT_DATA_TX_DESC_FLAGS1_VDEV_ID_LSB 0 #define HTT_DATA_TX_DESC_FLAGS1_EXT_TID_BITS 5 #define HTT_DATA_TX_DESC_FLAGS1_EXT_TID_MASK 0x07C0 #define HTT_DATA_TX_DESC_FLAGS1_EXT_TID_LSB 6 HTT_DATA_TX_DESC_FLAGS1_POSTPONED = 1 << 11, HTT_DATA_TX_DESC_FLAGS1_MORE_IN_BATCH = 1 << 12, HTT_DATA_TX_DESC_FLAGS1_CKSUM_L3_OFFLOAD = 1 << 13, HTT_DATA_TX_DESC_FLAGS1_CKSUM_L4_OFFLOAD = 1 << 14, HTT_DATA_TX_DESC_FLAGS1_TX_COMPLETE = 1 << 15 }; #define HTT_TX_CREDIT_DELTA_ABS_M 0xffff0000 #define HTT_TX_CREDIT_DELTA_ABS_S 16 #define HTT_TX_CREDIT_DELTA_ABS_GET(word) \ (((word) & HTT_TX_CREDIT_DELTA_ABS_M) >> HTT_TX_CREDIT_DELTA_ABS_S) #define HTT_TX_CREDIT_SIGN_BIT_M 0x00000100 #define HTT_TX_CREDIT_SIGN_BIT_S 8 #define HTT_TX_CREDIT_SIGN_BIT_GET(word) \ (((word) & HTT_TX_CREDIT_SIGN_BIT_M) >> HTT_TX_CREDIT_SIGN_BIT_S) enum htt_data_tx_ext_tid { HTT_DATA_TX_EXT_TID_NON_QOS_MCAST_BCAST = 16, HTT_DATA_TX_EXT_TID_MGMT = 17, HTT_DATA_TX_EXT_TID_INVALID = 31 }; #define HTT_INVALID_PEERID 0xFFFF /* * htt_data_tx_desc - used for data tx path * * Note: vdev_id irrelevant for pkt_type == raw and no_classify == 1. * ext_tid: for qos-data frames (0-15), see %HTT_DATA_TX_EXT_TID_ * for special kinds of tids * postponed: only for HL hosts. indicates if this is a resend * (HL hosts manage queues on the host ) * more_in_batch: only for HL hosts. indicates if more packets are * pending. this allows target to wait and aggregate * freq: 0 means home channel of given vdev. intended for offchannel */ struct htt_data_tx_desc { u8 flags0; /* %HTT_DATA_TX_DESC_FLAGS0_ */ __le16 flags1; /* %HTT_DATA_TX_DESC_FLAGS1_ */ __le16 len; __le16 id; __le32 frags_paddr; union { __le32 peerid; struct { __le16 peerid; __le16 freq; } __packed offchan_tx; } __packed; u8 prefetch[0]; /* start of frame, for FW classification engine */ } __packed; struct htt_data_tx_desc_64 { u8 flags0; /* %HTT_DATA_TX_DESC_FLAGS0_ */ __le16 flags1; /* %HTT_DATA_TX_DESC_FLAGS1_ */ __le16 len; __le16 id; __le64 frags_paddr; union { __le32 peerid; struct { __le16 peerid; __le16 freq; } __packed offchan_tx; } __packed; u8 prefetch[0]; /* start of frame, for FW classification engine */ } __packed; enum htt_rx_ring_flags { HTT_RX_RING_FLAGS_MAC80211_HDR = 1 << 0, HTT_RX_RING_FLAGS_MSDU_PAYLOAD = 1 << 1, HTT_RX_RING_FLAGS_PPDU_START = 1 << 2, HTT_RX_RING_FLAGS_PPDU_END = 1 << 3, HTT_RX_RING_FLAGS_MPDU_START = 1 << 4, HTT_RX_RING_FLAGS_MPDU_END = 1 << 5, HTT_RX_RING_FLAGS_MSDU_START = 1 << 6, HTT_RX_RING_FLAGS_MSDU_END = 1 << 7, HTT_RX_RING_FLAGS_RX_ATTENTION = 1 << 8, HTT_RX_RING_FLAGS_FRAG_INFO = 1 << 9, HTT_RX_RING_FLAGS_UNICAST_RX = 1 << 10, HTT_RX_RING_FLAGS_MULTICAST_RX = 1 << 11, HTT_RX_RING_FLAGS_CTRL_RX = 1 << 12, HTT_RX_RING_FLAGS_MGMT_RX = 1 << 13, HTT_RX_RING_FLAGS_NULL_RX = 1 << 14, HTT_RX_RING_FLAGS_PHY_DATA_RX = 1 << 15 }; #define HTT_RX_RING_SIZE_MIN 128 #define HTT_RX_RING_SIZE_MAX 2048 #define HTT_RX_RING_SIZE HTT_RX_RING_SIZE_MAX #define HTT_RX_RING_FILL_LEVEL (((HTT_RX_RING_SIZE) / 2) - 1) #define HTT_RX_RING_FILL_LEVEL_DUAL_MAC (HTT_RX_RING_SIZE - 1) struct htt_rx_ring_rx_desc_offsets { /* the following offsets are in 4-byte units */ __le16 mac80211_hdr_offset; __le16 msdu_payload_offset; __le16 ppdu_start_offset; __le16 ppdu_end_offset; __le16 mpdu_start_offset; __le16 mpdu_end_offset; __le16 msdu_start_offset; __le16 msdu_end_offset; __le16 rx_attention_offset; __le16 frag_info_offset; } __packed; struct htt_rx_ring_setup_ring32 { __le32 fw_idx_shadow_reg_paddr; __le32 rx_ring_base_paddr; __le16 rx_ring_len; /* in 4-byte words */ __le16 rx_ring_bufsize; /* rx skb size - in bytes */ __le16 flags; /* %HTT_RX_RING_FLAGS_ */ __le16 fw_idx_init_val; struct htt_rx_ring_rx_desc_offsets offsets; } __packed; struct htt_rx_ring_setup_ring64 { __le64 fw_idx_shadow_reg_paddr; __le64 rx_ring_base_paddr; __le16 rx_ring_len; /* in 4-byte words */ __le16 rx_ring_bufsize; /* rx skb size - in bytes */ __le16 flags; /* %HTT_RX_RING_FLAGS_ */ __le16 fw_idx_init_val; struct htt_rx_ring_rx_desc_offsets offsets; } __packed; struct htt_rx_ring_setup_hdr { u8 num_rings; /* supported values: 1, 2 */ __le16 rsvd0; } __packed; struct htt_rx_ring_setup_32 { struct htt_rx_ring_setup_hdr hdr; struct htt_rx_ring_setup_ring32 rings[]; } __packed; struct htt_rx_ring_setup_64 { struct htt_rx_ring_setup_hdr hdr; struct htt_rx_ring_setup_ring64 rings[]; } __packed; /* * htt_stats_req - request target to send specified statistics * * @msg_type: hardcoded %HTT_H2T_MSG_TYPE_STATS_REQ * @upload_types: see %htt_dbg_stats_type. this is 24bit field actually * so make sure its little-endian. * @reset_types: see %htt_dbg_stats_type. this is 24bit field actually * so make sure its little-endian. * @cfg_val: stat_type specific configuration * @stat_type: see %htt_dbg_stats_type * @cookie_lsb: used for confirmation message from target->host * @cookie_msb: ditto as %cookie */ struct htt_stats_req { u8 upload_types[3]; u8 rsvd0; u8 reset_types[3]; struct { u8 mpdu_bytes; u8 mpdu_num_msdus; u8 msdu_bytes; } __packed; u8 stat_type; __le32 cookie_lsb; __le32 cookie_msb; } __packed; #define HTT_STATS_REQ_CFG_STAT_TYPE_INVALID 0xff #define HTT_STATS_BIT_MASK GENMASK(16, 0) /* * htt_oob_sync_req - request out-of-band sync * * The HTT SYNC tells the target to suspend processing of subsequent * HTT host-to-target messages until some other target agent locally * informs the target HTT FW that the current sync counter is equal to * or greater than (in a modulo sense) the sync counter specified in * the SYNC message. * * This allows other host-target components to synchronize their operation * with HTT, e.g. to ensure that tx frames don't get transmitted until a * security key has been downloaded to and activated by the target. * In the absence of any explicit synchronization counter value * specification, the target HTT FW will use zero as the default current * sync value. * * The HTT target FW will suspend its host->target message processing as long * as 0 < (in-band sync counter - out-of-band sync counter) & 0xff < 128. */ struct htt_oob_sync_req { u8 sync_count; __le16 rsvd0; } __packed; struct htt_aggr_conf { u8 max_num_ampdu_subframes; /* amsdu_subframes is limited by 0x1F mask */ u8 max_num_amsdu_subframes; } __packed; struct htt_aggr_conf_v2 { u8 max_num_ampdu_subframes; /* amsdu_subframes is limited by 0x1F mask */ u8 max_num_amsdu_subframes; u8 reserved; } __packed; #define HTT_MGMT_FRM_HDR_DOWNLOAD_LEN 32 struct htt_mgmt_tx_desc_qca99x0 { __le32 rate; } __packed; struct htt_mgmt_tx_desc { u8 pad[sizeof(u32) - sizeof(struct htt_cmd_hdr)]; __le32 msdu_paddr; __le32 desc_id; __le32 len; __le32 vdev_id; u8 hdr[HTT_MGMT_FRM_HDR_DOWNLOAD_LEN]; union { struct htt_mgmt_tx_desc_qca99x0 qca99x0; } __packed; } __packed; enum htt_mgmt_tx_status { HTT_MGMT_TX_STATUS_OK = 0, HTT_MGMT_TX_STATUS_RETRY = 1, HTT_MGMT_TX_STATUS_DROP = 2 }; /*=== target -> host messages ===============================================*/ enum htt_main_t2h_msg_type { HTT_MAIN_T2H_MSG_TYPE_VERSION_CONF = 0x0, HTT_MAIN_T2H_MSG_TYPE_RX_IND = 0x1, HTT_MAIN_T2H_MSG_TYPE_RX_FLUSH = 0x2, HTT_MAIN_T2H_MSG_TYPE_PEER_MAP = 0x3, HTT_MAIN_T2H_MSG_TYPE_PEER_UNMAP = 0x4, HTT_MAIN_T2H_MSG_TYPE_RX_ADDBA = 0x5, HTT_MAIN_T2H_MSG_TYPE_RX_DELBA = 0x6, HTT_MAIN_T2H_MSG_TYPE_TX_COMPL_IND = 0x7, HTT_MAIN_T2H_MSG_TYPE_PKTLOG = 0x8, HTT_MAIN_T2H_MSG_TYPE_STATS_CONF = 0x9, HTT_MAIN_T2H_MSG_TYPE_RX_FRAG_IND = 0xa, HTT_MAIN_T2H_MSG_TYPE_SEC_IND = 0xb, HTT_MAIN_T2H_MSG_TYPE_TX_INSPECT_IND = 0xd, HTT_MAIN_T2H_MSG_TYPE_MGMT_TX_COMPL_IND = 0xe, HTT_MAIN_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND = 0xf, HTT_MAIN_T2H_MSG_TYPE_RX_PN_IND = 0x10, HTT_MAIN_T2H_MSG_TYPE_RX_OFFLOAD_DELIVER_IND = 0x11, HTT_MAIN_T2H_MSG_TYPE_TEST, /* keep this last */ HTT_MAIN_T2H_NUM_MSGS }; enum htt_10x_t2h_msg_type { HTT_10X_T2H_MSG_TYPE_VERSION_CONF = 0x0, HTT_10X_T2H_MSG_TYPE_RX_IND = 0x1, HTT_10X_T2H_MSG_TYPE_RX_FLUSH = 0x2, HTT_10X_T2H_MSG_TYPE_PEER_MAP = 0x3, HTT_10X_T2H_MSG_TYPE_PEER_UNMAP = 0x4, HTT_10X_T2H_MSG_TYPE_RX_ADDBA = 0x5, HTT_10X_T2H_MSG_TYPE_RX_DELBA = 0x6, HTT_10X_T2H_MSG_TYPE_TX_COMPL_IND = 0x7, HTT_10X_T2H_MSG_TYPE_PKTLOG = 0x8, HTT_10X_T2H_MSG_TYPE_STATS_CONF = 0x9, HTT_10X_T2H_MSG_TYPE_RX_FRAG_IND = 0xa, HTT_10X_T2H_MSG_TYPE_SEC_IND = 0xb, HTT_10X_T2H_MSG_TYPE_RC_UPDATE_IND = 0xc, HTT_10X_T2H_MSG_TYPE_TX_INSPECT_IND = 0xd, HTT_10X_T2H_MSG_TYPE_TEST = 0xe, HTT_10X_T2H_MSG_TYPE_CHAN_CHANGE = 0xf, HTT_10X_T2H_MSG_TYPE_AGGR_CONF = 0x11, HTT_10X_T2H_MSG_TYPE_STATS_NOUPLOAD = 0x12, HTT_10X_T2H_MSG_TYPE_MGMT_TX_COMPL_IND = 0x13, /* keep this last */ HTT_10X_T2H_NUM_MSGS }; enum htt_tlv_t2h_msg_type { HTT_TLV_T2H_MSG_TYPE_VERSION_CONF = 0x0, HTT_TLV_T2H_MSG_TYPE_RX_IND = 0x1, HTT_TLV_T2H_MSG_TYPE_RX_FLUSH = 0x2, HTT_TLV_T2H_MSG_TYPE_PEER_MAP = 0x3, HTT_TLV_T2H_MSG_TYPE_PEER_UNMAP = 0x4, HTT_TLV_T2H_MSG_TYPE_RX_ADDBA = 0x5, HTT_TLV_T2H_MSG_TYPE_RX_DELBA = 0x6, HTT_TLV_T2H_MSG_TYPE_TX_COMPL_IND = 0x7, HTT_TLV_T2H_MSG_TYPE_PKTLOG = 0x8, HTT_TLV_T2H_MSG_TYPE_STATS_CONF = 0x9, HTT_TLV_T2H_MSG_TYPE_RX_FRAG_IND = 0xa, HTT_TLV_T2H_MSG_TYPE_SEC_IND = 0xb, HTT_TLV_T2H_MSG_TYPE_RC_UPDATE_IND = 0xc, /* deprecated */ HTT_TLV_T2H_MSG_TYPE_TX_INSPECT_IND = 0xd, HTT_TLV_T2H_MSG_TYPE_MGMT_TX_COMPL_IND = 0xe, HTT_TLV_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND = 0xf, HTT_TLV_T2H_MSG_TYPE_RX_PN_IND = 0x10, HTT_TLV_T2H_MSG_TYPE_RX_OFFLOAD_DELIVER_IND = 0x11, HTT_TLV_T2H_MSG_TYPE_RX_IN_ORD_PADDR_IND = 0x12, /* 0x13 reservd */ HTT_TLV_T2H_MSG_TYPE_WDI_IPA_OP_RESPONSE = 0x14, HTT_TLV_T2H_MSG_TYPE_CHAN_CHANGE = 0x15, HTT_TLV_T2H_MSG_TYPE_RX_OFLD_PKT_ERR = 0x16, HTT_TLV_T2H_MSG_TYPE_TEST, /* keep this last */ HTT_TLV_T2H_NUM_MSGS }; enum htt_10_4_t2h_msg_type { HTT_10_4_T2H_MSG_TYPE_VERSION_CONF = 0x0, HTT_10_4_T2H_MSG_TYPE_RX_IND = 0x1, HTT_10_4_T2H_MSG_TYPE_RX_FLUSH = 0x2, HTT_10_4_T2H_MSG_TYPE_PEER_MAP = 0x3, HTT_10_4_T2H_MSG_TYPE_PEER_UNMAP = 0x4, HTT_10_4_T2H_MSG_TYPE_RX_ADDBA = 0x5, HTT_10_4_T2H_MSG_TYPE_RX_DELBA = 0x6, HTT_10_4_T2H_MSG_TYPE_TX_COMPL_IND = 0x7, HTT_10_4_T2H_MSG_TYPE_PKTLOG = 0x8, HTT_10_4_T2H_MSG_TYPE_STATS_CONF = 0x9, HTT_10_4_T2H_MSG_TYPE_RX_FRAG_IND = 0xa, HTT_10_4_T2H_MSG_TYPE_SEC_IND = 0xb, HTT_10_4_T2H_MSG_TYPE_RC_UPDATE_IND = 0xc, HTT_10_4_T2H_MSG_TYPE_TX_INSPECT_IND = 0xd, HTT_10_4_T2H_MSG_TYPE_MGMT_TX_COMPL_IND = 0xe, HTT_10_4_T2H_MSG_TYPE_CHAN_CHANGE = 0xf, HTT_10_4_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND = 0x10, HTT_10_4_T2H_MSG_TYPE_RX_PN_IND = 0x11, HTT_10_4_T2H_MSG_TYPE_RX_OFFLOAD_DELIVER_IND = 0x12, HTT_10_4_T2H_MSG_TYPE_TEST = 0x13, HTT_10_4_T2H_MSG_TYPE_EN_STATS = 0x14, HTT_10_4_T2H_MSG_TYPE_AGGR_CONF = 0x15, HTT_10_4_T2H_MSG_TYPE_TX_FETCH_IND = 0x16, HTT_10_4_T2H_MSG_TYPE_TX_FETCH_CONFIRM = 0x17, HTT_10_4_T2H_MSG_TYPE_STATS_NOUPLOAD = 0x18, /* 0x19 to 0x2f are reserved */ HTT_10_4_T2H_MSG_TYPE_TX_MODE_SWITCH_IND = 0x30, HTT_10_4_T2H_MSG_TYPE_PEER_STATS = 0x31, /* keep this last */ HTT_10_4_T2H_NUM_MSGS }; enum htt_t2h_msg_type { HTT_T2H_MSG_TYPE_VERSION_CONF, HTT_T2H_MSG_TYPE_RX_IND, HTT_T2H_MSG_TYPE_RX_FLUSH, HTT_T2H_MSG_TYPE_PEER_MAP, HTT_T2H_MSG_TYPE_PEER_UNMAP, HTT_T2H_MSG_TYPE_RX_ADDBA, HTT_T2H_MSG_TYPE_RX_DELBA, HTT_T2H_MSG_TYPE_TX_COMPL_IND, HTT_T2H_MSG_TYPE_PKTLOG, HTT_T2H_MSG_TYPE_STATS_CONF, HTT_T2H_MSG_TYPE_RX_FRAG_IND, HTT_T2H_MSG_TYPE_SEC_IND, HTT_T2H_MSG_TYPE_RC_UPDATE_IND, HTT_T2H_MSG_TYPE_TX_INSPECT_IND, HTT_T2H_MSG_TYPE_MGMT_TX_COMPLETION, HTT_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND, HTT_T2H_MSG_TYPE_RX_PN_IND, HTT_T2H_MSG_TYPE_RX_OFFLOAD_DELIVER_IND, HTT_T2H_MSG_TYPE_RX_IN_ORD_PADDR_IND, HTT_T2H_MSG_TYPE_WDI_IPA_OP_RESPONSE, HTT_T2H_MSG_TYPE_CHAN_CHANGE, HTT_T2H_MSG_TYPE_RX_OFLD_PKT_ERR, HTT_T2H_MSG_TYPE_AGGR_CONF, HTT_T2H_MSG_TYPE_STATS_NOUPLOAD, HTT_T2H_MSG_TYPE_TEST, HTT_T2H_MSG_TYPE_EN_STATS, HTT_T2H_MSG_TYPE_TX_FETCH_IND, HTT_T2H_MSG_TYPE_TX_FETCH_CONFIRM, HTT_T2H_MSG_TYPE_TX_MODE_SWITCH_IND, HTT_T2H_MSG_TYPE_PEER_STATS, /* keep this last */ HTT_T2H_NUM_MSGS }; /* * htt_resp_hdr - header for target-to-host messages * * msg_type: see htt_t2h_msg_type */ struct htt_resp_hdr { u8 msg_type; } __packed; #define HTT_RESP_HDR_MSG_TYPE_OFFSET 0 #define HTT_RESP_HDR_MSG_TYPE_MASK 0xff #define HTT_RESP_HDR_MSG_TYPE_LSB 0 /* htt_ver_resp - response sent for htt_ver_req */ struct htt_ver_resp { u8 minor; u8 major; u8 rsvd0; } __packed; #define HTT_MGMT_TX_CMPL_FLAG_ACK_RSSI BIT(0) #define HTT_MGMT_TX_CMPL_INFO_ACK_RSSI_MASK GENMASK(7, 0) struct htt_mgmt_tx_completion { u8 rsvd0; u8 rsvd1; u8 flags; __le32 desc_id; __le32 status; __le32 ppdu_id; __le32 info; } __packed; #define HTT_RX_INDICATION_INFO0_EXT_TID_MASK (0x1F) #define HTT_RX_INDICATION_INFO0_EXT_TID_LSB (0) #define HTT_RX_INDICATION_INFO0_FLUSH_VALID (1 << 5) #define HTT_RX_INDICATION_INFO0_RELEASE_VALID (1 << 6) #define HTT_RX_INDICATION_INFO0_PPDU_DURATION BIT(7) #define HTT_RX_INDICATION_INFO1_FLUSH_START_SEQNO_MASK 0x0000003F #define HTT_RX_INDICATION_INFO1_FLUSH_START_SEQNO_LSB 0 #define HTT_RX_INDICATION_INFO1_FLUSH_END_SEQNO_MASK 0x00000FC0 #define HTT_RX_INDICATION_INFO1_FLUSH_END_SEQNO_LSB 6 #define HTT_RX_INDICATION_INFO1_RELEASE_START_SEQNO_MASK 0x0003F000 #define HTT_RX_INDICATION_INFO1_RELEASE_START_SEQNO_LSB 12 #define HTT_RX_INDICATION_INFO1_RELEASE_END_SEQNO_MASK 0x00FC0000 #define HTT_RX_INDICATION_INFO1_RELEASE_END_SEQNO_LSB 18 #define HTT_RX_INDICATION_INFO1_NUM_MPDU_RANGES_MASK 0xFF000000 #define HTT_RX_INDICATION_INFO1_NUM_MPDU_RANGES_LSB 24 #define HTT_TX_CMPL_FLAG_DATA_RSSI BIT(0) #define HTT_TX_CMPL_FLAG_PPID_PRESENT BIT(1) #define HTT_TX_CMPL_FLAG_PA_PRESENT BIT(2) #define HTT_TX_CMPL_FLAG_PPDU_DURATION_PRESENT BIT(3) #define HTT_TX_DATA_RSSI_ENABLE_WCN3990 BIT(3) #define HTT_TX_DATA_APPEND_RETRIES BIT(0) #define HTT_TX_DATA_APPEND_TIMESTAMP BIT(1) struct htt_rx_indication_hdr { u8 info0; /* %HTT_RX_INDICATION_INFO0_ */ __le16 peer_id; __le32 info1; /* %HTT_RX_INDICATION_INFO1_ */ } __packed; #define HTT_RX_INDICATION_INFO0_PHY_ERR_VALID (1 << 0) #define HTT_RX_INDICATION_INFO0_LEGACY_RATE_MASK (0x1E) #define HTT_RX_INDICATION_INFO0_LEGACY_RATE_LSB (1) #define HTT_RX_INDICATION_INFO0_LEGACY_RATE_CCK (1 << 5) #define HTT_RX_INDICATION_INFO0_END_VALID (1 << 6) #define HTT_RX_INDICATION_INFO0_START_VALID (1 << 7) #define HTT_RX_INDICATION_INFO1_VHT_SIG_A1_MASK 0x00FFFFFF #define HTT_RX_INDICATION_INFO1_VHT_SIG_A1_LSB 0 #define HTT_RX_INDICATION_INFO1_PREAMBLE_TYPE_MASK 0xFF000000 #define HTT_RX_INDICATION_INFO1_PREAMBLE_TYPE_LSB 24 #define HTT_RX_INDICATION_INFO2_VHT_SIG_A1_MASK 0x00FFFFFF #define HTT_RX_INDICATION_INFO2_VHT_SIG_A1_LSB 0 #define HTT_RX_INDICATION_INFO2_SERVICE_MASK 0xFF000000 #define HTT_RX_INDICATION_INFO2_SERVICE_LSB 24 enum htt_rx_legacy_rate { HTT_RX_OFDM_48 = 0, HTT_RX_OFDM_24 = 1, HTT_RX_OFDM_12, HTT_RX_OFDM_6, HTT_RX_OFDM_54, HTT_RX_OFDM_36, HTT_RX_OFDM_18, HTT_RX_OFDM_9, /* long preamble */ HTT_RX_CCK_11_LP = 0, HTT_RX_CCK_5_5_LP = 1, HTT_RX_CCK_2_LP, HTT_RX_CCK_1_LP, /* short preamble */ HTT_RX_CCK_11_SP, HTT_RX_CCK_5_5_SP, HTT_RX_CCK_2_SP }; enum htt_rx_legacy_rate_type { HTT_RX_LEGACY_RATE_OFDM = 0, HTT_RX_LEGACY_RATE_CCK }; enum htt_rx_preamble_type { HTT_RX_LEGACY = 0x4, HTT_RX_HT = 0x8, HTT_RX_HT_WITH_TXBF = 0x9, HTT_RX_VHT = 0xC, HTT_RX_VHT_WITH_TXBF = 0xD, }; /* * Fields: phy_err_valid, phy_err_code, tsf, * usec_timestamp, sub_usec_timestamp * ..are valid only if end_valid == 1. * * Fields: rssi_chains, legacy_rate_type, * legacy_rate_cck, preamble_type, service, * vht_sig_* * ..are valid only if start_valid == 1; */ struct htt_rx_indication_ppdu { u8 combined_rssi; u8 sub_usec_timestamp; u8 phy_err_code; u8 info0; /* HTT_RX_INDICATION_INFO0_ */ struct { u8 pri20_db; u8 ext20_db; u8 ext40_db; u8 ext80_db; } __packed rssi_chains[4]; __le32 tsf; __le32 usec_timestamp; __le32 info1; /* HTT_RX_INDICATION_INFO1_ */ __le32 info2; /* HTT_RX_INDICATION_INFO2_ */ } __packed; enum htt_rx_mpdu_status { HTT_RX_IND_MPDU_STATUS_UNKNOWN = 0x0, HTT_RX_IND_MPDU_STATUS_OK, HTT_RX_IND_MPDU_STATUS_ERR_FCS, HTT_RX_IND_MPDU_STATUS_ERR_DUP, HTT_RX_IND_MPDU_STATUS_ERR_REPLAY, HTT_RX_IND_MPDU_STATUS_ERR_INV_PEER, /* only accept EAPOL frames */ HTT_RX_IND_MPDU_STATUS_UNAUTH_PEER, HTT_RX_IND_MPDU_STATUS_OUT_OF_SYNC, /* Non-data in promiscuous mode */ HTT_RX_IND_MPDU_STATUS_MGMT_CTRL, HTT_RX_IND_MPDU_STATUS_TKIP_MIC_ERR, HTT_RX_IND_MPDU_STATUS_DECRYPT_ERR, HTT_RX_IND_MPDU_STATUS_MPDU_LENGTH_ERR, HTT_RX_IND_MPDU_STATUS_ENCRYPT_REQUIRED_ERR, HTT_RX_IND_MPDU_STATUS_PRIVACY_ERR, /* * MISC: discard for unspecified reasons. * Leave this enum value last. */ HTT_RX_IND_MPDU_STATUS_ERR_MISC = 0xFF }; struct htt_rx_indication_mpdu_range { u8 mpdu_count; u8 mpdu_range_status; /* %htt_rx_mpdu_status */ u8 pad0; u8 pad1; } __packed; struct htt_rx_indication_prefix { __le16 fw_rx_desc_bytes; u8 pad0; u8 pad1; } __packed; struct htt_rx_indication { struct htt_rx_indication_hdr hdr; struct htt_rx_indication_ppdu ppdu; struct htt_rx_indication_prefix prefix; /* * the following fields are both dynamically sized, so * take care addressing them */ /* the size of this is %fw_rx_desc_bytes */ struct fw_rx_desc_base fw_desc; /* * %mpdu_ranges starts after &%prefix + roundup(%fw_rx_desc_bytes, 4) * and has %num_mpdu_ranges elements. */ struct htt_rx_indication_mpdu_range mpdu_ranges[]; } __packed; /* High latency version of the RX indication */ struct htt_rx_indication_hl { struct htt_rx_indication_hdr hdr; struct htt_rx_indication_ppdu ppdu; struct htt_rx_indication_prefix prefix; struct fw_rx_desc_hl fw_desc; struct htt_rx_indication_mpdu_range mpdu_ranges[]; } __packed; struct htt_hl_rx_desc { __le32 info; __le32 pn_31_0; union { struct { __le16 pn_47_32; __le16 pn_63_48; } pn16; __le32 pn_63_32; } u0; __le32 pn_95_64; __le32 pn_127_96; } __packed; static inline struct htt_rx_indication_mpdu_range * htt_rx_ind_get_mpdu_ranges(struct htt_rx_indication *rx_ind) { void *ptr = rx_ind; ptr += sizeof(rx_ind->hdr) + sizeof(rx_ind->ppdu) + sizeof(rx_ind->prefix) + roundup(__le16_to_cpu(rx_ind->prefix.fw_rx_desc_bytes), 4); return ptr; } static inline struct htt_rx_indication_mpdu_range * htt_rx_ind_get_mpdu_ranges_hl(struct htt_rx_indication_hl *rx_ind) { void *ptr = rx_ind; ptr += sizeof(rx_ind->hdr) + sizeof(rx_ind->ppdu) + sizeof(rx_ind->prefix) + sizeof(rx_ind->fw_desc); return ptr; } enum htt_rx_flush_mpdu_status { HTT_RX_FLUSH_MPDU_DISCARD = 0, HTT_RX_FLUSH_MPDU_REORDER = 1, }; /* * htt_rx_flush - discard or reorder given range of mpdus * * Note: host must check if all sequence numbers between * [seq_num_start, seq_num_end-1] are valid. */ struct htt_rx_flush { __le16 peer_id; u8 tid; u8 rsvd0; u8 mpdu_status; /* %htt_rx_flush_mpdu_status */ u8 seq_num_start; /* it is 6 LSBs of 802.11 seq no */ u8 seq_num_end; /* it is 6 LSBs of 802.11 seq no */ }; struct htt_rx_peer_map { u8 vdev_id; __le16 peer_id; u8 addr[6]; u8 rsvd0; u8 rsvd1; } __packed; struct htt_rx_peer_unmap { u8 rsvd0; __le16 peer_id; } __packed; enum htt_txrx_sec_cast_type { HTT_TXRX_SEC_MCAST = 0, HTT_TXRX_SEC_UCAST }; enum htt_rx_pn_check_type { HTT_RX_NON_PN_CHECK = 0, HTT_RX_PN_CHECK }; enum htt_rx_tkip_demic_type { HTT_RX_NON_TKIP_MIC = 0, HTT_RX_TKIP_MIC }; enum htt_security_types { HTT_SECURITY_NONE, HTT_SECURITY_WEP128, HTT_SECURITY_WEP104, HTT_SECURITY_WEP40, HTT_SECURITY_TKIP, HTT_SECURITY_TKIP_NOMIC, HTT_SECURITY_AES_CCMP, HTT_SECURITY_WAPI, HTT_NUM_SECURITY_TYPES /* keep this last! */ }; #define ATH10K_HTT_TXRX_PEER_SECURITY_MAX 2 #define ATH10K_TXRX_NUM_EXT_TIDS 19 #define ATH10K_TXRX_NON_QOS_TID 16 enum htt_security_flags { #define HTT_SECURITY_TYPE_MASK 0x7F #define HTT_SECURITY_TYPE_LSB 0 HTT_SECURITY_IS_UNICAST = 1 << 7 }; struct htt_security_indication { union { /* dont use bitfields; undefined behaviour */ u8 flags; /* %htt_security_flags */ struct { u8 security_type:7, /* %htt_security_types */ is_unicast:1; } __packed; } __packed; __le16 peer_id; u8 michael_key[8]; u8 wapi_rsc[16]; } __packed; #define HTT_RX_BA_INFO0_TID_MASK 0x000F #define HTT_RX_BA_INFO0_TID_LSB 0 #define HTT_RX_BA_INFO0_PEER_ID_MASK 0xFFF0 #define HTT_RX_BA_INFO0_PEER_ID_LSB 4 struct htt_rx_addba { u8 window_size; __le16 info0; /* %HTT_RX_BA_INFO0_ */ } __packed; struct htt_rx_delba { u8 rsvd0; __le16 info0; /* %HTT_RX_BA_INFO0_ */ } __packed; enum htt_data_tx_status { HTT_DATA_TX_STATUS_OK = 0, HTT_DATA_TX_STATUS_DISCARD = 1, HTT_DATA_TX_STATUS_NO_ACK = 2, HTT_DATA_TX_STATUS_POSTPONE = 3 /* HL only */ }; enum htt_data_tx_flags { #define HTT_DATA_TX_STATUS_MASK 0x07 #define HTT_DATA_TX_STATUS_LSB 0 #define HTT_DATA_TX_TID_MASK 0x78 #define HTT_DATA_TX_TID_LSB 3 HTT_DATA_TX_TID_INVALID = 1 << 7 }; #define HTT_TX_COMPL_INV_MSDU_ID 0xFFFF struct htt_append_retries { __le16 msdu_id; u8 tx_retries; u8 flag; } __packed; struct htt_data_tx_completion_ext { struct htt_append_retries a_retries; __le32 t_stamp; __le16 msdus_rssi[]; } __packed; /* * @brief target -> host TX completion indication message definition * * @details * The following diagram shows the format of the TX completion indication sent * from the target to the host * * |31 28|27|26|25|24|23 16| 15 |14 11|10 8|7 0| * |-------------------------------------------------------------| * header: |rsvd |A2|TP|A1|A0| num | t_i| tid |status| msg_type | * |-------------------------------------------------------------| * payload: | MSDU1 ID | MSDU0 ID | * |-------------------------------------------------------------| * : MSDU3 ID : MSDU2 ID : * |-------------------------------------------------------------| * | struct htt_tx_compl_ind_append_retries | * |- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -| * | struct htt_tx_compl_ind_append_tx_tstamp | * |- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -| * | MSDU1 ACK RSSI | MSDU0 ACK RSSI | * |-------------------------------------------------------------| * : MSDU3 ACK RSSI : MSDU2 ACK RSSI : * |- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -| * -msg_type * Bits 7:0 * Purpose: identifies this as HTT TX completion indication * -status * Bits 10:8 * Purpose: the TX completion status of payload fragmentations descriptors * Value: could be HTT_TX_COMPL_IND_STAT_OK or HTT_TX_COMPL_IND_STAT_DISCARD * -tid * Bits 14:11 * Purpose: the tid associated with those fragmentation descriptors. It is * valid or not, depending on the tid_invalid bit. * Value: 0 to 15 * -tid_invalid * Bits 15:15 * Purpose: this bit indicates whether the tid field is valid or not * Value: 0 indicates valid, 1 indicates invalid * -num * Bits 23:16 * Purpose: the number of payload in this indication * Value: 1 to 255 * -A0 = append * Bits 24:24 * Purpose: append the struct htt_tx_compl_ind_append_retries which contains * the number of tx retries for one MSDU at the end of this message * Value: 0 indicates no appending, 1 indicates appending * -A1 = append1 * Bits 25:25 * Purpose: Append the struct htt_tx_compl_ind_append_tx_tstamp which * contains the timestamp info for each TX msdu id in payload. * Value: 0 indicates no appending, 1 indicates appending * -TP = MSDU tx power presence * Bits 26:26 * Purpose: Indicate whether the TX_COMPL_IND includes a tx power report * for each MSDU referenced by the TX_COMPL_IND message. * The order of the per-MSDU tx power reports matches the order * of the MSDU IDs. * Value: 0 indicates not appending, 1 indicates appending * -A2 = append2 * Bits 27:27 * Purpose: Indicate whether data ACK RSSI is appended for each MSDU in * TX_COMP_IND message. The order of the per-MSDU ACK RSSI report * matches the order of the MSDU IDs. * The ACK RSSI values are valid when status is COMPLETE_OK (and * this append2 bit is set). * Value: 0 indicates not appending, 1 indicates appending */ struct htt_data_tx_completion { union { u8 flags; struct { u8 status:3, tid:4, tid_invalid:1; } __packed; } __packed; u8 num_msdus; u8 flags2; /* HTT_TX_CMPL_FLAG_DATA_RSSI */ __le16 msdus[]; /* variable length based on %num_msdus */ } __packed; #define HTT_TX_PPDU_DUR_INFO0_PEER_ID_MASK GENMASK(15, 0) #define HTT_TX_PPDU_DUR_INFO0_TID_MASK GENMASK(20, 16) struct htt_data_tx_ppdu_dur { __le32 info0; /* HTT_TX_PPDU_DUR_INFO0_ */ __le32 tx_duration; /* in usecs */ } __packed; #define HTT_TX_COMPL_PPDU_DUR_INFO0_NUM_ENTRIES_MASK GENMASK(7, 0) struct htt_data_tx_compl_ppdu_dur { __le32 info0; /* HTT_TX_COMPL_PPDU_DUR_INFO0_ */ struct htt_data_tx_ppdu_dur ppdu_dur[]; } __packed; struct htt_tx_compl_ind_base { u32 hdr; u16 payload[1/*or more*/]; } __packed; struct htt_rc_tx_done_params { u32 rate_code; u32 rate_code_flags; u32 flags; u32 num_enqued; /* 1 for non-AMPDU */ u32 num_retries; u32 num_failed; /* for AMPDU */ u32 ack_rssi; u32 time_stamp; u32 is_probe; }; struct htt_rc_update { u8 vdev_id; __le16 peer_id; u8 addr[6]; u8 num_elems; u8 rsvd0; struct htt_rc_tx_done_params params[]; /* variable length %num_elems */ } __packed; /* see htt_rx_indication for similar fields and descriptions */ struct htt_rx_fragment_indication { union { u8 info0; /* %HTT_RX_FRAG_IND_INFO0_ */ struct { u8 ext_tid:5, flush_valid:1; } __packed; } __packed; __le16 peer_id; __le32 info1; /* %HTT_RX_FRAG_IND_INFO1_ */ __le16 fw_rx_desc_bytes; __le16 rsvd0; u8 fw_msdu_rx_desc[]; } __packed; #define ATH10K_IEEE80211_EXTIV BIT(5) #define ATH10K_IEEE80211_TKIP_MICLEN 8 /* trailing MIC */ #define HTT_RX_FRAG_IND_INFO0_HEADER_LEN 16 #define HTT_RX_FRAG_IND_INFO0_EXT_TID_MASK 0x1F #define HTT_RX_FRAG_IND_INFO0_EXT_TID_LSB 0 #define HTT_RX_FRAG_IND_INFO0_FLUSH_VALID_MASK 0x20 #define HTT_RX_FRAG_IND_INFO0_FLUSH_VALID_LSB 5 #define HTT_RX_FRAG_IND_INFO1_FLUSH_SEQ_NUM_START_MASK 0x0000003F #define HTT_RX_FRAG_IND_INFO1_FLUSH_SEQ_NUM_START_LSB 0 #define HTT_RX_FRAG_IND_INFO1_FLUSH_SEQ_NUM_END_MASK 0x00000FC0 #define HTT_RX_FRAG_IND_INFO1_FLUSH_SEQ_NUM_END_LSB 6 struct htt_rx_pn_ind { __le16 peer_id; u8 tid; u8 seqno_start; u8 seqno_end; u8 pn_ie_count; u8 reserved; u8 pn_ies[]; } __packed; struct htt_rx_offload_msdu { __le16 msdu_len; __le16 peer_id; u8 vdev_id; u8 tid; u8 fw_desc; u8 payload[]; } __packed; struct htt_rx_offload_ind { u8 reserved; __le16 msdu_count; } __packed; struct htt_rx_in_ord_msdu_desc { __le32 msdu_paddr; __le16 msdu_len; u8 fw_desc; u8 reserved; } __packed; struct htt_rx_in_ord_msdu_desc_ext { __le64 msdu_paddr; __le16 msdu_len; u8 fw_desc; u8 reserved; } __packed; struct htt_rx_in_ord_ind { u8 info; __le16 peer_id; u8 vdev_id; u8 reserved; __le16 msdu_count; union { DECLARE_FLEX_ARRAY(struct htt_rx_in_ord_msdu_desc, msdu_descs32); DECLARE_FLEX_ARRAY(struct htt_rx_in_ord_msdu_desc_ext, msdu_descs64); } __packed; } __packed; #define HTT_RX_IN_ORD_IND_INFO_TID_MASK 0x0000001f #define HTT_RX_IN_ORD_IND_INFO_TID_LSB 0 #define HTT_RX_IN_ORD_IND_INFO_OFFLOAD_MASK 0x00000020 #define HTT_RX_IN_ORD_IND_INFO_OFFLOAD_LSB 5 #define HTT_RX_IN_ORD_IND_INFO_FRAG_MASK 0x00000040 #define HTT_RX_IN_ORD_IND_INFO_FRAG_LSB 6 /* * target -> host test message definition * * The following field definitions describe the format of the test * message sent from the target to the host. * The message consists of a 4-octet header, followed by a variable * number of 32-bit integer values, followed by a variable number * of 8-bit character values. * * |31 16|15 8|7 0| * |-----------------------------------------------------------| * | num chars | num ints | msg type | * |-----------------------------------------------------------| * | int 0 | * |-----------------------------------------------------------| * | int 1 | * |-----------------------------------------------------------| * | ... | * |-----------------------------------------------------------| * | char 3 | char 2 | char 1 | char 0 | * |-----------------------------------------------------------| * | | | ... | char 4 | * |-----------------------------------------------------------| * - MSG_TYPE * Bits 7:0 * Purpose: identifies this as a test message * Value: HTT_MSG_TYPE_TEST * - NUM_INTS * Bits 15:8 * Purpose: indicate how many 32-bit integers follow the message header * - NUM_CHARS * Bits 31:16 * Purpose: indicate how many 8-bit characters follow the series of integers */ struct htt_rx_test { u8 num_ints; __le16 num_chars; /* payload consists of 2 lists: * a) num_ints * sizeof(__le32) * b) num_chars * sizeof(u8) aligned to 4bytes */ u8 payload[]; } __packed; static inline __le32 *htt_rx_test_get_ints(struct htt_rx_test *rx_test) { return (__le32 *)rx_test->payload; } static inline u8 *htt_rx_test_get_chars(struct htt_rx_test *rx_test) { return rx_test->payload + (rx_test->num_ints * sizeof(__le32)); } /* * target -> host packet log message * * The following field definitions describe the format of the packet log * message sent from the target to the host. * The message consists of a 4-octet header,followed by a variable number * of 32-bit character values. * * |31 24|23 16|15 8|7 0| * |-----------------------------------------------------------| * | | | | msg type | * |-----------------------------------------------------------| * | payload | * |-----------------------------------------------------------| * - MSG_TYPE * Bits 7:0 * Purpose: identifies this as a test message * Value: HTT_MSG_TYPE_PACKETLOG */ struct htt_pktlog_msg { u8 pad[3]; u8 payload[]; } __packed; struct htt_dbg_stats_rx_reorder_stats { /* Non QoS MPDUs received */ __le32 deliver_non_qos; /* MPDUs received in-order */ __le32 deliver_in_order; /* Flush due to reorder timer expired */ __le32 deliver_flush_timeout; /* Flush due to move out of window */ __le32 deliver_flush_oow; /* Flush due to DELBA */ __le32 deliver_flush_delba; /* MPDUs dropped due to FCS error */ __le32 fcs_error; /* MPDUs dropped due to monitor mode non-data packet */ __le32 mgmt_ctrl; /* MPDUs dropped due to invalid peer */ __le32 invalid_peer; /* MPDUs dropped due to duplication (non aggregation) */ __le32 dup_non_aggr; /* MPDUs dropped due to processed before */ __le32 dup_past; /* MPDUs dropped due to duplicate in reorder queue */ __le32 dup_in_reorder; /* Reorder timeout happened */ __le32 reorder_timeout; /* invalid bar ssn */ __le32 invalid_bar_ssn; /* reorder reset due to bar ssn */ __le32 ssn_reset; }; struct htt_dbg_stats_wal_tx_stats { /* Num HTT cookies queued to dispatch list */ __le32 comp_queued; /* Num HTT cookies dispatched */ __le32 comp_delivered; /* Num MSDU queued to WAL */ __le32 msdu_enqued; /* Num MPDU queue to WAL */ __le32 mpdu_enqued; /* Num MSDUs dropped by WMM limit */ __le32 wmm_drop; /* Num Local frames queued */ __le32 local_enqued; /* Num Local frames done */ __le32 local_freed; /* Num queued to HW */ __le32 hw_queued; /* Num PPDU reaped from HW */ __le32 hw_reaped; /* Num underruns */ __le32 underrun; /* Num PPDUs cleaned up in TX abort */ __le32 tx_abort; /* Num MPDUs requeued by SW */ __le32 mpdus_requeued; /* excessive retries */ __le32 tx_ko; /* data hw rate code */ __le32 data_rc; /* Scheduler self triggers */ __le32 self_triggers; /* frames dropped due to excessive sw retries */ __le32 sw_retry_failure; /* illegal rate phy errors */ __le32 illgl_rate_phy_err; /* wal pdev continuous xretry */ __le32 pdev_cont_xretry; /* wal pdev continuous xretry */ __le32 pdev_tx_timeout; /* wal pdev resets */ __le32 pdev_resets; __le32 phy_underrun; /* MPDU is more than txop limit */ __le32 txop_ovf; } __packed; struct htt_dbg_stats_wal_rx_stats { /* Cnts any change in ring routing mid-ppdu */ __le32 mid_ppdu_route_change; /* Total number of statuses processed */ __le32 status_rcvd; /* Extra frags on rings 0-3 */ __le32 r0_frags; __le32 r1_frags; __le32 r2_frags; __le32 r3_frags; /* MSDUs / MPDUs delivered to HTT */ __le32 htt_msdus; __le32 htt_mpdus; /* MSDUs / MPDUs delivered to local stack */ __le32 loc_msdus; __le32 loc_mpdus; /* AMSDUs that have more MSDUs than the status ring size */ __le32 oversize_amsdu; /* Number of PHY errors */ __le32 phy_errs; /* Number of PHY errors drops */ __le32 phy_err_drop; /* Number of mpdu errors - FCS, MIC, ENC etc. */ __le32 mpdu_errs; } __packed; struct htt_dbg_stats_wal_peer_stats { __le32 dummy; /* REMOVE THIS ONCE REAL PEER STAT COUNTERS ARE ADDED */ } __packed; struct htt_dbg_stats_wal_pdev_txrx { struct htt_dbg_stats_wal_tx_stats tx_stats; struct htt_dbg_stats_wal_rx_stats rx_stats; struct htt_dbg_stats_wal_peer_stats peer_stats; } __packed; struct htt_dbg_stats_rx_rate_info { __le32 mcs[10]; __le32 sgi[10]; __le32 nss[4]; __le32 stbc[10]; __le32 bw[3]; __le32 pream[6]; __le32 ldpc; __le32 txbf; }; /* * htt_dbg_stats_status - * present - The requested stats have been delivered in full. * This indicates that either the stats information was contained * in its entirety within this message, or else this message * completes the delivery of the requested stats info that was * partially delivered through earlier STATS_CONF messages. * partial - The requested stats have been delivered in part. * One or more subsequent STATS_CONF messages with the same * cookie value will be sent to deliver the remainder of the * information. * error - The requested stats could not be delivered, for example due * to a shortage of memory to construct a message holding the * requested stats. * invalid - The requested stat type is either not recognized, or the * target is configured to not gather the stats type in question. * - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - * series_done - This special value indicates that no further stats info * elements are present within a series of stats info elems * (within a stats upload confirmation message). */ enum htt_dbg_stats_status { HTT_DBG_STATS_STATUS_PRESENT = 0, HTT_DBG_STATS_STATUS_PARTIAL = 1, HTT_DBG_STATS_STATUS_ERROR = 2, HTT_DBG_STATS_STATUS_INVALID = 3, HTT_DBG_STATS_STATUS_SERIES_DONE = 7 }; /* * host -> target FRAG DESCRIPTOR/MSDU_EXT DESC bank * * The following field definitions describe the format of the HTT host * to target frag_desc/msdu_ext bank configuration message. * The message contains the based address and the min and max id of the * MSDU_EXT/FRAG_DESC that will be used by the HTT to map MSDU DESC and * MSDU_EXT/FRAG_DESC. * HTT will use id in HTT descriptor instead sending the frag_desc_ptr. * For QCA988X HW the firmware will use fragment_desc_ptr but in WIFI2.0 * the hardware does the mapping/translation. * * Total banks that can be configured is configured to 16. * * This should be called before any TX has be initiated by the HTT * * |31 16|15 8|7 5|4 0| * |------------------------------------------------------------| * | DESC_SIZE | NUM_BANKS | RES |SWP|pdev| msg type | * |------------------------------------------------------------| * | BANK0_BASE_ADDRESS | * |------------------------------------------------------------| * | ... | * |------------------------------------------------------------| * | BANK15_BASE_ADDRESS | * |------------------------------------------------------------| * | BANK0_MAX_ID | BANK0_MIN_ID | * |------------------------------------------------------------| * | ... | * |------------------------------------------------------------| * | BANK15_MAX_ID | BANK15_MIN_ID | * |------------------------------------------------------------| * Header fields: * - MSG_TYPE * Bits 7:0 * Value: 0x6 * - BANKx_BASE_ADDRESS * Bits 31:0 * Purpose: Provide a mechanism to specify the base address of the MSDU_EXT * bank physical/bus address. * - BANKx_MIN_ID * Bits 15:0 * Purpose: Provide a mechanism to specify the min index that needs to * mapped. * - BANKx_MAX_ID * Bits 31:16 * Purpose: Provide a mechanism to specify the max index that needs to * */ struct htt_frag_desc_bank_id { __le16 bank_min_id; __le16 bank_max_id; } __packed; /* real is 16 but it wouldn't fit in the max htt message size * so we use a conservatively safe value for now */ #define HTT_FRAG_DESC_BANK_MAX 4 #define HTT_FRAG_DESC_BANK_CFG_INFO_PDEV_ID_MASK 0x03 #define HTT_FRAG_DESC_BANK_CFG_INFO_PDEV_ID_LSB 0 #define HTT_FRAG_DESC_BANK_CFG_INFO_SWAP BIT(2) #define HTT_FRAG_DESC_BANK_CFG_INFO_Q_STATE_VALID BIT(3) #define HTT_FRAG_DESC_BANK_CFG_INFO_Q_STATE_DEPTH_TYPE_MASK BIT(4) #define HTT_FRAG_DESC_BANK_CFG_INFO_Q_STATE_DEPTH_TYPE_LSB 4 enum htt_q_depth_type { HTT_Q_DEPTH_TYPE_BYTES = 0, HTT_Q_DEPTH_TYPE_MSDUS = 1, }; #define HTT_TX_Q_STATE_NUM_PEERS (TARGET_10_4_NUM_QCACHE_PEERS_MAX + \ TARGET_10_4_NUM_VDEVS) #define HTT_TX_Q_STATE_NUM_TIDS 8 #define HTT_TX_Q_STATE_ENTRY_SIZE 1 #define HTT_TX_Q_STATE_ENTRY_MULTIPLIER 0 /** * struct htt_q_state_conf - part of htt_frag_desc_bank_cfg for host q state config * * Defines host q state format and behavior. See htt_q_state. * * @paddr: Queue physical address * @num_peers: Number of supported peers * @num_tids: Number of supported TIDs * @record_size: Defines the size of each host q entry in bytes. In practice * however firmware (at least 10.4.3-00191) ignores this host * configuration value and uses hardcoded value of 1. * @record_multiplier: This is valid only when q depth type is MSDUs. It * defines the exponent for the power of 2 multiplication. * @pad: struct padding for 32-bit alignment */ struct htt_q_state_conf { __le32 paddr; __le16 num_peers; __le16 num_tids; u8 record_size; u8 record_multiplier; u8 pad[2]; } __packed; struct htt_frag_desc_bank_cfg32 { u8 info; /* HTT_FRAG_DESC_BANK_CFG_INFO_ */ u8 num_banks; u8 desc_size; __le32 bank_base_addrs[HTT_FRAG_DESC_BANK_MAX]; struct htt_frag_desc_bank_id bank_id[HTT_FRAG_DESC_BANK_MAX]; struct htt_q_state_conf q_state; } __packed; struct htt_frag_desc_bank_cfg64 { u8 info; /* HTT_FRAG_DESC_BANK_CFG_INFO_ */ u8 num_banks; u8 desc_size; __le64 bank_base_addrs[HTT_FRAG_DESC_BANK_MAX]; struct htt_frag_desc_bank_id bank_id[HTT_FRAG_DESC_BANK_MAX]; struct htt_q_state_conf q_state; } __packed; #define HTT_TX_Q_STATE_ENTRY_COEFFICIENT 128 #define HTT_TX_Q_STATE_ENTRY_FACTOR_MASK 0x3f #define HTT_TX_Q_STATE_ENTRY_FACTOR_LSB 0 #define HTT_TX_Q_STATE_ENTRY_EXP_MASK 0xc0 #define HTT_TX_Q_STATE_ENTRY_EXP_LSB 6 /** * struct htt_q_state - shared between host and firmware via DMA * * This structure is used for the host to expose it's software queue state to * firmware so that its rate control can schedule fetch requests for optimized * performance. This is most notably used for MU-MIMO aggregation when multiple * MU clients are connected. * * @count: Each element defines the host queue depth. When q depth type was * configured as HTT_Q_DEPTH_TYPE_BYTES then each entry is defined as: * FACTOR * 128 * 8^EXP (see HTT_TX_Q_STATE_ENTRY_FACTOR_MASK and * HTT_TX_Q_STATE_ENTRY_EXP_MASK). When q depth type was configured as * HTT_Q_DEPTH_TYPE_MSDUS the number of packets is scaled by 2 ** * record_multiplier (see htt_q_state_conf). * @map: Used by firmware to quickly check which host queues are not empty. It * is a bitmap simply saying. * @seq: Used by firmware to quickly check if the host queues were updated * since it last checked. * * FIXME: Is the q_state map[] size calculation really correct? */ struct htt_q_state { u8 count[HTT_TX_Q_STATE_NUM_TIDS][HTT_TX_Q_STATE_NUM_PEERS]; u32 map[HTT_TX_Q_STATE_NUM_TIDS][(HTT_TX_Q_STATE_NUM_PEERS + 31) / 32]; __le32 seq; } __packed; #define HTT_TX_FETCH_RECORD_INFO_PEER_ID_MASK 0x0fff #define HTT_TX_FETCH_RECORD_INFO_PEER_ID_LSB 0 #define HTT_TX_FETCH_RECORD_INFO_TID_MASK 0xf000 #define HTT_TX_FETCH_RECORD_INFO_TID_LSB 12 struct htt_tx_fetch_record { __le16 info; /* HTT_TX_FETCH_IND_RECORD_INFO_ */ __le16 num_msdus; __le32 num_bytes; } __packed; struct htt_tx_fetch_ind { u8 pad0; __le16 fetch_seq_num; __le32 token; __le16 num_resp_ids; __le16 num_records; union { /* ath10k_htt_get_tx_fetch_ind_resp_ids() */ DECLARE_FLEX_ARRAY(__le32, resp_ids); DECLARE_FLEX_ARRAY(struct htt_tx_fetch_record, records); } __packed; } __packed; static inline void * ath10k_htt_get_tx_fetch_ind_resp_ids(struct htt_tx_fetch_ind *ind) { return (void *)&ind->records[le16_to_cpu(ind->num_records)]; } struct htt_tx_fetch_resp { u8 pad0; __le16 resp_id; __le16 fetch_seq_num; __le16 num_records; __le32 token; struct htt_tx_fetch_record records[]; } __packed; struct htt_tx_fetch_confirm { u8 pad0; __le16 num_resp_ids; __le32 resp_ids[]; } __packed; enum htt_tx_mode_switch_mode { HTT_TX_MODE_SWITCH_PUSH = 0, HTT_TX_MODE_SWITCH_PUSH_PULL = 1, }; #define HTT_TX_MODE_SWITCH_IND_INFO0_ENABLE BIT(0) #define HTT_TX_MODE_SWITCH_IND_INFO0_NUM_RECORDS_MASK 0xfffe #define HTT_TX_MODE_SWITCH_IND_INFO0_NUM_RECORDS_LSB 1 #define HTT_TX_MODE_SWITCH_IND_INFO1_MODE_MASK 0x0003 #define HTT_TX_MODE_SWITCH_IND_INFO1_MODE_LSB 0 #define HTT_TX_MODE_SWITCH_IND_INFO1_THRESHOLD_MASK 0xfffc #define HTT_TX_MODE_SWITCH_IND_INFO1_THRESHOLD_LSB 2 #define HTT_TX_MODE_SWITCH_RECORD_INFO0_PEER_ID_MASK 0x0fff #define HTT_TX_MODE_SWITCH_RECORD_INFO0_PEER_ID_LSB 0 #define HTT_TX_MODE_SWITCH_RECORD_INFO0_TID_MASK 0xf000 #define HTT_TX_MODE_SWITCH_RECORD_INFO0_TID_LSB 12 struct htt_tx_mode_switch_record { __le16 info0; /* HTT_TX_MODE_SWITCH_RECORD_INFO0_ */ __le16 num_max_msdus; } __packed; struct htt_tx_mode_switch_ind { u8 pad0; __le16 info0; /* HTT_TX_MODE_SWITCH_IND_INFO0_ */ __le16 info1; /* HTT_TX_MODE_SWITCH_IND_INFO1_ */ u8 pad1[2]; struct htt_tx_mode_switch_record records[]; } __packed; struct htt_channel_change { u8 pad[3]; __le32 freq; __le32 center_freq1; __le32 center_freq2; __le32 phymode; } __packed; struct htt_per_peer_tx_stats_ind { __le32 succ_bytes; __le32 retry_bytes; __le32 failed_bytes; u8 ratecode; u8 flags; __le16 peer_id; __le16 succ_pkts; __le16 retry_pkts; __le16 failed_pkts; __le16 tx_duration; __le32 reserved1; __le32 reserved2; } __packed; struct htt_peer_tx_stats { u8 num_ppdu; u8 ppdu_len; u8 version; u8 payload[]; } __packed; #define ATH10K_10_2_TX_STATS_OFFSET 136 #define PEER_STATS_FOR_NO_OF_PPDUS 4 struct ath10k_10_2_peer_tx_stats { u8 ratecode[PEER_STATS_FOR_NO_OF_PPDUS]; u8 success_pkts[PEER_STATS_FOR_NO_OF_PPDUS]; __le16 success_bytes[PEER_STATS_FOR_NO_OF_PPDUS]; u8 retry_pkts[PEER_STATS_FOR_NO_OF_PPDUS]; __le16 retry_bytes[PEER_STATS_FOR_NO_OF_PPDUS]; u8 failed_pkts[PEER_STATS_FOR_NO_OF_PPDUS]; __le16 failed_bytes[PEER_STATS_FOR_NO_OF_PPDUS]; u8 flags[PEER_STATS_FOR_NO_OF_PPDUS]; __le32 tx_duration; u8 tx_ppdu_cnt; u8 peer_id; } __packed; union htt_rx_pn_t { /* WEP: 24-bit PN */ u32 pn24; /* TKIP or CCMP: 48-bit PN */ u64 pn48; /* WAPI: 128-bit PN */ u64 pn128[2]; }; struct htt_cmd { struct htt_cmd_hdr hdr; union { struct htt_ver_req ver_req; struct htt_mgmt_tx_desc mgmt_tx; struct htt_data_tx_desc data_tx; struct htt_rx_ring_setup_32 rx_setup_32; struct htt_rx_ring_setup_64 rx_setup_64; struct htt_stats_req stats_req; struct htt_oob_sync_req oob_sync_req; struct htt_aggr_conf aggr_conf; struct htt_aggr_conf_v2 aggr_conf_v2; struct htt_frag_desc_bank_cfg32 frag_desc_bank_cfg32; struct htt_frag_desc_bank_cfg64 frag_desc_bank_cfg64; struct htt_tx_fetch_resp tx_fetch_resp; }; } __packed; struct htt_resp { struct htt_resp_hdr hdr; union { struct htt_ver_resp ver_resp; struct htt_mgmt_tx_completion mgmt_tx_completion; struct htt_data_tx_completion data_tx_completion; struct htt_rx_indication rx_ind; struct htt_rx_indication_hl rx_ind_hl; struct htt_rx_fragment_indication rx_frag_ind; struct htt_rx_peer_map peer_map; struct htt_rx_peer_unmap peer_unmap; struct htt_rx_flush rx_flush; struct htt_rx_addba rx_addba; struct htt_rx_delba rx_delba; struct htt_security_indication security_indication; struct htt_rc_update rc_update; struct htt_rx_test rx_test; struct htt_pktlog_msg pktlog_msg; struct htt_rx_pn_ind rx_pn_ind; struct htt_rx_offload_ind rx_offload_ind; struct htt_rx_in_ord_ind rx_in_ord_ind; struct htt_tx_fetch_ind tx_fetch_ind; struct htt_tx_fetch_confirm tx_fetch_confirm; struct htt_tx_mode_switch_ind tx_mode_switch_ind; struct htt_channel_change chan_change; struct htt_peer_tx_stats peer_tx_stats; } __packed; } __packed; /*** host side structures follow ***/ struct htt_tx_done { u16 msdu_id; u16 status; u8 ack_rssi; }; enum htt_tx_compl_state { HTT_TX_COMPL_STATE_NONE, HTT_TX_COMPL_STATE_ACK, HTT_TX_COMPL_STATE_NOACK, HTT_TX_COMPL_STATE_DISCARD, }; struct htt_peer_map_event { u8 vdev_id; u16 peer_id; u8 addr[ETH_ALEN]; }; struct htt_peer_unmap_event { u16 peer_id; }; struct ath10k_htt_txbuf_32 { struct htt_data_tx_desc_frag frags[2]; struct ath10k_htc_hdr htc_hdr; struct htt_cmd_hdr cmd_hdr; struct htt_data_tx_desc cmd_tx; } __packed __aligned(4); struct ath10k_htt_txbuf_64 { struct htt_data_tx_desc_frag frags[2]; struct ath10k_htc_hdr htc_hdr; struct htt_cmd_hdr cmd_hdr; struct htt_data_tx_desc_64 cmd_tx; } __packed __aligned(4); struct ath10k_htt { struct ath10k *ar; enum ath10k_htc_ep_id eid; struct sk_buff_head rx_indication_head; u8 target_version_major; u8 target_version_minor; struct completion target_version_received; u8 max_num_amsdu; u8 max_num_ampdu; const enum htt_t2h_msg_type *t2h_msg_types; u32 t2h_msg_types_max; struct { /* * Ring of network buffer objects - This ring is * used exclusively by the host SW. This ring * mirrors the dev_addrs_ring that is shared * between the host SW and the MAC HW. The host SW * uses this netbufs ring to locate the network * buffer objects whose data buffers the HW has * filled. */ struct sk_buff **netbufs_ring; /* This is used only with firmware supporting IN_ORD_IND. * * With Full Rx Reorder the HTT Rx Ring is more of a temporary * buffer ring from which buffer addresses are copied by the * firmware to MAC Rx ring. Firmware then delivers IN_ORD_IND * pointing to specific (re-ordered) buffers. * * FIXME: With kernel generic hashing functions there's a lot * of hash collisions for sk_buffs. */ bool in_ord_rx; DECLARE_HASHTABLE(skb_table, 4); /* * Ring of buffer addresses - * This ring holds the "physical" device address of the * rx buffers the host SW provides for the MAC HW to * fill. */ union { __le64 *paddrs_ring_64; __le32 *paddrs_ring_32; }; /* * Base address of ring, as a "physical" device address * rather than a CPU address. */ dma_addr_t base_paddr; /* how many elems in the ring (power of 2) */ int size; /* size - 1 */ unsigned int size_mask; /* how many rx buffers to keep in the ring */ int fill_level; /* how many rx buffers (full+empty) are in the ring */ int fill_cnt; /* * alloc_idx - where HTT SW has deposited empty buffers * This is allocated in consistent mem, so that the FW can * read this variable, and program the HW's FW_IDX reg with * the value of this shadow register. */ struct { __le32 *vaddr; dma_addr_t paddr; } alloc_idx; /* where HTT SW has processed bufs filled by rx MAC DMA */ struct { unsigned int msdu_payld; } sw_rd_idx; /* * refill_retry_timer - timer triggered when the ring is * not refilled to the level expected */ struct timer_list refill_retry_timer; /* Protects access to all rx ring buffer state variables */ spinlock_t lock; } rx_ring; unsigned int prefetch_len; /* Protects access to pending_tx, num_pending_tx */ spinlock_t tx_lock; int max_num_pending_tx; int num_pending_tx; int num_pending_mgmt_tx; struct idr pending_tx; wait_queue_head_t empty_tx_wq; /* FIFO for storing tx done status {ack, no-ack, discard} and msdu id */ DECLARE_KFIFO_PTR(txdone_fifo, struct htt_tx_done); /* set if host-fw communication goes haywire * used to avoid further failures */ bool rx_confused; atomic_t num_mpdus_ready; /* This is used to group tx/rx completions separately and process them * in batches to reduce cache stalls */ struct sk_buff_head rx_msdus_q; struct sk_buff_head rx_in_ord_compl_q; struct sk_buff_head tx_fetch_ind_q; /* rx_status template */ struct ieee80211_rx_status rx_status; struct { dma_addr_t paddr; union { struct htt_msdu_ext_desc *vaddr_desc_32; struct htt_msdu_ext_desc_64 *vaddr_desc_64; }; size_t size; } frag_desc; struct { dma_addr_t paddr; union { struct ath10k_htt_txbuf_32 *vaddr_txbuff_32; struct ath10k_htt_txbuf_64 *vaddr_txbuff_64; }; size_t size; } txbuf; struct { bool enabled; struct htt_q_state *vaddr; dma_addr_t paddr; u16 num_push_allowed; u16 num_peers; u16 num_tids; enum htt_tx_mode_switch_mode mode; enum htt_q_depth_type type; } tx_q_state; bool tx_mem_allocated; const struct ath10k_htt_tx_ops *tx_ops; const struct ath10k_htt_rx_ops *rx_ops; bool disable_tx_comp; bool bundle_tx; struct sk_buff_head tx_req_head; struct sk_buff_head tx_complete_head; }; struct ath10k_htt_tx_ops { int (*htt_send_rx_ring_cfg)(struct ath10k_htt *htt); int (*htt_send_frag_desc_bank_cfg)(struct ath10k_htt *htt); int (*htt_alloc_frag_desc)(struct ath10k_htt *htt); void (*htt_free_frag_desc)(struct ath10k_htt *htt); int (*htt_tx)(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txmode, struct sk_buff *msdu); int (*htt_alloc_txbuff)(struct ath10k_htt *htt); void (*htt_free_txbuff)(struct ath10k_htt *htt); int (*htt_h2t_aggr_cfg_msg)(struct ath10k_htt *htt, u8 max_subfrms_ampdu, u8 max_subfrms_amsdu); void (*htt_flush_tx)(struct ath10k_htt *htt); }; static inline int ath10k_htt_send_rx_ring_cfg(struct ath10k_htt *htt) { if (!htt->tx_ops->htt_send_rx_ring_cfg) return -EOPNOTSUPP; return htt->tx_ops->htt_send_rx_ring_cfg(htt); } static inline int ath10k_htt_send_frag_desc_bank_cfg(struct ath10k_htt *htt) { if (!htt->tx_ops->htt_send_frag_desc_bank_cfg) return -EOPNOTSUPP; return htt->tx_ops->htt_send_frag_desc_bank_cfg(htt); } static inline int ath10k_htt_alloc_frag_desc(struct ath10k_htt *htt) { if (!htt->tx_ops->htt_alloc_frag_desc) return -EOPNOTSUPP; return htt->tx_ops->htt_alloc_frag_desc(htt); } static inline void ath10k_htt_free_frag_desc(struct ath10k_htt *htt) { if (htt->tx_ops->htt_free_frag_desc) htt->tx_ops->htt_free_frag_desc(htt); } static inline int ath10k_htt_tx(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txmode, struct sk_buff *msdu) { return htt->tx_ops->htt_tx(htt, txmode, msdu); } static inline void ath10k_htt_flush_tx(struct ath10k_htt *htt) { if (htt->tx_ops->htt_flush_tx) htt->tx_ops->htt_flush_tx(htt); } static inline int ath10k_htt_alloc_txbuff(struct ath10k_htt *htt) { if (!htt->tx_ops->htt_alloc_txbuff) return -EOPNOTSUPP; return htt->tx_ops->htt_alloc_txbuff(htt); } static inline void ath10k_htt_free_txbuff(struct ath10k_htt *htt) { if (htt->tx_ops->htt_free_txbuff) htt->tx_ops->htt_free_txbuff(htt); } static inline int ath10k_htt_h2t_aggr_cfg_msg(struct ath10k_htt *htt, u8 max_subfrms_ampdu, u8 max_subfrms_amsdu) { if (!htt->tx_ops->htt_h2t_aggr_cfg_msg) return -EOPNOTSUPP; return htt->tx_ops->htt_h2t_aggr_cfg_msg(htt, max_subfrms_ampdu, max_subfrms_amsdu); } struct ath10k_htt_rx_ops { size_t (*htt_get_rx_ring_size)(struct ath10k_htt *htt); void (*htt_config_paddrs_ring)(struct ath10k_htt *htt, void *vaddr); void (*htt_set_paddrs_ring)(struct ath10k_htt *htt, dma_addr_t paddr, int idx); void* (*htt_get_vaddr_ring)(struct ath10k_htt *htt); void (*htt_reset_paddrs_ring)(struct ath10k_htt *htt, int idx); bool (*htt_rx_proc_rx_frag_ind)(struct ath10k_htt *htt, struct htt_rx_fragment_indication *rx, struct sk_buff *skb); }; static inline size_t ath10k_htt_get_rx_ring_size(struct ath10k_htt *htt) { if (!htt->rx_ops->htt_get_rx_ring_size) return 0; return htt->rx_ops->htt_get_rx_ring_size(htt); } static inline void ath10k_htt_config_paddrs_ring(struct ath10k_htt *htt, void *vaddr) { if (htt->rx_ops->htt_config_paddrs_ring) htt->rx_ops->htt_config_paddrs_ring(htt, vaddr); } static inline void ath10k_htt_set_paddrs_ring(struct ath10k_htt *htt, dma_addr_t paddr, int idx) { if (htt->rx_ops->htt_set_paddrs_ring) htt->rx_ops->htt_set_paddrs_ring(htt, paddr, idx); } static inline void *ath10k_htt_get_vaddr_ring(struct ath10k_htt *htt) { if (!htt->rx_ops->htt_get_vaddr_ring) return NULL; return htt->rx_ops->htt_get_vaddr_ring(htt); } static inline void ath10k_htt_reset_paddrs_ring(struct ath10k_htt *htt, int idx) { if (htt->rx_ops->htt_reset_paddrs_ring) htt->rx_ops->htt_reset_paddrs_ring(htt, idx); } static inline bool ath10k_htt_rx_proc_rx_frag_ind(struct ath10k_htt *htt, struct htt_rx_fragment_indication *rx, struct sk_buff *skb) { if (!htt->rx_ops->htt_rx_proc_rx_frag_ind) return true; return htt->rx_ops->htt_rx_proc_rx_frag_ind(htt, rx, skb); } /* the driver strongly assumes that the rx header status be 64 bytes long, * so all possible rx_desc structures must respect this assumption. */ #define RX_HTT_HDR_STATUS_LEN 64 /* The rx descriptor structure layout is programmed via rx ring setup * so that FW knows how to transfer the rx descriptor to the host. * Unfortunately, though, QCA6174's firmware doesn't currently behave correctly * when modifying the structure layout of the rx descriptor beyond what it expects * (even if it correctly programmed during the rx ring setup). * Therefore we must keep two different memory layouts, abstract the rx descriptor * representation and use ath10k_rx_desc_ops * for correctly accessing rx descriptor data. */ /* base struct used for abstracting the rx descriptor representation */ struct htt_rx_desc { union { /* This field is filled on the host using the msdu buffer * from htt_rx_indication */ struct fw_rx_desc_base fw_desc; u32 pad; } __packed; } __packed; /* rx descriptor for wcn3990 and possibly extensible for newer cards * Buffers like this are placed on the rx ring. */ struct htt_rx_desc_v2 { struct htt_rx_desc base; struct { struct rx_attention attention; struct rx_frag_info frag_info; struct rx_mpdu_start mpdu_start; struct rx_msdu_start msdu_start; struct rx_msdu_end msdu_end; struct rx_mpdu_end mpdu_end; struct rx_ppdu_start ppdu_start; struct rx_ppdu_end ppdu_end; } __packed; u8 rx_hdr_status[RX_HTT_HDR_STATUS_LEN]; u8 msdu_payload[]; }; /* QCA6174, QCA988x, QCA99x0 dedicated rx descriptor to make sure their firmware * works correctly. We keep a single rx descriptor for all these three * families of cards because from tests it seems to be the most stable solution, * e.g. having a rx descriptor only for QCA6174 seldom caused firmware crashes * during some tests. * Buffers like this are placed on the rx ring. */ struct htt_rx_desc_v1 { struct htt_rx_desc base; struct { struct rx_attention attention; struct rx_frag_info_v1 frag_info; struct rx_mpdu_start mpdu_start; struct rx_msdu_start_v1 msdu_start; struct rx_msdu_end_v1 msdu_end; struct rx_mpdu_end mpdu_end; struct rx_ppdu_start ppdu_start; struct rx_ppdu_end_v1 ppdu_end; } __packed; u8 rx_hdr_status[RX_HTT_HDR_STATUS_LEN]; u8 msdu_payload[]; }; /* rx_desc abstraction */ struct ath10k_htt_rx_desc_ops { /* These fields are mandatory, they must be specified in any instance */ /* sizeof() of the rx_desc structure used by this hw */ size_t rx_desc_size; /* offset of msdu_payload inside the rx_desc structure used by this hw */ size_t rx_desc_msdu_payload_offset; /* These fields are options. * When a field is not provided the default implementation gets used * (see the ath10k_rx_desc_* operations below for more info about the defaults) */ bool (*rx_desc_get_msdu_limit_error)(struct htt_rx_desc *rxd); int (*rx_desc_get_l3_pad_bytes)(struct htt_rx_desc *rxd); /* Safely cast from a void* buffer containing an rx descriptor * to the proper rx_desc structure */ struct htt_rx_desc *(*rx_desc_from_raw_buffer)(void *buff); void (*rx_desc_get_offsets)(struct htt_rx_ring_rx_desc_offsets *offs); struct rx_attention *(*rx_desc_get_attention)(struct htt_rx_desc *rxd); struct rx_frag_info_common *(*rx_desc_get_frag_info)(struct htt_rx_desc *rxd); struct rx_mpdu_start *(*rx_desc_get_mpdu_start)(struct htt_rx_desc *rxd); struct rx_mpdu_end *(*rx_desc_get_mpdu_end)(struct htt_rx_desc *rxd); struct rx_msdu_start_common *(*rx_desc_get_msdu_start)(struct htt_rx_desc *rxd); struct rx_msdu_end_common *(*rx_desc_get_msdu_end)(struct htt_rx_desc *rxd); struct rx_ppdu_start *(*rx_desc_get_ppdu_start)(struct htt_rx_desc *rxd); struct rx_ppdu_end_common *(*rx_desc_get_ppdu_end)(struct htt_rx_desc *rxd); u8 *(*rx_desc_get_rx_hdr_status)(struct htt_rx_desc *rxd); u8 *(*rx_desc_get_msdu_payload)(struct htt_rx_desc *rxd); }; extern const struct ath10k_htt_rx_desc_ops qca988x_rx_desc_ops; extern const struct ath10k_htt_rx_desc_ops qca99x0_rx_desc_ops; extern const struct ath10k_htt_rx_desc_ops wcn3990_rx_desc_ops; static inline int ath10k_htt_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { if (hw->rx_desc_ops->rx_desc_get_l3_pad_bytes) return hw->rx_desc_ops->rx_desc_get_l3_pad_bytes(rxd); return 0; } static inline bool ath10k_htt_rx_desc_msdu_limit_error(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { if (hw->rx_desc_ops->rx_desc_get_msdu_limit_error) return hw->rx_desc_ops->rx_desc_get_msdu_limit_error(rxd); return false; } /* The default implementation of all these getters is using the old rx_desc, * so that it is easier to define the ath10k_htt_rx_desc_ops instances. * But probably, if new wireless cards must be supported, it would be better * to switch the default implementation to the new rx_desc, since this would * make the extension easier . */ static inline struct htt_rx_desc * ath10k_htt_rx_desc_from_raw_buffer(struct ath10k_hw_params *hw, void *buff) { if (hw->rx_desc_ops->rx_desc_from_raw_buffer) return hw->rx_desc_ops->rx_desc_from_raw_buffer(buff); return &((struct htt_rx_desc_v1 *)buff)->base; } static inline void ath10k_htt_rx_desc_get_offsets(struct ath10k_hw_params *hw, struct htt_rx_ring_rx_desc_offsets *off) { if (hw->rx_desc_ops->rx_desc_get_offsets) { hw->rx_desc_ops->rx_desc_get_offsets(off); } else { #define desc_offset(x) (offsetof(struct htt_rx_desc_v1, x) / 4) off->mac80211_hdr_offset = __cpu_to_le16(desc_offset(rx_hdr_status)); off->msdu_payload_offset = __cpu_to_le16(desc_offset(msdu_payload)); off->ppdu_start_offset = __cpu_to_le16(desc_offset(ppdu_start)); off->ppdu_end_offset = __cpu_to_le16(desc_offset(ppdu_end)); off->mpdu_start_offset = __cpu_to_le16(desc_offset(mpdu_start)); off->mpdu_end_offset = __cpu_to_le16(desc_offset(mpdu_end)); off->msdu_start_offset = __cpu_to_le16(desc_offset(msdu_start)); off->msdu_end_offset = __cpu_to_le16(desc_offset(msdu_end)); off->rx_attention_offset = __cpu_to_le16(desc_offset(attention)); off->frag_info_offset = __cpu_to_le16(desc_offset(frag_info)); #undef desc_offset } } static inline struct rx_attention * ath10k_htt_rx_desc_get_attention(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_attention) return hw->rx_desc_ops->rx_desc_get_attention(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->attention; } static inline struct rx_frag_info_common * ath10k_htt_rx_desc_get_frag_info(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_frag_info) return hw->rx_desc_ops->rx_desc_get_frag_info(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->frag_info.common; } static inline struct rx_mpdu_start * ath10k_htt_rx_desc_get_mpdu_start(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_mpdu_start) return hw->rx_desc_ops->rx_desc_get_mpdu_start(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->mpdu_start; } static inline struct rx_mpdu_end * ath10k_htt_rx_desc_get_mpdu_end(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_mpdu_end) return hw->rx_desc_ops->rx_desc_get_mpdu_end(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->mpdu_end; } static inline struct rx_msdu_start_common * ath10k_htt_rx_desc_get_msdu_start(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_msdu_start) return hw->rx_desc_ops->rx_desc_get_msdu_start(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->msdu_start.common; } static inline struct rx_msdu_end_common * ath10k_htt_rx_desc_get_msdu_end(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_msdu_end) return hw->rx_desc_ops->rx_desc_get_msdu_end(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->msdu_end.common; } static inline struct rx_ppdu_start * ath10k_htt_rx_desc_get_ppdu_start(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_ppdu_start) return hw->rx_desc_ops->rx_desc_get_ppdu_start(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->ppdu_start; } static inline struct rx_ppdu_end_common * ath10k_htt_rx_desc_get_ppdu_end(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_ppdu_end) return hw->rx_desc_ops->rx_desc_get_ppdu_end(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return &rx_desc->ppdu_end.common; } static inline u8 * ath10k_htt_rx_desc_get_rx_hdr_status(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_rx_hdr_status) return hw->rx_desc_ops->rx_desc_get_rx_hdr_status(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return rx_desc->rx_hdr_status; } static inline u8 * ath10k_htt_rx_desc_get_msdu_payload(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) { struct htt_rx_desc_v1 *rx_desc; if (hw->rx_desc_ops->rx_desc_get_msdu_payload) return hw->rx_desc_ops->rx_desc_get_msdu_payload(rxd); rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); return rx_desc->msdu_payload; } #define HTT_RX_DESC_HL_INFO_SEQ_NUM_MASK 0x00000fff #define HTT_RX_DESC_HL_INFO_SEQ_NUM_LSB 0 #define HTT_RX_DESC_HL_INFO_ENCRYPTED_MASK 0x00001000 #define HTT_RX_DESC_HL_INFO_ENCRYPTED_LSB 12 #define HTT_RX_DESC_HL_INFO_CHAN_INFO_PRESENT_MASK 0x00002000 #define HTT_RX_DESC_HL_INFO_CHAN_INFO_PRESENT_LSB 13 #define HTT_RX_DESC_HL_INFO_MCAST_BCAST_MASK 0x00010000 #define HTT_RX_DESC_HL_INFO_MCAST_BCAST_LSB 16 #define HTT_RX_DESC_HL_INFO_KEY_ID_OCT_MASK 0x01fe0000 #define HTT_RX_DESC_HL_INFO_KEY_ID_OCT_LSB 17 struct htt_rx_desc_base_hl { __le32 info; /* HTT_RX_DESC_HL_INFO_ */ }; struct htt_rx_chan_info { __le16 primary_chan_center_freq_mhz; __le16 contig_chan1_center_freq_mhz; __le16 contig_chan2_center_freq_mhz; u8 phy_mode; u8 reserved; } __packed; #define HTT_RX_DESC_ALIGN 8 #define HTT_MAC_ADDR_LEN 6 /* * FIX THIS * Should be: sizeof(struct htt_host_rx_desc) + max rx MSDU size, * rounded up to a cache line size. */ #define HTT_RX_BUF_SIZE 2048 /* The HTT_RX_MSDU_SIZE can't be statically computed anymore, * because it depends on the underlying device rx_desc representation */ static inline int ath10k_htt_rx_msdu_size(struct ath10k_hw_params *hw) { return HTT_RX_BUF_SIZE - (int)hw->rx_desc_ops->rx_desc_size; } /* Refill a bunch of RX buffers for each refill round so that FW/HW can handle * aggregated traffic more nicely. */ #define ATH10K_HTT_MAX_NUM_REFILL 100 /* * DMA_MAP expects the buffer to be an integral number of cache lines. * Rather than checking the actual cache line size, this code makes a * conservative estimate of what the cache line size could be. */ #define HTT_LOG2_MAX_CACHE_LINE_SIZE 7 /* 2^7 = 128 */ #define HTT_MAX_CACHE_LINE_SIZE_MASK ((1 << HTT_LOG2_MAX_CACHE_LINE_SIZE) - 1) /* These values are default in most firmware revisions and apparently are a * sweet spot performance wise. */ #define ATH10K_HTT_MAX_NUM_AMSDU_DEFAULT 3 #define ATH10K_HTT_MAX_NUM_AMPDU_DEFAULT 64 int ath10k_htt_connect(struct ath10k_htt *htt); int ath10k_htt_init(struct ath10k *ar); int ath10k_htt_setup(struct ath10k_htt *htt); int ath10k_htt_tx_start(struct ath10k_htt *htt); void ath10k_htt_tx_stop(struct ath10k_htt *htt); void ath10k_htt_tx_destroy(struct ath10k_htt *htt); void ath10k_htt_tx_free(struct ath10k_htt *htt); int ath10k_htt_rx_alloc(struct ath10k_htt *htt); int ath10k_htt_rx_ring_refill(struct ath10k *ar); void ath10k_htt_rx_free(struct ath10k_htt *htt); void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb); void ath10k_htt_htc_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb); bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb); int ath10k_htt_h2t_ver_req_msg(struct ath10k_htt *htt); int ath10k_htt_h2t_stats_req(struct ath10k_htt *htt, u32 mask, u32 reset_mask, u64 cookie); void ath10k_htt_hif_tx_complete(struct ath10k *ar, struct sk_buff *skb); int ath10k_htt_tx_fetch_resp(struct ath10k *ar, __le32 token, __le16 fetch_seq_num, struct htt_tx_fetch_record *records, size_t num_records); void ath10k_htt_op_ep_tx_credits(struct ath10k *ar); void ath10k_htt_tx_txq_update(struct ieee80211_hw *hw, struct ieee80211_txq *txq); void ath10k_htt_tx_txq_recalc(struct ieee80211_hw *hw, struct ieee80211_txq *txq); void ath10k_htt_tx_txq_sync(struct ath10k *ar); void ath10k_htt_tx_dec_pending(struct ath10k_htt *htt); int ath10k_htt_tx_inc_pending(struct ath10k_htt *htt); void ath10k_htt_tx_mgmt_dec_pending(struct ath10k_htt *htt); int ath10k_htt_tx_mgmt_inc_pending(struct ath10k_htt *htt, bool is_mgmt, bool is_presp); int ath10k_htt_tx_alloc_msdu_id(struct ath10k_htt *htt, struct sk_buff *skb); void ath10k_htt_tx_free_msdu_id(struct ath10k_htt *htt, u16 msdu_id); int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu); void ath10k_htt_rx_pktlog_completion_handler(struct ath10k *ar, struct sk_buff *skb); int ath10k_htt_txrx_compl_task(struct ath10k *ar, int budget); int ath10k_htt_rx_hl_indication(struct ath10k *ar, int budget); void ath10k_htt_set_tx_ops(struct ath10k_htt *htt); void ath10k_htt_set_rx_ops(struct ath10k_htt *htt); #endif |
| 447 440 440 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_THROTTLE_H #define BLK_THROTTLE_H #include "blk-cgroup-rwstat.h" /* * To implement hierarchical throttling, throtl_grps form a tree and bios * are dispatched upwards level by level until they reach the top and get * issued. When dispatching bios from the children and local group at each * level, if the bios are dispatched into a single bio_list, there's a risk * of a local or child group which can queue many bios at once filling up * the list starving others. * * To avoid such starvation, dispatched bios are queued separately * according to where they came from. When they are again dispatched to * the parent, they're popped in round-robin order so that no single source * hogs the dispatch window. * * throtl_qnode is used to keep the queued bios separated by their sources. * Bios are queued to throtl_qnode which in turn is queued to * throtl_service_queue and then dispatched in round-robin order. * * It's also used to track the reference counts on blkg's. A qnode always * belongs to a throtl_grp and gets queued on itself or the parent, so * incrementing the reference of the associated throtl_grp when a qnode is * queued and decrementing when dequeued is enough to keep the whole blkg * tree pinned while bios are in flight. */ struct throtl_qnode { struct list_head node; /* service_queue->queued[] */ struct bio_list bios_bps; /* queued bios for bps limit */ struct bio_list bios_iops; /* queued bios for iops limit */ struct throtl_grp *tg; /* tg this qnode belongs to */ }; struct throtl_service_queue { struct throtl_service_queue *parent_sq; /* the parent service_queue */ /* * Bios queued directly to this service_queue or dispatched from * children throtl_grp's. */ struct list_head queued[2]; /* throtl_qnode [READ/WRITE] */ unsigned int nr_queued_bps[2]; /* number of queued bps bios */ unsigned int nr_queued_iops[2]; /* number of queued iops bios */ /* * RB tree of active children throtl_grp's, which are sorted by * their ->disptime. */ struct rb_root_cached pending_tree; /* RB tree of active tgs */ unsigned int nr_pending; /* # queued in the tree */ unsigned long first_pending_disptime; /* disptime of the first tg */ struct timer_list pending_timer; /* fires on first_pending_disptime */ }; enum tg_state_flags { THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */ THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */ /* * The sq's iops queue is empty, and a bio is about to be enqueued * to the first qnode's bios_iops list. */ THROTL_TG_IOPS_WAS_EMPTY = 1 << 2, THROTL_TG_CANCELING = 1 << 3, /* starts to cancel bio */ }; struct throtl_grp { /* must be the first member */ struct blkg_policy_data pd; /* active throtl group service_queue member */ struct rb_node rb_node; /* throtl_data this group belongs to */ struct throtl_data *td; /* this group's service queue */ struct throtl_service_queue service_queue; /* * qnode_on_self is used when bios are directly queued to this * throtl_grp so that local bios compete fairly with bios * dispatched from children. qnode_on_parent is used when bios are * dispatched from this throtl_grp into its parent and will compete * with the sibling qnode_on_parents and the parent's * qnode_on_self. */ struct throtl_qnode qnode_on_self[2]; struct throtl_qnode qnode_on_parent[2]; /* * Dispatch time in jiffies. This is the estimated time when group * will unthrottle and is ready to dispatch more bio. It is used as * key to sort active groups in service tree. */ unsigned long disptime; unsigned int flags; /* are there any throtl rules between this group and td? */ bool has_rules_bps[2]; bool has_rules_iops[2]; /* bytes per second rate limits */ uint64_t bps[2]; /* IOPS limits */ unsigned int iops[2]; /* * Number of bytes/bio's dispatched in current slice. * When new configuration is submitted while some bios are still throttled, * first calculate the carryover: the amount of bytes/IOs already waited * under the previous configuration. Then, [bytes/io]_disp are represented * as the negative of the carryover, and they will be used to calculate the * wait time under the new configuration. */ int64_t bytes_disp[2]; int io_disp[2]; /* When did we start a new slice */ unsigned long slice_start[2]; unsigned long slice_end[2]; struct blkg_rwstat stat_bytes; struct blkg_rwstat stat_ios; }; extern struct blkcg_policy blkcg_policy_throtl; static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct throtl_grp, pd) : NULL; } static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg) { return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl)); } /* * Internal throttling interface */ #ifndef CONFIG_BLK_DEV_THROTTLING static inline void blk_throtl_exit(struct gendisk *disk) { } static inline bool blk_throtl_bio(struct bio *bio) { return false; } static inline void blk_throtl_cancel_bios(struct gendisk *disk) { } #else /* CONFIG_BLK_DEV_THROTTLING */ void blk_throtl_exit(struct gendisk *disk); bool __blk_throtl_bio(struct bio *bio); void blk_throtl_cancel_bios(struct gendisk *disk); static inline bool blk_throtl_activated(struct request_queue *q) { /* * q->td guarantees that the blk-throttle module is already loaded, * and the plid of blk-throttle is assigned. * blkcg_policy_enabled() guarantees that the policy is activated * in the request_queue. */ return q->td != NULL && blkcg_policy_enabled(q, &blkcg_policy_throtl); } static inline bool blk_should_throtl(struct bio *bio) { struct throtl_grp *tg; int rw = bio_data_dir(bio); if (!blk_throtl_activated(bio->bi_bdev->bd_queue)) return false; tg = blkg_to_tg(bio->bi_blkg); if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) { if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf, bio->bi_iter.bi_size); } blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1); } /* iops limit is always counted */ if (tg->has_rules_iops[rw]) return true; if (tg->has_rules_bps[rw] && !bio_flagged(bio, BIO_BPS_THROTTLED)) return true; return false; } static inline bool blk_throtl_bio(struct bio *bio) { /* * block throttling takes effect if the policy is activated * in the bio's request_queue. */ if (!blk_should_throtl(bio)) return false; return __blk_throtl_bio(bio); } #endif /* CONFIG_BLK_DEV_THROTTLING */ #endif |
| 23 23 42 2 12 2 6 14 6 6 1 3 1 1 4 31 8 16 3 1 3 3 30 22 4 12 3 3 3 2 2 7 7 5 2 3 8 7 1 8 8 13 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> void nft_immediate_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); nft_data_copy(®s->data[priv->dreg], &priv->data, priv->dlen); } static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = { [NFTA_IMMEDIATE_DREG] = NLA_POLICY_MAX(NLA_BE32, NFT_REG32_MAX), [NFTA_IMMEDIATE_DATA] = { .type = NLA_NESTED }, }; static enum nft_data_types nft_reg_to_type(const struct nlattr *nla) { enum nft_data_types type; u8 reg; reg = ntohl(nla_get_be32(nla)); if (reg == NFT_REG_VERDICT) type = NFT_DATA_VERDICT; else type = NFT_DATA_VALUE; return type; } static int nft_immediate_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_immediate_expr *priv = nft_expr_priv(expr); struct nft_data_desc desc = { .size = sizeof(priv->data), }; int err; if (tb[NFTA_IMMEDIATE_DREG] == NULL || tb[NFTA_IMMEDIATE_DATA] == NULL) return -EINVAL; desc.type = nft_reg_to_type(tb[NFTA_IMMEDIATE_DREG]); err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]); if (err < 0) return err; priv->dlen = desc.len; err = nft_parse_register_store(ctx, tb[NFTA_IMMEDIATE_DREG], &priv->dreg, &priv->data, desc.type, desc.len); if (err < 0) goto err1; if (priv->dreg == NFT_REG_VERDICT) { struct nft_chain *chain = priv->data.verdict.chain; switch (priv->data.verdict.code) { case NFT_JUMP: case NFT_GOTO: err = nf_tables_bind_chain(ctx, chain); if (err < 0) goto err1; break; default: break; } } return 0; err1: nft_data_release(&priv->data, desc.type); return err; } static void nft_immediate_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); const struct nft_data *data = &priv->data; struct nft_ctx chain_ctx; struct nft_chain *chain; struct nft_rule *rule; if (priv->dreg == NFT_REG_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; if (!nft_chain_binding(chain)) break; chain_ctx = *ctx; chain_ctx.chain = chain; list_for_each_entry(rule, &chain->rules, list) nft_rule_expr_activate(&chain_ctx, rule); nft_clear(ctx->net, chain); break; default: break; } } return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); } static void nft_immediate_chain_deactivate(const struct nft_ctx *ctx, struct nft_chain *chain, enum nft_trans_phase phase) { struct nft_ctx chain_ctx; struct nft_rule *rule; chain_ctx = *ctx; chain_ctx.chain = chain; list_for_each_entry(rule, &chain->rules, list) nft_rule_expr_deactivate(&chain_ctx, rule, phase); } static void nft_immediate_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); const struct nft_data *data = &priv->data; struct nft_chain *chain; if (priv->dreg == NFT_REG_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; if (!nft_chain_binding(chain)) break; switch (phase) { case NFT_TRANS_PREPARE_ERROR: nf_tables_unbind_chain(ctx, chain); nft_deactivate_next(ctx->net, chain); break; case NFT_TRANS_PREPARE: nft_immediate_chain_deactivate(ctx, chain, phase); nft_deactivate_next(ctx->net, chain); break; default: nft_immediate_chain_deactivate(ctx, chain, phase); nft_chain_del(chain); chain->bound = false; nft_use_dec(&chain->table->use); break; } break; default: break; } } if (phase == NFT_TRANS_COMMIT) return; return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } static void nft_immediate_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); const struct nft_data *data = &priv->data; struct nft_rule *rule, *n; struct nft_ctx chain_ctx; struct nft_chain *chain; if (priv->dreg != NFT_REG_VERDICT) return; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; if (!nft_chain_binding(chain)) break; /* Rule construction failed, but chain is already bound: * let the transaction records release this chain and its rules. */ if (chain->bound) { nft_use_dec(&chain->use); break; } /* Rule has been deleted, release chain and its rules. */ chain_ctx = *ctx; chain_ctx.chain = chain; nft_use_dec(&chain->use); list_for_each_entry_safe(rule, n, &chain->rules, list) { nft_use_dec(&chain->use); list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } nf_tables_chain_destroy(chain); break; default: break; } } static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_IMMEDIATE_DREG, priv->dreg)) goto nla_put_failure; return nft_data_dump(skb, NFTA_IMMEDIATE_DATA, &priv->data, nft_dreg_to_type(priv->dreg), priv->dlen); nla_put_failure: return -1; } static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; if (priv->dreg != NFT_REG_VERDICT) return 0; data = &priv->data; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; pctx->level--; break; default: break; } return 0; } static int nft_immediate_offload_verdict(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_immediate_expr *priv) { struct flow_action_entry *entry; const struct nft_data *data; entry = nft_flow_action_entry_next(ctx, flow); if (!entry) return -E2BIG; data = &priv->data; switch (data->verdict.code) { case NF_ACCEPT: entry->id = FLOW_ACTION_ACCEPT; break; case NF_DROP: entry->id = FLOW_ACTION_DROP; break; default: return -EOPNOTSUPP; } return 0; } static int nft_immediate_offload(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); if (priv->dreg == NFT_REG_VERDICT) return nft_immediate_offload_verdict(ctx, flow, priv); memcpy(&ctx->regs[priv->dreg].data, &priv->data, sizeof(priv->data)); return 0; } static bool nft_immediate_offload_action(const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); if (priv->dreg == NFT_REG_VERDICT) return true; return false; } static const struct nft_expr_ops nft_imm_ops = { .type = &nft_imm_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)), .eval = nft_immediate_eval, .init = nft_immediate_init, .activate = nft_immediate_activate, .deactivate = nft_immediate_deactivate, .destroy = nft_immediate_destroy, .dump = nft_immediate_dump, .validate = nft_immediate_validate, .offload = nft_immediate_offload, .offload_action = nft_immediate_offload_action, }; struct nft_expr_type nft_imm_type __read_mostly = { .name = "immediate", .ops = &nft_imm_ops, .policy = nft_immediate_policy, .maxattr = NFTA_IMMEDIATE_MAX, .owner = THIS_MODULE, }; |
| 34 14 186 231 2 2 2 233 233 236 56 178 4 56 178 162 73 44 189 233 233 174 59 233 136 97 174 60 61 173 59 174 57 177 233 42 191 233 233 233 61 176 176 4 173 173 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to setting various queue properties from drivers */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blk-integrity.h> #include <linux/pagemap.h> #include <linux/backing-dev-defs.h> #include <linux/gcd.h> #include <linux/lcm.h> #include <linux/jiffies.h> #include <linux/gfp.h> #include <linux/dma-mapping.h> #include <linux/t10-pi.h> #include <linux/crc64.h> #include "blk.h" #include "blk-rq-qos.h" #include "blk-wbt.h" void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) { WRITE_ONCE(q->rq_timeout, timeout); } EXPORT_SYMBOL_GPL(blk_queue_rq_timeout); /** * blk_set_stacking_limits - set default limits for stacking devices * @lim: the queue_limits structure to reset * * Prepare queue limits for applying limits from underlying devices using * blk_stack_limits(). */ void blk_set_stacking_limits(struct queue_limits *lim) { memset(lim, 0, sizeof(*lim)); lim->logical_block_size = SECTOR_SIZE; lim->physical_block_size = SECTOR_SIZE; lim->io_min = SECTOR_SIZE; lim->discard_granularity = SECTOR_SIZE; lim->dma_alignment = SECTOR_SIZE - 1; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; /* Inherit limits from component devices */ lim->max_segments = USHRT_MAX; lim->max_discard_segments = USHRT_MAX; lim->max_hw_sectors = UINT_MAX; lim->max_segment_size = UINT_MAX; lim->max_sectors = UINT_MAX; lim->max_dev_sectors = UINT_MAX; lim->max_write_zeroes_sectors = UINT_MAX; lim->max_hw_wzeroes_unmap_sectors = UINT_MAX; lim->max_user_wzeroes_unmap_sectors = UINT_MAX; lim->max_hw_zone_append_sectors = UINT_MAX; lim->max_user_discard_sectors = UINT_MAX; lim->atomic_write_hw_max = UINT_MAX; } EXPORT_SYMBOL(blk_set_stacking_limits); void blk_apply_bdi_limits(struct backing_dev_info *bdi, struct queue_limits *lim) { u64 io_opt = lim->io_opt; /* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. For rotational devices that do * not report an optimal I/O size (e.g. ATA HDDs), use the maximum I/O * size to avoid falling back to the (rather inefficient) small default * read-ahead size. * * There is no hardware limitation for the read-ahead size and the user * might have increased the read-ahead size through sysfs, so don't ever * decrease it. */ if (!io_opt && (lim->features & BLK_FEAT_ROTATIONAL)) io_opt = (u64)lim->max_sectors << SECTOR_SHIFT; bdi->ra_pages = max3(bdi->ra_pages, io_opt * 2 >> PAGE_SHIFT, VM_READAHEAD_PAGES); bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT; } static int blk_validate_zoned_limits(struct queue_limits *lim) { if (!(lim->features & BLK_FEAT_ZONED)) { if (WARN_ON_ONCE(lim->max_open_zones) || WARN_ON_ONCE(lim->max_active_zones) || WARN_ON_ONCE(lim->zone_write_granularity) || WARN_ON_ONCE(lim->max_zone_append_sectors)) return -EINVAL; return 0; } if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED))) return -EINVAL; /* * Given that active zones include open zones, the maximum number of * open zones cannot be larger than the maximum number of active zones. */ if (lim->max_active_zones && lim->max_open_zones > lim->max_active_zones) return -EINVAL; if (lim->zone_write_granularity < lim->logical_block_size) lim->zone_write_granularity = lim->logical_block_size; /* * The Zone Append size is limited by the maximum I/O size and the zone * size given that it can't span zones. * * If no max_hw_zone_append_sectors limit is provided, the block layer * will emulated it, else we're also bound by the hardware limit. */ lim->max_zone_append_sectors = min_not_zero(lim->max_hw_zone_append_sectors, min(lim->chunk_sectors, lim->max_hw_sectors)); return 0; } static int blk_validate_integrity_limits(struct queue_limits *lim) { struct blk_integrity *bi = &lim->integrity; if (!bi->metadata_size) { if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE || bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) { pr_warn("invalid PI settings.\n"); return -EINVAL; } bi->flags |= BLK_INTEGRITY_NOGENERATE | BLK_INTEGRITY_NOVERIFY; return 0; } if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) { pr_warn("integrity support disabled.\n"); return -EINVAL; } if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE && (bi->flags & BLK_INTEGRITY_REF_TAG)) { pr_warn("ref tag not support without checksum.\n"); return -EINVAL; } if (bi->pi_offset + bi->pi_tuple_size > bi->metadata_size) { pr_warn("pi_offset (%u) + pi_tuple_size (%u) exceeds metadata_size (%u)\n", bi->pi_offset, bi->pi_tuple_size, bi->metadata_size); return -EINVAL; } switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_NONE: if (bi->pi_tuple_size) { pr_warn("pi_tuple_size must be 0 when checksum type is none\n"); return -EINVAL; } break; case BLK_INTEGRITY_CSUM_CRC: case BLK_INTEGRITY_CSUM_IP: if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) { pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n", sizeof(struct t10_pi_tuple), bi->pi_tuple_size); return -EINVAL; } break; case BLK_INTEGRITY_CSUM_CRC64: if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) { pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n", sizeof(struct crc64_pi_tuple), bi->pi_tuple_size); return -EINVAL; } break; } if (!bi->interval_exp) { bi->interval_exp = ilog2(lim->logical_block_size); } else if (bi->interval_exp < SECTOR_SHIFT || bi->interval_exp > ilog2(lim->logical_block_size)) { pr_warn("invalid interval_exp %u\n", bi->interval_exp); return -EINVAL; } /* * Some IO controllers can not handle data intervals straddling * multiple bio_vecs. For those, enforce alignment so that those are * never generated, and that each buffer is aligned as expected. */ if (!(bi->flags & BLK_SPLIT_INTERVAL_CAPABLE) && bi->csum_type) { lim->dma_alignment = max(lim->dma_alignment, (1U << bi->interval_exp) - 1); } /* * The block layer automatically adds integrity data for bios that don't * already have it. Limit the I/O size so that a single maximum size * metadata segment can cover the integrity data for the entire I/O. */ lim->max_sectors = min(lim->max_sectors, max_integrity_io_size(lim) >> SECTOR_SHIFT); return 0; } /* * Returns max guaranteed bytes which we can fit in a bio. * * We request that an atomic_write is ITER_UBUF iov_iter (so a single vector), * so we assume that we can fit in at least PAGE_SIZE in a segment, apart from * the first and last segments. */ static unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *lim) { unsigned int max_segments = min(BIO_MAX_VECS, lim->max_segments); unsigned int length; length = min(max_segments, 2) * lim->logical_block_size; if (max_segments > 2) length += (max_segments - 2) * PAGE_SIZE; return length; } static void blk_atomic_writes_update_limits(struct queue_limits *lim) { unsigned int unit_limit = min(lim->max_hw_sectors << SECTOR_SHIFT, blk_queue_max_guaranteed_bio(lim)); unit_limit = rounddown_pow_of_two(unit_limit); lim->atomic_write_max_sectors = min(lim->atomic_write_hw_max >> SECTOR_SHIFT, lim->max_hw_sectors); lim->atomic_write_unit_min = min(lim->atomic_write_hw_unit_min, unit_limit); lim->atomic_write_unit_max = min(lim->atomic_write_hw_unit_max, unit_limit); lim->atomic_write_boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT; } /* * Test whether any boundary is aligned with any chunk size. Stacked * devices store any stripe size in t->chunk_sectors. */ static bool blk_valid_atomic_writes_boundary(unsigned int chunk_sectors, unsigned int boundary_sectors) { if (!chunk_sectors || !boundary_sectors) return true; if (boundary_sectors > chunk_sectors && boundary_sectors % chunk_sectors) return false; if (chunk_sectors > boundary_sectors && chunk_sectors % boundary_sectors) return false; return true; } static void blk_validate_atomic_write_limits(struct queue_limits *lim) { unsigned int boundary_sectors; unsigned int atomic_write_hw_max_sectors = lim->atomic_write_hw_max >> SECTOR_SHIFT; if (!(lim->features & BLK_FEAT_ATOMIC_WRITES)) goto unsupported; /* UINT_MAX indicates stacked limits in initial state */ if (lim->atomic_write_hw_max == UINT_MAX) goto unsupported; if (!lim->atomic_write_hw_max) goto unsupported; if (WARN_ON_ONCE(!is_power_of_2(lim->atomic_write_hw_unit_min))) goto unsupported; if (WARN_ON_ONCE(!is_power_of_2(lim->atomic_write_hw_unit_max))) goto unsupported; if (WARN_ON_ONCE(lim->atomic_write_hw_unit_min > lim->atomic_write_hw_unit_max)) goto unsupported; if (WARN_ON_ONCE(lim->atomic_write_hw_unit_max > lim->atomic_write_hw_max)) goto unsupported; if (WARN_ON_ONCE(lim->chunk_sectors && atomic_write_hw_max_sectors > lim->chunk_sectors)) goto unsupported; boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT; if (boundary_sectors) { if (WARN_ON_ONCE(lim->atomic_write_hw_max > lim->atomic_write_hw_boundary)) goto unsupported; if (WARN_ON_ONCE(!blk_valid_atomic_writes_boundary( lim->chunk_sectors, boundary_sectors))) goto unsupported; /* * The boundary size just needs to be a multiple of unit_max * (and not necessarily a power-of-2), so this following check * could be relaxed in future. * Furthermore, if needed, unit_max could even be reduced so * that it is compliant with a !power-of-2 boundary. */ if (!is_power_of_2(boundary_sectors)) goto unsupported; } blk_atomic_writes_update_limits(lim); return; unsupported: lim->atomic_write_max_sectors = 0; lim->atomic_write_boundary_sectors = 0; lim->atomic_write_unit_min = 0; lim->atomic_write_unit_max = 0; } /* * Check that the limits in lim are valid, initialize defaults for unset * values, and cap values based on others where needed. */ int blk_validate_limits(struct queue_limits *lim) { unsigned int max_hw_sectors; unsigned int logical_block_sectors; unsigned long seg_size; int err; /* * Unless otherwise specified, default to 512 byte logical blocks and a * physical block size equal to the logical block size. */ if (!lim->logical_block_size) lim->logical_block_size = SECTOR_SIZE; else if (blk_validate_block_size(lim->logical_block_size)) { pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size); return -EINVAL; } if (lim->physical_block_size < lim->logical_block_size) { lim->physical_block_size = lim->logical_block_size; } else if (!is_power_of_2(lim->physical_block_size)) { pr_warn("Invalid physical block size (%d)\n", lim->physical_block_size); return -EINVAL; } /* * The minimum I/O size defaults to the physical block size unless * explicitly overridden. */ if (lim->io_min < lim->physical_block_size) lim->io_min = lim->physical_block_size; /* * The optimal I/O size may not be aligned to physical block size * (because it may be limited by dma engines which have no clue about * block size of the disks attached to them), so we round it down here. */ lim->io_opt = round_down(lim->io_opt, lim->physical_block_size); /* * max_hw_sectors has a somewhat weird default for historical reason, * but driver really should set their own instead of relying on this * value. * * The block layer relies on the fact that every driver can * handle at lest a page worth of data per I/O, and needs the value * aligned to the logical block size. */ if (!lim->max_hw_sectors) lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS)) return -EINVAL; logical_block_sectors = lim->logical_block_size >> SECTOR_SHIFT; if (WARN_ON_ONCE(logical_block_sectors > lim->max_hw_sectors)) return -EINVAL; lim->max_hw_sectors = round_down(lim->max_hw_sectors, logical_block_sectors); /* * The actual max_sectors value is a complex beast and also takes the * max_dev_sectors value (set by SCSI ULPs) and a user configurable * value into account. The ->max_sectors value is always calculated * from these, so directly setting it won't have any effect. */ max_hw_sectors = min_not_zero(lim->max_hw_sectors, lim->max_dev_sectors); if (lim->max_user_sectors) { if (lim->max_user_sectors < BLK_MIN_SEGMENT_SIZE / SECTOR_SIZE) return -EINVAL; lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors); } else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) { lim->max_sectors = min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT); } else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) { lim->max_sectors = min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT); } else { lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP); } lim->max_sectors = round_down(lim->max_sectors, logical_block_sectors); /* * Random default for the maximum number of segments. Driver should not * rely on this and set their own. */ if (!lim->max_segments) lim->max_segments = BLK_MAX_SEGMENTS; if (lim->max_hw_wzeroes_unmap_sectors && lim->max_hw_wzeroes_unmap_sectors != lim->max_write_zeroes_sectors) return -EINVAL; lim->max_wzeroes_unmap_sectors = min(lim->max_hw_wzeroes_unmap_sectors, lim->max_user_wzeroes_unmap_sectors); lim->max_discard_sectors = min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors); /* * When discard is not supported, discard_granularity should be reported * as 0 to userspace. */ if (lim->max_discard_sectors) lim->discard_granularity = max(lim->discard_granularity, lim->physical_block_size); else lim->discard_granularity = 0; if (!lim->max_discard_segments) lim->max_discard_segments = 1; /* * By default there is no limit on the segment boundary alignment, * but if there is one it can't be smaller than the page size as * that would break all the normal I/O patterns. */ if (!lim->seg_boundary_mask) lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; if (WARN_ON_ONCE(lim->seg_boundary_mask < BLK_MIN_SEGMENT_SIZE - 1)) return -EINVAL; /* * Stacking device may have both virtual boundary and max segment * size limit, so allow this setting now, and long-term the two * might need to move out of stacking limits since we have immutable * bvec and lower layer bio splitting is supposed to handle the two * correctly. */ if (lim->virt_boundary_mask) { if (!lim->max_segment_size) lim->max_segment_size = UINT_MAX; } else { /* * The maximum segment size has an odd historic 64k default that * drivers probably should override. Just like the I/O size we * require drivers to at least handle a full page per segment. */ if (!lim->max_segment_size) lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; if (WARN_ON_ONCE(lim->max_segment_size < BLK_MIN_SEGMENT_SIZE)) return -EINVAL; } /* setup max segment size for building new segment in fast path */ if (lim->seg_boundary_mask > lim->max_segment_size - 1) seg_size = lim->max_segment_size; else seg_size = lim->seg_boundary_mask + 1; lim->max_fast_segment_size = min_t(unsigned int, seg_size, PAGE_SIZE); /* * We require drivers to at least do logical block aligned I/O, but * historically could not check for that due to the separate calls * to set the limits. Once the transition is finished the check * below should be narrowed down to check the logical block size. */ if (!lim->dma_alignment) lim->dma_alignment = SECTOR_SIZE - 1; if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE)) return -EINVAL; if (lim->alignment_offset) { lim->alignment_offset &= (lim->physical_block_size - 1); lim->flags &= ~BLK_FLAG_MISALIGNED; } if (!(lim->features & BLK_FEAT_WRITE_CACHE)) lim->features &= ~BLK_FEAT_FUA; blk_validate_atomic_write_limits(lim); err = blk_validate_integrity_limits(lim); if (err) return err; return blk_validate_zoned_limits(lim); } EXPORT_SYMBOL_GPL(blk_validate_limits); /* * Set the default limits for a newly allocated queue. @lim contains the * initial limits set by the driver, which could be no limit in which case * all fields are cleared to zero. */ int blk_set_default_limits(struct queue_limits *lim) { /* * Most defaults are set by capping the bounds in blk_validate_limits, * but these limits are special and need an explicit initialization to * the max value here. */ lim->max_user_discard_sectors = UINT_MAX; lim->max_user_wzeroes_unmap_sectors = UINT_MAX; return blk_validate_limits(lim); } /** * queue_limits_commit_update - commit an atomic update of queue limits * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() * and updated by the caller to @q. The caller must have frozen the queue or * ensure that there are no outstanding I/Os by other means. * * Returns 0 if successful, else a negative error code. */ int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim) { int error; lockdep_assert_held(&q->limits_lock); error = blk_validate_limits(lim); if (error) goto out_unlock; #ifdef CONFIG_BLK_INLINE_ENCRYPTION if (q->crypto_profile && lim->integrity.tag_size) { pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n"); error = -EINVAL; goto out_unlock; } #endif q->limits = *lim; if (q->disk) blk_apply_bdi_limits(q->disk->bdi, lim); out_unlock: mutex_unlock(&q->limits_lock); return error; } EXPORT_SYMBOL_GPL(queue_limits_commit_update); /** * queue_limits_commit_update_frozen - commit an atomic update of queue limits * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() * and updated with the new values by the caller to @q. Freezes the queue * before the update and unfreezes it after. * * Returns 0 if successful, else a negative error code. */ int queue_limits_commit_update_frozen(struct request_queue *q, struct queue_limits *lim) { unsigned int memflags; int ret; memflags = blk_mq_freeze_queue(q); ret = queue_limits_commit_update(q, lim); blk_mq_unfreeze_queue(q, memflags); return ret; } EXPORT_SYMBOL_GPL(queue_limits_commit_update_frozen); /** * queue_limits_set - apply queue limits to queue * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were freshly initialized to @q. * To update existing limits use queue_limits_start_update() and * queue_limits_commit_update() instead. * * Returns 0 if successful, else a negative error code. */ int queue_limits_set(struct request_queue *q, struct queue_limits *lim) { mutex_lock(&q->limits_lock); return queue_limits_commit_update(q, lim); } EXPORT_SYMBOL_GPL(queue_limits_set); static int queue_limit_alignment_offset(const struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) << SECTOR_SHIFT; return (granularity + lim->alignment_offset - alignment) % granularity; } static unsigned int queue_limit_discard_alignment( const struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; /* Why are these in bytes, not sectors? */ alignment = lim->discard_alignment >> SECTOR_SHIFT; granularity = lim->discard_granularity >> SECTOR_SHIFT; /* Offset of the partition start in 'granularity' sectors */ offset = sector_div(sector, granularity); /* And why do we do this modulus *again* in blkdev_issue_discard()? */ offset = (granularity + alignment - offset) % granularity; /* Turn it back into bytes, gaah */ return offset << SECTOR_SHIFT; } static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs) { sectors = round_down(sectors, lbs >> SECTOR_SHIFT); if (sectors < PAGE_SIZE >> SECTOR_SHIFT) sectors = PAGE_SIZE >> SECTOR_SHIFT; return sectors; } /* Check if second and later bottom devices are compliant */ static bool blk_stack_atomic_writes_tail(struct queue_limits *t, struct queue_limits *b) { /* We're not going to support different boundary sizes.. yet */ if (t->atomic_write_hw_boundary != b->atomic_write_hw_boundary) return false; /* Can't support this */ if (t->atomic_write_hw_unit_min > b->atomic_write_hw_unit_max) return false; /* Or this */ if (t->atomic_write_hw_unit_max < b->atomic_write_hw_unit_min) return false; t->atomic_write_hw_max = min(t->atomic_write_hw_max, b->atomic_write_hw_max); t->atomic_write_hw_unit_min = max(t->atomic_write_hw_unit_min, b->atomic_write_hw_unit_min); t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max, b->atomic_write_hw_unit_max); return true; } static void blk_stack_atomic_writes_chunk_sectors(struct queue_limits *t) { unsigned int chunk_bytes; if (!t->chunk_sectors) return; /* * If chunk sectors is so large that its value in bytes overflows * UINT_MAX, then just shift it down so it definitely will fit. * We don't support atomic writes of such a large size anyway. */ if (check_shl_overflow(t->chunk_sectors, SECTOR_SHIFT, &chunk_bytes)) chunk_bytes = t->chunk_sectors; /* * Find values for limits which work for chunk size. * b->atomic_write_hw_unit_{min, max} may not be aligned with chunk * size, as the chunk size is not restricted to a power-of-2. * So we need to find highest power-of-2 which works for the chunk * size. * As an example scenario, we could have t->unit_max = 16K and * t->chunk_sectors = 24KB. For this case, reduce t->unit_max to a * value aligned with both limits, i.e. 8K in this example. */ t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max, max_pow_of_two_factor(chunk_bytes)); t->atomic_write_hw_unit_min = min(t->atomic_write_hw_unit_min, t->atomic_write_hw_unit_max); t->atomic_write_hw_max = min(t->atomic_write_hw_max, chunk_bytes); } /* Check stacking of first bottom device */ static bool blk_stack_atomic_writes_head(struct queue_limits *t, struct queue_limits *b) { if (!blk_valid_atomic_writes_boundary(t->chunk_sectors, b->atomic_write_hw_boundary >> SECTOR_SHIFT)) return false; t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max; t->atomic_write_hw_unit_min = b->atomic_write_hw_unit_min; t->atomic_write_hw_max = b->atomic_write_hw_max; t->atomic_write_hw_boundary = b->atomic_write_hw_boundary; return true; } static void blk_stack_atomic_writes_limits(struct queue_limits *t, struct queue_limits *b, sector_t start) { if (!(b->features & BLK_FEAT_ATOMIC_WRITES)) goto unsupported; if (!b->atomic_write_hw_unit_min) goto unsupported; if (!blk_atomic_write_start_sect_aligned(start, b)) goto unsupported; /* UINT_MAX indicates no stacking of bottom devices yet */ if (t->atomic_write_hw_max == UINT_MAX) { if (!blk_stack_atomic_writes_head(t, b)) goto unsupported; } else { if (!blk_stack_atomic_writes_tail(t, b)) goto unsupported; } blk_stack_atomic_writes_chunk_sectors(t); return; unsupported: t->atomic_write_hw_max = 0; t->atomic_write_hw_unit_max = 0; t->atomic_write_hw_unit_min = 0; t->atomic_write_hw_boundary = 0; } /** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @b: the underlying queue limits (bottom, component device) * @start: first data sector within component device * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment. * * Returns 0 if the top and bottom queue_limits are compatible. The * top device's block sizes and alignment offsets may be adjusted to * ensure alignment with the bottom device. If no compatible sizes * and alignments exist, -1 is returned and the resulting top * queue_limits will have the misaligned flag set to indicate that * the alignment_offset is undefined. */ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t start) { unsigned int top, bottom, alignment; int ret = 0; t->features |= (b->features & BLK_FEAT_INHERIT_MASK); /* * Some feaures need to be supported both by the stacking driver and all * underlying devices. The stacking driver sets these flags before * stacking the limits, and this will clear the flags if any of the * underlying devices does not support it. */ if (!(b->features & BLK_FEAT_NOWAIT)) t->features &= ~BLK_FEAT_NOWAIT; if (!(b->features & BLK_FEAT_POLL)) t->features &= ~BLK_FEAT_POLL; if (!(b->features & BLK_FEAT_PCI_P2PDMA)) t->features &= ~BLK_FEAT_PCI_P2PDMA; t->flags |= (b->flags & BLK_FLAG_MISALIGNED); t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_user_sectors = min_not_zero(t->max_user_sectors, b->max_user_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors); t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors, b->max_write_zeroes_sectors); t->max_user_wzeroes_unmap_sectors = min(t->max_user_wzeroes_unmap_sectors, b->max_user_wzeroes_unmap_sectors); t->max_hw_wzeroes_unmap_sectors = min(t->max_hw_wzeroes_unmap_sectors, b->max_hw_wzeroes_unmap_sectors); t->max_hw_zone_append_sectors = min(t->max_hw_zone_append_sectors, b->max_hw_zone_append_sectors); t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask); t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask, b->virt_boundary_mask); t->max_segments = min_not_zero(t->max_segments, b->max_segments); t->max_discard_segments = min_not_zero(t->max_discard_segments, b->max_discard_segments); t->max_integrity_segments = min_not_zero(t->max_integrity_segments, b->max_integrity_segments); t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); alignment = queue_limit_alignment_offset(b, start); /* Bottom device has different alignment. Check that it is * compatible with the current top alignment. */ if (t->alignment_offset != alignment) { top = max(t->physical_block_size, t->io_min) + t->alignment_offset; bottom = max(b->physical_block_size, b->io_min) + alignment; /* Verify that top and bottom intervals line up */ if (max(top, bottom) % min(top, bottom)) { t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } } t->logical_block_size = max(t->logical_block_size, b->logical_block_size); t->physical_block_size = max(t->physical_block_size, b->physical_block_size); t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm_not_zero(t->io_opt, b->io_opt); t->dma_alignment = max(t->dma_alignment, b->dma_alignment); /* Set non-power-of-2 compatible chunk_sectors boundary */ if (b->chunk_sectors) t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors); /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Minimum I/O a multiple of the physical block size? */ if (t->io_min & (t->physical_block_size - 1)) { t->io_min = t->physical_block_size; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Optimal I/O a multiple of the physical block size? */ if (t->io_opt & (t->physical_block_size - 1)) { t->io_opt = 0; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* chunk_sectors a multiple of the physical block size? */ if (t->chunk_sectors % (t->physical_block_size >> SECTOR_SHIFT)) { t->chunk_sectors = 0; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Find lowest common alignment_offset */ t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment) % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } t->max_sectors = blk_round_down_sectors(t->max_sectors, t->logical_block_size); t->max_hw_sectors = blk_round_down_sectors(t->max_hw_sectors, t->logical_block_size); t->max_dev_sectors = blk_round_down_sectors(t->max_dev_sectors, t->logical_block_size); /* Discard alignment and granularity */ if (b->discard_granularity) { alignment = queue_limit_discard_alignment(b, start); t->max_discard_sectors = min_not_zero(t->max_discard_sectors, b->max_discard_sectors); t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors, b->max_hw_discard_sectors); t->discard_granularity = max(t->discard_granularity, b->discard_granularity); t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) % t->discard_granularity; } t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors, b->max_secure_erase_sectors); t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); if (!(t->features & BLK_FEAT_ZONED)) { t->zone_write_granularity = 0; t->max_zone_append_sectors = 0; } blk_stack_atomic_writes_limits(t, b, start); return ret; } EXPORT_SYMBOL(blk_stack_limits); /** * queue_limits_stack_bdev - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @bdev: the underlying block device (bottom) * @offset: offset to beginning of data within component device * @pfx: prefix to use for warnings logged * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment. */ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx) { if (blk_stack_limits(t, bdev_limits(bdev), get_start_sect(bdev) + offset)) pr_notice("%s: Warning: Device %pg is misaligned\n", pfx, bdev); } EXPORT_SYMBOL_GPL(queue_limits_stack_bdev); /** * queue_limits_stack_integrity - stack integrity profile * @t: target queue limits * @b: base queue limits * * Check if the integrity profile in the @b can be stacked into the * target @t. Stacking is possible if either: * * a) does not have any integrity information stacked into it yet * b) the integrity profile in @b is identical to the one in @t * * If @b can be stacked into @t, return %true. Else return %false and clear the * integrity information in @t. */ bool queue_limits_stack_integrity(struct queue_limits *t, struct queue_limits *b) { struct blk_integrity *ti = &t->integrity; struct blk_integrity *bi = &b->integrity; if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) return true; if (ti->flags & BLK_INTEGRITY_STACKED) { if (ti->metadata_size != bi->metadata_size) goto incompatible; if (ti->interval_exp != bi->interval_exp) goto incompatible; if (ti->tag_size != bi->tag_size) goto incompatible; if (ti->csum_type != bi->csum_type) goto incompatible; if (ti->pi_tuple_size != bi->pi_tuple_size) goto incompatible; if ((ti->flags & BLK_INTEGRITY_REF_TAG) != (bi->flags & BLK_INTEGRITY_REF_TAG)) goto incompatible; if ((ti->flags & BLK_SPLIT_INTERVAL_CAPABLE) && !(bi->flags & BLK_SPLIT_INTERVAL_CAPABLE)) ti->flags &= ~BLK_SPLIT_INTERVAL_CAPABLE; } else { ti->flags = BLK_INTEGRITY_STACKED; ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) | (bi->flags & BLK_INTEGRITY_REF_TAG) | (bi->flags & BLK_SPLIT_INTERVAL_CAPABLE); ti->csum_type = bi->csum_type; ti->pi_tuple_size = bi->pi_tuple_size; ti->metadata_size = bi->metadata_size; ti->pi_offset = bi->pi_offset; ti->interval_exp = bi->interval_exp; ti->tag_size = bi->tag_size; } return true; incompatible: memset(ti, 0, sizeof(*ti)); return false; } EXPORT_SYMBOL_GPL(queue_limits_stack_integrity); /** * blk_set_queue_depth - tell the block layer about the device queue depth * @q: the request queue for the device * @depth: queue depth * */ void blk_set_queue_depth(struct request_queue *q, unsigned int depth) { q->queue_depth = depth; rq_qos_queue_depth_changed(q); } EXPORT_SYMBOL(blk_set_queue_depth); int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q->limits.flags & BLK_FLAG_MISALIGNED) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_start_sect); return q->limits.alignment_offset; } EXPORT_SYMBOL_GPL(bdev_alignment_offset); unsigned int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_start_sect); return q->limits.discard_alignment; } EXPORT_SYMBOL_GPL(bdev_discard_alignment); |
| 3 3 1 2 1 2 1 2 2 1 2 1 3 3 3 1 2 1 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs_platform.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_ialloc.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_bmap_btree.h" #include "xfs_alloc_btree.h" #include "xfs_log.h" #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" #include "xfs_da_format.h" #include "xfs_health.h" #include "xfs_ag.h" #include "xfs_rtbitmap.h" #include "xfs_exchrange.h" #include "xfs_rtgroup.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. */ /* * Check that all the V4 feature bits that the V5 filesystem format requires are * correctly set. */ static bool xfs_sb_validate_v5_features( struct xfs_sb *sbp) { /* We must not have any unknown V4 feature bits set */ if (sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) return false; /* * The CRC bit is considered an invalid V4 flag, so we have to add it * manually to the OKBITS mask. */ if (sbp->sb_features2 & ~(XFS_SB_VERSION2_OKBITS | XFS_SB_VERSION2_CRCBIT)) return false; /* Now check all the required V4 feature flags are set. */ #define V5_VERS_FLAGS (XFS_SB_VERSION_NLINKBIT | \ XFS_SB_VERSION_ALIGNBIT | \ XFS_SB_VERSION_LOGV2BIT | \ XFS_SB_VERSION_EXTFLGBIT | \ XFS_SB_VERSION_DIRV2BIT | \ XFS_SB_VERSION_MOREBITSBIT) #define V5_FEAT_FLAGS (XFS_SB_VERSION2_LAZYSBCOUNTBIT | \ XFS_SB_VERSION2_ATTR2BIT | \ XFS_SB_VERSION2_PROJID32BIT | \ XFS_SB_VERSION2_CRCBIT) if ((sbp->sb_versionnum & V5_VERS_FLAGS) != V5_VERS_FLAGS) return false; if ((sbp->sb_features2 & V5_FEAT_FLAGS) != V5_FEAT_FLAGS) return false; return true; } /* * We current support XFS v5 formats with known features and v4 superblocks with * at least V2 directories. */ bool xfs_sb_good_version( struct xfs_sb *sbp) { /* * All v5 filesystems are supported, but we must check that all the * required v4 feature flags are enabled correctly as the code checks * those flags and not for v5 support. */ if (xfs_sb_is_v5(sbp)) return xfs_sb_validate_v5_features(sbp); /* versions prior to v4 are not supported */ if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_4) return false; /* We must not have any unknown v4 feature bits set */ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) || ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) && (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS))) return false; /* V4 filesystems need v2 directories and unwritten extents */ if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT)) return false; if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT)) return false; /* It's a supported v4 filesystem */ return true; } uint64_t xfs_sb_version_to_features( struct xfs_sb *sbp) { uint64_t features = 0; /* optional V4 features */ if (sbp->sb_rblocks > 0) features |= XFS_FEAT_REALTIME; if (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT) features |= XFS_FEAT_NLINK; if (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT) features |= XFS_FEAT_ATTR; if (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT) features |= XFS_FEAT_QUOTA; if (sbp->sb_versionnum & XFS_SB_VERSION_ALIGNBIT) features |= XFS_FEAT_ALIGN; if (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT) features |= XFS_FEAT_LOGV2; if (sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT) features |= XFS_FEAT_DALIGN; if (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT) features |= XFS_FEAT_EXTFLG; if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) features |= XFS_FEAT_SECTOR; if (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT) features |= XFS_FEAT_ASCIICI; if (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) { if (sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT) features |= XFS_FEAT_LAZYSBCOUNT; if (sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT) features |= XFS_FEAT_PROJID32; if (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE) features |= XFS_FEAT_FTYPE; } if (!xfs_sb_is_v5(sbp)) return features; /* Always on V5 features */ features |= XFS_FEAT_ALIGN | XFS_FEAT_LOGV2 | XFS_FEAT_EXTFLG | XFS_FEAT_LAZYSBCOUNT | XFS_FEAT_PROJID32 | XFS_FEAT_V3INODES | XFS_FEAT_CRC | XFS_FEAT_PQUOTINO; /* Optional V5 features */ if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT) features |= XFS_FEAT_FINOBT; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_RMAPBT) features |= XFS_FEAT_RMAPBT; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_REFLINK) features |= XFS_FEAT_REFLINK; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT) features |= XFS_FEAT_INOBTCNT; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE) features |= XFS_FEAT_FTYPE; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES) features |= XFS_FEAT_SPINODES; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID) features |= XFS_FEAT_META_UUID; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_BIGTIME) features |= XFS_FEAT_BIGTIME; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR) features |= XFS_FEAT_NEEDSREPAIR; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NREXT64) features |= XFS_FEAT_NREXT64; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE) features |= XFS_FEAT_EXCHANGE_RANGE; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT) features |= XFS_FEAT_PARENT; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) features |= XFS_FEAT_METADIR; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) features |= XFS_FEAT_ZONED; return features; } /* Check all the superblock fields we care about when reading one in. */ STATIC int xfs_validate_sb_read( struct xfs_mount *mp, struct xfs_sb *sbp) { if (!xfs_sb_is_v5(sbp)) return 0; /* * Version 5 superblock feature mask validation. Reject combinations * the kernel cannot support up front before checking anything else. */ if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) { xfs_warn(mp, "Superblock has unknown compatible features (0x%x) enabled.", (sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN)); xfs_warn(mp, "Using a more recent kernel is recommended."); } if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Superblock has unknown read-only compatible features (0x%x) enabled.", (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); if (!xfs_is_readonly(mp)) { xfs_warn(mp, "Attempted to mount read-only compatible filesystem read-write."); xfs_warn(mp, "Filesystem can only be safely mounted read only."); return -EINVAL; } } if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) { xfs_warn(mp, "Superblock has unknown incompatible features (0x%x) enabled.", (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_UNKNOWN)); xfs_warn(mp, "Filesystem cannot be safely mounted by this kernel."); return -EINVAL; } return 0; } /* Return the number of extents covered by a single rt bitmap file */ static xfs_rtbxlen_t xfs_extents_per_rbm( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) return sbp->sb_rgextents; return sbp->sb_rextents; } /* * Return the payload size of a single rt bitmap block (without the metadata * header if any). */ static inline unsigned int xfs_rtbmblock_size( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) return sbp->sb_blocksize - sizeof(struct xfs_rtbuf_blkinfo); return sbp->sb_blocksize; } static uint64_t xfs_expected_rbmblocks( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) return 0; return howmany_64(xfs_extents_per_rbm(sbp), NBBY * xfs_rtbmblock_size(sbp)); } /* Validate the realtime geometry */ bool xfs_validate_rt_geometry( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) { if (sbp->sb_rextsize != 1) return false; } else { if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) return false; } if (sbp->sb_rblocks == 0) { if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 || sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) return false; return true; } if (sbp->sb_rextents == 0 || sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) || sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) || sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp)) return false; if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) { uint32_t mod; /* * Zoned RT devices must be aligned to the RT group size, * because garbage collection assumes that all zones have the * same size to avoid insane complexity if that weren't the * case. */ div_u64_rem(sbp->sb_rextents, sbp->sb_rgextents, &mod); if (mod) return false; } return true; } /* Check all the superblock fields we care about when writing one out. */ STATIC int xfs_validate_sb_write( struct xfs_mount *mp, struct xfs_buf *bp, struct xfs_sb *sbp) { /* * Carry out additional sb summary counter sanity checks when we write * the superblock. We skip this in the read validator because there * could be newer superblocks in the log and if the values are garbage * even after replay we'll recalculate them at the end of log mount. * * mkfs has traditionally written zeroed counters to inprogress and * secondary superblocks, so allow this usage to continue because * we never read counters from such superblocks. */ if (xfs_buf_daddr(bp) == XFS_SB_DADDR && !sbp->sb_inprogress && (sbp->sb_fdblocks > sbp->sb_dblocks || !xfs_verify_icount(mp, sbp->sb_icount) || sbp->sb_ifree > sbp->sb_icount)) { xfs_warn(mp, "SB summary counter sanity check failed"); return -EFSCORRUPTED; } if (!xfs_sb_is_v5(sbp)) return 0; /* * Version 5 superblock feature mask validation. Reject combinations * the kernel cannot support since we checked for unsupported bits in * the read verifier, which means that memory is corrupt. */ if (!xfs_is_readonly(mp) && xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); return -EFSCORRUPTED; } if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) { xfs_warn(mp, "Corruption detected in superblock incompatible features (0x%x)!", (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_UNKNOWN)); return -EFSCORRUPTED; } if (xfs_sb_has_incompat_log_feature(sbp, XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)) { xfs_warn(mp, "Corruption detected in superblock incompatible log features (0x%x)!", (sbp->sb_features_log_incompat & XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)); return -EFSCORRUPTED; } /* * We can't read verify the sb LSN because the read verifier is called * before the log is allocated and processed. We know the log is set up * before write verifier calls, so check it here. */ if (!xfs_log_check_lsn(mp, sbp->sb_lsn)) return -EFSCORRUPTED; return 0; } int xfs_compute_rgblklog( xfs_rtxlen_t rgextents, xfs_rgblock_t rextsize) { uint64_t rgblocks = (uint64_t)rgextents * rextsize; return xfs_highbit64(rgblocks - 1) + 1; } static int xfs_validate_sb_rtgroups( struct xfs_mount *mp, struct xfs_sb *sbp) { uint64_t groups; int rgblklog; if (sbp->sb_rextsize == 0) { xfs_warn(mp, "Realtime extent size must not be zero."); return -EINVAL; } if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) { xfs_warn(mp, "Realtime group size (%u) must be less than %u rt extents.", sbp->sb_rgextents, XFS_MAX_RGBLOCKS / sbp->sb_rextsize); return -EINVAL; } if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) { xfs_warn(mp, "Realtime group size (%u) must be at least %u rt extents.", sbp->sb_rgextents, XFS_MIN_RGEXTENTS); return -EINVAL; } if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) { xfs_warn(mp, "Realtime groups (%u) must be less than %u.", sbp->sb_rgcount, XFS_MAX_RGNUMBER); return -EINVAL; } groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents); if (groups != sbp->sb_rgcount) { xfs_warn(mp, "Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.", sbp->sb_rgcount, groups); return -EINVAL; } /* Exchange-range is required for fsr to work on realtime files */ if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) { xfs_warn(mp, "Realtime groups feature requires exchange-range support."); return -EINVAL; } rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, sbp->sb_rextsize); if (sbp->sb_rgblklog != rgblklog) { xfs_warn(mp, "Realtime group log (%d) does not match expected value (%d).", sbp->sb_rgblklog, rgblklog); return -EINVAL; } return 0; } static int xfs_validate_sb_zoned( struct xfs_mount *mp, struct xfs_sb *sbp) { if (sbp->sb_frextents != 0) { xfs_warn(mp, "sb_frextents must be zero for zoned file systems."); return -EINVAL; } if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) { xfs_warn(mp, "sb_rtstart (%lld) overlaps sb_dblocks (%lld).", sbp->sb_rtstart, sbp->sb_dblocks); return -EINVAL; } if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) { xfs_warn(mp, "sb_rtreserved (%lld) larger than sb_rblocks (%lld).", sbp->sb_rtreserved, sbp->sb_rblocks); return -EINVAL; } return 0; } /* Check the validity of the SB. */ STATIC int xfs_validate_sb_common( struct xfs_mount *mp, struct xfs_buf *bp, struct xfs_sb *sbp) { struct xfs_dsb *dsb = bp->b_addr; uint32_t agcount = 0; uint32_t rem; bool has_dalign; int error; if (!xfs_verify_magic(bp, dsb->sb_magicnum)) { xfs_warn(mp, "Superblock has bad magic number 0x%x. Not an XFS filesystem?", be32_to_cpu(dsb->sb_magicnum)); return -EWRONGFS; } if (!xfs_sb_good_version(sbp)) { xfs_warn(mp, "Superblock has unknown features enabled or corrupted feature masks."); return -EWRONGFS; } /* * Validate feature flags and state */ if (xfs_sb_is_v5(sbp)) { if (sbp->sb_blocksize < XFS_MIN_CRC_BLOCKSIZE) { xfs_notice(mp, "Block size (%u bytes) too small for Version 5 superblock (minimum %d bytes)", sbp->sb_blocksize, XFS_MIN_CRC_BLOCKSIZE); return -EFSCORRUPTED; } /* V5 has a separate project quota inode */ if (sbp->sb_qflags & (XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD)) { xfs_notice(mp, "Version 5 of Super block has XFS_OQUOTA bits."); return -EFSCORRUPTED; } /* * Full inode chunks must be aligned to inode chunk size when * sparse inodes are enabled to support the sparse chunk * allocation algorithm and prevent overlapping inode records. */ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES) { uint32_t align; align = XFS_INODES_PER_CHUNK * sbp->sb_inodesize >> sbp->sb_blocklog; if (sbp->sb_inoalignmt != align) { xfs_warn(mp, "Inode block alignment (%u) must match chunk size (%u) for sparse inodes.", sbp->sb_inoalignmt, align); return -EINVAL; } if (sbp->sb_spino_align && (sbp->sb_spino_align > sbp->sb_inoalignmt || (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { xfs_warn(mp, "Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", sbp->sb_spino_align, sbp->sb_inoalignmt); return -EINVAL; } } else if (sbp->sb_spino_align) { xfs_warn(mp, "Sparse inode alignment (%u) should be zero.", sbp->sb_spino_align); return -EINVAL; } if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { if (memchr_inv(sbp->sb_pad, 0, sizeof(sbp->sb_pad))) { xfs_warn(mp, "Metadir superblock padding fields must be zero."); return -EINVAL; } error = xfs_validate_sb_rtgroups(mp, sbp); if (error) return error; } if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { error = xfs_validate_sb_zoned(mp, sbp); if (error) return error; } } else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) { xfs_notice(mp, "Superblock earlier than Version 5 has XFS_{P|G}QUOTA_{ENFD|CHKD} bits."); return -EFSCORRUPTED; } if (unlikely( sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) { xfs_warn(mp, "filesystem is marked as having an external log; " "specify logdev on the mount command line."); return -EINVAL; } if (unlikely( sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) { xfs_warn(mp, "filesystem is marked as having an internal log; " "do not specify logdev on the mount command line."); return -EINVAL; } /* Compute agcount for this number of dblocks and agblocks */ if (sbp->sb_agblocks) { agcount = div_u64_rem(sbp->sb_dblocks, sbp->sb_agblocks, &rem); if (rem) agcount++; } /* * More sanity checking. Most of these were stolen directly from * xfs_repair. */ if (unlikely( sbp->sb_agcount <= 0 || sbp->sb_sectsize < XFS_MIN_SECTORSIZE || sbp->sb_sectsize > XFS_MAX_SECTORSIZE || sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG || sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG || sbp->sb_sectsize != (1 << sbp->sb_sectlog) || sbp->sb_blocksize < XFS_MIN_BLOCKSIZE || sbp->sb_blocksize > XFS_MAX_BLOCKSIZE || sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG || sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_blocksize != (1 << sbp->sb_blocklog) || sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_inodesize < XFS_DINODE_MIN_SIZE || sbp->sb_inodesize > XFS_DINODE_MAX_SIZE || sbp->sb_inodelog < XFS_DINODE_MIN_LOG || sbp->sb_inodelog > XFS_DINODE_MAX_LOG || sbp->sb_inodesize != (1 << sbp->sb_inodelog) || sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) || XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES || XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES || sbp->sb_agblklog != xfs_highbit32(sbp->sb_agblocks - 1) + 1 || agcount == 0 || agcount != sbp->sb_agcount || (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog) || (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE) || (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) || (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */) || sbp->sb_dblocks == 0 || sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) || sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp) || sbp->sb_shared_vn != 0)) { xfs_notice(mp, "SB sanity check failed"); return -EFSCORRUPTED; } /* * Logs that are too large are not supported at all. Reject them * outright. Logs that are too small are tolerated on v4 filesystems, * but we can only check that when mounting the log. Hence we skip * those checks here. */ if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) { xfs_notice(mp, "Log size 0x%x blocks too large, maximum size is 0x%llx blocks", sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS); return -EFSCORRUPTED; } if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) { xfs_warn(mp, "log size 0x%llx bytes too large, maximum size is 0x%llx bytes", XFS_FSB_TO_B(mp, sbp->sb_logblocks), XFS_MAX_LOG_BYTES); return -EFSCORRUPTED; } /* * Do not allow filesystems with corrupted log sector or stripe units to * be mounted. We cannot safely size the iclogs or write to the log if * the log stripe unit is not valid. */ if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) { if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) { xfs_notice(mp, "log sector size in bytes/log2 (0x%x/0x%x) must match", sbp->sb_logsectsize, 1U << sbp->sb_logsectlog); return -EFSCORRUPTED; } } else if (sbp->sb_logsectsize || sbp->sb_logsectlog) { xfs_notice(mp, "log sector size in bytes/log2 (0x%x/0x%x) are not zero", sbp->sb_logsectsize, sbp->sb_logsectlog); return -EFSCORRUPTED; } if (sbp->sb_logsunit > 1) { if (sbp->sb_logsunit % sbp->sb_blocksize) { xfs_notice(mp, "log stripe unit 0x%x bytes must be a multiple of block size", sbp->sb_logsunit); return -EFSCORRUPTED; } if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) { xfs_notice(mp, "log stripe unit 0x%x bytes over maximum size (0x%x bytes)", sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE); return -EFSCORRUPTED; } } if (!xfs_validate_rt_geometry(sbp)) { xfs_notice(mp, "realtime %sgeometry check failed", sbp->sb_rblocks ? "" : "zeroed "); return -EFSCORRUPTED; } /* * Either (sb_unit and !hasdalign) or (!sb_unit and hasdalign) * would imply the image is corrupted. */ has_dalign = sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT; if (!!sbp->sb_unit ^ has_dalign) { xfs_notice(mp, "SB stripe alignment sanity check failed"); return -EFSCORRUPTED; } if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit), XFS_FSB_TO_B(mp, sbp->sb_width), 0, xfs_buf_daddr(bp) == XFS_SB_DADDR, false)) return -EFSCORRUPTED; /* * Currently only very few inode sizes are supported. */ switch (sbp->sb_inodesize) { case 256: case 512: case 1024: case 2048: break; default: xfs_warn(mp, "inode size of %d bytes not supported", sbp->sb_inodesize); return -ENOSYS; } return 0; } void xfs_sb_quota_from_disk(struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { sbp->sb_uquotino = NULLFSINO; sbp->sb_gquotino = NULLFSINO; sbp->sb_pquotino = NULLFSINO; return; } /* * older mkfs doesn't initialize quota inodes to NULLFSINO. This * leads to in-core values having two different values for a quota * inode to be invalid: 0 and NULLFSINO. Change it to a single value * NULLFSINO. * * Note that this change affect only the in-core values. These * values are not written back to disk unless any quota information * is written to the disk. Even in that case, sb_pquotino field is * not written to disk unless the superblock supports pquotino. */ if (sbp->sb_uquotino == 0) sbp->sb_uquotino = NULLFSINO; if (sbp->sb_gquotino == 0) sbp->sb_gquotino = NULLFSINO; if (sbp->sb_pquotino == 0) sbp->sb_pquotino = NULLFSINO; /* * We need to do these manipilations only if we are working * with an older version of on-disk superblock. */ if (xfs_sb_is_v5(sbp)) return; if (sbp->sb_qflags & XFS_OQUOTA_ENFD) sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ? XFS_PQUOTA_ENFD : XFS_GQUOTA_ENFD; if (sbp->sb_qflags & XFS_OQUOTA_CHKD) sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ? XFS_PQUOTA_CHKD : XFS_GQUOTA_CHKD; sbp->sb_qflags &= ~(XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD); if (sbp->sb_qflags & XFS_PQUOTA_ACCT && sbp->sb_gquotino != NULLFSINO) { /* * In older version of superblock, on-disk superblock only * has sb_gquotino, and in-core superblock has both sb_gquotino * and sb_pquotino. But, only one of them is supported at any * point of time. So, if PQUOTA is set in disk superblock, * copy over sb_gquotino to sb_pquotino. The NULLFSINO test * above is to make sure we don't do this twice and wipe them * both out! */ sbp->sb_pquotino = sbp->sb_gquotino; sbp->sb_gquotino = NULLFSINO; } } static void __xfs_sb_from_disk( struct xfs_sb *to, struct xfs_dsb *from, bool convert_xquota) { to->sb_magicnum = be32_to_cpu(from->sb_magicnum); to->sb_blocksize = be32_to_cpu(from->sb_blocksize); to->sb_dblocks = be64_to_cpu(from->sb_dblocks); to->sb_rblocks = be64_to_cpu(from->sb_rblocks); to->sb_rextents = be64_to_cpu(from->sb_rextents); memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid)); to->sb_logstart = be64_to_cpu(from->sb_logstart); to->sb_rootino = be64_to_cpu(from->sb_rootino); to->sb_rbmino = be64_to_cpu(from->sb_rbmino); to->sb_rsumino = be64_to_cpu(from->sb_rsumino); to->sb_rextsize = be32_to_cpu(from->sb_rextsize); to->sb_agblocks = be32_to_cpu(from->sb_agblocks); to->sb_agcount = be32_to_cpu(from->sb_agcount); to->sb_rbmblocks = be32_to_cpu(from->sb_rbmblocks); to->sb_logblocks = be32_to_cpu(from->sb_logblocks); to->sb_versionnum = be16_to_cpu(from->sb_versionnum); to->sb_sectsize = be16_to_cpu(from->sb_sectsize); to->sb_inodesize = be16_to_cpu(from->sb_inodesize); to->sb_inopblock = be16_to_cpu(from->sb_inopblock); memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname)); to->sb_blocklog = from->sb_blocklog; to->sb_sectlog = from->sb_sectlog; to->sb_inodelog = from->sb_inodelog; to->sb_inopblog = from->sb_inopblog; to->sb_agblklog = from->sb_agblklog; to->sb_rextslog = from->sb_rextslog; to->sb_inprogress = from->sb_inprogress; to->sb_imax_pct = from->sb_imax_pct; to->sb_icount = be64_to_cpu(from->sb_icount); to->sb_ifree = be64_to_cpu(from->sb_ifree); to->sb_fdblocks = be64_to_cpu(from->sb_fdblocks); to->sb_frextents = be64_to_cpu(from->sb_frextents); to->sb_uquotino = be64_to_cpu(from->sb_uquotino); to->sb_gquotino = be64_to_cpu(from->sb_gquotino); to->sb_qflags = be16_to_cpu(from->sb_qflags); to->sb_flags = from->sb_flags; to->sb_shared_vn = from->sb_shared_vn; to->sb_inoalignmt = be32_to_cpu(from->sb_inoalignmt); to->sb_unit = be32_to_cpu(from->sb_unit); to->sb_width = be32_to_cpu(from->sb_width); to->sb_dirblklog = from->sb_dirblklog; to->sb_logsectlog = from->sb_logsectlog; to->sb_logsectsize = be16_to_cpu(from->sb_logsectsize); to->sb_logsunit = be32_to_cpu(from->sb_logsunit); to->sb_features2 = be32_to_cpu(from->sb_features2); to->sb_bad_features2 = be32_to_cpu(from->sb_bad_features2); to->sb_features_compat = be32_to_cpu(from->sb_features_compat); to->sb_features_ro_compat = be32_to_cpu(from->sb_features_ro_compat); to->sb_features_incompat = be32_to_cpu(from->sb_features_incompat); to->sb_features_log_incompat = be32_to_cpu(from->sb_features_log_incompat); /* crc is only used on disk, not in memory; just init to 0 here. */ to->sb_crc = 0; to->sb_spino_align = be32_to_cpu(from->sb_spino_align); to->sb_pquotino = be64_to_cpu(from->sb_pquotino); to->sb_lsn = be64_to_cpu(from->sb_lsn); /* * sb_meta_uuid is only on disk if it differs from sb_uuid and the * feature flag is set; if not set we keep it only in memory. */ if (xfs_sb_is_v5(to) && (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID)) uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid); else uuid_copy(&to->sb_meta_uuid, &from->sb_uuid); /* Convert on-disk flags to in-memory flags? */ if (convert_xquota) xfs_sb_quota_from_disk(to); if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { to->sb_metadirino = be64_to_cpu(from->sb_metadirino); to->sb_rgblklog = from->sb_rgblklog; memcpy(to->sb_pad, from->sb_pad, sizeof(to->sb_pad)); to->sb_rgcount = be32_to_cpu(from->sb_rgcount); to->sb_rgextents = be32_to_cpu(from->sb_rgextents); to->sb_rbmino = NULLFSINO; to->sb_rsumino = NULLFSINO; } else { to->sb_metadirino = NULLFSINO; to->sb_rgcount = 1; to->sb_rgextents = 0; } if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { to->sb_rtstart = be64_to_cpu(from->sb_rtstart); to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved); } else { to->sb_rtstart = 0; to->sb_rtreserved = 0; } } void xfs_sb_from_disk( struct xfs_sb *to, struct xfs_dsb *from) { __xfs_sb_from_disk(to, from, true); } static void xfs_sb_quota_to_disk( struct xfs_dsb *to, struct xfs_sb *from) { uint16_t qflags = from->sb_qflags; if (xfs_sb_is_v5(from) && (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { to->sb_qflags = cpu_to_be16(from->sb_qflags); to->sb_uquotino = cpu_to_be64(0); to->sb_gquotino = cpu_to_be64(0); to->sb_pquotino = cpu_to_be64(0); return; } to->sb_uquotino = cpu_to_be64(from->sb_uquotino); /* * The in-memory superblock quota state matches the v5 on-disk format so * just write them out and return */ if (xfs_sb_is_v5(from)) { to->sb_qflags = cpu_to_be16(from->sb_qflags); to->sb_gquotino = cpu_to_be64(from->sb_gquotino); to->sb_pquotino = cpu_to_be64(from->sb_pquotino); return; } /* * For older superblocks (v4), the in-core version of sb_qflags do not * have XFS_OQUOTA_* flags, whereas the on-disk version does. So, * convert incore XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags. */ qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD); if (from->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD)) qflags |= XFS_OQUOTA_ENFD; if (from->sb_qflags & (XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) qflags |= XFS_OQUOTA_CHKD; to->sb_qflags = cpu_to_be16(qflags); /* * GQUOTINO and PQUOTINO cannot be used together in versions * of superblock that do not have pquotino. from->sb_flags * tells us which quota is active and should be copied to * disk. If neither are active, we should NULL the inode. * * In all cases, the separate pquotino must remain 0 because it * is beyond the "end" of the valid non-pquotino superblock. */ if (from->sb_qflags & XFS_GQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_gquotino); else if (from->sb_qflags & XFS_PQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_pquotino); else { /* * We can't rely on just the fields being logged to tell us * that it is safe to write NULLFSINO - we should only do that * if quotas are not actually enabled. Hence only write * NULLFSINO if both in-core quota inodes are NULL. */ if (from->sb_gquotino == NULLFSINO && from->sb_pquotino == NULLFSINO) to->sb_gquotino = cpu_to_be64(NULLFSINO); } to->sb_pquotino = 0; } void xfs_sb_to_disk( struct xfs_dsb *to, struct xfs_sb *from) { xfs_sb_quota_to_disk(to, from); to->sb_magicnum = cpu_to_be32(from->sb_magicnum); to->sb_blocksize = cpu_to_be32(from->sb_blocksize); to->sb_dblocks = cpu_to_be64(from->sb_dblocks); to->sb_rblocks = cpu_to_be64(from->sb_rblocks); to->sb_rextents = cpu_to_be64(from->sb_rextents); memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid)); to->sb_logstart = cpu_to_be64(from->sb_logstart); to->sb_rootino = cpu_to_be64(from->sb_rootino); to->sb_rbmino = cpu_to_be64(from->sb_rbmino); to->sb_rsumino = cpu_to_be64(from->sb_rsumino); to->sb_rextsize = cpu_to_be32(from->sb_rextsize); to->sb_agblocks = cpu_to_be32(from->sb_agblocks); to->sb_agcount = cpu_to_be32(from->sb_agcount); to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks); to->sb_logblocks = cpu_to_be32(from->sb_logblocks); to->sb_versionnum = cpu_to_be16(from->sb_versionnum); to->sb_sectsize = cpu_to_be16(from->sb_sectsize); to->sb_inodesize = cpu_to_be16(from->sb_inodesize); to->sb_inopblock = cpu_to_be16(from->sb_inopblock); memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname)); to->sb_blocklog = from->sb_blocklog; to->sb_sectlog = from->sb_sectlog; to->sb_inodelog = from->sb_inodelog; to->sb_inopblog = from->sb_inopblog; to->sb_agblklog = from->sb_agblklog; to->sb_rextslog = from->sb_rextslog; to->sb_inprogress = from->sb_inprogress; to->sb_imax_pct = from->sb_imax_pct; to->sb_icount = cpu_to_be64(from->sb_icount); to->sb_ifree = cpu_to_be64(from->sb_ifree); to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks); to->sb_frextents = cpu_to_be64(from->sb_frextents); to->sb_flags = from->sb_flags; to->sb_shared_vn = from->sb_shared_vn; to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt); to->sb_unit = cpu_to_be32(from->sb_unit); to->sb_width = cpu_to_be32(from->sb_width); to->sb_dirblklog = from->sb_dirblklog; to->sb_logsectlog = from->sb_logsectlog; to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize); to->sb_logsunit = cpu_to_be32(from->sb_logsunit); /* * We need to ensure that bad_features2 always matches features2. * Hence we enforce that here rather than having to remember to do it * everywhere else that updates features2. */ from->sb_bad_features2 = from->sb_features2; to->sb_features2 = cpu_to_be32(from->sb_features2); to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2); if (!xfs_sb_is_v5(from)) return; to->sb_features_compat = cpu_to_be32(from->sb_features_compat); to->sb_features_ro_compat = cpu_to_be32(from->sb_features_ro_compat); to->sb_features_incompat = cpu_to_be32(from->sb_features_incompat); to->sb_features_log_incompat = cpu_to_be32(from->sb_features_log_incompat); to->sb_spino_align = cpu_to_be32(from->sb_spino_align); to->sb_lsn = cpu_to_be64(from->sb_lsn); if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID) uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid); if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { to->sb_metadirino = cpu_to_be64(from->sb_metadirino); to->sb_rgblklog = from->sb_rgblklog; memset(to->sb_pad, 0, sizeof(to->sb_pad)); to->sb_rgcount = cpu_to_be32(from->sb_rgcount); to->sb_rgextents = cpu_to_be32(from->sb_rgextents); to->sb_rbmino = cpu_to_be64(0); to->sb_rsumino = cpu_to_be64(0); } if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { to->sb_rtstart = cpu_to_be64(from->sb_rtstart); to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved); } } /* * If the superblock has the CRC feature bit set or the CRC field is non-null, * check that the CRC is valid. We check the CRC field is non-null because a * single bit error could clear the feature bit and unused parts of the * superblock are supposed to be zero. Hence a non-null crc field indicates that * we've potentially lost a feature bit and we should check it anyway. * * However, past bugs (i.e. in growfs) left non-zeroed regions beyond the * last field in V4 secondary superblocks. So for secondary superblocks, * we are more forgiving, and ignore CRC failures if the primary doesn't * indicate that the fs version is V5. */ static void xfs_sb_read_verify( struct xfs_buf *bp) { struct xfs_sb sb; struct xfs_mount *mp = bp->b_mount; struct xfs_dsb *dsb = bp->b_addr; int error; /* * open code the version check to avoid needing to convert the entire * superblock from disk order just to check the version number */ if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC) && (((be16_to_cpu(dsb->sb_versionnum) & XFS_SB_VERSION_NUMBITS) == XFS_SB_VERSION_5) || dsb->sb_crc != 0)) { if (!xfs_buf_verify_cksum(bp, XFS_SB_CRC_OFF)) { /* Only fail bad secondaries on a known V5 filesystem */ if (xfs_buf_daddr(bp) == XFS_SB_DADDR || xfs_has_crc(mp)) { error = -EFSBADCRC; goto out_error; } } } /* * Check all the superblock fields. Don't byteswap the xquota flags * because _verify_common checks the on-disk values. */ __xfs_sb_from_disk(&sb, dsb, false); error = xfs_validate_sb_read(mp, &sb); if (error) goto out_error; error = xfs_validate_sb_common(mp, bp, &sb); out_error: if (error == -EFSCORRUPTED || error == -EFSBADCRC) xfs_verifier_error(bp, error, __this_address); else if (error) xfs_buf_ioerror(bp, error); } /* * We may be probed for a filesystem match, so we may not want to emit * messages when the superblock buffer is not actually an XFS superblock. * If we find an XFS superblock, then run a normal, noisy mount because we are * really going to mount it and want to know about errors. */ static void xfs_sb_quiet_read_verify( struct xfs_buf *bp) { struct xfs_dsb *dsb = bp->b_addr; if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) { /* XFS filesystem, verify noisily! */ xfs_sb_read_verify(bp); return; } /* quietly fail */ xfs_buf_ioerror(bp, -EWRONGFS); } static void xfs_sb_write_verify( struct xfs_buf *bp) { struct xfs_sb sb; struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dsb *dsb = bp->b_addr; int error; /* * Check all the superblock fields. Don't byteswap the xquota flags * because _verify_common checks the on-disk values. */ __xfs_sb_from_disk(&sb, dsb, false); error = xfs_validate_sb_common(mp, bp, &sb); if (error) goto out_error; error = xfs_validate_sb_write(mp, bp, &sb); if (error) goto out_error; if (!xfs_sb_is_v5(&sb)) return; if (bip) dsb->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF); return; out_error: xfs_verifier_error(bp, error, __this_address); } const struct xfs_buf_ops xfs_sb_buf_ops = { .name = "xfs_sb", .magic = { cpu_to_be32(XFS_SB_MAGIC), cpu_to_be32(XFS_SB_MAGIC) }, .verify_read = xfs_sb_read_verify, .verify_write = xfs_sb_write_verify, }; const struct xfs_buf_ops xfs_sb_quiet_buf_ops = { .name = "xfs_sb_quiet", .magic = { cpu_to_be32(XFS_SB_MAGIC), cpu_to_be32(XFS_SB_MAGIC) }, .verify_read = xfs_sb_quiet_read_verify, .verify_write = xfs_sb_write_verify, }; /* Compute cached rt geometry from the incore sb. */ void xfs_sb_mount_rextsize( struct xfs_mount *mp, struct xfs_sb *sbp) { struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize); mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize); if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize; rgs->blklog = mp->m_sb.sb_rgblklog; rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog); rgs->start_fsb = mp->m_sb.sb_rtstart; if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)) rgs->has_daddr_gaps = true; } else { rgs->blocks = 0; rgs->blklog = 0; rgs->blkmask = (uint64_t)-1; } } /* Update incore sb rt extent size, then recompute the cached rt geometry. */ void xfs_mount_sb_set_rextsize( struct xfs_mount *mp, struct xfs_sb *sbp, xfs_agblock_t rextsize) { sbp->sb_rextsize = rextsize; if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) sbp->sb_rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, rextsize); xfs_sb_mount_rextsize(mp, sbp); } /* * xfs_mount_common * * Mount initialization code establishing various mount * fields from the superblock associated with the given * mount structure. * * Inode geometry are calculated in xfs_ialloc_setup_geometry. */ void xfs_sb_mount_common( struct xfs_mount *mp, struct xfs_sb *sbp) { struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG]; mp->m_agfrotor = 0; atomic_set(&mp->m_agirotor, 0); mp->m_maxagi = mp->m_sb.sb_agcount; mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG; mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT; mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT; mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1; mp->m_blockmask = sbp->sb_blocksize - 1; mp->m_blockwsize = xfs_rtbmblock_size(sbp) >> XFS_WORDLOG; mp->m_rtx_per_rbmblock = mp->m_blockwsize << XFS_NBWORDLOG; ags->blocks = mp->m_sb.sb_agblocks; ags->blklog = mp->m_sb.sb_agblklog; ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog); xfs_sb_mount_rextsize(mp, sbp); mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2; mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2; mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2; mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2; mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2; mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2; mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2; mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2; mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2; mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2; mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2; mp->m_bsize = XFS_FSB_TO_BB(mp, 1); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); } /* * xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock * into the superblock buffer to be logged. It does not provide the higher * level of locking that is needed to protect the in-core superblock from * concurrent access. */ void xfs_log_sb( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *bp = xfs_trans_getsb(tp); /* * Lazy sb counters don't update the in-core superblock so do that now. * If this is at unmount, the counters will be exactly correct, but at * any other time they will only be ballpark correct because of * reservations that have been taken out percpu counters. If we have an * unclean shutdown, this will be corrected by log recovery rebuilding * the counters from the AGF block counts. */ if (xfs_has_lazysbcount(mp)) { mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount); mp->m_sb.sb_ifree = min_t(uint64_t, percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS); } /* * sb_frextents was added to the lazy sb counters when the rt groups * feature was introduced. This counter can go negative due to the way * we handle nearly-lockless reservations, so we must use the _positive * variant here to avoid writing out nonsense frextents. * * RT groups are only supported on v5 file systems, which always * have lazy SB counters. */ if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) { mp->m_sb.sb_frextents = xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS); } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1); } /* * xfs_sync_sb * * Sync the superblock to disk. * * Note that the caller is responsible for checking the frozen state of the * filesystem. This procedure uses the non-blocking transaction allocator and * thus will allow modifications to a frozen fs. This is required because this * code can be called during the process of freezing where use of the high-level * allocator would deadlock. */ int xfs_sync_sb( struct xfs_mount *mp, bool wait) { struct xfs_trans *tp; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, XFS_TRANS_NO_WRITECOUNT, &tp); if (error) return error; xfs_log_sb(tp); if (wait) xfs_trans_set_sync(tp); return xfs_trans_commit(tp); } /* * Update all the secondary superblocks to match the new state of the primary. * Because we are completely overwriting all the existing fields in the * secondary superblock buffers, there is no need to read them in from disk. * Just get a new buffer, stamp it and write it. * * The sb buffers need to be cached here so that we serialise against other * operations that access the secondary superblocks, but we don't want to keep * them in memory once it is written so we mark it as a one-shot buffer. */ int xfs_update_secondary_sbs( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; int saved_error = 0; int error = 0; LIST_HEAD (buffer_list); /* update secondary superblocks. */ while ((pag = xfs_perag_next_from(mp, pag, 1))) { struct xfs_buf *bp; error = xfs_buf_get(mp->m_ddev_targp, XFS_AG_DADDR(mp, pag_agno(pag), XFS_SB_DADDR), XFS_FSS_TO_BB(mp, 1), &bp); /* * If we get an error reading or writing alternate superblocks, * continue. xfs_repair chooses the "best" superblock based * on most matches; if we break early, we'll leave more * superblocks un-updated than updated, and xfs_repair may * pick them over the properly-updated primary. */ if (error) { xfs_warn(mp, "error allocating secondary superblock for ag %d", pag_agno(pag)); if (!saved_error) saved_error = error; continue; } bp->b_ops = &xfs_sb_buf_ops; xfs_buf_oneshot(bp); xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); xfs_sb_to_disk(bp->b_addr, &mp->m_sb); xfs_buf_delwri_queue(bp, &buffer_list); xfs_buf_relse(bp); /* don't hold too many buffers at once */ if (pag_agno(pag) % 16) continue; error = xfs_buf_delwri_submit(&buffer_list); if (error) { xfs_warn(mp, "write error %d updating a secondary superblock near ag %d", error, pag_agno(pag)); if (!saved_error) saved_error = error; continue; } } error = xfs_buf_delwri_submit(&buffer_list); if (error) xfs_warn(mp, "error %d writing secondary superblocks", error); return saved_error ? saved_error : error; } /* * Same behavior as xfs_sync_sb, except that it is always synchronous and it * also writes the superblock buffer to disk sector 0 immediately. */ int xfs_sync_sb_buf( struct xfs_mount *mp, bool update_rtsb) { struct xfs_trans *tp; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); if (error) return error; xfs_log_sb(tp); if (update_rtsb) xfs_log_rtsb(tp, xfs_trans_getsb(tp)); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) return error; /* Re-acquire and write the sb and rtsb to disk. */ xfs_buf_lock(mp->m_sb_bp); error = xfs_bwrite(mp->m_sb_bp); xfs_buf_unlock(mp->m_sb_bp); if (error) return error; if (update_rtsb && mp->m_rtsb_bp) { xfs_buf_lock(mp->m_rtsb_bp); error = xfs_bwrite(mp->m_rtsb_bp); xfs_buf_unlock(mp->m_rtsb_bp); } return error; } void xfs_fs_geometry( struct xfs_mount *mp, struct xfs_fsop_geom *geo, int struct_version) { struct xfs_sb *sbp = &mp->m_sb; memset(geo, 0, sizeof(struct xfs_fsop_geom)); geo->blocksize = sbp->sb_blocksize; geo->rtextsize = sbp->sb_rextsize; geo->agblocks = sbp->sb_agblocks; geo->agcount = sbp->sb_agcount; geo->logblocks = sbp->sb_logblocks; geo->sectsize = sbp->sb_sectsize; geo->inodesize = sbp->sb_inodesize; geo->imaxpct = sbp->sb_imax_pct; geo->datablocks = sbp->sb_dblocks; geo->rtblocks = sbp->sb_rblocks; geo->rtextents = sbp->sb_rextents; geo->logstart = sbp->sb_logstart; BUILD_BUG_ON(sizeof(geo->uuid) != sizeof(sbp->sb_uuid)); memcpy(geo->uuid, &sbp->sb_uuid, sizeof(sbp->sb_uuid)); if (struct_version < 2) return; geo->sunit = sbp->sb_unit; geo->swidth = sbp->sb_width; if (struct_version < 3) return; geo->version = XFS_FSOP_GEOM_VERSION; geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK | XFS_FSOP_GEOM_FLAGS_DIRV2 | XFS_FSOP_GEOM_FLAGS_EXTFLG | XFS_FSOP_GEOM_FLAGS_ATTR2; if (xfs_has_attr(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR; if (xfs_has_quota(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_QUOTA; if (xfs_has_align(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_IALIGN; if (xfs_has_dalign(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_DALIGN; if (xfs_has_asciici(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_DIRV2CI; if (xfs_has_lazysbcount(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_LAZYSB; if (xfs_has_projid32(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_PROJID32; if (xfs_has_crc(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_V5SB; if (xfs_has_ftype(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_FTYPE; if (xfs_has_finobt(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_FINOBT; if (xfs_has_sparseinodes(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_SPINODES; if (xfs_has_rmapbt(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_RMAPBT; if (xfs_has_reflink(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_REFLINK; if (xfs_has_bigtime(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME; if (xfs_has_inobtcounts(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT; if (xfs_has_parent(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_PARENT; if (xfs_has_sector(mp)) { geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR; geo->logsectsize = sbp->sb_logsectsize; } else { geo->logsectsize = BBSIZE; } if (xfs_has_large_extent_counts(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64; if (xfs_has_exchange_range(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE; if (xfs_has_metadir(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR; if (xfs_has_zoned(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED; geo->rtsectsize = sbp->sb_blocksize; geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp); if (struct_version < 4) return; if (xfs_has_logv2(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_LOGV2; geo->logsunit = sbp->sb_logsunit; if (struct_version < 5) return; geo->version = XFS_FSOP_GEOM_VERSION_V5; if (xfs_has_rtgroups(mp)) { geo->rgcount = sbp->sb_rgcount; geo->rgextents = sbp->sb_rgextents; } if (xfs_has_zoned(mp)) { geo->rtstart = sbp->sb_rtstart; geo->rtreserved = sbp->sb_rtreserved; } } /* Read a secondary superblock. */ int xfs_sb_read_secondary( struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp) { struct xfs_buf *bp; int error; ASSERT(agno != 0 && agno != NULLAGNUMBER); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops); if (xfs_metadata_is_sick(error)) xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB); if (error) return error; xfs_buf_set_ref(bp, XFS_SSB_REF); *bpp = bp; return 0; } /* Get an uninitialised secondary superblock buffer. */ int xfs_sb_get_secondary( struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp) { struct xfs_buf *bp; int error; ASSERT(agno != 0 && agno != NULLAGNUMBER); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp); if (error) return error; bp->b_ops = &xfs_sb_buf_ops; xfs_buf_oneshot(bp); *bpp = bp; return 0; } /* * sunit, swidth, sectorsize(optional with 0) should be all in bytes, so users * won't be confused by values in error messages. This function returns false * if the stripe geometry is invalid and the caller is unable to repair the * stripe configuration later in the mount process. */ bool xfs_validate_stripe_geometry( struct xfs_mount *mp, __s64 sunit, __s64 swidth, int sectorsize, bool may_repair, bool silent) { if (swidth > INT_MAX) { if (!silent) xfs_notice(mp, "stripe width (%lld) is too large", swidth); goto check_override; } if (sunit > swidth) { if (!silent) xfs_notice(mp, "stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth); goto check_override; } if (sectorsize && (int)sunit % sectorsize) { if (!silent) xfs_notice(mp, "stripe unit (%lld) must be a multiple of the sector size (%d)", sunit, sectorsize); goto check_override; } if (sunit && !swidth) { if (!silent) xfs_notice(mp, "invalid stripe unit (%lld) and stripe width of 0", sunit); goto check_override; } if (!sunit && swidth) { if (!silent) xfs_notice(mp, "invalid stripe width (%lld) and stripe unit of 0", swidth); goto check_override; } if (sunit && (int)swidth % (int)sunit) { if (!silent) xfs_notice(mp, "stripe width (%lld) must be a multiple of the stripe unit (%lld)", swidth, sunit); goto check_override; } return true; check_override: if (!may_repair) return false; /* * During mount, mp->m_dalign will not be set unless the sunit mount * option was set. If it was set, ignore the bad stripe alignment values * and allow the validation and overwrite later in the mount process to * attempt to overwrite the bad stripe alignment values with the values * supplied by mount options. */ if (!mp->m_dalign) return false; if (!silent) xfs_notice(mp, "Will try to correct with specified mount options sunit (%d) and swidth (%d)", BBTOB(mp->m_dalign), BBTOB(mp->m_swidth)); return true; } /* * Compute the maximum level number of the realtime summary file, as defined by * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct * use of rt volumes with more than 2^32 extents. */ uint8_t xfs_compute_rextslog( xfs_rtbxlen_t rtextents) { if (!rtextents) return 0; return xfs_highbit64(rtextents); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * MCE event pool management in MCE context * * Copyright (C) 2015 Intel Corp. * Author: Chen, Gong <gong.chen@linux.intel.com> */ #include <linux/smp.h> #include <linux/mm.h> #include <linux/genalloc.h> #include <linux/llist.h> #include "internal.h" /* * printk() is not safe in MCE context. This is a lock-less memory allocator * used to save error information organized in a lock-less list. * * This memory pool is only to be used to save MCE records in MCE context. * MCE events are rare, so a fixed size memory pool should be enough. * Allocate on a sliding scale based on number of CPUs. */ #define MCE_MIN_ENTRIES 80 #define MCE_PER_CPU 2 static struct gen_pool *mce_evt_pool; static LLIST_HEAD(mce_event_llist); /* * Compare the record "t" with each of the records on list "l" to see if * an equivalent one is present in the list. */ static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l) { struct mce_hw_err *err1, *err2; struct mce_evt_llist *node; err1 = &t->err; llist_for_each_entry(node, &l->llnode, llnode) { err2 = &node->err; if (!mce_cmp(&err1->m, &err2->m)) return true; } return false; } /* * The system has panicked - we'd like to peruse the list of MCE records * that have been queued, but not seen by anyone yet. The list is in * reverse time order, so we need to reverse it. While doing that we can * also drop duplicate records (these were logged because some banks are * shared between cores or by all threads on a socket). */ struct llist_node *mce_gen_pool_prepare_records(void) { struct llist_node *head; LLIST_HEAD(new_head); struct mce_evt_llist *node, *t; head = llist_del_all(&mce_event_llist); if (!head) return NULL; /* squeeze out duplicates while reversing order */ llist_for_each_entry_safe(node, t, head, llnode) { if (!is_duplicate_mce_record(node, t)) llist_add(&node->llnode, &new_head); } return new_head.first; } void mce_gen_pool_process(struct work_struct *__unused) { struct mce_evt_llist *node, *tmp; struct llist_node *head; struct mce *mce; head = llist_del_all(&mce_event_llist); if (!head) return; head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->err.m; blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } } bool mce_gen_pool_empty(void) { return llist_empty(&mce_event_llist); } bool mce_gen_pool_add(struct mce_hw_err *err) { struct mce_evt_llist *node; if (filter_mce(&err->m)) return false; if (!mce_evt_pool) return false; node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); if (!node) { pr_warn_ratelimited("MCE records pool full!\n"); return false; } memcpy(&node->err, err, sizeof(*err)); llist_add(&node->llnode, &mce_event_llist); return true; } static bool mce_gen_pool_create(void) { int mce_numrecords, mce_poolsz, order; struct gen_pool *gpool; void *mce_pool; order = order_base_2(sizeof(struct mce_evt_llist)); gpool = gen_pool_create(order, -1); if (!gpool) return false; mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU); mce_poolsz = mce_numrecords * (1 << order); mce_pool = kmalloc(mce_poolsz, GFP_KERNEL); if (!mce_pool) { gen_pool_destroy(gpool); return false; } if (gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1)) { gen_pool_destroy(gpool); kfree(mce_pool); return false; } mce_evt_pool = gpool; return true; } bool mce_gen_pool_init(void) { /* Just init mce_gen_pool once. */ if (mce_evt_pool) return true; return mce_gen_pool_create(); } |
| 47 3 39 10 10 10 10 10 2 2 2 2 1 1 1 2 2 2 2 2 3 1 2 2 9 2 1 4 1 1 4 1 3 2 2 3 3 2 1 3 3 1 2 5 11 5 11 8 8 8 8 18 18 17 1 16 55 25 1 47 3 1 2 2 3 9 3 3 18 2 8 17 2 12 23 13 44 1 1 10 28 2 3 32 13 3 13 31 2 49 14 2 8 32 2 4 35 4 35 8 32 43 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Quota code necessary even when VFS quota support is not compiled * into the kernel. The interesting stuff is over in dquot.c, here * we have symbols for initial quotactl(2) handling, the sysctl(2) * variables, etc - things needed even when quota support disabled. */ #include <linux/fs.h> #include <linux/namei.h> #include <linux/slab.h> #include <asm/current.h> #include <linux/blkdev.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/quotaops.h> #include <linux/types.h> #include <linux/mount.h> #include <linux/writeback.h> #include <linux/nospec.h> #include "compat.h" #include "../internal.h" static int check_quotactl_permission(struct super_block *sb, int type, int cmd, qid_t id) { switch (cmd) { /* these commands do not require any special privilegues */ case Q_GETFMT: case Q_SYNC: case Q_GETINFO: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XQUOTASYNC: break; /* allow to query information for dquots we "own" */ case Q_GETQUOTA: case Q_XGETQUOTA: if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) || (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id)))) break; fallthrough; default: if (!capable(CAP_SYS_ADMIN)) return -EPERM; } return security_quotactl(cmd, type, id, sb); } static void quota_sync_one(struct super_block *sb, void *arg) { int type = *(int *)arg; if (sb->s_qcop && sb->s_qcop->quota_sync && (sb->s_quota_types & (1 << type))) sb->s_qcop->quota_sync(sb, type); } static int quota_sync_all(int type) { int ret; ret = security_quotactl(Q_SYNC, type, 0, NULL); if (!ret) iterate_supers(quota_sync_one, &type); return ret; } unsigned int qtype_enforce_flag(int type) { switch (type) { case USRQUOTA: return FS_QUOTA_UDQ_ENFD; case GRPQUOTA: return FS_QUOTA_GDQ_ENFD; case PRJQUOTA: return FS_QUOTA_PDQ_ENFD; } return 0; } static int quota_quotaon(struct super_block *sb, int type, qid_t id, const struct path *path) { if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) return -ENOSYS; if (sb->s_qcop->quota_enable) return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) return PTR_ERR(path); return sb->s_qcop->quota_on(sb, type, id, path); } static int quota_quotaoff(struct super_block *sb, int type) { if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable) return -ENOSYS; if (sb->s_qcop->quota_disable) return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type)); return sb->s_qcop->quota_off(sb, type); } static int quota_getfmt(struct super_block *sb, int type, void __user *addr) { __u32 fmt; if (!sb_has_quota_active(sb, type)) return -ESRCH; fmt = sb_dqopt(sb)->info[type].dqi_format->qf_fmt_id; if (copy_to_user(addr, &fmt, sizeof(fmt))) return -EFAULT; return 0; } static int quota_getinfo(struct super_block *sb, int type, void __user *addr) { struct qc_state state; struct qc_type_state *tstate; struct if_dqinfo uinfo; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; ret = sb->s_qcop->get_state(sb, &state); if (ret) return ret; tstate = state.s_state + type; if (!(tstate->flags & QCI_ACCT_ENABLED)) return -ESRCH; memset(&uinfo, 0, sizeof(uinfo)); uinfo.dqi_bgrace = tstate->spc_timelimit; uinfo.dqi_igrace = tstate->ino_timelimit; if (tstate->flags & QCI_SYSFILE) uinfo.dqi_flags |= DQF_SYS_FILE; if (tstate->flags & QCI_ROOT_SQUASH) uinfo.dqi_flags |= DQF_ROOT_SQUASH; uinfo.dqi_valid = IIF_ALL; if (copy_to_user(addr, &uinfo, sizeof(uinfo))) return -EFAULT; return 0; } static int quota_setinfo(struct super_block *sb, int type, void __user *addr) { struct if_dqinfo info; struct qc_info qinfo; if (copy_from_user(&info, addr, sizeof(info))) return -EFAULT; if (!sb->s_qcop->set_info) return -ENOSYS; if (info.dqi_valid & ~(IIF_FLAGS | IIF_BGRACE | IIF_IGRACE)) return -EINVAL; memset(&qinfo, 0, sizeof(qinfo)); if (info.dqi_valid & IIF_FLAGS) { if (info.dqi_flags & ~DQF_SETINFO_MASK) return -EINVAL; if (info.dqi_flags & DQF_ROOT_SQUASH) qinfo.i_flags |= QCI_ROOT_SQUASH; qinfo.i_fieldmask |= QC_FLAGS; } if (info.dqi_valid & IIF_BGRACE) { qinfo.i_spc_timelimit = info.dqi_bgrace; qinfo.i_fieldmask |= QC_SPC_TIMER; } if (info.dqi_valid & IIF_IGRACE) { qinfo.i_ino_timelimit = info.dqi_igrace; qinfo.i_fieldmask |= QC_INO_TIMER; } return sb->s_qcop->set_info(sb, type, &qinfo); } static inline qsize_t qbtos(qsize_t blocks) { return blocks << QIF_DQBLKSIZE_BITS; } static inline qsize_t stoqb(qsize_t space) { return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; } static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src) { memset(dst, 0, sizeof(*dst)); dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit); dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit); dst->dqb_curspace = src->d_space; dst->dqb_ihardlimit = src->d_ino_hardlimit; dst->dqb_isoftlimit = src->d_ino_softlimit; dst->dqb_curinodes = src->d_ino_count; dst->dqb_btime = src->d_spc_timer; dst->dqb_itime = src->d_ino_timer; dst->dqb_valid = QIF_ALL; } static int quota_getquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; struct qc_dqblk fdq; struct if_dqblk idq; int ret; if (!sb->s_qcop->get_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_dqblk(sb, qid, &fdq); if (ret) return ret; copy_to_if_dqblk(&idq, &fdq); if (compat_need_64bit_alignment_fixup()) { struct compat_if_dqblk __user *compat_dqblk = addr; if (copy_to_user(compat_dqblk, &idq, sizeof(*compat_dqblk))) return -EFAULT; if (put_user(idq.dqb_valid, &compat_dqblk->dqb_valid)) return -EFAULT; } else { if (copy_to_user(addr, &idq, sizeof(idq))) return -EFAULT; } return 0; } /* * Return quota for next active quota >= this id, if any exists, * otherwise return -ENOENT via ->get_nextdqblk */ static int quota_getnextquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; struct qc_dqblk fdq; struct if_nextdqblk idq; int ret; if (!sb->s_qcop->get_nextdqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_nextdqblk(sb, &qid, &fdq); if (ret) return ret; /* struct if_nextdqblk is a superset of struct if_dqblk */ copy_to_if_dqblk((struct if_dqblk *)&idq, &fdq); idq.dqb_id = from_kqid(current_user_ns(), qid); if (copy_to_user(addr, &idq, sizeof(idq))) return -EFAULT; return 0; } static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src) { dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit); dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit); dst->d_space = src->dqb_curspace; dst->d_ino_hardlimit = src->dqb_ihardlimit; dst->d_ino_softlimit = src->dqb_isoftlimit; dst->d_ino_count = src->dqb_curinodes; dst->d_spc_timer = src->dqb_btime; dst->d_ino_timer = src->dqb_itime; dst->d_fieldmask = 0; if (src->dqb_valid & QIF_BLIMITS) dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD; if (src->dqb_valid & QIF_SPACE) dst->d_fieldmask |= QC_SPACE; if (src->dqb_valid & QIF_ILIMITS) dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD; if (src->dqb_valid & QIF_INODES) dst->d_fieldmask |= QC_INO_COUNT; if (src->dqb_valid & QIF_BTIME) dst->d_fieldmask |= QC_SPC_TIMER; if (src->dqb_valid & QIF_ITIME) dst->d_fieldmask |= QC_INO_TIMER; } static int quota_setquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct qc_dqblk fdq; struct if_dqblk idq; struct kqid qid; if (compat_need_64bit_alignment_fixup()) { struct compat_if_dqblk __user *compat_dqblk = addr; if (copy_from_user(&idq, compat_dqblk, sizeof(*compat_dqblk)) || get_user(idq.dqb_valid, &compat_dqblk->dqb_valid)) return -EFAULT; } else { if (copy_from_user(&idq, addr, sizeof(idq))) return -EFAULT; } if (!sb->s_qcop->set_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; copy_from_if_dqblk(&fdq, &idq); return sb->s_qcop->set_dqblk(sb, qid, &fdq); } static int quota_enable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; if (!sb->s_qcop->quota_enable) return -ENOSYS; return sb->s_qcop->quota_enable(sb, flags); } static int quota_disable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; if (!sb->s_qcop->quota_disable) return -ENOSYS; return sb->s_qcop->quota_disable(sb, flags); } static int quota_state_to_flags(struct qc_state *state) { int flags = 0; if (state->s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) flags |= FS_QUOTA_UDQ_ACCT; if (state->s_state[USRQUOTA].flags & QCI_LIMITS_ENFORCED) flags |= FS_QUOTA_UDQ_ENFD; if (state->s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) flags |= FS_QUOTA_GDQ_ACCT; if (state->s_state[GRPQUOTA].flags & QCI_LIMITS_ENFORCED) flags |= FS_QUOTA_GDQ_ENFD; if (state->s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) flags |= FS_QUOTA_PDQ_ACCT; if (state->s_state[PRJQUOTA].flags & QCI_LIMITS_ENFORCED) flags |= FS_QUOTA_PDQ_ENFD; return flags; } static int quota_getstate(struct super_block *sb, int type, struct fs_quota_stat *fqs) { struct qc_state state; int ret; memset(&state, 0, sizeof (struct qc_state)); ret = sb->s_qcop->get_state(sb, &state); if (ret < 0) return ret; memset(fqs, 0, sizeof(*fqs)); fqs->qs_version = FS_QSTAT_VERSION; fqs->qs_flags = quota_state_to_flags(&state); /* No quota enabled? */ if (!fqs->qs_flags) return -ENOSYS; fqs->qs_incoredqs = state.s_incoredqs; fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; /* Inodes may be allocated even if inactive; copy out if present */ if (state.s_state[USRQUOTA].ino) { fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; } if (state.s_state[GRPQUOTA].ino) { fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; } if (state.s_state[PRJQUOTA].ino) { /* * Q_XGETQSTAT doesn't have room for both group and project * quotas. So, allow the project quota values to be copied out * only if there is no group quota information available. */ if (!(state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED)) { fqs->qs_gquota.qfs_ino = state.s_state[PRJQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[PRJQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[PRJQUOTA].nextents; } } return 0; } static int compat_copy_fs_qfilestat(struct compat_fs_qfilestat __user *to, struct fs_qfilestat *from) { if (copy_to_user(to, from, sizeof(*to)) || put_user(from->qfs_nextents, &to->qfs_nextents)) return -EFAULT; return 0; } static int compat_copy_fs_quota_stat(struct compat_fs_quota_stat __user *to, struct fs_quota_stat *from) { if (put_user(from->qs_version, &to->qs_version) || put_user(from->qs_flags, &to->qs_flags) || put_user(from->qs_pad, &to->qs_pad) || compat_copy_fs_qfilestat(&to->qs_uquota, &from->qs_uquota) || compat_copy_fs_qfilestat(&to->qs_gquota, &from->qs_gquota) || put_user(from->qs_incoredqs, &to->qs_incoredqs) || put_user(from->qs_btimelimit, &to->qs_btimelimit) || put_user(from->qs_itimelimit, &to->qs_itimelimit) || put_user(from->qs_rtbtimelimit, &to->qs_rtbtimelimit) || put_user(from->qs_bwarnlimit, &to->qs_bwarnlimit) || put_user(from->qs_iwarnlimit, &to->qs_iwarnlimit)) return -EFAULT; return 0; } static int quota_getxstate(struct super_block *sb, int type, void __user *addr) { struct fs_quota_stat fqs; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; ret = quota_getstate(sb, type, &fqs); if (ret) return ret; if (compat_need_64bit_alignment_fixup()) return compat_copy_fs_quota_stat(addr, &fqs); if (copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return 0; } static int quota_getstatev(struct super_block *sb, int type, struct fs_quota_statv *fqs) { struct qc_state state; int ret; memset(&state, 0, sizeof (struct qc_state)); ret = sb->s_qcop->get_state(sb, &state); if (ret < 0) return ret; memset(fqs, 0, sizeof(*fqs)); fqs->qs_version = FS_QSTAT_VERSION; fqs->qs_flags = quota_state_to_flags(&state); /* No quota enabled? */ if (!fqs->qs_flags) return -ENOSYS; fqs->qs_incoredqs = state.s_incoredqs; fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; fqs->qs_rtbwarnlimit = state.s_state[type].rt_spc_warnlimit; /* Inodes may be allocated even if inactive; copy out if present */ if (state.s_state[USRQUOTA].ino) { fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; } if (state.s_state[GRPQUOTA].ino) { fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; } if (state.s_state[PRJQUOTA].ino) { fqs->qs_pquota.qfs_ino = state.s_state[PRJQUOTA].ino; fqs->qs_pquota.qfs_nblks = state.s_state[PRJQUOTA].blocks; fqs->qs_pquota.qfs_nextents = state.s_state[PRJQUOTA].nextents; } return 0; } static int quota_getxstatev(struct super_block *sb, int type, void __user *addr) { struct fs_quota_statv fqs; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; memset(&fqs, 0, sizeof(fqs)); if (copy_from_user(&fqs, addr, 1)) /* Just read qs_version */ return -EFAULT; /* If this kernel doesn't support user specified version, fail */ switch (fqs.qs_version) { case FS_QSTATV_VERSION1: break; default: return -EINVAL; } ret = quota_getstatev(sb, type, &fqs); if (!ret && copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return ret; } /* * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them * out of there as xfsprogs rely on definitions being in that header file. So * just define same functions here for quota purposes. */ #define XFS_BB_SHIFT 9 static inline u64 quota_bbtob(u64 blocks) { return blocks << XFS_BB_SHIFT; } static inline u64 quota_btobb(u64 bytes) { return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT; } static inline s64 copy_from_xfs_dqblk_ts(const struct fs_disk_quota *d, __s32 timer, __s8 timer_hi) { if (d->d_fieldmask & FS_DQ_BIGTIME) return (u32)timer | (s64)timer_hi << 32; return timer; } static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src) { dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit); dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit); dst->d_ino_hardlimit = src->d_ino_hardlimit; dst->d_ino_softlimit = src->d_ino_softlimit; dst->d_space = quota_bbtob(src->d_bcount); dst->d_ino_count = src->d_icount; dst->d_ino_timer = copy_from_xfs_dqblk_ts(src, src->d_itimer, src->d_itimer_hi); dst->d_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_btimer, src->d_btimer_hi); dst->d_ino_warns = src->d_iwarns; dst->d_spc_warns = src->d_bwarns; dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit); dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit); dst->d_rt_space = quota_bbtob(src->d_rtbcount); dst->d_rt_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_rtbtimer, src->d_rtbtimer_hi); dst->d_rt_spc_warns = src->d_rtbwarns; dst->d_fieldmask = 0; if (src->d_fieldmask & FS_DQ_ISOFT) dst->d_fieldmask |= QC_INO_SOFT; if (src->d_fieldmask & FS_DQ_IHARD) dst->d_fieldmask |= QC_INO_HARD; if (src->d_fieldmask & FS_DQ_BSOFT) dst->d_fieldmask |= QC_SPC_SOFT; if (src->d_fieldmask & FS_DQ_BHARD) dst->d_fieldmask |= QC_SPC_HARD; if (src->d_fieldmask & FS_DQ_RTBSOFT) dst->d_fieldmask |= QC_RT_SPC_SOFT; if (src->d_fieldmask & FS_DQ_RTBHARD) dst->d_fieldmask |= QC_RT_SPC_HARD; if (src->d_fieldmask & FS_DQ_BTIMER) dst->d_fieldmask |= QC_SPC_TIMER; if (src->d_fieldmask & FS_DQ_ITIMER) dst->d_fieldmask |= QC_INO_TIMER; if (src->d_fieldmask & FS_DQ_RTBTIMER) dst->d_fieldmask |= QC_RT_SPC_TIMER; if (src->d_fieldmask & FS_DQ_BWARNS) dst->d_fieldmask |= QC_SPC_WARNS; if (src->d_fieldmask & FS_DQ_IWARNS) dst->d_fieldmask |= QC_INO_WARNS; if (src->d_fieldmask & FS_DQ_RTBWARNS) dst->d_fieldmask |= QC_RT_SPC_WARNS; if (src->d_fieldmask & FS_DQ_BCOUNT) dst->d_fieldmask |= QC_SPACE; if (src->d_fieldmask & FS_DQ_ICOUNT) dst->d_fieldmask |= QC_INO_COUNT; if (src->d_fieldmask & FS_DQ_RTBCOUNT) dst->d_fieldmask |= QC_RT_SPACE; } static void copy_qcinfo_from_xfs_dqblk(struct qc_info *dst, struct fs_disk_quota *src) { memset(dst, 0, sizeof(*dst)); dst->i_spc_timelimit = src->d_btimer; dst->i_ino_timelimit = src->d_itimer; dst->i_rt_spc_timelimit = src->d_rtbtimer; dst->i_ino_warnlimit = src->d_iwarns; dst->i_spc_warnlimit = src->d_bwarns; dst->i_rt_spc_warnlimit = src->d_rtbwarns; if (src->d_fieldmask & FS_DQ_BWARNS) dst->i_fieldmask |= QC_SPC_WARNS; if (src->d_fieldmask & FS_DQ_IWARNS) dst->i_fieldmask |= QC_INO_WARNS; if (src->d_fieldmask & FS_DQ_RTBWARNS) dst->i_fieldmask |= QC_RT_SPC_WARNS; if (src->d_fieldmask & FS_DQ_BTIMER) dst->i_fieldmask |= QC_SPC_TIMER; if (src->d_fieldmask & FS_DQ_ITIMER) dst->i_fieldmask |= QC_INO_TIMER; if (src->d_fieldmask & FS_DQ_RTBTIMER) dst->i_fieldmask |= QC_RT_SPC_TIMER; } static int quota_setxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; struct qc_dqblk qdq; struct kqid qid; if (copy_from_user(&fdq, addr, sizeof(fdq))) return -EFAULT; if (!sb->s_qcop->set_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; /* Are we actually setting timer / warning limits for all users? */ if (from_kqid(sb->s_user_ns, qid) == 0 && fdq.d_fieldmask & (FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK)) { struct qc_info qinfo; int ret; if (!sb->s_qcop->set_info) return -EINVAL; copy_qcinfo_from_xfs_dqblk(&qinfo, &fdq); ret = sb->s_qcop->set_info(sb, type, &qinfo); if (ret) return ret; /* These are already done */ fdq.d_fieldmask &= ~(FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK); } copy_from_xfs_dqblk(&qdq, &fdq); return sb->s_qcop->set_dqblk(sb, qid, &qdq); } static inline void copy_to_xfs_dqblk_ts(const struct fs_disk_quota *d, __s32 *timer_lo, __s8 *timer_hi, s64 timer) { *timer_lo = timer; if (d->d_fieldmask & FS_DQ_BIGTIME) *timer_hi = timer >> 32; } static inline bool want_bigtime(s64 timer) { return timer > S32_MAX || timer < S32_MIN; } static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src, int type, qid_t id) { memset(dst, 0, sizeof(*dst)); if (want_bigtime(src->d_ino_timer) || want_bigtime(src->d_spc_timer) || want_bigtime(src->d_rt_spc_timer)) dst->d_fieldmask |= FS_DQ_BIGTIME; dst->d_version = FS_DQUOT_VERSION; dst->d_id = id; if (type == USRQUOTA) dst->d_flags = FS_USER_QUOTA; else if (type == PRJQUOTA) dst->d_flags = FS_PROJ_QUOTA; else dst->d_flags = FS_GROUP_QUOTA; dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit); dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit); dst->d_ino_hardlimit = src->d_ino_hardlimit; dst->d_ino_softlimit = src->d_ino_softlimit; dst->d_bcount = quota_btobb(src->d_space); dst->d_icount = src->d_ino_count; copy_to_xfs_dqblk_ts(dst, &dst->d_itimer, &dst->d_itimer_hi, src->d_ino_timer); copy_to_xfs_dqblk_ts(dst, &dst->d_btimer, &dst->d_btimer_hi, src->d_spc_timer); dst->d_iwarns = src->d_ino_warns; dst->d_bwarns = src->d_spc_warns; dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit); dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit); dst->d_rtbcount = quota_btobb(src->d_rt_space); copy_to_xfs_dqblk_ts(dst, &dst->d_rtbtimer, &dst->d_rtbtimer_hi, src->d_rt_spc_timer); dst->d_rtbwarns = src->d_rt_spc_warns; } static int quota_getxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; struct qc_dqblk qdq; struct kqid qid; int ret; if (!sb->s_qcop->get_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_dqblk(sb, qid, &qdq); if (ret) return ret; copy_to_xfs_dqblk(&fdq, &qdq, type, id); if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } /* * Return quota for next active quota >= this id, if any exists, * otherwise return -ENOENT via ->get_nextdqblk. */ static int quota_getnextxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; struct qc_dqblk qdq; struct kqid qid; qid_t id_out; int ret; if (!sb->s_qcop->get_nextdqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_nextdqblk(sb, &qid, &qdq); if (ret) return ret; id_out = from_kqid(current_user_ns(), qid); copy_to_xfs_dqblk(&fdq, &qdq, type, id_out); if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } static int quota_rmxquota(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; if (!sb->s_qcop->rm_xquota) return -ENOSYS; return sb->s_qcop->rm_xquota(sb, flags); } /* Copy parameters and call proper function */ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, void __user *addr, const struct path *path) { int ret; type = array_index_nospec(type, MAXQUOTAS); /* * Quota not supported on this fs? Check this before s_quota_types * since they needn't be set if quota is not supported at all. */ if (!sb->s_qcop) return -ENOSYS; if (!(sb->s_quota_types & (1 << type))) return -EINVAL; ret = check_quotactl_permission(sb, type, cmd, id); if (ret < 0) return ret; switch (cmd) { case Q_QUOTAON: return quota_quotaon(sb, type, id, path); case Q_QUOTAOFF: return quota_quotaoff(sb, type); case Q_GETFMT: return quota_getfmt(sb, type, addr); case Q_GETINFO: return quota_getinfo(sb, type, addr); case Q_SETINFO: return quota_setinfo(sb, type, addr); case Q_GETQUOTA: return quota_getquota(sb, type, id, addr); case Q_GETNEXTQUOTA: return quota_getnextquota(sb, type, id, addr); case Q_SETQUOTA: return quota_setquota(sb, type, id, addr); case Q_SYNC: if (!sb->s_qcop->quota_sync) return -ENOSYS; return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: return quota_enable(sb, addr); case Q_XQUOTAOFF: return quota_disable(sb, addr); case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: return quota_getxstate(sb, type, addr); case Q_XGETQSTATV: return quota_getxstatev(sb, type, addr); case Q_XSETQLIM: return quota_setxquota(sb, type, id, addr); case Q_XGETQUOTA: return quota_getxquota(sb, type, id, addr); case Q_XGETNEXTQUOTA: return quota_getnextxquota(sb, type, id, addr); case Q_XQUOTASYNC: if (sb_rdonly(sb)) return -EROFS; /* XFS quotas are fully coherent now, making this call a noop */ return 0; default: return -EINVAL; } } /* Return 1 if 'cmd' will block on frozen filesystem */ static int quotactl_cmd_write(int cmd) { /* * We cannot allow Q_GETQUOTA and Q_GETNEXTQUOTA without write access * as dquot_acquire() may allocate space for new structure and OCFS2 * needs to increment on-disk use count. */ switch (cmd) { case Q_GETFMT: case Q_GETINFO: case Q_SYNC: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETQUOTA: case Q_XGETNEXTQUOTA: case Q_XQUOTASYNC: return 0; } return 1; } /* Return true if quotactl command is manipulating quota on/off state */ static bool quotactl_cmd_onoff(int cmd) { return (cmd == Q_QUOTAON) || (cmd == Q_QUOTAOFF) || (cmd == Q_XQUOTAON) || (cmd == Q_XQUOTAOFF); } /* * look up a superblock on which quota ops will be performed * - use the name of a block device to find the superblock thereon */ static struct super_block *quotactl_block(const char __user *special, int cmd) { #ifdef CONFIG_BLOCK struct super_block *sb; CLASS(filename, tmp)(special); bool excl = false, thawed = false; int error; dev_t dev; if (IS_ERR(tmp)) return ERR_CAST(tmp); error = lookup_bdev(tmp->name, &dev); if (error) return ERR_PTR(error); if (quotactl_cmd_onoff(cmd)) { excl = true; thawed = true; } else if (quotactl_cmd_write(cmd)) { thawed = true; } retry: sb = user_get_super(dev, excl); if (!sb) return ERR_PTR(-ENODEV); if (thawed && sb->s_writers.frozen != SB_UNFROZEN) { if (excl) up_write(&sb->s_umount); else up_read(&sb->s_umount); /* Wait for sb to unfreeze */ sb_start_write(sb); sb_end_write(sb); put_super(sb); cond_resched(); goto retry; } return sb; #else return ERR_PTR(-ENODEV); #endif } /* * This is the system call interface. This communicates with * the user-level programs. Currently this only supports diskquota * calls. Maybe we need to add the process quotas etc. in the future, * but we probably should use rlimits for that. */ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr) { uint cmds, type; struct super_block *sb = NULL; struct path path, *pathp = NULL; int ret; cmds = cmd >> SUBCMDSHIFT; type = cmd & SUBCMDMASK; if (type >= MAXQUOTAS) return -EINVAL; /* * As a special case Q_SYNC can be called without a specific device. * It will iterate all superblocks that have quota enabled and call * the sync action on each of them. */ if (!special) { if (cmds == Q_SYNC) return quota_sync_all(type); return -ENODEV; } /* * Path for quotaon has to be resolved before grabbing superblock * because that gets s_umount sem which is also possibly needed by path * resolution (think about autofs) and thus deadlocks could arise. */ if (cmds == Q_QUOTAON) { ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); if (ret) pathp = ERR_PTR(ret); else pathp = &path; } sb = quotactl_block(special, cmds); if (IS_ERR(sb)) { ret = PTR_ERR(sb); goto out; } ret = do_quotactl(sb, type, cmds, id, addr, pathp); if (!quotactl_cmd_onoff(cmds)) drop_super(sb); else drop_super_exclusive(sb); out: if (pathp && !IS_ERR(pathp)) path_put(pathp); return ret; } SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd, qid_t, id, void __user *, addr) { struct super_block *sb; unsigned int cmds = cmd >> SUBCMDSHIFT; unsigned int type = cmd & SUBCMDMASK; CLASS(fd_raw, f)(fd); int ret; if (fd_empty(f)) return -EBADF; if (type >= MAXQUOTAS) return -EINVAL; if (quotactl_cmd_write(cmds)) { ret = mnt_want_write(fd_file(f)->f_path.mnt); if (ret) return ret; } sb = fd_file(f)->f_path.mnt->mnt_sb; if (quotactl_cmd_onoff(cmds)) down_write(&sb->s_umount); else down_read(&sb->s_umount); ret = do_quotactl(sb, type, cmds, id, addr, ERR_PTR(-EINVAL)); if (quotactl_cmd_onoff(cmds)) up_write(&sb->s_umount); else up_read(&sb->s_umount); if (quotactl_cmd_write(cmds)) mnt_drop_write(fd_file(f)->f_path.mnt); return ret; } |
| 11734 564 22793 723 44186 4047 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for non-atomic * bit operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #include <linux/instrumented.h> /** * ___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___set_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); } /** * ___clear_bit - Clears a bit in memory * @nr: the bit to clear * @addr: the address to start counting from * * Unlike clear_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___clear_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); } /** * ___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___change_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); } static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* * We treat non-atomic read-write bitops a little more special. * Given the operations here only modify a single bit, assuming * non-atomicity of the writer is sufficient may be reasonable * for certain usage (and follows the permissible nature of the * assume-plain-writes-atomic rule): * 1. report read-modify-write races -> check read; * 2. do not report races with marked readers, but do report * races with unmarked readers -> check "atomic" write. */ kcsan_check_read(addr + BIT_WORD(nr), sizeof(long)); /* * Use generic write instrumentation, in case other sanitizers * or tools are enabled alongside KCSAN. */ instrument_write(addr + BIT_WORD(nr), sizeof(long)); } else { instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); } } /** * ___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } /** * ___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } /** * ___test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } /** * _test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool _test_bit(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); } /** * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool _test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit_acquire(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 6 6 6 2 2 2 3 3 3 3 6 2 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /******************************************************************************* * * Module Name: nsxfeval - Public interfaces to the ACPI subsystem * ACPI Object evaluation interfaces * ******************************************************************************/ #define EXPORT_ACPI_INTERFACES #include <acpi/acpi.h> #include "accommon.h" #include "acnamesp.h" #include "acinterp.h" #define _COMPONENT ACPI_NAMESPACE ACPI_MODULE_NAME("nsxfeval") /* Local prototypes */ static void acpi_ns_resolve_references(struct acpi_evaluate_info *info); /******************************************************************************* * * FUNCTION: acpi_evaluate_object_typed * * PARAMETERS: handle - Object handle (optional) * pathname - Object pathname (optional) * external_params - List of parameters to pass to a method, * terminated by NULL. May be NULL * if no parameters are being passed. * return_buffer - Where to put the object's return value (if * any). If NULL, no value is returned. * return_type - Expected type of return object * * RETURN: Status * * DESCRIPTION: Find and evaluate the given object, passing the given * parameters if necessary. One of "Handle" or "Pathname" must * be valid (non-null) * ******************************************************************************/ acpi_status acpi_evaluate_object_typed(acpi_handle handle, acpi_string pathname, struct acpi_object_list *external_params, struct acpi_buffer *return_buffer, acpi_object_type return_type) { acpi_status status; u8 free_buffer_on_error = FALSE; acpi_handle target_handle; char *full_pathname; ACPI_FUNCTION_TRACE(acpi_evaluate_object_typed); /* Return buffer must be valid */ if (!return_buffer) { return_ACPI_STATUS(AE_BAD_PARAMETER); } if (return_buffer->length == ACPI_ALLOCATE_BUFFER) { free_buffer_on_error = TRUE; } /* Get a handle here, in order to build an error message if needed */ target_handle = handle; if (pathname) { status = acpi_get_handle(handle, pathname, &target_handle); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } } full_pathname = acpi_ns_get_external_pathname(target_handle); if (!full_pathname) { return_ACPI_STATUS(AE_NO_MEMORY); } /* Evaluate the object */ status = acpi_evaluate_object(target_handle, NULL, external_params, return_buffer); if (ACPI_FAILURE(status)) { goto exit; } /* Type ANY means "don't care about return value type" */ if (return_type == ACPI_TYPE_ANY) { goto exit; } if (return_buffer->length == 0) { /* Error because caller specifically asked for a return value */ ACPI_ERROR((AE_INFO, "%s did not return any object", full_pathname)); status = AE_NULL_OBJECT; goto exit; } /* Examine the object type returned from evaluate_object */ if (((union acpi_object *)return_buffer->pointer)->type == return_type) { goto exit; } /* Return object type does not match requested type */ ACPI_ERROR((AE_INFO, "Incorrect return type from %s - received [%s], requested [%s]", full_pathname, acpi_ut_get_type_name(((union acpi_object *)return_buffer-> pointer)->type), acpi_ut_get_type_name(return_type))); if (free_buffer_on_error) { /* * Free a buffer created via ACPI_ALLOCATE_BUFFER. * Note: We use acpi_os_free here because acpi_os_allocate was used * to allocate the buffer. This purposefully bypasses the * (optionally enabled) allocation tracking mechanism since we * only want to track internal allocations. */ acpi_os_free(return_buffer->pointer); return_buffer->pointer = NULL; } return_buffer->length = 0; status = AE_TYPE; exit: ACPI_FREE(full_pathname); return_ACPI_STATUS(status); } ACPI_EXPORT_SYMBOL(acpi_evaluate_object_typed) /******************************************************************************* * * FUNCTION: acpi_evaluate_object * * PARAMETERS: handle - Object handle (optional) * pathname - Object pathname (optional) * external_params - List of parameters to pass to method, * terminated by NULL. May be NULL * if no parameters are being passed. * return_buffer - Where to put method's return value (if * any). If NULL, no value is returned. * * RETURN: Status * * DESCRIPTION: Find and evaluate the given object, passing the given * parameters if necessary. One of "Handle" or "Pathname" must * be valid (non-null) * ******************************************************************************/ acpi_status acpi_evaluate_object(acpi_handle handle, acpi_string pathname, struct acpi_object_list *external_params, struct acpi_buffer *return_buffer) { acpi_status status; struct acpi_evaluate_info *info; acpi_size buffer_space_needed; u32 i; ACPI_FUNCTION_TRACE(acpi_evaluate_object); /* Allocate and initialize the evaluation information block */ info = ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_evaluate_info)); if (!info) { return_ACPI_STATUS(AE_NO_MEMORY); } /* Convert and validate the device handle */ info->prefix_node = acpi_ns_validate_handle(handle); if (!info->prefix_node) { status = AE_BAD_PARAMETER; goto cleanup; } /* * Get the actual namespace node for the target object. * Handles these cases: * * 1) Null node, valid pathname from root (absolute path) * 2) Node and valid pathname (path relative to Node) * 3) Node, Null pathname */ if ((pathname) && (ACPI_IS_ROOT_PREFIX(pathname[0]))) { /* The path is fully qualified, just evaluate by name */ info->prefix_node = NULL; } else if (!handle) { /* * A handle is optional iff a fully qualified pathname is specified. * Since we've already handled fully qualified names above, this is * an error. */ if (!pathname) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Both Handle and Pathname are NULL")); } else { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Null Handle with relative pathname [%s]", pathname)); } status = AE_BAD_PARAMETER; goto cleanup; } info->relative_pathname = pathname; /* * Convert all external objects passed as arguments to the * internal version(s). */ if (external_params && external_params->count) { info->param_count = (u16)external_params->count; /* Warn on impossible argument count */ if (info->param_count > ACPI_METHOD_NUM_ARGS) { ACPI_WARN_PREDEFINED((AE_INFO, pathname, ACPI_WARN_ALWAYS, "Excess arguments (%u) - using only %u", info->param_count, ACPI_METHOD_NUM_ARGS)); info->param_count = ACPI_METHOD_NUM_ARGS; } /* * Allocate a new parameter block for the internal objects * Add 1 to count to allow for null terminated internal list */ info->parameters = ACPI_ALLOCATE_ZEROED(((acpi_size)info-> param_count + 1) * sizeof(void *)); if (!info->parameters) { status = AE_NO_MEMORY; goto cleanup; } /* Convert each external object in the list to an internal object */ for (i = 0; i < info->param_count; i++) { status = acpi_ut_copy_eobject_to_iobject(&external_params-> pointer[i], &info-> parameters[i]); if (ACPI_FAILURE(status)) { goto cleanup; } } info->parameters[info->param_count] = NULL; } #ifdef _FUTURE_FEATURE /* * Begin incoming argument count analysis. Check for too few args * and too many args. */ switch (acpi_ns_get_type(info->node)) { case ACPI_TYPE_METHOD: /* Check incoming argument count against the method definition */ if (info->obj_desc->method.param_count > info->param_count) { ACPI_ERROR((AE_INFO, "Insufficient arguments (%u) - %u are required", info->param_count, info->obj_desc->method.param_count)); status = AE_MISSING_ARGUMENTS; goto cleanup; } else if (info->obj_desc->method.param_count < info->param_count) { ACPI_WARNING((AE_INFO, "Excess arguments (%u) - only %u are required", info->param_count, info->obj_desc->method.param_count)); /* Just pass the required number of arguments */ info->param_count = info->obj_desc->method.param_count; } /* * Any incoming external objects to be passed as arguments to the * method must be converted to internal objects */ if (info->param_count) { /* * Allocate a new parameter block for the internal objects * Add 1 to count to allow for null terminated internal list */ info->parameters = ACPI_ALLOCATE_ZEROED(((acpi_size) info-> param_count + 1) * sizeof(void *)); if (!info->parameters) { status = AE_NO_MEMORY; goto cleanup; } /* Convert each external object in the list to an internal object */ for (i = 0; i < info->param_count; i++) { status = acpi_ut_copy_eobject_to_iobject (&external_params->pointer[i], &info->parameters[i]); if (ACPI_FAILURE(status)) { goto cleanup; } } info->parameters[info->param_count] = NULL; } break; default: /* Warn if arguments passed to an object that is not a method */ if (info->param_count) { ACPI_WARNING((AE_INFO, "%u arguments were passed to a non-method ACPI object", info->param_count)); } break; } #endif /* Now we can evaluate the object */ status = acpi_ns_evaluate(info); /* * If we are expecting a return value, and all went well above, * copy the return value to an external object. */ if (!return_buffer) { goto cleanup_return_object; } if (!info->return_object) { return_buffer->length = 0; goto cleanup; } if (ACPI_GET_DESCRIPTOR_TYPE(info->return_object) == ACPI_DESC_TYPE_NAMED) { /* * If we received a NS Node as a return object, this means that * the object we are evaluating has nothing interesting to * return (such as a mutex, etc.) We return an error because * these types are essentially unsupported by this interface. * We don't check up front because this makes it easier to add * support for various types at a later date if necessary. */ status = AE_TYPE; info->return_object = NULL; /* No need to delete a NS Node */ return_buffer->length = 0; } if (ACPI_FAILURE(status)) { goto cleanup_return_object; } /* Dereference Index and ref_of references */ acpi_ns_resolve_references(info); /* Get the size of the returned object */ status = acpi_ut_get_object_size(info->return_object, &buffer_space_needed); if (ACPI_SUCCESS(status)) { /* Validate/Allocate/Clear caller buffer */ status = acpi_ut_initialize_buffer(return_buffer, buffer_space_needed); if (ACPI_FAILURE(status)) { /* * Caller's buffer is too small or a new one can't * be allocated */ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Needed buffer size %X, %s\n", (u32)buffer_space_needed, acpi_format_exception(status))); } else { /* We have enough space for the object, build it */ status = acpi_ut_copy_iobject_to_eobject(info->return_object, return_buffer); } } cleanup_return_object: if (info->return_object) { /* * Delete the internal return object. NOTE: Interpreter must be * locked to avoid race condition. */ acpi_ex_enter_interpreter(); /* Remove one reference on the return object (should delete it) */ acpi_ut_remove_reference(info->return_object); acpi_ex_exit_interpreter(); } cleanup: /* Free the input parameter list (if we created one) */ if (info->parameters) { /* Free the allocated parameter block */ acpi_ut_delete_internal_object_list(info->parameters); } ACPI_FREE(info); return_ACPI_STATUS(status); } ACPI_EXPORT_SYMBOL(acpi_evaluate_object) /******************************************************************************* * * FUNCTION: acpi_ns_resolve_references * * PARAMETERS: info - Evaluation info block * * RETURN: Info->return_object is replaced with the dereferenced object * * DESCRIPTION: Dereference certain reference objects. Called before an * internal return object is converted to an external union acpi_object. * * Performs an automatic dereference of Index and ref_of reference objects. * These reference objects are not supported by the union acpi_object, so this is a * last resort effort to return something useful. Also, provides compatibility * with other ACPI implementations. * * NOTE: does not handle references within returned package objects or nested * references, but this support could be added later if found to be necessary. * ******************************************************************************/ static void acpi_ns_resolve_references(struct acpi_evaluate_info *info) { union acpi_operand_object *obj_desc = NULL; struct acpi_namespace_node *node; /* We are interested in reference objects only */ if ((info->return_object)->common.type != ACPI_TYPE_LOCAL_REFERENCE) { return; } /* * Two types of references are supported - those created by Index and * ref_of operators. A name reference (AML_NAMEPATH_OP) can be converted * to a union acpi_object, so it is not dereferenced here. A ddb_handle * (AML_LOAD_OP) cannot be dereferenced, nor can it be converted to * a union acpi_object. */ switch (info->return_object->reference.class) { case ACPI_REFCLASS_INDEX: obj_desc = *(info->return_object->reference.where); break; case ACPI_REFCLASS_REFOF: node = info->return_object->reference.object; if (node) { obj_desc = node->object; } break; default: return; } /* Replace the existing reference object */ if (obj_desc) { acpi_ut_add_reference(obj_desc); acpi_ut_remove_reference(info->return_object); info->return_object = obj_desc; } return; } /******************************************************************************* * * FUNCTION: acpi_walk_namespace * * PARAMETERS: type - acpi_object_type to search for * start_object - Handle in namespace where search begins * max_depth - Depth to which search is to reach * descending_callback - Called during tree descent * when an object of "Type" is found * ascending_callback - Called during tree ascent * when an object of "Type" is found * context - Passed to user function(s) above * return_value - Location where return value of * user_function is put if terminated early * * RETURNS Return value from the user_function if terminated early. * Otherwise, returns NULL. * * DESCRIPTION: Performs a modified depth-first walk of the namespace tree, * starting (and ending) at the object specified by start_handle. * The callback function is called whenever an object that matches * the type parameter is found. If the callback function returns * a non-zero value, the search is terminated immediately and this * value is returned to the caller. * * The point of this procedure is to provide a generic namespace * walk routine that can be called from multiple places to * provide multiple services; the callback function(s) can be * tailored to each task, whether it is a print function, * a compare function, etc. * ******************************************************************************/ acpi_status acpi_walk_namespace(acpi_object_type type, acpi_handle start_object, u32 max_depth, acpi_walk_callback descending_callback, acpi_walk_callback ascending_callback, void *context, void **return_value) { acpi_status status; ACPI_FUNCTION_TRACE(acpi_walk_namespace); /* Parameter validation */ if ((type > ACPI_TYPE_LOCAL_MAX) || (!max_depth) || (!descending_callback && !ascending_callback)) { return_ACPI_STATUS(AE_BAD_PARAMETER); } /* * Need to acquire the namespace reader lock to prevent interference * with any concurrent table unloads (which causes the deletion of * namespace objects). We cannot allow the deletion of a namespace node * while the user function is using it. The exception to this are the * nodes created and deleted during control method execution -- these * nodes are marked as temporary nodes and are ignored by the namespace * walk. Thus, control methods can be executed while holding the * namespace deletion lock (and the user function can execute control * methods.) */ status = acpi_ut_acquire_read_lock(&acpi_gbl_namespace_rw_lock); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } /* * Lock the namespace around the walk. The namespace will be * unlocked/locked around each call to the user function - since the user * function must be allowed to make ACPICA calls itself (for example, it * will typically execute control methods during device enumeration.) */ status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { goto unlock_and_exit; } /* Now we can validate the starting node */ if (!acpi_ns_validate_handle(start_object)) { status = AE_BAD_PARAMETER; goto unlock_and_exit2; } status = acpi_ns_walk_namespace(type, start_object, max_depth, ACPI_NS_WALK_UNLOCK, descending_callback, ascending_callback, context, return_value); unlock_and_exit2: (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); unlock_and_exit: (void)acpi_ut_release_read_lock(&acpi_gbl_namespace_rw_lock); return_ACPI_STATUS(status); } ACPI_EXPORT_SYMBOL(acpi_walk_namespace) /******************************************************************************* * * FUNCTION: acpi_ns_get_device_callback * * PARAMETERS: Callback from acpi_get_device * * RETURN: Status * * DESCRIPTION: Takes callbacks from walk_namespace and filters out all non- * present devices, or if they specified a HID, it filters based * on that. * ******************************************************************************/ static acpi_status acpi_ns_get_device_callback(acpi_handle obj_handle, u32 nesting_level, void *context, void **return_value) { struct acpi_get_devices_info *info = context; acpi_status status; struct acpi_namespace_node *node; u32 flags; struct acpi_pnp_device_id *hid; struct acpi_pnp_device_id_list *cid; u32 i; u8 found; int no_match; status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { return (status); } node = acpi_ns_validate_handle(obj_handle); status = acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { return (status); } if (!node) { return (AE_BAD_PARAMETER); } /* * First, filter based on the device HID and CID. * * 01/2010: For this case where a specific HID is requested, we don't * want to run _STA until we have an actual HID match. Thus, we will * not unnecessarily execute _STA on devices for which the caller * doesn't care about. Previously, _STA was executed unconditionally * on all devices found here. * * A side-effect of this change is that now we will continue to search * for a matching HID even under device trees where the parent device * would have returned a _STA that indicates it is not present or * not functioning (thus aborting the search on that branch). */ if (info->hid != NULL) { status = acpi_ut_execute_HID(node, &hid); if (status == AE_NOT_FOUND) { return (AE_OK); } else if (ACPI_FAILURE(status)) { return (AE_CTRL_DEPTH); } no_match = strcmp(hid->string, info->hid); ACPI_FREE(hid); if (no_match) { /* * HID does not match, attempt match within the * list of Compatible IDs (CIDs) */ status = acpi_ut_execute_CID(node, &cid); if (status == AE_NOT_FOUND) { return (AE_OK); } else if (ACPI_FAILURE(status)) { return (AE_CTRL_DEPTH); } /* Walk the CID list */ found = FALSE; for (i = 0; i < cid->count; i++) { if (strcmp(cid->ids[i].string, info->hid) == 0) { /* Found a matching CID */ found = TRUE; break; } } ACPI_FREE(cid); if (!found) { return (AE_OK); } } } /* Run _STA to determine if device is present */ status = acpi_ut_execute_STA(node, &flags); if (ACPI_FAILURE(status)) { return (AE_CTRL_DEPTH); } if (!(flags & ACPI_STA_DEVICE_PRESENT) && !(flags & ACPI_STA_DEVICE_FUNCTIONING)) { /* * Don't examine the children of the device only when the * device is neither present nor functional. See ACPI spec, * description of _STA for more information. */ return (AE_CTRL_DEPTH); } /* We have a valid device, invoke the user function */ status = info->user_function(obj_handle, nesting_level, info->context, return_value); return (status); } /******************************************************************************* * * FUNCTION: acpi_get_devices * * PARAMETERS: HID - HID to search for. Can be NULL. * user_function - Called when a matching object is found * context - Passed to user function * return_value - Location where return value of * user_function is put if terminated early * * RETURNS Return value from the user_function if terminated early. * Otherwise, returns NULL. * * DESCRIPTION: Performs a modified depth-first walk of the namespace tree, * starting (and ending) at the object specified by start_handle. * The user_function is called whenever an object of type * Device is found. If the user function returns * a non-zero value, the search is terminated immediately and this * value is returned to the caller. * * This is a wrapper for walk_namespace, but the callback performs * additional filtering. Please see acpi_ns_get_device_callback. * ******************************************************************************/ acpi_status acpi_get_devices(const char *HID, acpi_walk_callback user_function, void *context, void **return_value) { acpi_status status; struct acpi_get_devices_info info; ACPI_FUNCTION_TRACE(acpi_get_devices); /* Parameter validation */ if (!user_function) { return_ACPI_STATUS(AE_BAD_PARAMETER); } /* * We're going to call their callback from OUR callback, so we need * to know what it is, and their context parameter. */ info.hid = HID; info.context = context; info.user_function = user_function; /* * Lock the namespace around the walk. * The namespace will be unlocked/locked around each call * to the user function - since this function * must be allowed to make Acpi calls itself. */ status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } status = acpi_ns_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX, ACPI_NS_WALK_UNLOCK, acpi_ns_get_device_callback, NULL, &info, return_value); (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); return_ACPI_STATUS(status); } ACPI_EXPORT_SYMBOL(acpi_get_devices) /******************************************************************************* * * FUNCTION: acpi_attach_data * * PARAMETERS: obj_handle - Namespace node * handler - Handler for this attachment * data - Pointer to data to be attached * * RETURN: Status * * DESCRIPTION: Attach arbitrary data and handler to a namespace node. * ******************************************************************************/ acpi_status acpi_attach_data(acpi_handle obj_handle, acpi_object_handler handler, void *data) { struct acpi_namespace_node *node; acpi_status status; /* Parameter validation */ if (!obj_handle || !handler || !data) { return (AE_BAD_PARAMETER); } status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { return (status); } /* Convert and validate the handle */ node = acpi_ns_validate_handle(obj_handle); if (!node) { status = AE_BAD_PARAMETER; goto unlock_and_exit; } status = acpi_ns_attach_data(node, handler, data); unlock_and_exit: (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); return (status); } ACPI_EXPORT_SYMBOL(acpi_attach_data) /******************************************************************************* * * FUNCTION: acpi_detach_data * * PARAMETERS: obj_handle - Namespace node handle * handler - Handler used in call to acpi_attach_data * * RETURN: Status * * DESCRIPTION: Remove data that was previously attached to a node. * ******************************************************************************/ acpi_status acpi_detach_data(acpi_handle obj_handle, acpi_object_handler handler) { struct acpi_namespace_node *node; acpi_status status; /* Parameter validation */ if (!obj_handle || !handler) { return (AE_BAD_PARAMETER); } status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { return (status); } /* Convert and validate the handle */ node = acpi_ns_validate_handle(obj_handle); if (!node) { status = AE_BAD_PARAMETER; goto unlock_and_exit; } status = acpi_ns_detach_data(node, handler); unlock_and_exit: (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); return (status); } ACPI_EXPORT_SYMBOL(acpi_detach_data) /******************************************************************************* * * FUNCTION: acpi_get_data_full * * PARAMETERS: obj_handle - Namespace node * handler - Handler used in call to attach_data * data - Where the data is returned * callback - function to execute before returning * * RETURN: Status * * DESCRIPTION: Retrieve data that was previously attached to a namespace node * and execute a callback before returning. * ******************************************************************************/ acpi_status acpi_get_data_full(acpi_handle obj_handle, acpi_object_handler handler, void **data, void (*callback)(void *)) { struct acpi_namespace_node *node; acpi_status status; /* Parameter validation */ if (!obj_handle || !handler || !data) { return (AE_BAD_PARAMETER); } status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); if (ACPI_FAILURE(status)) { return (status); } /* Convert and validate the handle */ node = acpi_ns_validate_handle(obj_handle); if (!node) { status = AE_BAD_PARAMETER; goto unlock_and_exit; } status = acpi_ns_get_attached_data(node, handler, data); if (ACPI_SUCCESS(status) && callback) { callback(*data); } unlock_and_exit: (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); return (status); } ACPI_EXPORT_SYMBOL(acpi_get_data_full) /******************************************************************************* * * FUNCTION: acpi_get_data * * PARAMETERS: obj_handle - Namespace node * handler - Handler used in call to attach_data * data - Where the data is returned * * RETURN: Status * * DESCRIPTION: Retrieve data that was previously attached to a namespace node. * ******************************************************************************/ acpi_status acpi_get_data(acpi_handle obj_handle, acpi_object_handler handler, void **data) { return acpi_get_data_full(obj_handle, handler, data, NULL); } ACPI_EXPORT_SYMBOL(acpi_get_data) |
| 2 2 6 2 1 2 2 1 1 2 2 3 3 1 1 2 1 1 1 2 2 2 8 8 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NetLabel CALIPSO/IPv6 Support * * This file defines the CALIPSO/IPv6 functions for the NetLabel system. The * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and CALIPSO. * * Authors: Paul Moore <paul@paul-moore.com> * Huw Davies <huw@codeweavers.com> */ /* (c) Copyright Hewlett-Packard Development Company, L.P., 2006 * (c) Copyright Huw Davies <huw@codeweavers.com>, 2015 */ #include <linux/types.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/audit.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/netlabel.h> #include <net/calipso.h> #include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_calipso.h" #include "netlabel_mgmt.h" #include "netlabel_domainhash.h" /* Argument struct for calipso_doi_walk() */ struct netlbl_calipso_doiwalk_arg { struct netlink_callback *nl_cb; struct sk_buff *skb; u32 seq; }; /* Argument struct for netlbl_domhsh_walk() */ struct netlbl_domhsh_walk_arg { struct netlbl_audit *audit_info; u32 doi; }; /* NetLabel Generic NETLINK CALIPSO family */ static struct genl_family netlbl_calipso_gnl_family; /* NetLabel Netlink attribute policy */ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = { [NLBL_CALIPSO_A_DOI] = { .type = NLA_U32 }, [NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 }, }; static const struct netlbl_calipso_ops *calipso_ops; /** * netlbl_calipso_ops_register - Register the CALIPSO operations * @ops: ops to register * * Description: * Register the CALIPSO packet engine operations. * */ const struct netlbl_calipso_ops * netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) { return xchg(&calipso_ops, ops); } EXPORT_SYMBOL(netlbl_calipso_ops_register); static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) { return READ_ONCE(calipso_ops); } /* NetLabel Command Handlers */ /** * netlbl_calipso_add_pass - Adds a CALIPSO pass DOI definition * @info: the Generic NETLINK info block * @audit_info: NetLabel audit information * * Description: * Create a new CALIPSO_MAP_PASS DOI definition based on the given ADD message * and add it to the CALIPSO engine. Return zero on success and non-zero on * error. * */ static int netlbl_calipso_add_pass(struct genl_info *info, struct netlbl_audit *audit_info) { int ret_val; struct calipso_doi *doi_def = NULL; doi_def = kmalloc_obj(*doi_def); if (!doi_def) return -ENOMEM; doi_def->type = CALIPSO_MAP_PASS; doi_def->doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); ret_val = calipso_doi_add(doi_def, audit_info); if (ret_val != 0) calipso_doi_free(doi_def); return ret_val; } /** * netlbl_calipso_add - Handle an ADD message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Create a new DOI definition based on the given ADD message and add it to the * CALIPSO engine. Returns zero on success, negative values on failure. * */ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct netlbl_audit audit_info; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (!info->attrs[NLBL_CALIPSO_A_DOI] || !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; if (!ops) return -EOPNOTSUPP; netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: ret_val = netlbl_calipso_add_pass(info, &audit_info); break; } if (ret_val == 0) atomic_inc(&netlabel_mgmt_protocount); return ret_val; } /** * netlbl_calipso_list - Handle a LIST message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated LIST message and respond accordingly. * Returns zero on success and negative values on error. * */ static int netlbl_calipso_list(struct sk_buff *skb, struct genl_info *info) { int ret_val; struct sk_buff *ans_skb = NULL; void *data; u32 doi; struct calipso_doi *doi_def; if (!info->attrs[NLBL_CALIPSO_A_DOI]) { ret_val = -EINVAL; goto list_failure; } doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); doi_def = calipso_doi_getdef(doi); if (!doi_def) { ret_val = -EINVAL; goto list_failure; } ans_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ans_skb) { ret_val = -ENOMEM; goto list_failure_put; } data = genlmsg_put_reply(ans_skb, info, &netlbl_calipso_gnl_family, 0, NLBL_CALIPSO_C_LIST); if (!data) { ret_val = -ENOMEM; goto list_failure_put; } ret_val = nla_put_u32(ans_skb, NLBL_CALIPSO_A_MTYPE, doi_def->type); if (ret_val != 0) goto list_failure_put; calipso_doi_putdef(doi_def); genlmsg_end(ans_skb, data); return genlmsg_reply(ans_skb, info); list_failure_put: calipso_doi_putdef(doi_def); list_failure: kfree_skb(ans_skb); return ret_val; } /** * netlbl_calipso_listall_cb - calipso_doi_walk() callback for LISTALL * @doi_def: the CALIPSO DOI definition * @arg: the netlbl_calipso_doiwalk_arg structure * * Description: * This function is designed to be used as a callback to the * calipso_doi_walk() function for use in generating a response for a LISTALL * message. Returns the size of the message on success, negative values on * failure. * */ static int netlbl_calipso_listall_cb(struct calipso_doi *doi_def, void *arg) { int ret_val = -ENOMEM; struct netlbl_calipso_doiwalk_arg *cb_arg = arg; void *data; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_calipso_gnl_family, NLM_F_MULTI, NLBL_CALIPSO_C_LISTALL); if (!data) goto listall_cb_failure; ret_val = nla_put_u32(cb_arg->skb, NLBL_CALIPSO_A_DOI, doi_def->doi); if (ret_val != 0) goto listall_cb_failure; ret_val = nla_put_u32(cb_arg->skb, NLBL_CALIPSO_A_MTYPE, doi_def->type); if (ret_val != 0) goto listall_cb_failure; genlmsg_end(cb_arg->skb, data); return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); return ret_val; } /** * netlbl_calipso_listall - Handle a LISTALL message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated LISTALL message and respond accordingly. Returns * zero on success and negative values on error. * */ static int netlbl_calipso_listall(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_calipso_doiwalk_arg cb_arg; u32 doi_skip = cb->args[0]; cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; calipso_doi_walk(&doi_skip, netlbl_calipso_listall_cb, &cb_arg); cb->args[0] = doi_skip; return skb->len; } /** * netlbl_calipso_remove_cb - netlbl_calipso_remove() callback for REMOVE * @entry: LSM domain mapping entry * @arg: the netlbl_domhsh_walk_arg structure * * Description: * This function is intended for use by netlbl_calipso_remove() as the callback * for the netlbl_domhsh_walk() function; it removes LSM domain map entries * which are associated with the CALIPSO DOI specified in @arg. Returns zero on * success, negative values on failure. * */ static int netlbl_calipso_remove_cb(struct netlbl_dom_map *entry, void *arg) { struct netlbl_domhsh_walk_arg *cb_arg = arg; if (entry->def.type == NETLBL_NLTYPE_CALIPSO && entry->def.calipso->doi == cb_arg->doi) return netlbl_domhsh_remove_entry(entry, cb_arg->audit_info); return 0; } /** * netlbl_calipso_remove - Handle a REMOVE message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated REMOVE message and respond accordingly. Returns * zero on success, negative values on failure. * */ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct netlbl_domhsh_walk_arg cb_arg; struct netlbl_audit audit_info; u32 skip_bkt = 0; u32 skip_chain = 0; if (!info->attrs[NLBL_CALIPSO_A_DOI]) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, netlbl_calipso_remove_cb, &cb_arg); if (ret_val == 0 || ret_val == -ENOENT) { ret_val = calipso_doi_remove(cb_arg.doi, &audit_info); if (ret_val == 0) atomic_dec(&netlabel_mgmt_protocount); } return ret_val; } /* NetLabel Generic NETLINK Command Definitions */ static const struct genl_small_ops netlbl_calipso_ops[] = { { .cmd = NLBL_CALIPSO_C_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_calipso_add, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_REMOVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_calipso_remove, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = netlbl_calipso_list, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LISTALL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_calipso_listall, }, }; static struct genl_family netlbl_calipso_gnl_family __ro_after_init = { .hdrsize = 0, .name = NETLBL_NLTYPE_CALIPSO_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_CALIPSO_A_MAX, .policy = calipso_genl_policy, .module = THIS_MODULE, .small_ops = netlbl_calipso_ops, .n_small_ops = ARRAY_SIZE(netlbl_calipso_ops), .resv_start_op = NLBL_CALIPSO_C_LISTALL + 1, }; /* NetLabel Generic NETLINK Protocol Functions */ /** * netlbl_calipso_genl_init - Register the CALIPSO NetLabel component * * Description: * Register the CALIPSO packet NetLabel component with the Generic NETLINK * mechanism. Returns zero on success, negative values on failure. * */ int __init netlbl_calipso_genl_init(void) { return genl_register_family(&netlbl_calipso_gnl_family); } /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure * @audit_info: NetLabel audit information * * Description: * The caller defines a new DOI for use by the CALIPSO engine and calls this * function to add it to the list of acceptable domains. The caller must * ensure that the mapping table specified in @doi_def->map meets all of the * requirements of the mapping type (see calipso.h for details). Returns * zero on success and non-zero on failure. * */ int calipso_doi_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_add(doi_def, audit_info); return ret_val; } /** * calipso_doi_free - Frees a DOI definition * @doi_def: the DOI definition * * Description: * This function frees all of the memory associated with a DOI definition. * */ void calipso_doi_free(struct calipso_doi *doi_def) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->doi_free(doi_def); } /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will * be called to release their own LSM domain mappings as well as our own * domain list. Returns zero on success and negative values on failure. * */ int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_remove(doi, audit_info); return ret_val; } /** * calipso_doi_getdef - Returns a reference to a valid DOI definition * @doi: the DOI value * * Description: * Searches for a valid DOI definition and if one is found it is returned to * the caller. Otherwise NULL is returned. The caller must ensure that * calipso_doi_putdef() is called when the caller is done. * */ struct calipso_doi *calipso_doi_getdef(u32 doi) { struct calipso_doi *ret_val = NULL; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_getdef(doi); return ret_val; } /** * calipso_doi_putdef - Releases a reference for the given DOI definition * @doi_def: the DOI definition * * Description: * Releases a DOI definition reference obtained from calipso_doi_getdef(). * */ void calipso_doi_putdef(struct calipso_doi *doi_def) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->doi_putdef(doi_def); } /** * calipso_doi_walk - Iterate through the DOI definitions * @skip_cnt: skip past this number of DOI definitions, updated * @callback: callback for each DOI definition * @cb_arg: argument for the callback function * * Description: * Iterate over the DOI definition list, skipping the first @skip_cnt entries. * For each entry call @callback, if @callback returns a negative value stop * 'walking' through the list and return. Updates the value in @skip_cnt upon * return. Returns zero on success, negative values on failure. * */ int calipso_doi_walk(u32 *skip_cnt, int (*callback)(struct calipso_doi *doi_def, void *arg), void *cb_arg) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_walk(skip_cnt, callback, cb_arg); return ret_val; } /** * calipso_sock_getattr - Get the security attributes from a sock * @sk: the sock * @secattr: the security attributes * * Description: * Query @sk to see if there is a CALIPSO option attached to the sock and if * there is return the CALIPSO security attributes in @secattr. This function * requires that @sk be locked, or privately held, but it does not do any * locking itself. Returns zero on success and negative values on failure. * */ int calipso_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->sock_getattr(sk, secattr); return ret_val; } /** * calipso_sock_setattr - Add a CALIPSO option to a socket * @sk: the socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. This function requires * exclusive access to @sk, which means it either needs to be in the * process of being created or locked. Returns zero on success and negative * values on failure. * */ int calipso_sock_setattr(struct sock *sk, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->sock_setattr(sk, doi_def, secattr); return ret_val; } /** * calipso_sock_delattr - Delete the CALIPSO option from a socket * @sk: the socket * * Description: * Removes the CALIPSO option from a socket, if present. * */ void calipso_sock_delattr(struct sock *sk) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->sock_delattr(sk); } /** * calipso_req_setattr - Add a CALIPSO option to a connection request socket * @req: the connection request socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. Returns zero on success and * negative values on failure. * */ int calipso_req_setattr(struct request_sock *req, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->req_setattr(req, doi_def, secattr); return ret_val; } /** * calipso_req_delattr - Delete the CALIPSO option from a request socket * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. * */ void calipso_req_delattr(struct request_sock *req) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->req_delattr(req); } /** * calipso_optptr - Find the CALIPSO option in the packet * @skb: the packet * * Description: * Parse the packet's IP header looking for a CALIPSO option. Returns a pointer * to the start of the CALIPSO option on success, NULL if one if not found. * */ unsigned char *calipso_optptr(const struct sk_buff *skb) { unsigned char *ret_val = NULL; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_optptr(skb); return ret_val; } /** * calipso_getattr - Get the security attributes from a memory block. * @calipso: the CALIPSO option * @secattr: the security attributes * * Description: * Inspect @calipso and return the security attributes in @secattr. * Returns zero on success and negative values on failure. * */ int calipso_getattr(const unsigned char *calipso, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->opt_getattr(calipso, secattr); return ret_val; } /** * calipso_skbuff_setattr - Set the CALIPSO option on a packet * @skb: the packet * @doi_def: the CALIPSO DOI to use * @secattr: the security attributes * * Description: * Set the CALIPSO option on the given packet based on the security attributes. * Returns a pointer to the IP header on success and NULL on failure. * */ int calipso_skbuff_setattr(struct sk_buff *skb, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_setattr(skb, doi_def, secattr); return ret_val; } /** * calipso_skbuff_delattr - Delete any CALIPSO options from a packet * @skb: the packet * * Description: * Removes any and all CALIPSO options from the given packet. Returns zero on * success, negative values on failure. * */ int calipso_skbuff_delattr(struct sk_buff *skb) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_delattr(skb); return ret_val; } /** * calipso_cache_invalidate - Invalidates the current CALIPSO cache * * Description: * Invalidates and frees any entries in the CALIPSO cache. Returns zero on * success and negative values on failure. * */ void calipso_cache_invalidate(void) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->cache_invalidate(); } /** * calipso_cache_add - Add an entry to the CALIPSO cache * @calipso_ptr: the CALIPSO option * @secattr: the packet's security attributes * * Description: * Add a new entry into the CALIPSO label mapping cache. * Returns zero on success, negative values on failure. * */ int calipso_cache_add(const unsigned char *calipso_ptr, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->cache_add(calipso_ptr, secattr); return ret_val; } |
| 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | // SPDX-License-Identifier: GPL-2.0 /* RTT/RTO calculation. * * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com) * * https://tools.ietf.org/html/rfc6298 * https://tools.ietf.org/html/rfc1122#section-4.2.3.1 * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf */ #include <linux/net.h> #include "ar-internal.h" #define RXRPC_RTO_MAX (120 * USEC_PER_SEC) #define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * USEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_call *call) { return 200; } static u32 __rxrpc_set_rto(const struct rxrpc_call *call) { return (call->srtt_us >> 3) + call->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) { return clamp(200000, rto + 100000, RXRPC_RTO_MAX); } /* * Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 * piece by Van Jacobson. * NOTE: the next three routines used to be one big routine. * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ static void rxrpc_rtt_estimator(struct rxrpc_call *call, long sample_rtt_us) { long m = sample_rtt_us; /* RTT */ u32 srtt = call->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev * are scaled versions of rtt and mean deviation. * This is designed to be as fast as possible * m stands for "measurement". * * On a 1990 paper the rto value is changed to: * RTO = rtt + 4 * mdev * * Funny. This algorithm seems to be very broken. * These formulae increase RTO, when it should be decreased, increase * too slowly, when it should be increased quickly, decrease too quickly * etc. I guess in BSD RTO takes ONE value, so that it is absolutely * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ if (srtt != 0) { m -= (srtt >> 3); /* m is now error in rtt est */ srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ m -= (call->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain * for mdev in this case (alpha*beta). * Like Eifel it also prevents growth of rto, * but also it limits too fast rto decreases, * happening in pure Eifel. */ if (m > 0) m >>= 3; } else { m -= (call->mdev_us >> 2); /* similar update on mdev */ } call->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ if (call->mdev_us > call->mdev_max_us) { call->mdev_max_us = call->mdev_us; if (call->mdev_max_us > call->rttvar_us) call->rttvar_us = call->mdev_max_us; } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ call->mdev_us = m << 1; /* make sure rto = 3*rtt */ call->rttvar_us = umax(call->mdev_us, rxrpc_rto_min_us(call)); call->mdev_max_us = call->rttvar_us; } call->srtt_us = umax(srtt, 1); } /* * Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ static void rxrpc_set_rto(struct rxrpc_call *call) { u32 rto; /* 1. If rtt variance happened to be less 50msec, it is hallucination. * It cannot be less due to utterly erratic ACK generation made * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ * to do with delayed acks, because at cwnd>2 true delack timeout * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ rto = __rxrpc_set_rto(call); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do. */ /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ call->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_update_rtt_min(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { /* Window size 5mins in approx usec (ipv4.sysctl_tcp_min_rtt_wlen) */ u32 wlen_us = 5ULL * NSEC_PER_SEC / 1024; minmax_running_min(&call->min_rtt, wlen_us, resp_time / 1024, (u32)rtt_us ? : jiffies_to_usecs(1)); } static void rxrpc_ack_update_rtt(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { if (rtt_us < 0) return; /* Update RACK min RTT [RFC8985 6.1 Step 1]. */ rxrpc_update_rtt_min(call, resp_time, rtt_us); rxrpc_rtt_estimator(call, rtt_us); rxrpc_set_rto(call); /* Only reset backoff on valid RTT measurement [RFC6298]. */ call->backoff = 0; } /* * Add RTT information to cache. This is called in softirq mode and has * exclusive access to the call RTT data. */ void rxrpc_call_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { s64 rtt_us; rtt_us = ktime_to_us(ktime_sub(resp_time, send_time)); if (rtt_us < 0) return; rxrpc_ack_update_rtt(call, resp_time, rtt_us); if (call->rtt_count < 3) call->rtt_count++; call->rtt_taken++; WRITE_ONCE(call->peer->recent_srtt_us, call->srtt_us / 8); WRITE_ONCE(call->peer->recent_rto_us, call->rto_us); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, rtt_us, call->srtt_us, call->rto_us); } /* * Get the retransmission timeout to set in nanoseconds, backing it off each * time we retransmit. */ ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans) { u64 timo_us; u32 backoff = READ_ONCE(call->backoff); timo_us = call->rto_us; timo_us <<= backoff; if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(call->backoff, backoff + 1); if (timo_us < 1) timo_us = 1; return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_call_init_rtt(struct rxrpc_call *call) { call->rtt_last_req = KTIME_MIN; call->rto_us = RXRPC_TIMEOUT_INIT; call->mdev_us = RXRPC_TIMEOUT_INIT; call->backoff = 0; //minmax_reset(&call->rtt_min, rxrpc_jiffies32, ~0U); } |
| 6 6 2 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Manage send buffer. * Producer: * Copy user space data into send buffer, if send buffer space available. * Consumer: * Trigger RDMA write into RMBE of peer and send CDC, if RMBE space available. * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/tcp.h> #include "smc.h" #include "smc_wr.h" #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" #include "smc_stats.h" #include "smc_tracepoint.h" #define SMC_TX_WORK_DELAY 0 /***************************** sndbuf producer *******************************/ /* callback implementation for sk.sk_write_space() * to wakeup sndbuf producers that blocked with smc_tx_wait(). * called under sk_socket lock. */ static void smc_tx_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; struct smc_sock *smc = smc_sk(sk); struct socket_wq *wq; /* similar to sk_stream_write_space */ if (atomic_read(&smc->conn.sndbuf_space) && sock) { if (test_bit(SOCK_NOSPACE, &sock->flags)) SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk); clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } } /* Wakeup sndbuf producers that blocked with smc_tx_wait(). * Cf. tcp_data_snd_check()=>tcp_check_space()=>tcp_new_space(). */ void smc_tx_sndbuf_nonfull(struct smc_sock *smc) { if (smc->sk.sk_socket && test_bit(SOCK_NOSPACE, &smc->sk.sk_socket->flags)) smc->sk.sk_write_space(&smc->sk); } /* blocks sndbuf producer until at least one byte of free space available * or urgent Byte was consumed */ static int smc_tx_wait(struct smc_sock *smc, int flags) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; long timeo; int rc = 0; /* similar to sk_stream_wait_memory */ timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); add_wait_queue(sk_sleep(sk), &wait); while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN) || conn->killed || conn->local_tx_ctrl.conn_state_flags.peer_done_writing) { rc = -EPIPE; break; } if (smc_cdc_rxed_any_close(conn)) { rc = -ECONNRESET; break; } if (!timeo) { /* ensure EPOLLOUT is subsequently generated */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); rc = -EAGAIN; break; } if (signal_pending(current)) { rc = sock_intr_errno(timeo); break; } sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend) break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, READ_ONCE(sk->sk_err) || (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend), &wait); } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static bool smc_tx_is_corked(struct smc_sock *smc) { struct tcp_sock *tp = tcp_sk(smc->clcsock->sk); return (tp->nonagle & TCP_NAGLE_CORK) ? true : false; } /* If we have pending CDC messages, do not send: * Because CQE of this CDC message will happen shortly, it gives * a chance to coalesce future sendmsg() payload in to one RDMA Write, * without need for a timer, and with no latency trade off. * Algorithm here: * 1. First message should never cork * 2. If we have pending Tx CDC messages, wait for the first CDC * message's completion * 3. Don't cork to much data in a single RDMA Write to prevent burst * traffic, total corked message should not exceed sendbuf/2 */ static bool smc_should_autocork(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; int corking_size; corking_size = min_t(unsigned int, conn->sndbuf_desc->len >> 1, sock_net(&smc->sk)->smc.sysctl_autocorking_size); if (atomic_read(&conn->cdc_pend_tx_wr) == 0 || smc_tx_prepared_sends(conn) > corking_size) return false; return true; } static bool smc_tx_should_cork(struct smc_sock *smc, struct msghdr *msg) { struct smc_connection *conn = &smc->conn; if (smc_should_autocork(smc)) return true; /* for a corked socket defer the RDMA writes if * sndbuf_space is still available. The applications * should known how/when to uncork it. */ if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && atomic_read(&conn->sndbuf_space)) return true; return false; } /* sndbuf producer: main API called by socket layer. * called under sock lock. */ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) { size_t copylen, send_done = 0, send_remaining = len; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; union smc_host_cursor prep; struct sock *sk = &smc->sk; char *sndbuf_base; int tx_cnt_prep; int writespace; int rc, chunk; /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) { rc = -EPIPE; goto out_err; } if (sk->sk_state == SMC_INIT) return -ENOTCONN; if (len > conn->sndbuf_desc->len) SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk); if (len > conn->peer_rmbe_size) SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk); if (msg->msg_flags & MSG_OOB) SMC_STAT_INC(smc, urg_data_cnt); while (msg_data_left(msg)) { if (smc->sk.sk_shutdown & SEND_SHUTDOWN || (smc->sk.sk_err == ECONNABORTED) || conn->killed) return -EPIPE; if (smc_cdc_rxed_any_close(conn)) return send_done ?: -ECONNRESET; if (msg->msg_flags & MSG_OOB) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { if (send_done) return send_done; rc = smc_tx_wait(smc, msg->msg_flags); if (rc) goto out_err; continue; } /* initialize variables for 1st iteration of subsequent loop */ /* could be just 1 byte, even after smc_tx_wait above */ writespace = atomic_read(&conn->sndbuf_space); /* not more than what user space asked for */ copylen = min_t(size_t, send_remaining, writespace); /* determine start of sndbuf */ sndbuf_base = conn->sndbuf_desc->cpu_addr; smc_curs_copy(&prep, &conn->tx_curs_prep, conn); tx_cnt_prep = prep.count; /* determine chunks where to write into sndbuf */ /* either unwrapped case, or 1st chunk of wrapped case */ chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len - tx_cnt_prep); chunk_len_sum = chunk_len; chunk_off = tx_cnt_prep; for (chunk = 0; chunk < 2; chunk++) { rc = memcpy_from_msg(sndbuf_base + chunk_off, msg, chunk_len); if (rc) { smc_sndbuf_sync_sg_for_device(conn); if (send_done) return send_done; goto out_err; } send_done += chunk_len; send_remaining -= chunk_len; if (chunk_len_sum == copylen) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ chunk_len = copylen - chunk_len; /* remainder */ chunk_len_sum += chunk_len; chunk_off = 0; /* modulo offset in send ring buffer */ } smc_sndbuf_sync_sg_for_device(conn); /* update cursors */ smc_curs_add(conn->sndbuf_desc->len, &prep, copylen); smc_curs_copy(&conn->tx_curs_prep, &prep, conn); /* increased in send tasklet smc_cdc_tx_handler() */ smp_mb__before_atomic(); atomic_sub(copylen, &conn->sndbuf_space); /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ smp_mb__after_atomic(); /* since we just produced more new data into sndbuf, * trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ if ((msg->msg_flags & MSG_OOB) && !send_remaining) conn->urg_tx_pend = true; /* If we need to cork, do nothing and wait for the next * sendmsg() call or push on tx completion */ if (!smc_tx_should_cork(smc, msg)) smc_tx_sndbuf_nonempty(conn); trace_smc_tx_sendmsg(smc, copylen); } /* while (msg_data_left(msg)) */ return send_done; out_err: rc = sk_stream_error(sk, msg->msg_flags, rc); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(rc == -EAGAIN)) sk->sk_write_space(sk); return rc; } /***************************** sndbuf consumer *******************************/ /* sndbuf consumer: actual data transfer of one target chunk with ISM write */ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, u32 offset, int signal) { int rc; rc = smc_ism_write(conn->lgr->smcd, conn->peer_token, conn->peer_rmbe_idx, signal, conn->tx_off + offset, data, len); if (rc) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; return rc; } /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; struct smc_link *link = conn->lnk; int rc; rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); rdma_wr->wr.num_sge = num_sges; rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][link->link_idx].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][link->link_idx].rkey; rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) smcr_link_down_cond_sched(link); return rc; } /* sndbuf consumer */ static inline void smc_tx_advance_cursors(struct smc_connection *conn, union smc_host_cursor *prod, union smc_host_cursor *sent, size_t len) { smc_curs_add(conn->peer_rmbe_size, prod, len); /* increased in recv tasklet smc_cdc_msg_rcv() */ smp_mb__before_atomic(); /* data in flight reduces usable snd_wnd */ atomic_sub(len, &conn->peer_rmbe_space); /* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */ smp_mb__after_atomic(); smc_curs_add(conn->sndbuf_desc->len, sent, len); } /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, size_t dst_off, size_t dst_len, struct smc_rdma_wr *wr_rdma_buf) { struct smc_link *link = conn->lnk; dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[link->link_idx].sgl); u64 virt_addr = (uintptr_t)conn->sndbuf_desc->cpu_addr; int src_len_sum = src_len, dst_len_sum = dst_len; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { struct ib_rdma_wr *wr = &wr_rdma_buf->wr_tx_rdma[dstchunk]; struct ib_sge *sge = wr->wr.sg_list; u64 base_addr = dma_addr; if (dst_len < link->qp_attr.cap.max_inline_data) { base_addr = virt_addr; wr->wr.send_flags |= IB_SEND_INLINE; } else { wr->wr.send_flags &= ~IB_SEND_INLINE; } num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { sge[srcchunk].addr = conn->sndbuf_desc->is_vm ? (virt_addr + src_off) : (base_addr + src_off); sge[srcchunk].length = src_len; if (conn->sndbuf_desc->is_vm) sge[srcchunk].lkey = conn->sndbuf_desc->mr[link->link_idx]->lkey; num_sges++; src_off += src_len; if (src_off >= conn->sndbuf_desc->len) src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } rc = smc_tx_rdma_write(conn, dst_off, num_sges, wr); if (rc) return rc; if (dst_len_sum == len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ dst_off = 0; /* modulo offset in RMBE ring buffer */ dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, dst_len, conn->sndbuf_desc->len - sent_count); src_len_sum = src_len; } return 0; } /* SMC-D helper for smc_tx_rdma_writes() */ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, size_t dst_off, size_t dst_len) { int src_len_sum = src_len, dst_len_sum = dst_len; int srcchunk, dstchunk; int rc; if (conn->sndbuf_desc->is_attached) return 0; for (dstchunk = 0; dstchunk < 2; dstchunk++) { for (srcchunk = 0; srcchunk < 2; srcchunk++) { void *data = conn->sndbuf_desc->cpu_addr + src_off; rc = smcd_tx_ism_write(conn, data, src_len, dst_off + sizeof(struct smcd_cdc_msg), 0); if (rc) return rc; dst_off += src_len; src_off += src_len; if (src_off >= conn->sndbuf_desc->len) src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } if (dst_len_sum == len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ dst_off = 0; /* modulo offset in RMBE ring buffer */ dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off); src_len_sum = src_len; } return 0; } /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ static int smc_tx_rdma_writes(struct smc_connection *conn, struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; struct smc_cdc_producer_flags *pflags; int to_send, rmbespace; int rc; /* source: sndbuf */ smc_curs_copy(&sent, &conn->tx_curs_sent, conn); smc_curs_copy(&prep, &conn->tx_curs_prep, conn); /* cf. wmem_alloc - (snd_max - snd_una) */ to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); if (to_send <= 0) return 0; /* destination: RMBE */ /* cf. snd_wnd */ rmbespace = atomic_read(&conn->peer_rmbe_space); if (rmbespace <= 0) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); return 0; } smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); /* if usable snd_wnd closes ask peer to advertise once it opens again */ pflags = &conn->local_tx_ctrl.prod_flags; pflags->write_blocked = (to_send >= rmbespace); /* cf. usable snd_wnd */ len = min(to_send, rmbespace); /* initialize variables for first iteration of subsequent nested loop */ dst_off = prod.count; if (prod.wrap == cons.wrap) { /* the filled destination area is unwrapped, * hence the available free destination space is wrapped * and we need 2 destination chunks of sum len; start with 1st * which is limited by what's available in sndbuf */ dst_len = min_t(size_t, conn->peer_rmbe_size - prod.count, len); } else { /* the filled destination area is wrapped, * hence the available free destination space is unwrapped * and we need a single destination chunk of entire len */ dst_len = len; } /* dst_len determines the maximum src_len */ if (sent.count + dst_len <= conn->sndbuf_desc->len) { /* unwrapped src case: single chunk of entire dst_len */ src_len = dst_len; } else { /* wrapped src case: 2 chunks of sum dst_len; start with 1st: */ src_len = conn->sndbuf_desc->len - sent.count; } if (conn->lgr->is_smcd) rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len, dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, dst_off, dst_len, wr_rdma_buf); if (rc) return rc; if (conn->urg_tx_pend && len == to_send) pflags->urg_data_present = 1; smc_tx_advance_cursors(conn, &prod, &sent, len); /* update connection's cursors with advanced local cursors */ smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn); /* dst: peer RMBE */ smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */ return 0; } /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; if (!link || !smc_wr_tx_link_hold(link)) return -ENOLINK; rc = smc_cdc_get_free_slot(conn, link, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { smc_wr_tx_link_put(link); if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); if (smc->sk.sk_err == ECONNABORTED) return sock_error(&smc->sk); if (conn->killed) return -EPIPE; rc = 0; mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } return rc; } spin_lock_bh(&conn->send_lock); if (link != conn->lnk) { /* link of connection changed, tx_work will restart */ smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); rc = -ENOLINK; goto out_unlock; } if (!pflags->urg_data_present) { rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); goto out_unlock; } } rc = smc_cdc_msg_send(conn, wr_buf, pend); if (!rc && pflags->urg_data_present) { pflags->urg_data_pending = 0; pflags->urg_data_present = 0; } out_unlock: spin_unlock_bh(&conn->send_lock); smc_wr_tx_link_put(link); return rc; } static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; int rc = 0; spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); if (!rc && pflags->urg_data_present) { pflags->urg_data_pending = 0; pflags->urg_data_present = 0; } spin_unlock_bh(&conn->send_lock); return rc; } int smc_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc = 0; /* No data in the send queue */ if (unlikely(smc_tx_prepared_sends(conn) <= 0)) goto out; /* Peer don't have RMBE space */ if (unlikely(atomic_read(&conn->peer_rmbe_space) <= 0)) { SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); goto out; } if (conn->killed || conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) { rc = -EPIPE; /* connection being aborted */ goto out; } if (conn->lgr->is_smcd) rc = smcd_tx_sndbuf_nonempty(conn); else rc = smcr_tx_sndbuf_nonempty(conn); if (!rc) { /* trigger socket release if connection is closing */ smc_close_wake_tx_prepared(smc); } out: return rc; } /* Wakeup sndbuf consumers from process context * since there is more data to transmit. The caller * must hold sock lock. */ void smc_tx_pending(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc; if (smc->sk.sk_err) return; rc = smc_tx_sndbuf_nonempty(conn); if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; } /* Wakeup sndbuf consumers from process context * since there is more data to transmit in locked * sock. */ void smc_tx_work(struct work_struct *work) { struct smc_connection *conn = container_of(to_delayed_work(work), struct smc_connection, tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); lock_sock(&smc->sk); smc_tx_pending(conn); release_sock(&smc->sk); } void smc_tx_consumer_update(struct smc_connection *conn, bool force) { union smc_host_cursor cfed, cons, prod; int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn); smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - smc_curs_diff_large(conn->rmb_desc->len, &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if (conn->killed || conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) return; if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && !conn->killed) { queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); return; } } if (conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; } /***************************** send initialize *******************************/ /* Initialize send properties on connection establishment. NB: not __init! */ void smc_tx_init(struct smc_sock *smc) { smc->sk.sk_write_space = smc_tx_write_space; } |
| 7 1 1 2 4 2 2 2 2 1 1 1 1 1 3 2 1 2 2 2 2 19 19 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Checksum updating actions * * Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org> */ #include <linux/types.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/netlink.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/icmp.h> #include <linux/icmpv6.h> #include <linux/igmp.h> #include <net/tcp.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include <net/sctp/checksum.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_csum.h> #include <net/tc_act/tc_csum.h> #include <net/tc_wrapper.h> static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_csum_params *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy, NULL); if (err < 0) return err; if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_csum_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) /* dont override defaults */ return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } else { return err; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; p = to_tcf_csum(*a); params_new = kzalloc_obj(*params_new); if (unlikely(!params_new)) { err = -ENOMEM; goto put_chain; } params_new->update_flags = parm->update_flags; params_new->action = parm->action; spin_lock_bh(&p->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(p->params, params_new, lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params_new) kfree_rcu(params_new, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } /** * tcf_csum_skb_nextlayer - Get next layer pointer * @skb: sk_buff to use * @ihl: previous summed headers length * @ipl: complete packet length * @jhl: next header length * * Check the expected next layer availability in the specified sk_buff. * Return the next layer pointer if pass, NULL otherwise. */ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, unsigned int jhl) { int ntkoff = skb_network_offset(skb); int hl = ihl + jhl; if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) || skb_try_make_writable(skb, hl + ntkoff)) return NULL; else return (void *)(skb_network_header(skb) + ihl); } static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct icmphdr *icmph; icmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmph)); if (icmph == NULL) return 0; icmph->checksum = 0; skb->csum = csum_partial(icmph, ipl - ihl, 0); icmph->checksum = csum_fold(skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_igmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct igmphdr *igmph; igmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*igmph)); if (igmph == NULL) return 0; igmph->csum = 0; skb->csum = csum_partial(igmph, ipl - ihl, 0); igmph->csum = csum_fold(skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct icmp6hdr *icmp6h; const struct ipv6hdr *ip6h; icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h)); if (icmp6h == NULL) return 0; ip6h = ipv6_hdr(skb); icmp6h->icmp6_cksum = 0; skb->csum = csum_partial(icmp6h, ipl - ihl, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ipl - ihl, IPPROTO_ICMPV6, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct tcphdr *tcph; const struct iphdr *iph; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) return 1; tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; iph = ip_hdr(skb); tcph->check = 0; skb->csum = csum_partial(tcph, ipl - ihl, 0); tcph->check = tcp_v4_check(ipl - ihl, iph->saddr, iph->daddr, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct tcphdr *tcph; const struct ipv6hdr *ip6h; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) return 1; tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; ip6h = ipv6_hdr(skb); tcph->check = 0; skb->csum = csum_partial(tcph, ipl - ihl, 0); tcph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ipl - ihl, IPPROTO_TCP, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, int udplite) { struct udphdr *udph; const struct iphdr *iph; u16 ul; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4 | SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM)) return 1; /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use iph->tot_len, or just ipl. */ udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); if (udph == NULL) return 0; iph = ip_hdr(skb); ul = udp_get_len_short(udph); if (udplite || udph->check) { udph->check = 0; if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); else goto ignore_obscure_skb; } else { if (ul != ipl - ihl) goto ignore_obscure_skb; skb->csum = csum_partial(udph, ul, 0); } udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, ul, iph->protocol, skb->csum); if (!udph->check) udph->check = CSUM_MANGLED_0; } skb->ip_summed = CHECKSUM_NONE; ignore_obscure_skb: return 1; } static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, int udplite) { struct udphdr *udph; const struct ipv6hdr *ip6h; u16 ul; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4 | SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM)) return 1; /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl. */ udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); if (udph == NULL) return 0; ip6h = ipv6_hdr(skb); ul = udp_get_len_short(udph); udph->check = 0; if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); else goto ignore_obscure_skb; } else { if (ul != ipl - ihl) goto ignore_obscure_skb; skb->csum = csum_partial(udph, ul, 0); } udph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ul, udplite ? IPPROTO_UDPLITE : IPPROTO_UDP, skb->csum); if (!udph->check) udph->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_NONE; ignore_obscure_skb: return 1; } static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct sctphdr *sctph; if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); if (!sctph) return 0; sctph->checksum = sctp_compute_cksum(skb, skb_network_offset(skb) + ihl); skb_reset_csum_not_inet(skb); return 1; } static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) { const struct iphdr *iph; int ntkoff; ntkoff = skb_network_offset(skb); if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff)) goto fail; iph = ip_hdr(skb); switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) { case IPPROTO_ICMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_IGMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP) if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4, ntohs(iph->tot_len), 0)) goto fail; break; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4, ntohs(iph->tot_len), 1)) goto fail; break; case IPPROTO_SCTP: if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && !tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; } if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff)) goto fail; ip_send_check(ip_hdr(skb)); } return 1; fail: return 0; } static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl, unsigned int *pl) { int off, len, optlen; unsigned char *xh = (void *)ip6xh; off = sizeof(*ip6xh); len = ixhl - off; while (len > 1) { switch (xh[off]) { case IPV6_TLV_PAD1: optlen = 1; break; case IPV6_TLV_JUMBO: optlen = xh[off + 1] + 2; if (optlen != 6 || len < 6 || (off & 3) != 2) /* wrong jumbo option length/alignment */ return 0; *pl = ntohl(*(__be32 *)(xh + off + 2)); goto done; default: optlen = xh[off + 1] + 2; if (optlen > len) /* ignore obscure options */ goto done; break; } off += optlen; len -= optlen; } done: return 1; } static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags) { struct ipv6hdr *ip6h; struct ipv6_opt_hdr *ip6xh; unsigned int hl, ixhl; unsigned int pl; int ntkoff; u8 nexthdr; ntkoff = skb_network_offset(skb); hl = sizeof(*ip6h); if (!pskb_may_pull(skb, hl + ntkoff)) goto fail; ip6h = ipv6_hdr(skb); pl = ntohs(ip6h->payload_len); nexthdr = ip6h->nexthdr; do { switch (nexthdr) { case NEXTHDR_FRAGMENT: goto ignore_skb; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff)) goto fail; ip6xh = (void *)(skb_network_header(skb) + hl); ixhl = ipv6_optlen(ip6xh); if (!pskb_may_pull(skb, hl + ixhl + ntkoff)) goto fail; ip6xh = (void *)(skb_network_header(skb) + hl); if ((nexthdr == NEXTHDR_HOP) && !(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl))) goto fail; nexthdr = ip6xh->nexthdr; hl += ixhl; break; case IPPROTO_ICMPV6: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) if (!tcf_csum_ipv6_icmp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) if (!tcf_csum_ipv6_tcp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) if (!tcf_csum_ipv6_udp(skb, hl, pl + sizeof(*ip6h), 0)) goto fail; goto done; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) if (!tcf_csum_ipv6_udp(skb, hl, pl + sizeof(*ip6h), 1)) goto fail; goto done; case IPPROTO_SCTP: if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && !tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; default: goto ignore_skb; } } while (pskb_may_pull(skb, hl + 1 + ntkoff)); done: ignore_skb: return 1; fail: return 0; } TC_INDIRECT_SCOPE int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); bool orig_vlan_tag_present = false; unsigned int vlan_hdr_count = 0; struct tcf_csum_params *params; u32 update_flags; __be16 protocol; int action; params = rcu_dereference_bh(p->params); tcf_lastuse_update(&p->tcf_tm); tcf_action_update_bstats(&p->common, skb); action = params->action; if (unlikely(action == TC_ACT_SHOT)) goto drop; update_flags = params->update_flags; protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) goto drop; break; case cpu_to_be16(ETH_P_IPV6): if (!tcf_csum_ipv6(skb, update_flags)) goto drop; break; case cpu_to_be16(ETH_P_8021AD): fallthrough; case cpu_to_be16(ETH_P_8021Q): if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) { protocol = skb->protocol; orig_vlan_tag_present = true; } else { struct vlan_hdr *vlan; if (!pskb_may_pull(skb, VLAN_HLEN)) goto drop; vlan = (struct vlan_hdr *)skb->data; protocol = vlan->h_vlan_encapsulated_proto; skb_pull(skb, VLAN_HLEN); skb_reset_network_header(skb); vlan_hdr_count++; } goto again; } out: /* Restore the skb for the pulled VLAN tags */ while (vlan_hdr_count--) { skb_push(skb, VLAN_HLEN); skb_reset_network_header(skb); } return action; drop: tcf_action_inc_drop_qstats(&p->common); action = TC_ACT_SHOT; goto out; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { const struct tcf_csum *p = to_tcf_csum(a); unsigned char *b = skb_tail_pointer(skb); const struct tcf_csum_params *params; struct tc_csum opt = { .index = p->tcf_index, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; rcu_read_lock(); params = rcu_dereference(p->params); opt.action = params->action; opt.update_flags = params->update_flags; if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD)) goto nla_put_failure; rcu_read_unlock(); return skb->len; nla_put_failure: rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } static void tcf_csum_cleanup(struct tc_action *a) { struct tcf_csum *p = to_tcf_csum(a); struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); if (params) kfree_rcu(params, rcu); } static size_t tcf_csum_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_csum)); } static int tcf_csum_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; entry->id = FLOW_ACTION_CSUM; entry->csum_flags = tcf_csum_update_flags(act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_CSUM; } return 0; } static struct tc_action_ops act_csum_ops = { .kind = "csum", .id = TCA_ID_CSUM, .owner = THIS_MODULE, .act = tcf_csum_act, .dump = tcf_csum_dump, .init = tcf_csum_init, .cleanup = tcf_csum_cleanup, .get_fill_size = tcf_csum_get_fill_size, .offload_act_setup = tcf_csum_offload_act_setup, .size = sizeof(struct tcf_csum), }; MODULE_ALIAS_NET_ACT("csum"); static __net_init int csum_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); return tc_action_net_init(net, tn, &act_csum_ops); } static void __net_exit csum_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_csum_ops.net_id); } static struct pernet_operations csum_net_ops = { .init = csum_init_net, .exit_batch = csum_exit_net, .id = &act_csum_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_DESCRIPTION("Checksum updating actions"); MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { return tcf_register_action(&act_csum_ops, &csum_net_ops); } static void __exit csum_cleanup_module(void) { tcf_unregister_action(&act_csum_ops, &csum_net_ops); } module_init(csum_init_module); module_exit(csum_cleanup_module); |
| 72 72 71 2 1 3 3 2 1 72 70 2 70 3 47 68 68 45 45 45 45 45 1 2 3 3 2 1 2 1 3 1 1 3 18 18 2 16 2 2 3 3 3 2 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cgroup.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include "cgroup-internal.h" #include <trace/events/cgroup.h> /* * Update CGRP_FROZEN of cgroup.flag * Return true if flags is updated; false if flags has no change */ static bool cgroup_update_frozen_flag(struct cgroup *cgrp, bool frozen) { lockdep_assert_held(&css_set_lock); /* Already there? */ if (test_bit(CGRP_FROZEN, &cgrp->flags) == frozen) return false; if (frozen) set_bit(CGRP_FROZEN, &cgrp->flags); else clear_bit(CGRP_FROZEN, &cgrp->flags); cgroup_file_notify(&cgrp->events_file); TRACE_CGROUP_PATH(notify_frozen, cgrp, frozen); return true; } /* * Propagate the cgroup frozen state upwards by the cgroup tree. */ static void cgroup_propagate_frozen(struct cgroup *cgrp, bool frozen) { int desc = 1; /* * If the new state is frozen, some freezing ancestor cgroups may change * their state too, depending on if all their descendants are frozen. * * Otherwise, all ancestor cgroups are forced into the non-frozen state. */ while ((cgrp = cgroup_parent(cgrp))) { if (frozen) { cgrp->freezer.nr_frozen_descendants += desc; if (!test_bit(CGRP_FREEZE, &cgrp->flags) || (cgrp->freezer.nr_frozen_descendants != cgrp->nr_descendants)) continue; } else { cgrp->freezer.nr_frozen_descendants -= desc; } if (cgroup_update_frozen_flag(cgrp, frozen)) desc++; } } /* * Revisit the cgroup frozen state. * Checks if the cgroup is really frozen and perform all state transitions. */ void cgroup_update_frozen(struct cgroup *cgrp) { bool frozen; /* * If the cgroup has to be frozen (CGRP_FREEZE bit set), * and all tasks are frozen and/or stopped, let's consider * the cgroup frozen. Otherwise it's not frozen. */ frozen = test_bit(CGRP_FREEZE, &cgrp->flags) && cgrp->freezer.nr_frozen_tasks == __cgroup_task_count(cgrp); /* If flags is updated, update the state of ancestor cgroups. */ if (cgroup_update_frozen_flag(cgrp, frozen)) cgroup_propagate_frozen(cgrp, frozen); } /* * Increment cgroup's nr_frozen_tasks. */ static void cgroup_inc_frozen_cnt(struct cgroup *cgrp) { cgrp->freezer.nr_frozen_tasks++; } /* * Decrement cgroup's nr_frozen_tasks. */ static void cgroup_dec_frozen_cnt(struct cgroup *cgrp) { cgrp->freezer.nr_frozen_tasks--; WARN_ON_ONCE(cgrp->freezer.nr_frozen_tasks < 0); } /* * Enter frozen/stopped state, if not yet there. Update cgroup's counters, * and revisit the state of the cgroup, if necessary. */ void cgroup_enter_frozen(void) { struct cgroup *cgrp; if (current->frozen) return; spin_lock_irq(&css_set_lock); current->frozen = true; cgrp = task_dfl_cgroup(current); cgroup_inc_frozen_cnt(cgrp); cgroup_update_frozen(cgrp); spin_unlock_irq(&css_set_lock); } /* * Conditionally leave frozen/stopped state. Update cgroup's counters, * and revisit the state of the cgroup, if necessary. * * If always_leave is not set, and the cgroup is freezing, * we're racing with the cgroup freezing. In this case, we don't * drop the frozen counter to avoid a transient switch to * the unfrozen state. */ void cgroup_leave_frozen(bool always_leave) { struct cgroup *cgrp; spin_lock_irq(&css_set_lock); cgrp = task_dfl_cgroup(current); if (always_leave || !test_bit(CGRP_FREEZE, &cgrp->flags)) { cgroup_dec_frozen_cnt(cgrp); cgroup_update_frozen(cgrp); WARN_ON_ONCE(!current->frozen); current->frozen = false; } else if (!(current->jobctl & JOBCTL_TRAP_FREEZE)) { spin_lock(¤t->sighand->siglock); current->jobctl |= JOBCTL_TRAP_FREEZE; set_thread_flag(TIF_SIGPENDING); spin_unlock(¤t->sighand->siglock); } spin_unlock_irq(&css_set_lock); } /* * Freeze or unfreeze the task by setting or clearing the JOBCTL_TRAP_FREEZE * jobctl bit. */ static void cgroup_freeze_task(struct task_struct *task, bool freeze) { unsigned long flags; /* If the task is about to die, don't bother with freezing it. */ if (!lock_task_sighand(task, &flags)) return; if (freeze) { task->jobctl |= JOBCTL_TRAP_FREEZE; signal_wake_up(task, false); } else { task->jobctl &= ~JOBCTL_TRAP_FREEZE; wake_up_process(task); } unlock_task_sighand(task, &flags); } /* * Freeze or unfreeze all tasks in the given cgroup. */ static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze, u64 ts_nsec) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); write_seqcount_begin(&cgrp->freezer.freeze_seq); if (freeze) { set_bit(CGRP_FREEZE, &cgrp->flags); cgrp->freezer.freeze_start_nsec = ts_nsec; } else { clear_bit(CGRP_FREEZE, &cgrp->flags); cgrp->freezer.frozen_nsec += (ts_nsec - cgrp->freezer.freeze_start_nsec); } write_seqcount_end(&cgrp->freezer.freeze_seq); spin_unlock_irq(&css_set_lock); if (freeze) TRACE_CGROUP_PATH(freeze, cgrp); else TRACE_CGROUP_PATH(unfreeze, cgrp); css_task_iter_start(&cgrp->self, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Ignore kernel threads here. Freezing cgroups containing * kthreads isn't supported. */ if (task->flags & PF_KTHREAD) continue; cgroup_freeze_task(task, freeze); } css_task_iter_end(&it); /* * Cgroup state should be revisited here to cover empty leaf cgroups * and cgroups which descendants are already in the desired state. */ spin_lock_irq(&css_set_lock); if (cgrp->nr_descendants == cgrp->freezer.nr_frozen_descendants) cgroup_update_frozen(cgrp); spin_unlock_irq(&css_set_lock); } /* * Adjust the task state (freeze or unfreeze) and revisit the state of * source and destination cgroups. */ void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst) { lockdep_assert_held(&css_set_lock); /* * Kernel threads are not supposed to be frozen at all. */ if (task->flags & PF_KTHREAD) return; /* * It's not necessary to do changes if both of the src and dst cgroups * are not freezing and task is not frozen. */ if (!test_bit(CGRP_FREEZE, &src->flags) && !test_bit(CGRP_FREEZE, &dst->flags) && !task->frozen) return; /* * Adjust counters of freezing and frozen tasks. * Note, that if the task is frozen, but the destination cgroup is not * frozen, we bump both counters to keep them balanced. */ if (task->frozen) { cgroup_inc_frozen_cnt(dst); cgroup_dec_frozen_cnt(src); } cgroup_update_frozen(dst); cgroup_update_frozen(src); /* * Force the task to the desired state. */ cgroup_freeze_task(task, test_bit(CGRP_FREEZE, &dst->flags)); } void cgroup_freeze(struct cgroup *cgrp, bool freeze) { struct cgroup_subsys_state *css; struct cgroup *parent; struct cgroup *dsct; bool applied = false; u64 ts_nsec; bool old_e; lockdep_assert_held(&cgroup_mutex); /* * Nothing changed? Just exit. */ if (cgrp->freezer.freeze == freeze) return; cgrp->freezer.freeze = freeze; ts_nsec = ktime_get_ns(); /* * Propagate changes downwards the cgroup tree. */ css_for_each_descendant_pre(css, &cgrp->self) { dsct = css->cgroup; if (cgroup_is_dead(dsct)) continue; /* * e_freeze is affected by parent's e_freeze and dst's freeze. * If old e_freeze eq new e_freeze, no change, its children * will not be affected. So do nothing and skip the subtree */ old_e = dsct->freezer.e_freeze; parent = cgroup_parent(dsct); dsct->freezer.e_freeze = (dsct->freezer.freeze || parent->freezer.e_freeze); if (dsct->freezer.e_freeze == old_e) { css = css_rightmost_descendant(css); continue; } /* * Do change actual state: freeze or unfreeze. */ cgroup_do_freeze(dsct, freeze, ts_nsec); applied = true; } /* * Even if the actual state hasn't changed, let's notify a user. * The state can be enforced by an ancestor cgroup: the cgroup * can already be in the desired state or it can be locked in the * opposite state, so that the transition will never happen. * In both cases it's better to notify a user, that there is * nothing to wait for. */ if (!applied) { TRACE_CGROUP_PATH(notify_frozen, cgrp, test_bit(CGRP_FROZEN, &cgrp->flags)); cgroup_file_notify(&cgrp->events_file); } } |
| 51 51 51 51 2877 6 2871 2698 2698 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * devtmpfs - kernel-maintained tmpfs-based /dev * * Copyright (C) 2009, Kay Sievers <kay.sievers@vrfy.org> * * During bootup, before any driver core device is registered, * devtmpfs, a tmpfs-based filesystem is created. Every driver-core * device which requests a device node, will add a node in this * filesystem. * By default, all devices are named after the name of the device, * owned by root and have a default mode of 0600. Subsystems can * overwrite the default setting if needed. */ #define pr_fmt(fmt) "devtmpfs: " fmt #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/device.h> #include <linux/blkdev.h> #include <linux/namei.h> #include <linux/fs.h> #include <linux/shmem_fs.h> #include <linux/ramfs.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/kthread.h> #include <linux/init_syscalls.h> #include <uapi/linux/mount.h> #include "base.h" #ifdef CONFIG_DEVTMPFS_SAFE #define DEVTMPFS_MFLAGS (MS_SILENT | MS_NOEXEC | MS_NOSUID) #else #define DEVTMPFS_MFLAGS (MS_SILENT) #endif static struct task_struct *thread; static int __initdata mount_dev = IS_ENABLED(CONFIG_DEVTMPFS_MOUNT); static DEFINE_SPINLOCK(req_lock); static struct req { struct req *next; struct completion done; int err; const char *name; umode_t mode; /* 0 => delete */ kuid_t uid; kgid_t gid; struct device *dev; } *requests; static int __init mount_param(char *str) { return kstrtoint(str, 0, &mount_dev) == 0; } __setup("devtmpfs.mount=", mount_param); static struct vfsmount *mnt; static struct file_system_type internal_fs_type = { .name = "devtmpfs", #ifdef CONFIG_TMPFS .init_fs_context = shmem_init_fs_context, #else .init_fs_context = ramfs_init_fs_context, #endif .kill_sb = kill_anon_super, }; /* Simply take a ref on the existing mount */ static int devtmpfs_get_tree(struct fs_context *fc) { struct super_block *sb = mnt->mnt_sb; atomic_inc(&sb->s_active); down_write(&sb->s_umount); fc->root = dget(sb->s_root); return 0; } /* Ops are filled in during init depending on underlying shmem or ramfs type */ static struct fs_context_operations devtmpfs_context_ops = {}; /* Call the underlying initialization and set to our ops */ static int devtmpfs_init_fs_context(struct fs_context *fc) { int ret; #ifdef CONFIG_TMPFS ret = shmem_init_fs_context(fc); #else ret = ramfs_init_fs_context(fc); #endif if (ret < 0) return ret; fc->ops = &devtmpfs_context_ops; return 0; } static struct file_system_type dev_fs_type = { .name = "devtmpfs", .init_fs_context = devtmpfs_init_fs_context, }; static int devtmpfs_submit_req(struct req *req, const char *tmp) { init_completion(&req->done); spin_lock(&req_lock); req->next = requests; requests = req; spin_unlock(&req_lock); wake_up_process(thread); wait_for_completion(&req->done); kfree(tmp); return req->err; } int devtmpfs_create_node(struct device *dev) { const char *tmp = NULL; struct req req; if (!thread) return 0; req.mode = 0; req.uid = GLOBAL_ROOT_UID; req.gid = GLOBAL_ROOT_GID; req.name = device_get_devnode(dev, &req.mode, &req.uid, &req.gid, &tmp); if (!req.name) return -ENOMEM; if (req.mode == 0) req.mode = 0600; if (is_blockdev(dev)) req.mode |= S_IFBLK; else req.mode |= S_IFCHR; req.dev = dev; return devtmpfs_submit_req(&req, tmp); } int devtmpfs_delete_node(struct device *dev) { const char *tmp = NULL; struct req req; if (!thread) return 0; req.name = device_get_devnode(dev, NULL, NULL, NULL, &tmp); if (!req.name) return -ENOMEM; req.mode = 0; req.dev = dev; return devtmpfs_submit_req(&req, tmp); } static int dev_mkdir(const char *name, umode_t mode) { struct dentry *dentry; struct path path; dentry = start_creating_path(AT_FDCWD, name, &path, LOOKUP_DIRECTORY); if (IS_ERR(dentry)) return PTR_ERR(dentry); dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode, NULL); if (!IS_ERR(dentry)) /* mark as kernel-created inode */ d_inode(dentry)->i_private = &thread; end_creating_path(&path, dentry); return PTR_ERR_OR_ZERO(dentry); } static int create_path(const char *nodepath) { char *path; char *s; int err = 0; /* parent directories do not exist, create them */ path = kstrdup(nodepath, GFP_KERNEL); if (!path) return -ENOMEM; s = path; for (;;) { s = strchr(s, '/'); if (!s) break; s[0] = '\0'; err = dev_mkdir(path, 0755); if (err && err != -EEXIST) break; s[0] = '/'; s++; } kfree(path); return err; } static int handle_create(const char *nodename, umode_t mode, kuid_t uid, kgid_t gid, struct device *dev) { struct dentry *dentry; struct path path; int err; dentry = start_creating_path(AT_FDCWD, nodename, &path, 0); if (dentry == ERR_PTR(-ENOENT)) { create_path(nodename); dentry = start_creating_path(AT_FDCWD, nodename, &path, 0); } if (IS_ERR(dentry)) return PTR_ERR(dentry); err = vfs_mknod(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode, dev->devt, NULL); if (!err) { struct iattr newattrs; newattrs.ia_mode = mode; newattrs.ia_uid = uid; newattrs.ia_gid = gid; newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID; inode_lock(d_inode(dentry)); notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); /* mark as kernel-created inode */ d_inode(dentry)->i_private = &thread; } end_creating_path(&path, dentry); return err; } static int dev_rmdir(const char *name) { struct path parent; struct dentry *dentry; int err; dentry = start_removing_path(name, &parent); if (IS_ERR(dentry)) return PTR_ERR(dentry); if (d_inode(dentry)->i_private == &thread) err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry), dentry, NULL); else err = -EPERM; end_removing_path(&parent, dentry); return err; } static int delete_path(const char *nodepath) { char *path; int err = 0; path = kstrdup(nodepath, GFP_KERNEL); if (!path) return -ENOMEM; for (;;) { char *base; base = strrchr(path, '/'); if (!base) break; base[0] = '\0'; err = dev_rmdir(path); if (err) break; } kfree(path); return err; } static int dev_mynode(struct device *dev, struct inode *inode) { /* did we create it */ if (inode->i_private != &thread) return 0; /* does the dev_t match */ if (is_blockdev(dev)) { if (!S_ISBLK(inode->i_mode)) return 0; } else { if (!S_ISCHR(inode->i_mode)) return 0; } if (inode->i_rdev != dev->devt) return 0; /* ours */ return 1; } static int handle_remove(const char *nodename, struct device *dev) { struct path parent; struct dentry *dentry; struct inode *inode; int deleted = 0; int err = 0; dentry = start_removing_path(nodename, &parent); if (IS_ERR(dentry)) return PTR_ERR(dentry); inode = d_inode(dentry); if (dev_mynode(dev, inode)) { struct iattr newattrs; /* * before unlinking this node, reset permissions * of possible references like hardlinks */ newattrs.ia_uid = GLOBAL_ROOT_UID; newattrs.ia_gid = GLOBAL_ROOT_GID; newattrs.ia_mode = inode->i_mode & ~0777; newattrs.ia_valid = ATTR_UID|ATTR_GID|ATTR_MODE; inode_lock(d_inode(dentry)); notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL); inode_unlock(d_inode(dentry)); err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry), dentry, NULL); if (!err || err == -ENOENT) deleted = 1; } end_removing_path(&parent, dentry); if (deleted && strchr(nodename, '/')) delete_path(nodename); return err; } /* * If configured, or requested by the commandline, devtmpfs will be * auto-mounted after the kernel mounted the root filesystem. */ int __init devtmpfs_mount(void) { int err; if (!mount_dev) return 0; if (!thread) return 0; err = init_mount("devtmpfs", "dev", "devtmpfs", DEVTMPFS_MFLAGS, NULL); if (err) pr_info("error mounting %d\n", err); else pr_info("mounted\n"); return err; } static __initdata DECLARE_COMPLETION(setup_done); static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid, struct device *dev) { if (mode) return handle_create(name, mode, uid, gid, dev); else return handle_remove(name, dev); } static void __noreturn devtmpfs_work_loop(void) { while (1) { spin_lock(&req_lock); while (requests) { struct req *req = requests; requests = NULL; spin_unlock(&req_lock); while (req) { struct req *next = req->next; req->err = handle(req->name, req->mode, req->uid, req->gid, req->dev); complete(&req->done); req = next; } spin_lock(&req_lock); } __set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&req_lock); schedule(); } } static noinline int __init devtmpfs_setup(void *p) { int err; err = ksys_unshare(UNSHARE_EMPTY_MNTNS); if (err) goto out; err = init_mount("devtmpfs", "/", "devtmpfs", DEVTMPFS_MFLAGS, NULL); if (err) goto out; init_chdir("/.."); /* will traverse into overmounted root */ init_chroot("."); out: *(int *)p = err; return err; } /* * The __ref is because devtmpfs_setup needs to be __init for the routines it * calls. That call is done while devtmpfs_init, which is marked __init, * synchronously waits for it to complete. */ static int __ref devtmpfsd(void *p) { int err = devtmpfs_setup(p); complete(&setup_done); if (err) return err; devtmpfs_work_loop(); return 0; } /* * Get the underlying (shmem/ramfs) context ops to build ours */ static int devtmpfs_configure_context(void) { struct fs_context *fc; fc = fs_context_for_reconfigure(mnt->mnt_root, mnt->mnt_sb->s_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* Set up devtmpfs_context_ops based on underlying type */ devtmpfs_context_ops.free = fc->ops->free; devtmpfs_context_ops.dup = fc->ops->dup; devtmpfs_context_ops.parse_param = fc->ops->parse_param; devtmpfs_context_ops.parse_monolithic = fc->ops->parse_monolithic; devtmpfs_context_ops.get_tree = &devtmpfs_get_tree; devtmpfs_context_ops.reconfigure = fc->ops->reconfigure; put_fs_context(fc); return 0; } /* * Create devtmpfs instance, driver-core devices will add their device * nodes here. */ int __init devtmpfs_init(void) { char opts[] = "mode=0755"; int err; mnt = vfs_kern_mount(&internal_fs_type, 0, "devtmpfs", opts); if (IS_ERR(mnt)) { pr_err("unable to create devtmpfs %ld\n", PTR_ERR(mnt)); return PTR_ERR(mnt); } err = devtmpfs_configure_context(); if (err) { pr_err("unable to configure devtmpfs type %d\n", err); return err; } err = register_filesystem(&dev_fs_type); if (err) { pr_err("unable to register devtmpfs type %d\n", err); return err; } thread = kthread_run(devtmpfsd, &err, "kdevtmpfs"); if (!IS_ERR(thread)) { wait_for_completion(&setup_done); } else { err = PTR_ERR(thread); thread = NULL; } if (err) { pr_err("unable to create devtmpfs %d\n", err); unregister_filesystem(&dev_fs_type); thread = NULL; return err; } pr_info("initialized\n"); return 0; } |
| 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 11 26 26 26 26 26 26 26 9 26 10 26 9 26 26 26 26 8 26 26 26 26 26 26 26 26 26 26 26 26 3 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 1 1 26 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 | // 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. */ /*-************************************* * Dependencies ***************************************/ #include "../common/allocations.h" /* ZSTD_customMalloc, ZSTD_customCalloc, ZSTD_customFree */ #include "../common/zstd_deps.h" /* INT_MAX, ZSTD_memset, ZSTD_memcpy */ #include "../common/mem.h" #include "../common/error_private.h" #include "hist.h" /* HIST_countFast_wksp */ #define FSE_STATIC_LINKING_ONLY /* FSE_encodeSymbol */ #include "../common/fse.h" #include "../common/huf.h" #include "zstd_compress_internal.h" #include "zstd_compress_sequences.h" #include "zstd_compress_literals.h" #include "zstd_fast.h" #include "zstd_double_fast.h" #include "zstd_lazy.h" #include "zstd_opt.h" #include "zstd_ldm.h" #include "zstd_compress_superblock.h" #include "../common/bits.h" /* ZSTD_highbit32, ZSTD_rotateRight_U64 */ /* *************************************************************** * Tuning parameters *****************************************************************/ /*! * COMPRESS_HEAPMODE : * Select how default decompression function ZSTD_compress() allocates its context, * on stack (0, default), or into heap (1). * Note that functions with explicit context such as ZSTD_compressCCtx() are unaffected. */ /*! * ZSTD_HASHLOG3_MAX : * Maximum size of the hash table dedicated to find 3-bytes matches, * in log format, aka 17 => 1 << 17 == 128Ki positions. * This structure is only used in zstd_opt. * Since allocation is centralized for all strategies, it has to be known here. * The actual (selected) size of the hash table is then stored in ZSTD_MatchState_t.hashLog3, * so that zstd_opt.c doesn't need to know about this constant. */ #ifndef ZSTD_HASHLOG3_MAX # define ZSTD_HASHLOG3_MAX 17 #endif /*-************************************* * Helper functions ***************************************/ /* ZSTD_compressBound() * Note that the result from this function is only valid for * the one-pass compression functions. * When employing the streaming mode, * if flushes are frequently altering the size of blocks, * the overhead from block headers can make the compressed data larger * than the return value of ZSTD_compressBound(). */ size_t ZSTD_compressBound(size_t srcSize) { size_t const r = ZSTD_COMPRESSBOUND(srcSize); if (r==0) return ERROR(srcSize_wrong); return r; } /*-************************************* * Context memory management ***************************************/ struct ZSTD_CDict_s { const void* dictContent; size_t dictContentSize; ZSTD_dictContentType_e dictContentType; /* The dictContentType the CDict was created with */ U32* entropyWorkspace; /* entropy workspace of HUF_WORKSPACE_SIZE bytes */ ZSTD_cwksp workspace; ZSTD_MatchState_t matchState; ZSTD_compressedBlockState_t cBlockState; ZSTD_customMem customMem; U32 dictID; int compressionLevel; /* 0 indicates that advanced API was used to select CDict params */ ZSTD_ParamSwitch_e useRowMatchFinder; /* Indicates whether the CDict was created with params that would use * row-based matchfinder. Unless the cdict is reloaded, we will use * the same greedy/lazy matchfinder at compression time. */ }; /* typedef'd to ZSTD_CDict within "zstd.h" */ ZSTD_CCtx* ZSTD_createCCtx(void) { return ZSTD_createCCtx_advanced(ZSTD_defaultCMem); } static void ZSTD_initCCtx(ZSTD_CCtx* cctx, ZSTD_customMem memManager) { assert(cctx != NULL); ZSTD_memset(cctx, 0, sizeof(*cctx)); cctx->customMem = memManager; cctx->bmi2 = ZSTD_cpuSupportsBmi2(); { size_t const err = ZSTD_CCtx_reset(cctx, ZSTD_reset_parameters); assert(!ZSTD_isError(err)); (void)err; } } ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem) { ZSTD_STATIC_ASSERT(zcss_init==0); ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1)); if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; { ZSTD_CCtx* const cctx = (ZSTD_CCtx*)ZSTD_customMalloc(sizeof(ZSTD_CCtx), customMem); if (!cctx) return NULL; ZSTD_initCCtx(cctx, customMem); return cctx; } } ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize) { ZSTD_cwksp ws; ZSTD_CCtx* cctx; if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL; /* minimum size */ if ((size_t)workspace & 7) return NULL; /* must be 8-aligned */ ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_static_alloc); cctx = (ZSTD_CCtx*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CCtx)); if (cctx == NULL) return NULL; ZSTD_memset(cctx, 0, sizeof(ZSTD_CCtx)); ZSTD_cwksp_move(&cctx->workspace, &ws); cctx->staticSize = workspaceSize; /* statically sized space. tmpWorkspace never moves (but prev/next block swap places) */ if (!ZSTD_cwksp_check_available(&cctx->workspace, TMP_WORKSPACE_SIZE + 2 * sizeof(ZSTD_compressedBlockState_t))) return NULL; cctx->blockState.prevCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t)); cctx->blockState.nextCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t)); cctx->tmpWorkspace = ZSTD_cwksp_reserve_object(&cctx->workspace, TMP_WORKSPACE_SIZE); cctx->tmpWkspSize = TMP_WORKSPACE_SIZE; cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid()); return cctx; } /* * Clears and frees all of the dictionaries in the CCtx. */ static void ZSTD_clearAllDicts(ZSTD_CCtx* cctx) { ZSTD_customFree(cctx->localDict.dictBuffer, cctx->customMem); ZSTD_freeCDict(cctx->localDict.cdict); ZSTD_memset(&cctx->localDict, 0, sizeof(cctx->localDict)); ZSTD_memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict)); cctx->cdict = NULL; } static size_t ZSTD_sizeof_localDict(ZSTD_localDict dict) { size_t const bufferSize = dict.dictBuffer != NULL ? dict.dictSize : 0; size_t const cdictSize = ZSTD_sizeof_CDict(dict.cdict); return bufferSize + cdictSize; } static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx) { assert(cctx != NULL); assert(cctx->staticSize == 0); ZSTD_clearAllDicts(cctx); ZSTD_cwksp_free(&cctx->workspace, cctx->customMem); } size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx) { DEBUGLOG(3, "ZSTD_freeCCtx (address: %p)", (void*)cctx); if (cctx==NULL) return 0; /* support free on NULL */ RETURN_ERROR_IF(cctx->staticSize, memory_allocation, "not compatible with static CCtx"); { int cctxInWorkspace = ZSTD_cwksp_owns_buffer(&cctx->workspace, cctx); ZSTD_freeCCtxContent(cctx); if (!cctxInWorkspace) ZSTD_customFree(cctx, cctx->customMem); } return 0; } static size_t ZSTD_sizeof_mtctx(const ZSTD_CCtx* cctx) { (void)cctx; return 0; } size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx) { if (cctx==NULL) return 0; /* support sizeof on NULL */ /* cctx may be in the workspace */ return (cctx->workspace.workspace == cctx ? 0 : sizeof(*cctx)) + ZSTD_cwksp_sizeof(&cctx->workspace) + ZSTD_sizeof_localDict(cctx->localDict) + ZSTD_sizeof_mtctx(cctx); } size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs) { return ZSTD_sizeof_CCtx(zcs); /* same object */ } /* private API call, for dictBuilder only */ const SeqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); } /* Returns true if the strategy supports using a row based matchfinder */ static int ZSTD_rowMatchFinderSupported(const ZSTD_strategy strategy) { return (strategy >= ZSTD_greedy && strategy <= ZSTD_lazy2); } /* Returns true if the strategy and useRowMatchFinder mode indicate that we will use the row based matchfinder * for this compression. */ static int ZSTD_rowMatchFinderUsed(const ZSTD_strategy strategy, const ZSTD_ParamSwitch_e mode) { assert(mode != ZSTD_ps_auto); return ZSTD_rowMatchFinderSupported(strategy) && (mode == ZSTD_ps_enable); } /* Returns row matchfinder usage given an initial mode and cParams */ static ZSTD_ParamSwitch_e ZSTD_resolveRowMatchFinderMode(ZSTD_ParamSwitch_e mode, const ZSTD_compressionParameters* const cParams) { /* The Linux Kernel does not use SIMD, and 128KB is a very common size, e.g. in BtrFS. * The row match finder is slower for this size without SIMD, so disable it. */ const unsigned kWindowLogLowerBound = 17; if (mode != ZSTD_ps_auto) return mode; /* if requested enabled, but no SIMD, we still will use row matchfinder */ mode = ZSTD_ps_disable; if (!ZSTD_rowMatchFinderSupported(cParams->strategy)) return mode; if (cParams->windowLog > kWindowLogLowerBound) mode = ZSTD_ps_enable; return mode; } /* Returns block splitter usage (generally speaking, when using slower/stronger compression modes) */ static ZSTD_ParamSwitch_e ZSTD_resolveBlockSplitterMode(ZSTD_ParamSwitch_e mode, const ZSTD_compressionParameters* const cParams) { if (mode != ZSTD_ps_auto) return mode; return (cParams->strategy >= ZSTD_btopt && cParams->windowLog >= 17) ? ZSTD_ps_enable : ZSTD_ps_disable; } /* Returns 1 if the arguments indicate that we should allocate a chainTable, 0 otherwise */ static int ZSTD_allocateChainTable(const ZSTD_strategy strategy, const ZSTD_ParamSwitch_e useRowMatchFinder, const U32 forDDSDict) { assert(useRowMatchFinder != ZSTD_ps_auto); /* We always should allocate a chaintable if we are allocating a matchstate for a DDS dictionary matchstate. * We do not allocate a chaintable if we are using ZSTD_fast, or are using the row-based matchfinder. */ return forDDSDict || ((strategy != ZSTD_fast) && !ZSTD_rowMatchFinderUsed(strategy, useRowMatchFinder)); } /* Returns ZSTD_ps_enable if compression parameters are such that we should * enable long distance matching (wlog >= 27, strategy >= btopt). * Returns ZSTD_ps_disable otherwise. */ static ZSTD_ParamSwitch_e ZSTD_resolveEnableLdm(ZSTD_ParamSwitch_e mode, const ZSTD_compressionParameters* const cParams) { if (mode != ZSTD_ps_auto) return mode; return (cParams->strategy >= ZSTD_btopt && cParams->windowLog >= 27) ? ZSTD_ps_enable : ZSTD_ps_disable; } static int ZSTD_resolveExternalSequenceValidation(int mode) { return mode; } /* Resolves maxBlockSize to the default if no value is present. */ static size_t ZSTD_resolveMaxBlockSize(size_t maxBlockSize) { if (maxBlockSize == 0) { return ZSTD_BLOCKSIZE_MAX; } else { return maxBlockSize; } } static ZSTD_ParamSwitch_e ZSTD_resolveExternalRepcodeSearch(ZSTD_ParamSwitch_e value, int cLevel) { if (value != ZSTD_ps_auto) return value; if (cLevel < 10) { return ZSTD_ps_disable; } else { return ZSTD_ps_enable; } } /* Returns 1 if compression parameters are such that CDict hashtable and chaintable indices are tagged. * If so, the tags need to be removed in ZSTD_resetCCtx_byCopyingCDict. */ static int ZSTD_CDictIndicesAreTagged(const ZSTD_compressionParameters* const cParams) { return cParams->strategy == ZSTD_fast || cParams->strategy == ZSTD_dfast; } static ZSTD_CCtx_params ZSTD_makeCCtxParamsFromCParams( ZSTD_compressionParameters cParams) { ZSTD_CCtx_params cctxParams; /* should not matter, as all cParams are presumed properly defined */ ZSTD_CCtxParams_init(&cctxParams, ZSTD_CLEVEL_DEFAULT); cctxParams.cParams = cParams; /* Adjust advanced params according to cParams */ cctxParams.ldmParams.enableLdm = ZSTD_resolveEnableLdm(cctxParams.ldmParams.enableLdm, &cParams); if (cctxParams.ldmParams.enableLdm == ZSTD_ps_enable) { ZSTD_ldm_adjustParameters(&cctxParams.ldmParams, &cParams); assert(cctxParams.ldmParams.hashLog >= cctxParams.ldmParams.bucketSizeLog); assert(cctxParams.ldmParams.hashRateLog < 32); } cctxParams.postBlockSplitter = ZSTD_resolveBlockSplitterMode(cctxParams.postBlockSplitter, &cParams); cctxParams.useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(cctxParams.useRowMatchFinder, &cParams); cctxParams.validateSequences = ZSTD_resolveExternalSequenceValidation(cctxParams.validateSequences); cctxParams.maxBlockSize = ZSTD_resolveMaxBlockSize(cctxParams.maxBlockSize); cctxParams.searchForExternalRepcodes = ZSTD_resolveExternalRepcodeSearch(cctxParams.searchForExternalRepcodes, cctxParams.compressionLevel); assert(!ZSTD_checkCParams(cParams)); return cctxParams; } static ZSTD_CCtx_params* ZSTD_createCCtxParams_advanced( ZSTD_customMem customMem) { ZSTD_CCtx_params* params; if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; params = (ZSTD_CCtx_params*)ZSTD_customCalloc( sizeof(ZSTD_CCtx_params), customMem); if (!params) { return NULL; } ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); params->customMem = customMem; return params; } ZSTD_CCtx_params* ZSTD_createCCtxParams(void) { return ZSTD_createCCtxParams_advanced(ZSTD_defaultCMem); } size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params) { if (params == NULL) { return 0; } ZSTD_customFree(params, params->customMem); return 0; } size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params) { return ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); } size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) { RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!"); ZSTD_memset(cctxParams, 0, sizeof(*cctxParams)); cctxParams->compressionLevel = compressionLevel; cctxParams->fParams.contentSizeFlag = 1; return 0; } #define ZSTD_NO_CLEVEL 0 /* * Initializes `cctxParams` from `params` and `compressionLevel`. * @param compressionLevel If params are derived from a compression level then that compression level, otherwise ZSTD_NO_CLEVEL. */ static void ZSTD_CCtxParams_init_internal(ZSTD_CCtx_params* cctxParams, const ZSTD_parameters* params, int compressionLevel) { assert(!ZSTD_checkCParams(params->cParams)); ZSTD_memset(cctxParams, 0, sizeof(*cctxParams)); cctxParams->cParams = params->cParams; cctxParams->fParams = params->fParams; /* Should not matter, as all cParams are presumed properly defined. * But, set it for tracing anyway. */ cctxParams->compressionLevel = compressionLevel; cctxParams->useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(cctxParams->useRowMatchFinder, ¶ms->cParams); cctxParams->postBlockSplitter = ZSTD_resolveBlockSplitterMode(cctxParams->postBlockSplitter, ¶ms->cParams); cctxParams->ldmParams.enableLdm = ZSTD_resolveEnableLdm(cctxParams->ldmParams.enableLdm, ¶ms->cParams); cctxParams->validateSequences = ZSTD_resolveExternalSequenceValidation(cctxParams->validateSequences); cctxParams->maxBlockSize = ZSTD_resolveMaxBlockSize(cctxParams->maxBlockSize); cctxParams->searchForExternalRepcodes = ZSTD_resolveExternalRepcodeSearch(cctxParams->searchForExternalRepcodes, compressionLevel); DEBUGLOG(4, "ZSTD_CCtxParams_init_internal: useRowMatchFinder=%d, useBlockSplitter=%d ldm=%d", cctxParams->useRowMatchFinder, cctxParams->postBlockSplitter, cctxParams->ldmParams.enableLdm); } size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params) { RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!"); FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) , ""); ZSTD_CCtxParams_init_internal(cctxParams, ¶ms, ZSTD_NO_CLEVEL); return 0; } /* * Sets cctxParams' cParams and fParams from params, but otherwise leaves them alone. * @param params Validated zstd parameters. */ static void ZSTD_CCtxParams_setZstdParams( ZSTD_CCtx_params* cctxParams, const ZSTD_parameters* params) { assert(!ZSTD_checkCParams(params->cParams)); cctxParams->cParams = params->cParams; cctxParams->fParams = params->fParams; /* Should not matter, as all cParams are presumed properly defined. * But, set it for tracing anyway. */ cctxParams->compressionLevel = ZSTD_NO_CLEVEL; } ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param) { ZSTD_bounds bounds = { 0, 0, 0 }; switch(param) { case ZSTD_c_compressionLevel: bounds.lowerBound = ZSTD_minCLevel(); bounds.upperBound = ZSTD_maxCLevel(); return bounds; case ZSTD_c_windowLog: bounds.lowerBound = ZSTD_WINDOWLOG_MIN; bounds.upperBound = ZSTD_WINDOWLOG_MAX; return bounds; case ZSTD_c_hashLog: bounds.lowerBound = ZSTD_HASHLOG_MIN; bounds.upperBound = ZSTD_HASHLOG_MAX; return bounds; case ZSTD_c_chainLog: bounds.lowerBound = ZSTD_CHAINLOG_MIN; bounds.upperBound = ZSTD_CHAINLOG_MAX; return bounds; case ZSTD_c_searchLog: bounds.lowerBound = ZSTD_SEARCHLOG_MIN; bounds.upperBound = ZSTD_SEARCHLOG_MAX; return bounds; case ZSTD_c_minMatch: bounds.lowerBound = ZSTD_MINMATCH_MIN; bounds.upperBound = ZSTD_MINMATCH_MAX; return bounds; case ZSTD_c_targetLength: bounds.lowerBound = ZSTD_TARGETLENGTH_MIN; bounds.upperBound = ZSTD_TARGETLENGTH_MAX; return bounds; case ZSTD_c_strategy: bounds.lowerBound = ZSTD_STRATEGY_MIN; bounds.upperBound = ZSTD_STRATEGY_MAX; return bounds; case ZSTD_c_contentSizeFlag: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_checksumFlag: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_dictIDFlag: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_nbWorkers: bounds.lowerBound = 0; bounds.upperBound = 0; return bounds; case ZSTD_c_jobSize: bounds.lowerBound = 0; bounds.upperBound = 0; return bounds; case ZSTD_c_overlapLog: bounds.lowerBound = 0; bounds.upperBound = 0; return bounds; case ZSTD_c_enableDedicatedDictSearch: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_enableLongDistanceMatching: bounds.lowerBound = (int)ZSTD_ps_auto; bounds.upperBound = (int)ZSTD_ps_disable; return bounds; case ZSTD_c_ldmHashLog: bounds.lowerBound = ZSTD_LDM_HASHLOG_MIN; bounds.upperBound = ZSTD_LDM_HASHLOG_MAX; return bounds; case ZSTD_c_ldmMinMatch: bounds.lowerBound = ZSTD_LDM_MINMATCH_MIN; bounds.upperBound = ZSTD_LDM_MINMATCH_MAX; return bounds; case ZSTD_c_ldmBucketSizeLog: bounds.lowerBound = ZSTD_LDM_BUCKETSIZELOG_MIN; bounds.upperBound = ZSTD_LDM_BUCKETSIZELOG_MAX; return bounds; case ZSTD_c_ldmHashRateLog: bounds.lowerBound = ZSTD_LDM_HASHRATELOG_MIN; bounds.upperBound = ZSTD_LDM_HASHRATELOG_MAX; return bounds; /* experimental parameters */ case ZSTD_c_rsyncable: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_forceMaxWindow : bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_format: ZSTD_STATIC_ASSERT(ZSTD_f_zstd1 < ZSTD_f_zstd1_magicless); bounds.lowerBound = ZSTD_f_zstd1; bounds.upperBound = ZSTD_f_zstd1_magicless; /* note : how to ensure at compile time that this is the highest value enum ? */ return bounds; case ZSTD_c_forceAttachDict: ZSTD_STATIC_ASSERT(ZSTD_dictDefaultAttach < ZSTD_dictForceLoad); bounds.lowerBound = ZSTD_dictDefaultAttach; bounds.upperBound = ZSTD_dictForceLoad; /* note : how to ensure at compile time that this is the highest value enum ? */ return bounds; case ZSTD_c_literalCompressionMode: ZSTD_STATIC_ASSERT(ZSTD_ps_auto < ZSTD_ps_enable && ZSTD_ps_enable < ZSTD_ps_disable); bounds.lowerBound = (int)ZSTD_ps_auto; bounds.upperBound = (int)ZSTD_ps_disable; return bounds; case ZSTD_c_targetCBlockSize: bounds.lowerBound = ZSTD_TARGETCBLOCKSIZE_MIN; bounds.upperBound = ZSTD_TARGETCBLOCKSIZE_MAX; return bounds; case ZSTD_c_srcSizeHint: bounds.lowerBound = ZSTD_SRCSIZEHINT_MIN; bounds.upperBound = ZSTD_SRCSIZEHINT_MAX; return bounds; case ZSTD_c_stableInBuffer: case ZSTD_c_stableOutBuffer: bounds.lowerBound = (int)ZSTD_bm_buffered; bounds.upperBound = (int)ZSTD_bm_stable; return bounds; case ZSTD_c_blockDelimiters: bounds.lowerBound = (int)ZSTD_sf_noBlockDelimiters; bounds.upperBound = (int)ZSTD_sf_explicitBlockDelimiters; return bounds; case ZSTD_c_validateSequences: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_splitAfterSequences: bounds.lowerBound = (int)ZSTD_ps_auto; bounds.upperBound = (int)ZSTD_ps_disable; return bounds; case ZSTD_c_blockSplitterLevel: bounds.lowerBound = 0; bounds.upperBound = ZSTD_BLOCKSPLITTER_LEVEL_MAX; return bounds; case ZSTD_c_useRowMatchFinder: bounds.lowerBound = (int)ZSTD_ps_auto; bounds.upperBound = (int)ZSTD_ps_disable; return bounds; case ZSTD_c_deterministicRefPrefix: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_prefetchCDictTables: bounds.lowerBound = (int)ZSTD_ps_auto; bounds.upperBound = (int)ZSTD_ps_disable; return bounds; case ZSTD_c_enableSeqProducerFallback: bounds.lowerBound = 0; bounds.upperBound = 1; return bounds; case ZSTD_c_maxBlockSize: bounds.lowerBound = ZSTD_BLOCKSIZE_MAX_MIN; bounds.upperBound = ZSTD_BLOCKSIZE_MAX; return bounds; case ZSTD_c_repcodeResolution: bounds.lowerBound = (int)ZSTD_ps_auto; bounds.upperBound = (int)ZSTD_ps_disable; return bounds; default: bounds.error = ERROR(parameter_unsupported); return bounds; } } /* ZSTD_cParam_clampBounds: * Clamps the value into the bounded range. */ static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value) { ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); if (ZSTD_isError(bounds.error)) return bounds.error; if (*value < bounds.lowerBound) *value = bounds.lowerBound; if (*value > bounds.upperBound) *value = bounds.upperBound; return 0; } #define BOUNDCHECK(cParam, val) \ do { \ RETURN_ERROR_IF(!ZSTD_cParam_withinBounds(cParam,val), \ parameter_outOfBound, "Param out of bounds"); \ } while (0) static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) { switch(param) { case ZSTD_c_compressionLevel: case ZSTD_c_hashLog: case ZSTD_c_chainLog: case ZSTD_c_searchLog: case ZSTD_c_minMatch: case ZSTD_c_targetLength: case ZSTD_c_strategy: case ZSTD_c_blockSplitterLevel: return 1; case ZSTD_c_format: case ZSTD_c_windowLog: case ZSTD_c_contentSizeFlag: case ZSTD_c_checksumFlag: case ZSTD_c_dictIDFlag: case ZSTD_c_forceMaxWindow : case ZSTD_c_nbWorkers: case ZSTD_c_jobSize: case ZSTD_c_overlapLog: case ZSTD_c_rsyncable: case ZSTD_c_enableDedicatedDictSearch: case ZSTD_c_enableLongDistanceMatching: case ZSTD_c_ldmHashLog: case ZSTD_c_ldmMinMatch: case ZSTD_c_ldmBucketSizeLog: case ZSTD_c_ldmHashRateLog: case ZSTD_c_forceAttachDict: case ZSTD_c_literalCompressionMode: case ZSTD_c_targetCBlockSize: case ZSTD_c_srcSizeHint: case ZSTD_c_stableInBuffer: case ZSTD_c_stableOutBuffer: case ZSTD_c_blockDelimiters: case ZSTD_c_validateSequences: case ZSTD_c_splitAfterSequences: case ZSTD_c_useRowMatchFinder: case ZSTD_c_deterministicRefPrefix: case ZSTD_c_prefetchCDictTables: case ZSTD_c_enableSeqProducerFallback: case ZSTD_c_maxBlockSize: case ZSTD_c_repcodeResolution: default: return 0; } } size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value) { DEBUGLOG(4, "ZSTD_CCtx_setParameter (%i, %i)", (int)param, value); if (cctx->streamStage != zcss_init) { if (ZSTD_isUpdateAuthorized(param)) { cctx->cParamsChanged = 1; } else { RETURN_ERROR(stage_wrong, "can only set params in cctx init stage"); } } switch(param) { case ZSTD_c_nbWorkers: RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported, "MT not compatible with static alloc"); break; case ZSTD_c_compressionLevel: case ZSTD_c_windowLog: case ZSTD_c_hashLog: case ZSTD_c_chainLog: case ZSTD_c_searchLog: case ZSTD_c_minMatch: case ZSTD_c_targetLength: case ZSTD_c_strategy: case ZSTD_c_ldmHashRateLog: case ZSTD_c_format: case ZSTD_c_contentSizeFlag: case ZSTD_c_checksumFlag: case ZSTD_c_dictIDFlag: case ZSTD_c_forceMaxWindow: case ZSTD_c_forceAttachDict: case ZSTD_c_literalCompressionMode: case ZSTD_c_jobSize: case ZSTD_c_overlapLog: case ZSTD_c_rsyncable: case ZSTD_c_enableDedicatedDictSearch: case ZSTD_c_enableLongDistanceMatching: case ZSTD_c_ldmHashLog: case ZSTD_c_ldmMinMatch: case ZSTD_c_ldmBucketSizeLog: case ZSTD_c_targetCBlockSize: case ZSTD_c_srcSizeHint: case ZSTD_c_stableInBuffer: case ZSTD_c_stableOutBuffer: case ZSTD_c_blockDelimiters: case ZSTD_c_validateSequences: case ZSTD_c_splitAfterSequences: case ZSTD_c_blockSplitterLevel: case ZSTD_c_useRowMatchFinder: case ZSTD_c_deterministicRefPrefix: case ZSTD_c_prefetchCDictTables: case ZSTD_c_enableSeqProducerFallback: case ZSTD_c_maxBlockSize: case ZSTD_c_repcodeResolution: break; default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); } return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value); } size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, ZSTD_cParameter param, int value) { DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value); switch(param) { case ZSTD_c_format : BOUNDCHECK(ZSTD_c_format, value); CCtxParams->format = (ZSTD_format_e)value; return (size_t)CCtxParams->format; case ZSTD_c_compressionLevel : { FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value), ""); if (value == 0) CCtxParams->compressionLevel = ZSTD_CLEVEL_DEFAULT; /* 0 == default */ else CCtxParams->compressionLevel = value; if (CCtxParams->compressionLevel >= 0) return (size_t)CCtxParams->compressionLevel; return 0; /* return type (size_t) cannot represent negative values */ } case ZSTD_c_windowLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_windowLog, value); CCtxParams->cParams.windowLog = (U32)value; return CCtxParams->cParams.windowLog; case ZSTD_c_hashLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_hashLog, value); CCtxParams->cParams.hashLog = (U32)value; return CCtxParams->cParams.hashLog; case ZSTD_c_chainLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_chainLog, value); CCtxParams->cParams.chainLog = (U32)value; return CCtxParams->cParams.chainLog; case ZSTD_c_searchLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_searchLog, value); CCtxParams->cParams.searchLog = (U32)value; return (size_t)value; case ZSTD_c_minMatch : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_minMatch, value); CCtxParams->cParams.minMatch = (U32)value; return CCtxParams->cParams.minMatch; case ZSTD_c_targetLength : BOUNDCHECK(ZSTD_c_targetLength, value); CCtxParams->cParams.targetLength = (U32)value; return CCtxParams->cParams.targetLength; case ZSTD_c_strategy : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_strategy, value); CCtxParams->cParams.strategy = (ZSTD_strategy)value; return (size_t)CCtxParams->cParams.strategy; case ZSTD_c_contentSizeFlag : /* Content size written in frame header _when known_ (default:1) */ DEBUGLOG(4, "set content size flag = %u", (value!=0)); CCtxParams->fParams.contentSizeFlag = value != 0; return (size_t)CCtxParams->fParams.contentSizeFlag; case ZSTD_c_checksumFlag : /* A 32-bits content checksum will be calculated and written at end of frame (default:0) */ CCtxParams->fParams.checksumFlag = value != 0; return (size_t)CCtxParams->fParams.checksumFlag; case ZSTD_c_dictIDFlag : /* When applicable, dictionary's dictID is provided in frame header (default:1) */ DEBUGLOG(4, "set dictIDFlag = %u", (value!=0)); CCtxParams->fParams.noDictIDFlag = !value; return !CCtxParams->fParams.noDictIDFlag; case ZSTD_c_forceMaxWindow : CCtxParams->forceWindow = (value != 0); return (size_t)CCtxParams->forceWindow; case ZSTD_c_forceAttachDict : { const ZSTD_dictAttachPref_e pref = (ZSTD_dictAttachPref_e)value; BOUNDCHECK(ZSTD_c_forceAttachDict, (int)pref); CCtxParams->attachDictPref = pref; return CCtxParams->attachDictPref; } case ZSTD_c_literalCompressionMode : { const ZSTD_ParamSwitch_e lcm = (ZSTD_ParamSwitch_e)value; BOUNDCHECK(ZSTD_c_literalCompressionMode, (int)lcm); CCtxParams->literalCompressionMode = lcm; return CCtxParams->literalCompressionMode; } case ZSTD_c_nbWorkers : RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; case ZSTD_c_jobSize : RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; case ZSTD_c_overlapLog : RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; case ZSTD_c_rsyncable : RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; case ZSTD_c_enableDedicatedDictSearch : CCtxParams->enableDedicatedDictSearch = (value!=0); return (size_t)CCtxParams->enableDedicatedDictSearch; case ZSTD_c_enableLongDistanceMatching : BOUNDCHECK(ZSTD_c_enableLongDistanceMatching, value); CCtxParams->ldmParams.enableLdm = (ZSTD_ParamSwitch_e)value; return CCtxParams->ldmParams.enableLdm; case ZSTD_c_ldmHashLog : if (value!=0) /* 0 ==> auto */ BOUNDCHECK(ZSTD_c_ldmHashLog, value); CCtxParams->ldmParams.hashLog = (U32)value; return CCtxParams->ldmParams.hashLog; case ZSTD_c_ldmMinMatch : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_ldmMinMatch, value); CCtxParams->ldmParams.minMatchLength = (U32)value; return CCtxParams->ldmParams.minMatchLength; case ZSTD_c_ldmBucketSizeLog : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_ldmBucketSizeLog, value); CCtxParams->ldmParams.bucketSizeLog = (U32)value; return CCtxParams->ldmParams.bucketSizeLog; case ZSTD_c_ldmHashRateLog : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_ldmHashRateLog, value); CCtxParams->ldmParams.hashRateLog = (U32)value; return CCtxParams->ldmParams.hashRateLog; case ZSTD_c_targetCBlockSize : if (value!=0) { /* 0 ==> default */ value = MAX(value, ZSTD_TARGETCBLOCKSIZE_MIN); BOUNDCHECK(ZSTD_c_targetCBlockSize, value); } CCtxParams->targetCBlockSize = (U32)value; return CCtxParams->targetCBlockSize; case ZSTD_c_srcSizeHint : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_srcSizeHint, value); CCtxParams->srcSizeHint = value; return (size_t)CCtxParams->srcSizeHint; case ZSTD_c_stableInBuffer: BOUNDCHECK(ZSTD_c_stableInBuffer, value); CCtxParams->inBufferMode = (ZSTD_bufferMode_e)value; return CCtxParams->inBufferMode; case ZSTD_c_stableOutBuffer: BOUNDCHECK(ZSTD_c_stableOutBuffer, value); CCtxParams->outBufferMode = (ZSTD_bufferMode_e)value; return CCtxParams->outBufferMode; case ZSTD_c_blockDelimiters: BOUNDCHECK(ZSTD_c_blockDelimiters, value); CCtxParams->blockDelimiters = (ZSTD_SequenceFormat_e)value; return CCtxParams->blockDelimiters; case ZSTD_c_validateSequences: BOUNDCHECK(ZSTD_c_validateSequences, value); CCtxParams->validateSequences = value; return (size_t)CCtxParams->validateSequences; case ZSTD_c_splitAfterSequences: BOUNDCHECK(ZSTD_c_splitAfterSequences, value); CCtxParams->postBlockSplitter = (ZSTD_ParamSwitch_e)value; return CCtxParams->postBlockSplitter; case ZSTD_c_blockSplitterLevel: BOUNDCHECK(ZSTD_c_blockSplitterLevel, value); CCtxParams->preBlockSplitter_level = value; return (size_t)CCtxParams->preBlockSplitter_level; case ZSTD_c_useRowMatchFinder: BOUNDCHECK(ZSTD_c_useRowMatchFinder, value); CCtxParams->useRowMatchFinder = (ZSTD_ParamSwitch_e)value; return CCtxParams->useRowMatchFinder; case ZSTD_c_deterministicRefPrefix: BOUNDCHECK(ZSTD_c_deterministicRefPrefix, value); CCtxParams->deterministicRefPrefix = !!value; return (size_t)CCtxParams->deterministicRefPrefix; case ZSTD_c_prefetchCDictTables: BOUNDCHECK(ZSTD_c_prefetchCDictTables, value); CCtxParams->prefetchCDictTables = (ZSTD_ParamSwitch_e)value; return CCtxParams->prefetchCDictTables; case ZSTD_c_enableSeqProducerFallback: BOUNDCHECK(ZSTD_c_enableSeqProducerFallback, value); CCtxParams->enableMatchFinderFallback = value; return (size_t)CCtxParams->enableMatchFinderFallback; case ZSTD_c_maxBlockSize: if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_maxBlockSize, value); assert(value>=0); CCtxParams->maxBlockSize = (size_t)value; return CCtxParams->maxBlockSize; case ZSTD_c_repcodeResolution: BOUNDCHECK(ZSTD_c_repcodeResolution, value); CCtxParams->searchForExternalRepcodes = (ZSTD_ParamSwitch_e)value; return CCtxParams->searchForExternalRepcodes; default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); } } size_t ZSTD_CCtx_getParameter(ZSTD_CCtx const* cctx, ZSTD_cParameter param, int* value) { return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value); } size_t ZSTD_CCtxParams_getParameter( ZSTD_CCtx_params const* CCtxParams, ZSTD_cParameter param, int* value) { switch(param) { case ZSTD_c_format : *value = (int)CCtxParams->format; break; case ZSTD_c_compressionLevel : *value = CCtxParams->compressionLevel; break; case ZSTD_c_windowLog : *value = (int)CCtxParams->cParams.windowLog; break; case ZSTD_c_hashLog : *value = (int)CCtxParams->cParams.hashLog; break; case ZSTD_c_chainLog : *value = (int)CCtxParams->cParams.chainLog; break; case ZSTD_c_searchLog : *value = (int)CCtxParams->cParams.searchLog; break; case ZSTD_c_minMatch : *value = (int)CCtxParams->cParams.minMatch; break; case ZSTD_c_targetLength : *value = (int)CCtxParams->cParams.targetLength; break; case ZSTD_c_strategy : *value = (int)CCtxParams->cParams.strategy; break; case ZSTD_c_contentSizeFlag : *value = CCtxParams->fParams.contentSizeFlag; break; case ZSTD_c_checksumFlag : *value = CCtxParams->fParams.checksumFlag; break; case ZSTD_c_dictIDFlag : *value = !CCtxParams->fParams.noDictIDFlag; break; case ZSTD_c_forceMaxWindow : *value = CCtxParams->forceWindow; break; case ZSTD_c_forceAttachDict : *value = (int)CCtxParams->attachDictPref; break; case ZSTD_c_literalCompressionMode : *value = (int)CCtxParams->literalCompressionMode; break; case ZSTD_c_nbWorkers : assert(CCtxParams->nbWorkers == 0); *value = CCtxParams->nbWorkers; break; case ZSTD_c_jobSize : RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); case ZSTD_c_overlapLog : RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); case ZSTD_c_rsyncable : RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); case ZSTD_c_enableDedicatedDictSearch : *value = CCtxParams->enableDedicatedDictSearch; break; case ZSTD_c_enableLongDistanceMatching : *value = (int)CCtxParams->ldmParams.enableLdm; break; case ZSTD_c_ldmHashLog : *value = (int)CCtxParams->ldmParams.hashLog; break; case ZSTD_c_ldmMinMatch : *value = (int)CCtxParams->ldmParams.minMatchLength; break; case ZSTD_c_ldmBucketSizeLog : *value = (int)CCtxParams->ldmParams.bucketSizeLog; break; case ZSTD_c_ldmHashRateLog : *value = (int)CCtxParams->ldmParams.hashRateLog; break; case ZSTD_c_targetCBlockSize : *value = (int)CCtxParams->targetCBlockSize; break; case ZSTD_c_srcSizeHint : *value = (int)CCtxParams->srcSizeHint; break; case ZSTD_c_stableInBuffer : *value = (int)CCtxParams->inBufferMode; break; case ZSTD_c_stableOutBuffer : *value = (int)CCtxParams->outBufferMode; break; case ZSTD_c_blockDelimiters : *value = (int)CCtxParams->blockDelimiters; break; case ZSTD_c_validateSequences : *value = (int)CCtxParams->validateSequences; break; case ZSTD_c_splitAfterSequences : *value = (int)CCtxParams->postBlockSplitter; break; case ZSTD_c_blockSplitterLevel : *value = CCtxParams->preBlockSplitter_level; break; case ZSTD_c_useRowMatchFinder : *value = (int)CCtxParams->useRowMatchFinder; break; case ZSTD_c_deterministicRefPrefix: *value = (int)CCtxParams->deterministicRefPrefix; break; case ZSTD_c_prefetchCDictTables: *value = (int)CCtxParams->prefetchCDictTables; break; case ZSTD_c_enableSeqProducerFallback: *value = CCtxParams->enableMatchFinderFallback; break; case ZSTD_c_maxBlockSize: *value = (int)CCtxParams->maxBlockSize; break; case ZSTD_c_repcodeResolution: *value = (int)CCtxParams->searchForExternalRepcodes; break; default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); } return 0; } /* ZSTD_CCtx_setParametersUsingCCtxParams() : * just applies `params` into `cctx` * no action is performed, parameters are merely stored. * If ZSTDMT is enabled, parameters are pushed to cctx->mtctx. * This is possible even if a compression is ongoing. * In which case, new parameters will be applied on the fly, starting with next compression job. */ size_t ZSTD_CCtx_setParametersUsingCCtxParams( ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params) { DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams"); RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "The context is in the wrong stage!"); RETURN_ERROR_IF(cctx->cdict, stage_wrong, "Can't override parameters with cdict attached (some must " "be inherited from the cdict)."); cctx->requestedParams = *params; return 0; } size_t ZSTD_CCtx_setCParams(ZSTD_CCtx* cctx, ZSTD_compressionParameters cparams) { ZSTD_STATIC_ASSERT(sizeof(cparams) == 7 * 4 /* all params are listed below */); DEBUGLOG(4, "ZSTD_CCtx_setCParams"); /* only update if all parameters are valid */ FORWARD_IF_ERROR(ZSTD_checkCParams(cparams), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_windowLog, (int)cparams.windowLog), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_chainLog, (int)cparams.chainLog), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, (int)cparams.hashLog), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_searchLog, (int)cparams.searchLog), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_minMatch, (int)cparams.minMatch), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_targetLength, (int)cparams.targetLength), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_strategy, (int)cparams.strategy), ""); return 0; } size_t ZSTD_CCtx_setFParams(ZSTD_CCtx* cctx, ZSTD_frameParameters fparams) { ZSTD_STATIC_ASSERT(sizeof(fparams) == 3 * 4 /* all params are listed below */); DEBUGLOG(4, "ZSTD_CCtx_setFParams"); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_contentSizeFlag, fparams.contentSizeFlag != 0), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, fparams.checksumFlag != 0), ""); FORWARD_IF_ERROR(ZSTD_CCtx_setParameter(cctx, ZSTD_c_dictIDFlag, fparams.noDictIDFlag == 0), ""); return 0; } size_t ZSTD_CCtx_setParams(ZSTD_CCtx* cctx, ZSTD_parameters params) { DEBUGLOG(4, "ZSTD_CCtx_setParams"); /* First check cParams, because we want to update all or none. */ FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams), ""); /* Next set fParams, because this could fail if the cctx isn't in init stage. */ FORWARD_IF_ERROR(ZSTD_CCtx_setFParams(cctx, params.fParams), ""); /* Finally set cParams, which should succeed. */ FORWARD_IF_ERROR(ZSTD_CCtx_setCParams(cctx, params.cParams), ""); return 0; } size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize) { DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %llu bytes", pledgedSrcSize); RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't set pledgedSrcSize when not in init stage."); cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1; return 0; } static ZSTD_compressionParameters ZSTD_dedicatedDictSearch_getCParams( int const compressionLevel, size_t const dictSize); static int ZSTD_dedicatedDictSearch_isSupported( const ZSTD_compressionParameters* cParams); static void ZSTD_dedicatedDictSearch_revertCParams( ZSTD_compressionParameters* cParams); /* * Initializes the local dictionary using requested parameters. * NOTE: Initialization does not employ the pledged src size, * because the dictionary may be used for multiple compressions. */ static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx) { ZSTD_localDict* const dl = &cctx->localDict; if (dl->dict == NULL) { /* No local dictionary. */ assert(dl->dictBuffer == NULL); assert(dl->cdict == NULL); assert(dl->dictSize == 0); return 0; } if (dl->cdict != NULL) { /* Local dictionary already initialized. */ assert(cctx->cdict == dl->cdict); return 0; } assert(dl->dictSize > 0); assert(cctx->cdict == NULL); assert(cctx->prefixDict.dict == NULL); dl->cdict = ZSTD_createCDict_advanced2( dl->dict, dl->dictSize, ZSTD_dlm_byRef, dl->dictContentType, &cctx->requestedParams, cctx->customMem); RETURN_ERROR_IF(!dl->cdict, memory_allocation, "ZSTD_createCDict_advanced failed"); cctx->cdict = dl->cdict; return 0; } size_t ZSTD_CCtx_loadDictionary_advanced( ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) { DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize); RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't load a dictionary when cctx is not in init stage."); ZSTD_clearAllDicts(cctx); /* erase any previously set dictionary */ if (dict == NULL || dictSize == 0) /* no dictionary */ return 0; if (dictLoadMethod == ZSTD_dlm_byRef) { cctx->localDict.dict = dict; } else { /* copy dictionary content inside CCtx to own its lifetime */ void* dictBuffer; RETURN_ERROR_IF(cctx->staticSize, memory_allocation, "static CCtx can't allocate for an internal copy of dictionary"); dictBuffer = ZSTD_customMalloc(dictSize, cctx->customMem); RETURN_ERROR_IF(dictBuffer==NULL, memory_allocation, "allocation failed for dictionary content"); ZSTD_memcpy(dictBuffer, dict, dictSize); cctx->localDict.dictBuffer = dictBuffer; /* owned ptr to free */ cctx->localDict.dict = dictBuffer; /* read-only reference */ } cctx->localDict.dictSize = dictSize; cctx->localDict.dictContentType = dictContentType; return 0; } size_t ZSTD_CCtx_loadDictionary_byReference( ZSTD_CCtx* cctx, const void* dict, size_t dictSize) { return ZSTD_CCtx_loadDictionary_advanced( cctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); } size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize) { return ZSTD_CCtx_loadDictionary_advanced( cctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); } size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) { RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't ref a dict when ctx not in init stage."); /* Free the existing local cdict (if any) to save memory. */ ZSTD_clearAllDicts(cctx); cctx->cdict = cdict; return 0; } size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool) { RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't ref a pool when ctx not in init stage."); cctx->pool = pool; return 0; } size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize) { return ZSTD_CCtx_refPrefix_advanced(cctx, prefix, prefixSize, ZSTD_dct_rawContent); } size_t ZSTD_CCtx_refPrefix_advanced( ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) { RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't ref a prefix when ctx not in init stage."); ZSTD_clearAllDicts(cctx); if (prefix != NULL && prefixSize > 0) { cctx->prefixDict.dict = prefix; cctx->prefixDict.dictSize = prefixSize; cctx->prefixDict.dictContentType = dictContentType; } return 0; } /*! ZSTD_CCtx_reset() : * Also dumps dictionary */ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset) { if ( (reset == ZSTD_reset_session_only) || (reset == ZSTD_reset_session_and_parameters) ) { cctx->streamStage = zcss_init; cctx->pledgedSrcSizePlusOne = 0; } if ( (reset == ZSTD_reset_parameters) || (reset == ZSTD_reset_session_and_parameters) ) { RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Reset parameters is only possible during init stage."); ZSTD_clearAllDicts(cctx); return ZSTD_CCtxParams_reset(&cctx->requestedParams); } return 0; } /* ZSTD_checkCParams() : control CParam values remain within authorized range. @return : 0, or an error code if one value is beyond authorized range */ size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams) { BOUNDCHECK(ZSTD_c_windowLog, (int)cParams.windowLog); BOUNDCHECK(ZSTD_c_chainLog, (int)cParams.chainLog); BOUNDCHECK(ZSTD_c_hashLog, (int)cParams.hashLog); BOUNDCHECK(ZSTD_c_searchLog, (int)cParams.searchLog); BOUNDCHECK(ZSTD_c_minMatch, (int)cParams.minMatch); BOUNDCHECK(ZSTD_c_targetLength,(int)cParams.targetLength); BOUNDCHECK(ZSTD_c_strategy, (int)cParams.strategy); return 0; } /* ZSTD_clampCParams() : * make CParam values within valid range. * @return : valid CParams */ static ZSTD_compressionParameters ZSTD_clampCParams(ZSTD_compressionParameters cParams) { # define CLAMP_TYPE(cParam, val, type) \ do { \ ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); \ if ((int)val<bounds.lowerBound) val=(type)bounds.lowerBound; \ else if ((int)val>bounds.upperBound) val=(type)bounds.upperBound; \ } while (0) # define CLAMP(cParam, val) CLAMP_TYPE(cParam, val, unsigned) CLAMP(ZSTD_c_windowLog, cParams.windowLog); CLAMP(ZSTD_c_chainLog, cParams.chainLog); CLAMP(ZSTD_c_hashLog, cParams.hashLog); CLAMP(ZSTD_c_searchLog, cParams.searchLog); CLAMP(ZSTD_c_minMatch, cParams.minMatch); CLAMP(ZSTD_c_targetLength,cParams.targetLength); CLAMP_TYPE(ZSTD_c_strategy,cParams.strategy, ZSTD_strategy); return cParams; } /* ZSTD_cycleLog() : * condition for correct operation : hashLog > 1 */ U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat) { U32 const btScale = ((U32)strat >= (U32)ZSTD_btlazy2); return hashLog - btScale; } /* ZSTD_dictAndWindowLog() : * Returns an adjusted window log that is large enough to fit the source and the dictionary. * The zstd format says that the entire dictionary is valid if one byte of the dictionary * is within the window. So the hashLog and chainLog should be large enough to reference both * the dictionary and the window. So we must use this adjusted dictAndWindowLog when downsizing * the hashLog and windowLog. * NOTE: srcSize must not be ZSTD_CONTENTSIZE_UNKNOWN. */ static U32 ZSTD_dictAndWindowLog(U32 windowLog, U64 srcSize, U64 dictSize) { const U64 maxWindowSize = 1ULL << ZSTD_WINDOWLOG_MAX; /* No dictionary ==> No change */ if (dictSize == 0) { return windowLog; } assert(windowLog <= ZSTD_WINDOWLOG_MAX); assert(srcSize != ZSTD_CONTENTSIZE_UNKNOWN); /* Handled in ZSTD_adjustCParams_internal() */ { U64 const windowSize = 1ULL << windowLog; U64 const dictAndWindowSize = dictSize + windowSize; /* If the window size is already large enough to fit both the source and the dictionary * then just use the window size. Otherwise adjust so that it fits the dictionary and * the window. */ if (windowSize >= dictSize + srcSize) { return windowLog; /* Window size large enough already */ } else if (dictAndWindowSize >= maxWindowSize) { return ZSTD_WINDOWLOG_MAX; /* Larger than max window log */ } else { return ZSTD_highbit32((U32)dictAndWindowSize - 1) + 1; } } } /* ZSTD_adjustCParams_internal() : * optimize `cPar` for a specified input (`srcSize` and `dictSize`). * mostly downsize to reduce memory consumption and initialization latency. * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known. * `mode` is the mode for parameter adjustment. See docs for `ZSTD_CParamMode_e`. * note : `srcSize==0` means 0! * condition : cPar is presumed validated (can be checked using ZSTD_checkCParams()). */ static ZSTD_compressionParameters ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize, ZSTD_CParamMode_e mode, ZSTD_ParamSwitch_e useRowMatchFinder) { const U64 minSrcSize = 513; /* (1<<9) + 1 */ const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1); assert(ZSTD_checkCParams(cPar)==0); /* Cascade the selected strategy down to the next-highest one built into * this binary. */ #ifdef ZSTD_EXCLUDE_BTULTRA_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_btultra2) { cPar.strategy = ZSTD_btultra; } if (cPar.strategy == ZSTD_btultra) { cPar.strategy = ZSTD_btopt; } #endif #ifdef ZSTD_EXCLUDE_BTOPT_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_btopt) { cPar.strategy = ZSTD_btlazy2; } #endif #ifdef ZSTD_EXCLUDE_BTLAZY2_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_btlazy2) { cPar.strategy = ZSTD_lazy2; } #endif #ifdef ZSTD_EXCLUDE_LAZY2_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_lazy2) { cPar.strategy = ZSTD_lazy; } #endif #ifdef ZSTD_EXCLUDE_LAZY_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_lazy) { cPar.strategy = ZSTD_greedy; } #endif #ifdef ZSTD_EXCLUDE_GREEDY_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_greedy) { cPar.strategy = ZSTD_dfast; } #endif #ifdef ZSTD_EXCLUDE_DFAST_BLOCK_COMPRESSOR if (cPar.strategy == ZSTD_dfast) { cPar.strategy = ZSTD_fast; cPar.targetLength = 0; } #endif switch (mode) { case ZSTD_cpm_unknown: case ZSTD_cpm_noAttachDict: /* If we don't know the source size, don't make any * assumptions about it. We will already have selected * smaller parameters if a dictionary is in use. */ break; case ZSTD_cpm_createCDict: /* Assume a small source size when creating a dictionary * with an unknown source size. */ if (dictSize && srcSize == ZSTD_CONTENTSIZE_UNKNOWN) srcSize = minSrcSize; break; case ZSTD_cpm_attachDict: /* Dictionary has its own dedicated parameters which have * already been selected. We are selecting parameters * for only the source. */ dictSize = 0; break; default: assert(0); break; } /* resize windowLog if input is small enough, to use less memory */ if ( (srcSize <= maxWindowResize) && (dictSize <= maxWindowResize) ) { U32 const tSize = (U32)(srcSize + dictSize); static U32 const hashSizeMin = 1 << ZSTD_HASHLOG_MIN; U32 const srcLog = (tSize < hashSizeMin) ? ZSTD_HASHLOG_MIN : ZSTD_highbit32(tSize-1) + 1; if (cPar.windowLog > srcLog) cPar.windowLog = srcLog; } if (srcSize != ZSTD_CONTENTSIZE_UNKNOWN) { U32 const dictAndWindowLog = ZSTD_dictAndWindowLog(cPar.windowLog, (U64)srcSize, (U64)dictSize); U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy); if (cPar.hashLog > dictAndWindowLog+1) cPar.hashLog = dictAndWindowLog+1; if (cycleLog > dictAndWindowLog) cPar.chainLog -= (cycleLog - dictAndWindowLog); } if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN) cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* minimum wlog required for valid frame header */ /* We can't use more than 32 bits of hash in total, so that means that we require: * (hashLog + 8) <= 32 && (chainLog + 8) <= 32 */ if (mode == ZSTD_cpm_createCDict && ZSTD_CDictIndicesAreTagged(&cPar)) { U32 const maxShortCacheHashLog = 32 - ZSTD_SHORT_CACHE_TAG_BITS; if (cPar.hashLog > maxShortCacheHashLog) { cPar.hashLog = maxShortCacheHashLog; } if (cPar.chainLog > maxShortCacheHashLog) { cPar.chainLog = maxShortCacheHashLog; } } /* At this point, we aren't 100% sure if we are using the row match finder. * Unless it is explicitly disabled, conservatively assume that it is enabled. * In this case it will only be disabled for small sources, so shrinking the * hash log a little bit shouldn't result in any ratio loss. */ if (useRowMatchFinder == ZSTD_ps_auto) useRowMatchFinder = ZSTD_ps_enable; /* We can't hash more than 32-bits in total. So that means that we require: * (hashLog - rowLog + 8) <= 32 */ if (ZSTD_rowMatchFinderUsed(cPar.strategy, useRowMatchFinder)) { /* Switch to 32-entry rows if searchLog is 5 (or more) */ U32 const rowLog = BOUNDED(4, cPar.searchLog, 6); U32 const maxRowHashLog = 32 - ZSTD_ROW_HASH_TAG_BITS; U32 const maxHashLog = maxRowHashLog + rowLog; assert(cPar.hashLog >= rowLog); if (cPar.hashLog > maxHashLog) { cPar.hashLog = maxHashLog; } } return cPar; } ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize) { cPar = ZSTD_clampCParams(cPar); /* resulting cPar is necessarily valid (all parameters within range) */ if (srcSize == 0) srcSize = ZSTD_CONTENTSIZE_UNKNOWN; return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize, ZSTD_cpm_unknown, ZSTD_ps_auto); } static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_CParamMode_e mode); static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_CParamMode_e mode); static void ZSTD_overrideCParams( ZSTD_compressionParameters* cParams, const ZSTD_compressionParameters* overrides) { if (overrides->windowLog) cParams->windowLog = overrides->windowLog; if (overrides->hashLog) cParams->hashLog = overrides->hashLog; if (overrides->chainLog) cParams->chainLog = overrides->chainLog; if (overrides->searchLog) cParams->searchLog = overrides->searchLog; if (overrides->minMatch) cParams->minMatch = overrides->minMatch; if (overrides->targetLength) cParams->targetLength = overrides->targetLength; if (overrides->strategy) cParams->strategy = overrides->strategy; } ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams( const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_CParamMode_e mode) { ZSTD_compressionParameters cParams; if (srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN && CCtxParams->srcSizeHint > 0) { assert(CCtxParams->srcSizeHint>=0); srcSizeHint = (U64)CCtxParams->srcSizeHint; } cParams = ZSTD_getCParams_internal(CCtxParams->compressionLevel, srcSizeHint, dictSize, mode); if (CCtxParams->ldmParams.enableLdm == ZSTD_ps_enable) cParams.windowLog = ZSTD_LDM_DEFAULT_WINDOW_LOG; ZSTD_overrideCParams(&cParams, &CCtxParams->cParams); assert(!ZSTD_checkCParams(cParams)); /* srcSizeHint == 0 means 0 */ return ZSTD_adjustCParams_internal(cParams, srcSizeHint, dictSize, mode, CCtxParams->useRowMatchFinder); } static size_t ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams, const ZSTD_ParamSwitch_e useRowMatchFinder, const int enableDedicatedDictSearch, const U32 forCCtx) { /* chain table size should be 0 for fast or row-hash strategies */ size_t const chainSize = ZSTD_allocateChainTable(cParams->strategy, useRowMatchFinder, enableDedicatedDictSearch && !forCCtx) ? ((size_t)1 << cParams->chainLog) : 0; size_t const hSize = ((size_t)1) << cParams->hashLog; U32 const hashLog3 = (forCCtx && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0; size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0; /* We don't use ZSTD_cwksp_alloc_size() here because the tables aren't * surrounded by redzones in ASAN. */ size_t const tableSpace = chainSize * sizeof(U32) + hSize * sizeof(U32) + h3Size * sizeof(U32); size_t const optPotentialSpace = ZSTD_cwksp_aligned64_alloc_size((MaxML+1) * sizeof(U32)) + ZSTD_cwksp_aligned64_alloc_size((MaxLL+1) * sizeof(U32)) + ZSTD_cwksp_aligned64_alloc_size((MaxOff+1) * sizeof(U32)) + ZSTD_cwksp_aligned64_alloc_size((1<<Litbits) * sizeof(U32)) + ZSTD_cwksp_aligned64_alloc_size(ZSTD_OPT_SIZE * sizeof(ZSTD_match_t)) + ZSTD_cwksp_aligned64_alloc_size(ZSTD_OPT_SIZE * sizeof(ZSTD_optimal_t)); size_t const lazyAdditionalSpace = ZSTD_rowMatchFinderUsed(cParams->strategy, useRowMatchFinder) ? ZSTD_cwksp_aligned64_alloc_size(hSize) : 0; size_t const optSpace = (forCCtx && (cParams->strategy >= ZSTD_btopt)) ? optPotentialSpace : 0; size_t const slackSpace = ZSTD_cwksp_slack_space_required(); /* tables are guaranteed to be sized in multiples of 64 bytes (or 16 uint32_t) */ ZSTD_STATIC_ASSERT(ZSTD_HASHLOG_MIN >= 4 && ZSTD_WINDOWLOG_MIN >= 4 && ZSTD_CHAINLOG_MIN >= 4); assert(useRowMatchFinder != ZSTD_ps_auto); DEBUGLOG(4, "chainSize: %u - hSize: %u - h3Size: %u", (U32)chainSize, (U32)hSize, (U32)h3Size); return tableSpace + optSpace + slackSpace + lazyAdditionalSpace; } /* Helper function for calculating memory requirements. * Gives a tighter bound than ZSTD_sequenceBound() by taking minMatch into account. */ static size_t ZSTD_maxNbSeq(size_t blockSize, unsigned minMatch, int useSequenceProducer) { U32 const divider = (minMatch==3 || useSequenceProducer) ? 3 : 4; return blockSize / divider; } static size_t ZSTD_estimateCCtxSize_usingCCtxParams_internal( const ZSTD_compressionParameters* cParams, const ldmParams_t* ldmParams, const int isStatic, const ZSTD_ParamSwitch_e useRowMatchFinder, const size_t buffInSize, const size_t buffOutSize, const U64 pledgedSrcSize, int useSequenceProducer, size_t maxBlockSize) { size_t const windowSize = (size_t) BOUNDED(1ULL, 1ULL << cParams->windowLog, pledgedSrcSize); size_t const blockSize = MIN(ZSTD_resolveMaxBlockSize(maxBlockSize), windowSize); size_t const maxNbSeq = ZSTD_maxNbSeq(blockSize, cParams->minMatch, useSequenceProducer); size_t const tokenSpace = ZSTD_cwksp_alloc_size(WILDCOPY_OVERLENGTH + blockSize) + ZSTD_cwksp_aligned64_alloc_size(maxNbSeq * sizeof(SeqDef)) + 3 * ZSTD_cwksp_alloc_size(maxNbSeq * sizeof(BYTE)); size_t const tmpWorkSpace = ZSTD_cwksp_alloc_size(TMP_WORKSPACE_SIZE); size_t const blockStateSpace = 2 * ZSTD_cwksp_alloc_size(sizeof(ZSTD_compressedBlockState_t)); size_t const matchStateSize = ZSTD_sizeof_matchState(cParams, useRowMatchFinder, /* enableDedicatedDictSearch */ 0, /* forCCtx */ 1); size_t const ldmSpace = ZSTD_ldm_getTableSize(*ldmParams); size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(*ldmParams, blockSize); size_t const ldmSeqSpace = ldmParams->enableLdm == ZSTD_ps_enable ? ZSTD_cwksp_aligned64_alloc_size(maxNbLdmSeq * sizeof(rawSeq)) : 0; size_t const bufferSpace = ZSTD_cwksp_alloc_size(buffInSize) + ZSTD_cwksp_alloc_size(buffOutSize); size_t const cctxSpace = isStatic ? ZSTD_cwksp_alloc_size(sizeof(ZSTD_CCtx)) : 0; size_t const maxNbExternalSeq = ZSTD_sequenceBound(blockSize); size_t const externalSeqSpace = useSequenceProducer ? ZSTD_cwksp_aligned64_alloc_size(maxNbExternalSeq * sizeof(ZSTD_Sequence)) : 0; size_t const neededSpace = cctxSpace + tmpWorkSpace + blockStateSpace + ldmSpace + ldmSeqSpace + matchStateSize + tokenSpace + bufferSpace + externalSeqSpace; DEBUGLOG(5, "estimate workspace : %u", (U32)neededSpace); return neededSpace; } size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params) { ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); ZSTD_ParamSwitch_e const useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(params->useRowMatchFinder, &cParams); RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); /* estimateCCtxSize is for one-shot compression. So no buffers should * be needed. However, we still allocate two 0-sized buffers, which can * take space under ASAN. */ return ZSTD_estimateCCtxSize_usingCCtxParams_internal( &cParams, ¶ms->ldmParams, 1, useRowMatchFinder, 0, 0, ZSTD_CONTENTSIZE_UNKNOWN, ZSTD_hasExtSeqProd(params), params->maxBlockSize); } size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams) { ZSTD_CCtx_params initialParams = ZSTD_makeCCtxParamsFromCParams(cParams); if (ZSTD_rowMatchFinderSupported(cParams.strategy)) { /* Pick bigger of not using and using row-based matchfinder for greedy and lazy strategies */ size_t noRowCCtxSize; size_t rowCCtxSize; initialParams.useRowMatchFinder = ZSTD_ps_disable; noRowCCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(&initialParams); initialParams.useRowMatchFinder = ZSTD_ps_enable; rowCCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(&initialParams); return MAX(noRowCCtxSize, rowCCtxSize); } else { return ZSTD_estimateCCtxSize_usingCCtxParams(&initialParams); } } static size_t ZSTD_estimateCCtxSize_internal(int compressionLevel) { int tier = 0; size_t largestSize = 0; static const unsigned long long srcSizeTiers[4] = {16 KB, 128 KB, 256 KB, ZSTD_CONTENTSIZE_UNKNOWN}; for (; tier < 4; ++tier) { /* Choose the set of cParams for a given level across all srcSizes that give the largest cctxSize */ ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, srcSizeTiers[tier], 0, ZSTD_cpm_noAttachDict); largestSize = MAX(ZSTD_estimateCCtxSize_usingCParams(cParams), largestSize); } return largestSize; } size_t ZSTD_estimateCCtxSize(int compressionLevel) { int level; size_t memBudget = 0; for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) { /* Ensure monotonically increasing memory usage as compression level increases */ size_t const newMB = ZSTD_estimateCCtxSize_internal(level); if (newMB > memBudget) memBudget = newMB; } return memBudget; } size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params) { RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); { ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); size_t const blockSize = MIN(ZSTD_resolveMaxBlockSize(params->maxBlockSize), (size_t)1 << cParams.windowLog); size_t const inBuffSize = (params->inBufferMode == ZSTD_bm_buffered) ? ((size_t)1 << cParams.windowLog) + blockSize : 0; size_t const outBuffSize = (params->outBufferMode == ZSTD_bm_buffered) ? ZSTD_compressBound(blockSize) + 1 : 0; ZSTD_ParamSwitch_e const useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(params->useRowMatchFinder, ¶ms->cParams); return ZSTD_estimateCCtxSize_usingCCtxParams_internal( &cParams, ¶ms->ldmParams, 1, useRowMatchFinder, inBuffSize, outBuffSize, ZSTD_CONTENTSIZE_UNKNOWN, ZSTD_hasExtSeqProd(params), params->maxBlockSize); } } size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams) { ZSTD_CCtx_params initialParams = ZSTD_makeCCtxParamsFromCParams(cParams); if (ZSTD_rowMatchFinderSupported(cParams.strategy)) { /* Pick bigger of not using and using row-based matchfinder for greedy and lazy strategies */ size_t noRowCCtxSize; size_t rowCCtxSize; initialParams.useRowMatchFinder = ZSTD_ps_disable; noRowCCtxSize = ZSTD_estimateCStreamSize_usingCCtxParams(&initialParams); initialParams.useRowMatchFinder = ZSTD_ps_enable; rowCCtxSize = ZSTD_estimateCStreamSize_usingCCtxParams(&initialParams); return MAX(noRowCCtxSize, rowCCtxSize); } else { return ZSTD_estimateCStreamSize_usingCCtxParams(&initialParams); } } static size_t ZSTD_estimateCStreamSize_internal(int compressionLevel) { ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); return ZSTD_estimateCStreamSize_usingCParams(cParams); } size_t ZSTD_estimateCStreamSize(int compressionLevel) { int level; size_t memBudget = 0; for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) { size_t const newMB = ZSTD_estimateCStreamSize_internal(level); if (newMB > memBudget) memBudget = newMB; } return memBudget; } /* ZSTD_getFrameProgression(): * tells how much data has been consumed (input) and produced (output) for current frame. * able to count progression inside worker threads (non-blocking mode). */ ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx) { { ZSTD_frameProgression fp; size_t const buffered = (cctx->inBuff == NULL) ? 0 : cctx->inBuffPos - cctx->inToCompress; if (buffered) assert(cctx->inBuffPos >= cctx->inToCompress); assert(buffered <= ZSTD_BLOCKSIZE_MAX); fp.ingested = cctx->consumedSrcSize + buffered; fp.consumed = cctx->consumedSrcSize; fp.produced = cctx->producedCSize; fp.flushed = cctx->producedCSize; /* simplified; some data might still be left within streaming output buffer */ fp.currentJobID = 0; fp.nbActiveWorkers = 0; return fp; } } /*! ZSTD_toFlushNow() * Only useful for multithreading scenarios currently (nbWorkers >= 1). */ size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx) { (void)cctx; return 0; /* over-simplification; could also check if context is currently running in streaming mode, and in which case, report how many bytes are left to be flushed within output buffer */ } static void ZSTD_assertEqualCParams(ZSTD_compressionParameters cParams1, ZSTD_compressionParameters cParams2) { (void)cParams1; (void)cParams2; assert(cParams1.windowLog == cParams2.windowLog); assert(cParams1.chainLog == cParams2.chainLog); assert(cParams1.hashLog == cParams2.hashLog); assert(cParams1.searchLog == cParams2.searchLog); assert(cParams1.minMatch == cParams2.minMatch); assert(cParams1.targetLength == cParams2.targetLength); assert(cParams1.strategy == cParams2.strategy); } void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs) { int i; for (i = 0; i < ZSTD_REP_NUM; ++i) bs->rep[i] = repStartValue[i]; bs->entropy.huf.repeatMode = HUF_repeat_none; bs->entropy.fse.offcode_repeatMode = FSE_repeat_none; bs->entropy.fse.matchlength_repeatMode = FSE_repeat_none; bs->entropy.fse.litlength_repeatMode = FSE_repeat_none; } /*! ZSTD_invalidateMatchState() * Invalidate all the matches in the match finder tables. * Requires nextSrc and base to be set (can be NULL). */ static void ZSTD_invalidateMatchState(ZSTD_MatchState_t* ms) { ZSTD_window_clear(&ms->window); ms->nextToUpdate = ms->window.dictLimit; ms->loadedDictEnd = 0; ms->opt.litLengthSum = 0; /* force reset of btopt stats */ ms->dictMatchState = NULL; } /* * Controls, for this matchState reset, whether the tables need to be cleared / * prepared for the coming compression (ZSTDcrp_makeClean), or whether the * tables can be left unclean (ZSTDcrp_leaveDirty), because we know that a * subsequent operation will overwrite the table space anyways (e.g., copying * the matchState contents in from a CDict). */ typedef enum { ZSTDcrp_makeClean, ZSTDcrp_leaveDirty } ZSTD_compResetPolicy_e; /* * Controls, for this matchState reset, whether indexing can continue where it * left off (ZSTDirp_continue), or whether it needs to be restarted from zero * (ZSTDirp_reset). */ typedef enum { ZSTDirp_continue, ZSTDirp_reset } ZSTD_indexResetPolicy_e; typedef enum { ZSTD_resetTarget_CDict, ZSTD_resetTarget_CCtx } ZSTD_resetTarget_e; /* Mixes bits in a 64 bits in a value, based on XXH3_rrmxmx */ static U64 ZSTD_bitmix(U64 val, U64 len) { val ^= ZSTD_rotateRight_U64(val, 49) ^ ZSTD_rotateRight_U64(val, 24); val *= 0x9FB21C651E98DF25ULL; val ^= (val >> 35) + len ; val *= 0x9FB21C651E98DF25ULL; return val ^ (val >> 28); } /* Mixes in the hashSalt and hashSaltEntropy to create a new hashSalt */ static void ZSTD_advanceHashSalt(ZSTD_MatchState_t* ms) { ms->hashSalt = ZSTD_bitmix(ms->hashSalt, 8) ^ ZSTD_bitmix((U64) ms->hashSaltEntropy, 4); } static size_t ZSTD_reset_matchState(ZSTD_MatchState_t* ms, ZSTD_cwksp* ws, const ZSTD_compressionParameters* cParams, const ZSTD_ParamSwitch_e useRowMatchFinder, const ZSTD_compResetPolicy_e crp, const ZSTD_indexResetPolicy_e forceResetIndex, const ZSTD_resetTarget_e forWho) { /* disable chain table allocation for fast or row-based strategies */ size_t const chainSize = ZSTD_allocateChainTable(cParams->strategy, useRowMatchFinder, ms->dedicatedDictSearch && (forWho == ZSTD_resetTarget_CDict)) ? ((size_t)1 << cParams->chainLog) : 0; size_t const hSize = ((size_t)1) << cParams->hashLog; U32 const hashLog3 = ((forWho == ZSTD_resetTarget_CCtx) && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0; size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0; DEBUGLOG(4, "reset indices : %u", forceResetIndex == ZSTDirp_reset); assert(useRowMatchFinder != ZSTD_ps_auto); if (forceResetIndex == ZSTDirp_reset) { ZSTD_window_init(&ms->window); ZSTD_cwksp_mark_tables_dirty(ws); } ms->hashLog3 = hashLog3; ms->lazySkipping = 0; ZSTD_invalidateMatchState(ms); assert(!ZSTD_cwksp_reserve_failed(ws)); /* check that allocation hasn't already failed */ ZSTD_cwksp_clear_tables(ws); DEBUGLOG(5, "reserving table space"); /* table Space */ ms->hashTable = (U32*)ZSTD_cwksp_reserve_table(ws, hSize * sizeof(U32)); ms->chainTable = (U32*)ZSTD_cwksp_reserve_table(ws, chainSize * sizeof(U32)); ms->hashTable3 = (U32*)ZSTD_cwksp_reserve_table(ws, h3Size * sizeof(U32)); RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation, "failed a workspace allocation in ZSTD_reset_matchState"); DEBUGLOG(4, "reset table : %u", crp!=ZSTDcrp_leaveDirty); if (crp!=ZSTDcrp_leaveDirty) { /* reset tables only */ ZSTD_cwksp_clean_tables(ws); } if (ZSTD_rowMatchFinderUsed(cParams->strategy, useRowMatchFinder)) { /* Row match finder needs an additional table of hashes ("tags") */ size_t const tagTableSize = hSize; /* We want to generate a new salt in case we reset a Cctx, but we always want to use * 0 when we reset a Cdict */ if(forWho == ZSTD_resetTarget_CCtx) { ms->tagTable = (BYTE*) ZSTD_cwksp_reserve_aligned_init_once(ws, tagTableSize); ZSTD_advanceHashSalt(ms); } else { /* When we are not salting we want to always memset the memory */ ms->tagTable = (BYTE*) ZSTD_cwksp_reserve_aligned64(ws, tagTableSize); ZSTD_memset(ms->tagTable, 0, tagTableSize); ms->hashSalt = 0; } { /* Switch to 32-entry rows if searchLog is 5 (or more) */ U32 const rowLog = BOUNDED(4, cParams->searchLog, 6); assert(cParams->hashLog >= rowLog); ms->rowHashLog = cParams->hashLog - rowLog; } } /* opt parser space */ if ((forWho == ZSTD_resetTarget_CCtx) && (cParams->strategy >= ZSTD_btopt)) { DEBUGLOG(4, "reserving optimal parser space"); ms->opt.litFreq = (unsigned*)ZSTD_cwksp_reserve_aligned64(ws, (1<<Litbits) * sizeof(unsigned)); ms->opt.litLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned64(ws, (MaxLL+1) * sizeof(unsigned)); ms->opt.matchLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned64(ws, (MaxML+1) * sizeof(unsigned)); ms->opt.offCodeFreq = (unsigned*)ZSTD_cwksp_reserve_aligned64(ws, (MaxOff+1) * sizeof(unsigned)); ms->opt.matchTable = (ZSTD_match_t*)ZSTD_cwksp_reserve_aligned64(ws, ZSTD_OPT_SIZE * sizeof(ZSTD_match_t)); ms->opt.priceTable = (ZSTD_optimal_t*)ZSTD_cwksp_reserve_aligned64(ws, ZSTD_OPT_SIZE * sizeof(ZSTD_optimal_t)); } ms->cParams = *cParams; RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation, "failed a workspace allocation in ZSTD_reset_matchState"); return 0; } /* ZSTD_indexTooCloseToMax() : * minor optimization : prefer memset() rather than reduceIndex() * which is measurably slow in some circumstances (reported for Visual Studio). * Works when re-using a context for a lot of smallish inputs : * if all inputs are smaller than ZSTD_INDEXOVERFLOW_MARGIN, * memset() will be triggered before reduceIndex(). */ #define ZSTD_INDEXOVERFLOW_MARGIN (16 MB) static int ZSTD_indexTooCloseToMax(ZSTD_window_t w) { return (size_t)(w.nextSrc - w.base) > (ZSTD_CURRENT_MAX - ZSTD_INDEXOVERFLOW_MARGIN); } /* ZSTD_dictTooBig(): * When dictionaries are larger than ZSTD_CHUNKSIZE_MAX they can't be loaded in * one go generically. So we ensure that in that case we reset the tables to zero, * so that we can load as much of the dictionary as possible. */ static int ZSTD_dictTooBig(size_t const loadedDictSize) { return loadedDictSize > ZSTD_CHUNKSIZE_MAX; } /*! ZSTD_resetCCtx_internal() : * @param loadedDictSize The size of the dictionary to be loaded * into the context, if any. If no dictionary is used, or the * dictionary is being attached / copied, then pass 0. * note : `params` are assumed fully validated at this stage. */ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, ZSTD_CCtx_params const* params, U64 const pledgedSrcSize, size_t const loadedDictSize, ZSTD_compResetPolicy_e const crp, ZSTD_buffered_policy_e const zbuff) { ZSTD_cwksp* const ws = &zc->workspace; DEBUGLOG(4, "ZSTD_resetCCtx_internal: pledgedSrcSize=%u, wlog=%u, useRowMatchFinder=%d useBlockSplitter=%d", (U32)pledgedSrcSize, params->cParams.windowLog, (int)params->useRowMatchFinder, (int)params->postBlockSplitter); assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams))); zc->isFirstBlock = 1; /* Set applied params early so we can modify them for LDM, * and point params at the applied params. */ zc->appliedParams = *params; params = &zc->appliedParams; assert(params->useRowMatchFinder != ZSTD_ps_auto); assert(params->postBlockSplitter != ZSTD_ps_auto); assert(params->ldmParams.enableLdm != ZSTD_ps_auto); assert(params->maxBlockSize != 0); if (params->ldmParams.enableLdm == ZSTD_ps_enable) { /* Adjust long distance matching parameters */ ZSTD_ldm_adjustParameters(&zc->appliedParams.ldmParams, ¶ms->cParams); assert(params->ldmParams.hashLog >= params->ldmParams.bucketSizeLog); assert(params->ldmParams.hashRateLog < 32); } { size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << params->cParams.windowLog), pledgedSrcSize)); size_t const blockSize = MIN(params->maxBlockSize, windowSize); size_t const maxNbSeq = ZSTD_maxNbSeq(blockSize, params->cParams.minMatch, ZSTD_hasExtSeqProd(params)); size_t const buffOutSize = (zbuff == ZSTDb_buffered && params->outBufferMode == ZSTD_bm_buffered) ? ZSTD_compressBound(blockSize) + 1 : 0; size_t const buffInSize = (zbuff == ZSTDb_buffered && params->inBufferMode == ZSTD_bm_buffered) ? windowSize + blockSize : 0; size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(params->ldmParams, blockSize); int const indexTooClose = ZSTD_indexTooCloseToMax(zc->blockState.matchState.window); int const dictTooBig = ZSTD_dictTooBig(loadedDictSize); ZSTD_indexResetPolicy_e needsIndexReset = (indexTooClose || dictTooBig || !zc->initialized) ? ZSTDirp_reset : ZSTDirp_continue; size_t const neededSpace = ZSTD_estimateCCtxSize_usingCCtxParams_internal( ¶ms->cParams, ¶ms->ldmParams, zc->staticSize != 0, params->useRowMatchFinder, buffInSize, buffOutSize, pledgedSrcSize, ZSTD_hasExtSeqProd(params), params->maxBlockSize); FORWARD_IF_ERROR(neededSpace, "cctx size estimate failed!"); if (!zc->staticSize) ZSTD_cwksp_bump_oversized_duration(ws, 0); { /* Check if workspace is large enough, alloc a new one if needed */ int const workspaceTooSmall = ZSTD_cwksp_sizeof(ws) < neededSpace; int const workspaceWasteful = ZSTD_cwksp_check_wasteful(ws, neededSpace); int resizeWorkspace = workspaceTooSmall || workspaceWasteful; DEBUGLOG(4, "Need %zu B workspace", neededSpace); DEBUGLOG(4, "windowSize: %zu - blockSize: %zu", windowSize, blockSize); if (resizeWorkspace) { DEBUGLOG(4, "Resize workspaceSize from %zuKB to %zuKB", ZSTD_cwksp_sizeof(ws) >> 10, neededSpace >> 10); RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize"); needsIndexReset = ZSTDirp_reset; ZSTD_cwksp_free(ws, zc->customMem); FORWARD_IF_ERROR(ZSTD_cwksp_create(ws, neededSpace, zc->customMem), ""); DEBUGLOG(5, "reserving object space"); /* Statically sized space. * tmpWorkspace never moves, * though prev/next block swap places */ assert(ZSTD_cwksp_check_available(ws, 2 * sizeof(ZSTD_compressedBlockState_t))); zc->blockState.prevCBlock = (ZSTD_compressedBlockState_t*) ZSTD_cwksp_reserve_object(ws, sizeof(ZSTD_compressedBlockState_t)); RETURN_ERROR_IF(zc->blockState.prevCBlock == NULL, memory_allocation, "couldn't allocate prevCBlock"); zc->blockState.nextCBlock = (ZSTD_compressedBlockState_t*) ZSTD_cwksp_reserve_object(ws, sizeof(ZSTD_compressedBlockState_t)); RETURN_ERROR_IF(zc->blockState.nextCBlock == NULL, memory_allocation, "couldn't allocate nextCBlock"); zc->tmpWorkspace = ZSTD_cwksp_reserve_object(ws, TMP_WORKSPACE_SIZE); RETURN_ERROR_IF(zc->tmpWorkspace == NULL, memory_allocation, "couldn't allocate tmpWorkspace"); zc->tmpWkspSize = TMP_WORKSPACE_SIZE; } } ZSTD_cwksp_clear(ws); /* init params */ zc->blockState.matchState.cParams = params->cParams; zc->blockState.matchState.prefetchCDictTables = params->prefetchCDictTables == ZSTD_ps_enable; zc->pledgedSrcSizePlusOne = pledgedSrcSize+1; zc->consumedSrcSize = 0; zc->producedCSize = 0; if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN) zc->appliedParams.fParams.contentSizeFlag = 0; DEBUGLOG(4, "pledged content size : %u ; flag : %u", (unsigned)pledgedSrcSize, zc->appliedParams.fParams.contentSizeFlag); zc->blockSizeMax = blockSize; xxh64_reset(&zc->xxhState, 0); zc->stage = ZSTDcs_init; zc->dictID = 0; zc->dictContentSize = 0; ZSTD_reset_compressedBlockState(zc->blockState.prevCBlock); FORWARD_IF_ERROR(ZSTD_reset_matchState( &zc->blockState.matchState, ws, ¶ms->cParams, params->useRowMatchFinder, crp, needsIndexReset, ZSTD_resetTarget_CCtx), ""); zc->seqStore.sequencesStart = (SeqDef*)ZSTD_cwksp_reserve_aligned64(ws, maxNbSeq * sizeof(SeqDef)); /* ldm hash table */ if (params->ldmParams.enableLdm == ZSTD_ps_enable) { /* TODO: avoid memset? */ size_t const ldmHSize = ((size_t)1) << params->ldmParams.hashLog; zc->ldmState.hashTable = (ldmEntry_t*)ZSTD_cwksp_reserve_aligned64(ws, ldmHSize * sizeof(ldmEntry_t)); ZSTD_memset(zc->ldmState.hashTable, 0, ldmHSize * sizeof(ldmEntry_t)); zc->ldmSequences = (rawSeq*)ZSTD_cwksp_reserve_aligned64(ws, maxNbLdmSeq * sizeof(rawSeq)); zc->maxNbLdmSequences = maxNbLdmSeq; ZSTD_window_init(&zc->ldmState.window); zc->ldmState.loadedDictEnd = 0; } /* reserve space for block-level external sequences */ if (ZSTD_hasExtSeqProd(params)) { size_t const maxNbExternalSeq = ZSTD_sequenceBound(blockSize); zc->extSeqBufCapacity = maxNbExternalSeq; zc->extSeqBuf = (ZSTD_Sequence*)ZSTD_cwksp_reserve_aligned64(ws, maxNbExternalSeq * sizeof(ZSTD_Sequence)); } /* buffers */ /* ZSTD_wildcopy() is used to copy into the literals buffer, * so we have to oversize the buffer by WILDCOPY_OVERLENGTH bytes. */ zc->seqStore.litStart = ZSTD_cwksp_reserve_buffer(ws, blockSize + WILDCOPY_OVERLENGTH); zc->seqStore.maxNbLit = blockSize; zc->bufferedPolicy = zbuff; zc->inBuffSize = buffInSize; zc->inBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffInSize); zc->outBuffSize = buffOutSize; zc->outBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffOutSize); /* ldm bucketOffsets table */ if (params->ldmParams.enableLdm == ZSTD_ps_enable) { /* TODO: avoid memset? */ size_t const numBuckets = ((size_t)1) << (params->ldmParams.hashLog - params->ldmParams.bucketSizeLog); zc->ldmState.bucketOffsets = ZSTD_cwksp_reserve_buffer(ws, numBuckets); ZSTD_memset(zc->ldmState.bucketOffsets, 0, numBuckets); } /* sequences storage */ ZSTD_referenceExternalSequences(zc, NULL, 0); zc->seqStore.maxNbSeq = maxNbSeq; zc->seqStore.llCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); zc->seqStore.mlCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); zc->seqStore.ofCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); DEBUGLOG(3, "wksp: finished allocating, %zd bytes remain available", ZSTD_cwksp_available_space(ws)); assert(ZSTD_cwksp_estimated_space_within_bounds(ws, neededSpace)); zc->initialized = 1; return 0; } } /* ZSTD_invalidateRepCodes() : * ensures next compression will not use repcodes from previous block. * Note : only works with regular variant; * do not use with extDict variant ! */ void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) { int i; for (i=0; i<ZSTD_REP_NUM; i++) cctx->blockState.prevCBlock->rep[i] = 0; assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window)); } /* These are the approximate sizes for each strategy past which copying the * dictionary tables into the working context is faster than using them * in-place. */ static const size_t attachDictSizeCutoffs[ZSTD_STRATEGY_MAX+1] = { 8 KB, /* unused */ 8 KB, /* ZSTD_fast */ 16 KB, /* ZSTD_dfast */ 32 KB, /* ZSTD_greedy */ 32 KB, /* ZSTD_lazy */ 32 KB, /* ZSTD_lazy2 */ 32 KB, /* ZSTD_btlazy2 */ 32 KB, /* ZSTD_btopt */ 8 KB, /* ZSTD_btultra */ 8 KB /* ZSTD_btultra2 */ }; static int ZSTD_shouldAttachDict(const ZSTD_CDict* cdict, const ZSTD_CCtx_params* params, U64 pledgedSrcSize) { size_t cutoff = attachDictSizeCutoffs[cdict->matchState.cParams.strategy]; int const dedicatedDictSearch = cdict->matchState.dedicatedDictSearch; return dedicatedDictSearch || ( ( pledgedSrcSize <= cutoff || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN || params->attachDictPref == ZSTD_dictForceAttach ) && params->attachDictPref != ZSTD_dictForceCopy && !params->forceWindow ); /* dictMatchState isn't correctly * handled in _enforceMaxDist */ } static size_t ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, ZSTD_CCtx_params params, U64 pledgedSrcSize, ZSTD_buffered_policy_e zbuff) { DEBUGLOG(4, "ZSTD_resetCCtx_byAttachingCDict() pledgedSrcSize=%llu", (unsigned long long)pledgedSrcSize); { ZSTD_compressionParameters adjusted_cdict_cParams = cdict->matchState.cParams; unsigned const windowLog = params.cParams.windowLog; assert(windowLog != 0); /* Resize working context table params for input only, since the dict * has its own tables. */ /* pledgedSrcSize == 0 means 0! */ if (cdict->matchState.dedicatedDictSearch) { ZSTD_dedicatedDictSearch_revertCParams(&adjusted_cdict_cParams); } params.cParams = ZSTD_adjustCParams_internal(adjusted_cdict_cParams, pledgedSrcSize, cdict->dictContentSize, ZSTD_cpm_attachDict, params.useRowMatchFinder); params.cParams.windowLog = windowLog; params.useRowMatchFinder = cdict->useRowMatchFinder; /* cdict overrides */ FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, ¶ms, pledgedSrcSize, /* loadedDictSize */ 0, ZSTDcrp_makeClean, zbuff), ""); assert(cctx->appliedParams.cParams.strategy == adjusted_cdict_cParams.strategy); } { const U32 cdictEnd = (U32)( cdict->matchState.window.nextSrc - cdict->matchState.window.base); const U32 cdictLen = cdictEnd - cdict->matchState.window.dictLimit; if (cdictLen == 0) { /* don't even attach dictionaries with no contents */ DEBUGLOG(4, "skipping attaching empty dictionary"); } else { DEBUGLOG(4, "attaching dictionary into context"); cctx->blockState.matchState.dictMatchState = &cdict->matchState; /* prep working match state so dict matches never have negative indices * when they are translated to the working context's index space. */ if (cctx->blockState.matchState.window.dictLimit < cdictEnd) { cctx->blockState.matchState.window.nextSrc = cctx->blockState.matchState.window.base + cdictEnd; ZSTD_window_clear(&cctx->blockState.matchState.window); } /* loadedDictEnd is expressed within the referential of the active context */ cctx->blockState.matchState.loadedDictEnd = cctx->blockState.matchState.window.dictLimit; } } cctx->dictID = cdict->dictID; cctx->dictContentSize = cdict->dictContentSize; /* copy block state */ ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState)); return 0; } static void ZSTD_copyCDictTableIntoCCtx(U32* dst, U32 const* src, size_t tableSize, ZSTD_compressionParameters const* cParams) { if (ZSTD_CDictIndicesAreTagged(cParams)){ /* Remove tags from the CDict table if they are present. * See docs on "short cache" in zstd_compress_internal.h for context. */ size_t i; for (i = 0; i < tableSize; i++) { U32 const taggedIndex = src[i]; U32 const index = taggedIndex >> ZSTD_SHORT_CACHE_TAG_BITS; dst[i] = index; } } else { ZSTD_memcpy(dst, src, tableSize * sizeof(U32)); } } static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, ZSTD_CCtx_params params, U64 pledgedSrcSize, ZSTD_buffered_policy_e zbuff) { const ZSTD_compressionParameters *cdict_cParams = &cdict->matchState.cParams; assert(!cdict->matchState.dedicatedDictSearch); DEBUGLOG(4, "ZSTD_resetCCtx_byCopyingCDict() pledgedSrcSize=%llu", (unsigned long long)pledgedSrcSize); { unsigned const windowLog = params.cParams.windowLog; assert(windowLog != 0); /* Copy only compression parameters related to tables. */ params.cParams = *cdict_cParams; params.cParams.windowLog = windowLog; params.useRowMatchFinder = cdict->useRowMatchFinder; FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, ¶ms, pledgedSrcSize, /* loadedDictSize */ 0, ZSTDcrp_leaveDirty, zbuff), ""); assert(cctx->appliedParams.cParams.strategy == cdict_cParams->strategy); assert(cctx->appliedParams.cParams.hashLog == cdict_cParams->hashLog); assert(cctx->appliedParams.cParams.chainLog == cdict_cParams->chainLog); } ZSTD_cwksp_mark_tables_dirty(&cctx->workspace); assert(params.useRowMatchFinder != ZSTD_ps_auto); /* copy tables */ { size_t const chainSize = ZSTD_allocateChainTable(cdict_cParams->strategy, cdict->useRowMatchFinder, 0 /* DDS guaranteed disabled */) ? ((size_t)1 << cdict_cParams->chainLog) : 0; size_t const hSize = (size_t)1 << cdict_cParams->hashLog; ZSTD_copyCDictTableIntoCCtx(cctx->blockState.matchState.hashTable, cdict->matchState.hashTable, hSize, cdict_cParams); /* Do not copy cdict's chainTable if cctx has parameters such that it would not use chainTable */ if (ZSTD_allocateChainTable(cctx->appliedParams.cParams.strategy, cctx->appliedParams.useRowMatchFinder, 0 /* forDDSDict */)) { ZSTD_copyCDictTableIntoCCtx(cctx->blockState.matchState.chainTable, cdict->matchState.chainTable, chainSize, cdict_cParams); } /* copy tag table */ if (ZSTD_rowMatchFinderUsed(cdict_cParams->strategy, cdict->useRowMatchFinder)) { size_t const tagTableSize = hSize; ZSTD_memcpy(cctx->blockState.matchState.tagTable, cdict->matchState.tagTable, tagTableSize); cctx->blockState.matchState.hashSalt = cdict->matchState.hashSalt; } } /* Zero the hashTable3, since the cdict never fills it */ assert(cctx->blockState.matchState.hashLog3 <= 31); { U32 const h3log = cctx->blockState.matchState.hashLog3; size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0; assert(cdict->matchState.hashLog3 == 0); ZSTD_memset(cctx->blockState.matchState.hashTable3, 0, h3Size * sizeof(U32)); } ZSTD_cwksp_mark_tables_clean(&cctx->workspace); /* copy dictionary offsets */ { ZSTD_MatchState_t const* srcMatchState = &cdict->matchState; ZSTD_MatchState_t* dstMatchState = &cctx->blockState.matchState; dstMatchState->window = srcMatchState->window; dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; } cctx->dictID = cdict->dictID; cctx->dictContentSize = cdict->dictContentSize; /* copy block state */ ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState)); return 0; } /* We have a choice between copying the dictionary context into the working * context, or referencing the dictionary context from the working context * in-place. We decide here which strategy to use. */ static size_t ZSTD_resetCCtx_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, const ZSTD_CCtx_params* params, U64 pledgedSrcSize, ZSTD_buffered_policy_e zbuff) { DEBUGLOG(4, "ZSTD_resetCCtx_usingCDict (pledgedSrcSize=%u)", (unsigned)pledgedSrcSize); if (ZSTD_shouldAttachDict(cdict, params, pledgedSrcSize)) { return ZSTD_resetCCtx_byAttachingCDict( cctx, cdict, *params, pledgedSrcSize, zbuff); } else { return ZSTD_resetCCtx_byCopyingCDict( cctx, cdict, *params, pledgedSrcSize, zbuff); } } /*! ZSTD_copyCCtx_internal() : * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). * The "context", in this case, refers to the hash and chain tables, * entropy tables, and dictionary references. * `windowLog` value is enforced if != 0, otherwise value is copied from srcCCtx. * @return : 0, or an error code */ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, ZSTD_frameParameters fParams, U64 pledgedSrcSize, ZSTD_buffered_policy_e zbuff) { RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong, "Can't copy a ctx that's not in init stage."); DEBUGLOG(5, "ZSTD_copyCCtx_internal"); ZSTD_memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem)); { ZSTD_CCtx_params params = dstCCtx->requestedParams; /* Copy only compression parameters related to tables. */ params.cParams = srcCCtx->appliedParams.cParams; assert(srcCCtx->appliedParams.useRowMatchFinder != ZSTD_ps_auto); assert(srcCCtx->appliedParams.postBlockSplitter != ZSTD_ps_auto); assert(srcCCtx->appliedParams.ldmParams.enableLdm != ZSTD_ps_auto); params.useRowMatchFinder = srcCCtx->appliedParams.useRowMatchFinder; params.postBlockSplitter = srcCCtx->appliedParams.postBlockSplitter; params.ldmParams = srcCCtx->appliedParams.ldmParams; params.fParams = fParams; params.maxBlockSize = srcCCtx->appliedParams.maxBlockSize; ZSTD_resetCCtx_internal(dstCCtx, ¶ms, pledgedSrcSize, /* loadedDictSize */ 0, ZSTDcrp_leaveDirty, zbuff); assert(dstCCtx->appliedParams.cParams.windowLog == srcCCtx->appliedParams.cParams.windowLog); assert(dstCCtx->appliedParams.cParams.strategy == srcCCtx->appliedParams.cParams.strategy); assert(dstCCtx->appliedParams.cParams.hashLog == srcCCtx->appliedParams.cParams.hashLog); assert(dstCCtx->appliedParams.cParams.chainLog == srcCCtx->appliedParams.cParams.chainLog); assert(dstCCtx->blockState.matchState.hashLog3 == srcCCtx->blockState.matchState.hashLog3); } ZSTD_cwksp_mark_tables_dirty(&dstCCtx->workspace); /* copy tables */ { size_t const chainSize = ZSTD_allocateChainTable(srcCCtx->appliedParams.cParams.strategy, srcCCtx->appliedParams.useRowMatchFinder, 0 /* forDDSDict */) ? ((size_t)1 << srcCCtx->appliedParams.cParams.chainLog) : 0; size_t const hSize = (size_t)1 << srcCCtx->appliedParams.cParams.hashLog; U32 const h3log = srcCCtx->blockState.matchState.hashLog3; size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0; ZSTD_memcpy(dstCCtx->blockState.matchState.hashTable, srcCCtx->blockState.matchState.hashTable, hSize * sizeof(U32)); ZSTD_memcpy(dstCCtx->blockState.matchState.chainTable, srcCCtx->blockState.matchState.chainTable, chainSize * sizeof(U32)); ZSTD_memcpy(dstCCtx->blockState.matchState.hashTable3, srcCCtx->blockState.matchState.hashTable3, h3Size * sizeof(U32)); } ZSTD_cwksp_mark_tables_clean(&dstCCtx->workspace); /* copy dictionary offsets */ { const ZSTD_MatchState_t* srcMatchState = &srcCCtx->blockState.matchState; ZSTD_MatchState_t* dstMatchState = &dstCCtx->blockState.matchState; dstMatchState->window = srcMatchState->window; dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; } dstCCtx->dictID = srcCCtx->dictID; dstCCtx->dictContentSize = srcCCtx->dictContentSize; /* copy block state */ ZSTD_memcpy(dstCCtx->blockState.prevCBlock, srcCCtx->blockState.prevCBlock, sizeof(*srcCCtx->blockState.prevCBlock)); return 0; } /*! ZSTD_copyCCtx() : * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). * pledgedSrcSize==0 means "unknown". * @return : 0, or an error code */ size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize) { ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; ZSTD_buffered_policy_e const zbuff = srcCCtx->bufferedPolicy; ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1); if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN; fParams.contentSizeFlag = (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN); return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, fParams, pledgedSrcSize, zbuff); } #define ZSTD_ROWSIZE 16 /*! ZSTD_reduceTable() : * reduce table indexes by `reducerValue`, or squash to zero. * PreserveMark preserves "unsorted mark" for btlazy2 strategy. * It must be set to a clear 0/1 value, to remove branch during inlining. * Presume table size is a multiple of ZSTD_ROWSIZE * to help auto-vectorization */ FORCE_INLINE_TEMPLATE void ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerValue, int const preserveMark) { int const nbRows = (int)size / ZSTD_ROWSIZE; int cellNb = 0; int rowNb; /* Protect special index values < ZSTD_WINDOW_START_INDEX. */ U32 const reducerThreshold = reducerValue + ZSTD_WINDOW_START_INDEX; assert((size & (ZSTD_ROWSIZE-1)) == 0); /* multiple of ZSTD_ROWSIZE */ assert(size < (1U<<31)); /* can be cast to int */ for (rowNb=0 ; rowNb < nbRows ; rowNb++) { int column; for (column=0; column<ZSTD_ROWSIZE; column++) { U32 newVal; if (preserveMark && table[cellNb] == ZSTD_DUBT_UNSORTED_MARK) { /* This write is pointless, but is required(?) for the compiler * to auto-vectorize the loop. */ newVal = ZSTD_DUBT_UNSORTED_MARK; } else if (table[cellNb] < reducerThreshold) { newVal = 0; } else { newVal = table[cellNb] - reducerValue; } table[cellNb] = newVal; cellNb++; } } } static void ZSTD_reduceTable(U32* const table, U32 const size, U32 const reducerValue) { ZSTD_reduceTable_internal(table, size, reducerValue, 0); } static void ZSTD_reduceTable_btlazy2(U32* const table, U32 const size, U32 const reducerValue) { ZSTD_reduceTable_internal(table, size, reducerValue, 1); } /*! ZSTD_reduceIndex() : * rescale all indexes to avoid future overflow (indexes are U32) */ static void ZSTD_reduceIndex (ZSTD_MatchState_t* ms, ZSTD_CCtx_params const* params, const U32 reducerValue) { { U32 const hSize = (U32)1 << params->cParams.hashLog; ZSTD_reduceTable(ms->hashTable, hSize, reducerValue); } if (ZSTD_allocateChainTable(params->cParams.strategy, params->useRowMatchFinder, (U32)ms->dedicatedDictSearch)) { U32 const chainSize = (U32)1 << params->cParams.chainLog; if (params->cParams.strategy == ZSTD_btlazy2) ZSTD_reduceTable_btlazy2(ms->chainTable, chainSize, reducerValue); else ZSTD_reduceTable(ms->chainTable, chainSize, reducerValue); } if (ms->hashLog3) { U32 const h3Size = (U32)1 << ms->hashLog3; ZSTD_reduceTable(ms->hashTable3, h3Size, reducerValue); } } /*-******************************************************* * Block entropic compression *********************************************************/ /* See doc/zstd_compression_format.md for detailed format description */ int ZSTD_seqToCodes(const SeqStore_t* seqStorePtr) { const SeqDef* const sequences = seqStorePtr->sequencesStart; BYTE* const llCodeTable = seqStorePtr->llCode; BYTE* const ofCodeTable = seqStorePtr->ofCode; BYTE* const mlCodeTable = seqStorePtr->mlCode; U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); U32 u; int longOffsets = 0; assert(nbSeq <= seqStorePtr->maxNbSeq); for (u=0; u<nbSeq; u++) { U32 const llv = sequences[u].litLength; U32 const ofCode = ZSTD_highbit32(sequences[u].offBase); U32 const mlv = sequences[u].mlBase; llCodeTable[u] = (BYTE)ZSTD_LLcode(llv); ofCodeTable[u] = (BYTE)ofCode; mlCodeTable[u] = (BYTE)ZSTD_MLcode(mlv); assert(!(MEM_64bits() && ofCode >= STREAM_ACCUMULATOR_MIN)); if (MEM_32bits() && ofCode >= STREAM_ACCUMULATOR_MIN) longOffsets = 1; } if (seqStorePtr->longLengthType==ZSTD_llt_literalLength) llCodeTable[seqStorePtr->longLengthPos] = MaxLL; if (seqStorePtr->longLengthType==ZSTD_llt_matchLength) mlCodeTable[seqStorePtr->longLengthPos] = MaxML; return longOffsets; } /* ZSTD_useTargetCBlockSize(): * Returns if target compressed block size param is being used. * If used, compression will do best effort to make a compressed block size to be around targetCBlockSize. * Returns 1 if true, 0 otherwise. */ static int ZSTD_useTargetCBlockSize(const ZSTD_CCtx_params* cctxParams) { DEBUGLOG(5, "ZSTD_useTargetCBlockSize (targetCBlockSize=%zu)", cctxParams->targetCBlockSize); return (cctxParams->targetCBlockSize != 0); } /* ZSTD_blockSplitterEnabled(): * Returns if block splitting param is being used * If used, compression will do best effort to split a block in order to improve compression ratio. * At the time this function is called, the parameter must be finalized. * Returns 1 if true, 0 otherwise. */ static int ZSTD_blockSplitterEnabled(ZSTD_CCtx_params* cctxParams) { DEBUGLOG(5, "ZSTD_blockSplitterEnabled (postBlockSplitter=%d)", cctxParams->postBlockSplitter); assert(cctxParams->postBlockSplitter != ZSTD_ps_auto); return (cctxParams->postBlockSplitter == ZSTD_ps_enable); } /* Type returned by ZSTD_buildSequencesStatistics containing finalized symbol encoding types * and size of the sequences statistics */ typedef struct { U32 LLtype; U32 Offtype; U32 MLtype; size_t size; size_t lastCountSize; /* Accounts for bug in 1.3.4. More detail in ZSTD_entropyCompressSeqStore_internal() */ int longOffsets; } ZSTD_symbolEncodingTypeStats_t; /* ZSTD_buildSequencesStatistics(): * Returns a ZSTD_symbolEncodingTypeStats_t, or a zstd error code in the `size` field. * Modifies `nextEntropy` to have the appropriate values as a side effect. * nbSeq must be greater than 0. * * entropyWkspSize must be of size at least ENTROPY_WORKSPACE_SIZE - (MaxSeq + 1)*sizeof(U32) */ static ZSTD_symbolEncodingTypeStats_t ZSTD_buildSequencesStatistics( const SeqStore_t* seqStorePtr, size_t nbSeq, const ZSTD_fseCTables_t* prevEntropy, ZSTD_fseCTables_t* nextEntropy, BYTE* dst, const BYTE* const dstEnd, ZSTD_strategy strategy, unsigned* countWorkspace, void* entropyWorkspace, size_t entropyWkspSize) { BYTE* const ostart = dst; const BYTE* const oend = dstEnd; BYTE* op = ostart; FSE_CTable* CTable_LitLength = nextEntropy->litlengthCTable; FSE_CTable* CTable_OffsetBits = nextEntropy->offcodeCTable; FSE_CTable* CTable_MatchLength = nextEntropy->matchlengthCTable; const BYTE* const ofCodeTable = seqStorePtr->ofCode; const BYTE* const llCodeTable = seqStorePtr->llCode; const BYTE* const mlCodeTable = seqStorePtr->mlCode; ZSTD_symbolEncodingTypeStats_t stats; stats.lastCountSize = 0; /* convert length/distances into codes */ stats.longOffsets = ZSTD_seqToCodes(seqStorePtr); assert(op <= oend); assert(nbSeq != 0); /* ZSTD_selectEncodingType() divides by nbSeq */ /* build CTable for Literal Lengths */ { unsigned max = MaxLL; size_t const mostFrequent = HIST_countFast_wksp(countWorkspace, &max, llCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */ DEBUGLOG(5, "Building LL table"); nextEntropy->litlength_repeatMode = prevEntropy->litlength_repeatMode; stats.LLtype = ZSTD_selectEncodingType(&nextEntropy->litlength_repeatMode, countWorkspace, max, mostFrequent, nbSeq, LLFSELog, prevEntropy->litlengthCTable, LL_defaultNorm, LL_defaultNormLog, ZSTD_defaultAllowed, strategy); assert(set_basic < set_compressed && set_rle < set_compressed); assert(!(stats.LLtype < set_compressed && nextEntropy->litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ { size_t const countSize = ZSTD_buildCTable( op, (size_t)(oend - op), CTable_LitLength, LLFSELog, (SymbolEncodingType_e)stats.LLtype, countWorkspace, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL, prevEntropy->litlengthCTable, sizeof(prevEntropy->litlengthCTable), entropyWorkspace, entropyWkspSize); if (ZSTD_isError(countSize)) { DEBUGLOG(3, "ZSTD_buildCTable for LitLens failed"); stats.size = countSize; return stats; } if (stats.LLtype == set_compressed) stats.lastCountSize = countSize; op += countSize; assert(op <= oend); } } /* build CTable for Offsets */ { unsigned max = MaxOff; size_t const mostFrequent = HIST_countFast_wksp( countWorkspace, &max, ofCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */ /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */ ZSTD_DefaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed; DEBUGLOG(5, "Building OF table"); nextEntropy->offcode_repeatMode = prevEntropy->offcode_repeatMode; stats.Offtype = ZSTD_selectEncodingType(&nextEntropy->offcode_repeatMode, countWorkspace, max, mostFrequent, nbSeq, OffFSELog, prevEntropy->offcodeCTable, OF_defaultNorm, OF_defaultNormLog, defaultPolicy, strategy); assert(!(stats.Offtype < set_compressed && nextEntropy->offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */ { size_t const countSize = ZSTD_buildCTable( op, (size_t)(oend - op), CTable_OffsetBits, OffFSELog, (SymbolEncodingType_e)stats.Offtype, countWorkspace, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, prevEntropy->offcodeCTable, sizeof(prevEntropy->offcodeCTable), entropyWorkspace, entropyWkspSize); if (ZSTD_isError(countSize)) { DEBUGLOG(3, "ZSTD_buildCTable for Offsets failed"); stats.size = countSize; return stats; } if (stats.Offtype == set_compressed) stats.lastCountSize = countSize; op += countSize; assert(op <= oend); } } /* build CTable for MatchLengths */ { unsigned max = MaxML; size_t const mostFrequent = HIST_countFast_wksp( countWorkspace, &max, mlCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */ DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op)); nextEntropy->matchlength_repeatMode = prevEntropy->matchlength_repeatMode; stats.MLtype = ZSTD_selectEncodingType(&nextEntropy->matchlength_repeatMode, countWorkspace, max, mostFrequent, nbSeq, MLFSELog, prevEntropy->matchlengthCTable, ML_defaultNorm, ML_defaultNormLog, ZSTD_defaultAllowed, strategy); assert(!(stats.MLtype < set_compressed && nextEntropy->matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ { size_t const countSize = ZSTD_buildCTable( op, (size_t)(oend - op), CTable_MatchLength, MLFSELog, (SymbolEncodingType_e)stats.MLtype, countWorkspace, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML, prevEntropy->matchlengthCTable, sizeof(prevEntropy->matchlengthCTable), entropyWorkspace, entropyWkspSize); if (ZSTD_isError(countSize)) { DEBUGLOG(3, "ZSTD_buildCTable for MatchLengths failed"); stats.size = countSize; return stats; } if (stats.MLtype == set_compressed) stats.lastCountSize = countSize; op += countSize; assert(op <= oend); } } stats.size = (size_t)(op-ostart); return stats; } /* ZSTD_entropyCompressSeqStore_internal(): * compresses both literals and sequences * Returns compressed size of block, or a zstd error. */ #define SUSPECT_UNCOMPRESSIBLE_LITERAL_RATIO 20 MEM_STATIC size_t ZSTD_entropyCompressSeqStore_internal( void* dst, size_t dstCapacity, const void* literals, size_t litSize, const SeqStore_t* seqStorePtr, const ZSTD_entropyCTables_t* prevEntropy, ZSTD_entropyCTables_t* nextEntropy, const ZSTD_CCtx_params* cctxParams, void* entropyWorkspace, size_t entropyWkspSize, const int bmi2) { ZSTD_strategy const strategy = cctxParams->cParams.strategy; unsigned* count = (unsigned*)entropyWorkspace; FSE_CTable* CTable_LitLength = nextEntropy->fse.litlengthCTable; FSE_CTable* CTable_OffsetBits = nextEntropy->fse.offcodeCTable; FSE_CTable* CTable_MatchLength = nextEntropy->fse.matchlengthCTable; const SeqDef* const sequences = seqStorePtr->sequencesStart; const size_t nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart); const BYTE* const ofCodeTable = seqStorePtr->ofCode; const BYTE* const llCodeTable = seqStorePtr->llCode; const BYTE* const mlCodeTable = seqStorePtr->mlCode; BYTE* const ostart = (BYTE*)dst; BYTE* const oend = ostart + dstCapacity; BYTE* op = ostart; size_t lastCountSize; int longOffsets = 0; entropyWorkspace = count + (MaxSeq + 1); entropyWkspSize -= (MaxSeq + 1) * sizeof(*count); DEBUGLOG(5, "ZSTD_entropyCompressSeqStore_internal (nbSeq=%zu, dstCapacity=%zu)", nbSeq, dstCapacity); ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog))); assert(entropyWkspSize >= HUF_WORKSPACE_SIZE); /* Compress literals */ { size_t const numSequences = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart); /* Base suspicion of uncompressibility on ratio of literals to sequences */ int const suspectUncompressible = (numSequences == 0) || (litSize / numSequences >= SUSPECT_UNCOMPRESSIBLE_LITERAL_RATIO); size_t const cSize = ZSTD_compressLiterals( op, dstCapacity, literals, litSize, entropyWorkspace, entropyWkspSize, &prevEntropy->huf, &nextEntropy->huf, cctxParams->cParams.strategy, ZSTD_literalsCompressionIsDisabled(cctxParams), suspectUncompressible, bmi2); FORWARD_IF_ERROR(cSize, "ZSTD_compressLiterals failed"); assert(cSize <= dstCapacity); op += cSize; } /* Sequences Header */ RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/, dstSize_tooSmall, "Can't fit seq hdr in output buf!"); if (nbSeq < 128) { *op++ = (BYTE)nbSeq; } else if (nbSeq < LONGNBSEQ) { op[0] = (BYTE)((nbSeq>>8) + 0x80); op[1] = (BYTE)nbSeq; op+=2; } else { op[0]=0xFF; MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)); op+=3; } assert(op <= oend); if (nbSeq==0) { /* Copy the old tables over as if we repeated them */ ZSTD_memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse)); return (size_t)(op - ostart); } { BYTE* const seqHead = op++; /* build stats for sequences */ const ZSTD_symbolEncodingTypeStats_t stats = ZSTD_buildSequencesStatistics(seqStorePtr, nbSeq, &prevEntropy->fse, &nextEntropy->fse, op, oend, strategy, count, entropyWorkspace, entropyWkspSize); FORWARD_IF_ERROR(stats.size, "ZSTD_buildSequencesStatistics failed!"); *seqHead = (BYTE)((stats.LLtype<<6) + (stats.Offtype<<4) + (stats.MLtype<<2)); lastCountSize = stats.lastCountSize; op += stats.size; longOffsets = stats.longOffsets; } { size_t const bitstreamSize = ZSTD_encodeSequences( op, (size_t)(oend - op), CTable_MatchLength, mlCodeTable, CTable_OffsetBits, ofCodeTable, CTable_LitLength, llCodeTable, sequences, nbSeq, longOffsets, bmi2); FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed"); op += bitstreamSize; assert(op <= oend); /* zstd versions <= 1.3.4 mistakenly report corruption when * FSE_readNCount() receives a buffer < 4 bytes. * Fixed by https://github.com/facebook/zstd/pull/1146. * This can happen when the last set_compressed table present is 2 * bytes and the bitstream is only one byte. * In this exceedingly rare case, we will simply emit an uncompressed * block, since it isn't worth optimizing. */ if (lastCountSize && (lastCountSize + bitstreamSize) < 4) { /* lastCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */ assert(lastCountSize + bitstreamSize == 3); DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by " "emitting an uncompressed block."); return 0; } } DEBUGLOG(5, "compressed block size : %u", (unsigned)(op - ostart)); return (size_t)(op - ostart); } static size_t ZSTD_entropyCompressSeqStore_wExtLitBuffer( void* dst, size_t dstCapacity, const void* literals, size_t litSize, size_t blockSize, const SeqStore_t* seqStorePtr, const ZSTD_entropyCTables_t* prevEntropy, ZSTD_entropyCTables_t* nextEntropy, const ZSTD_CCtx_params* cctxParams, void* entropyWorkspace, size_t entropyWkspSize, int bmi2) { size_t const cSize = ZSTD_entropyCompressSeqStore_internal( dst, dstCapacity, literals, litSize, seqStorePtr, prevEntropy, nextEntropy, cctxParams, entropyWorkspace, entropyWkspSize, bmi2); if (cSize == 0) return 0; /* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block. * Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block. */ if ((cSize == ERROR(dstSize_tooSmall)) & (blockSize <= dstCapacity)) { DEBUGLOG(4, "not enough dstCapacity (%zu) for ZSTD_entropyCompressSeqStore_internal()=> do not compress block", dstCapacity); return 0; /* block not compressed */ } FORWARD_IF_ERROR(cSize, "ZSTD_entropyCompressSeqStore_internal failed"); /* Check compressibility */ { size_t const maxCSize = blockSize - ZSTD_minGain(blockSize, cctxParams->cParams.strategy); if (cSize >= maxCSize) return 0; /* block not compressed */ } DEBUGLOG(5, "ZSTD_entropyCompressSeqStore() cSize: %zu", cSize); /* libzstd decoder before > v1.5.4 is not compatible with compressed blocks of size ZSTD_BLOCKSIZE_MAX exactly. * This restriction is indirectly already fulfilled by respecting ZSTD_minGain() condition above. */ assert(cSize < ZSTD_BLOCKSIZE_MAX); return cSize; } static size_t ZSTD_entropyCompressSeqStore( const SeqStore_t* seqStorePtr, const ZSTD_entropyCTables_t* prevEntropy, ZSTD_entropyCTables_t* nextEntropy, const ZSTD_CCtx_params* cctxParams, void* dst, size_t dstCapacity, size_t srcSize, void* entropyWorkspace, size_t entropyWkspSize, int bmi2) { return ZSTD_entropyCompressSeqStore_wExtLitBuffer( dst, dstCapacity, seqStorePtr->litStart, (size_t)(seqStorePtr->lit - seqStorePtr->litStart), srcSize, seqStorePtr, prevEntropy, nextEntropy, cctxParams, entropyWorkspace, entropyWkspSize, bmi2); } /* ZSTD_selectBlockCompressor() : * Not static, but internal use only (used by long distance matcher) * assumption : strat is a valid strategy */ ZSTD_BlockCompressor_f ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_ParamSwitch_e useRowMatchFinder, ZSTD_dictMode_e dictMode) { static const ZSTD_BlockCompressor_f blockCompressor[4][ZSTD_STRATEGY_MAX+1] = { { ZSTD_compressBlock_fast /* default for 0 */, ZSTD_compressBlock_fast, ZSTD_COMPRESSBLOCK_DOUBLEFAST, ZSTD_COMPRESSBLOCK_GREEDY, ZSTD_COMPRESSBLOCK_LAZY, ZSTD_COMPRESSBLOCK_LAZY2, ZSTD_COMPRESSBLOCK_BTLAZY2, ZSTD_COMPRESSBLOCK_BTOPT, ZSTD_COMPRESSBLOCK_BTULTRA, ZSTD_COMPRESSBLOCK_BTULTRA2 }, { ZSTD_compressBlock_fast_extDict /* default for 0 */, ZSTD_compressBlock_fast_extDict, ZSTD_COMPRESSBLOCK_DOUBLEFAST_EXTDICT, ZSTD_COMPRESSBLOCK_GREEDY_EXTDICT, ZSTD_COMPRESSBLOCK_LAZY_EXTDICT, ZSTD_COMPRESSBLOCK_LAZY2_EXTDICT, ZSTD_COMPRESSBLOCK_BTLAZY2_EXTDICT, ZSTD_COMPRESSBLOCK_BTOPT_EXTDICT, ZSTD_COMPRESSBLOCK_BTULTRA_EXTDICT, ZSTD_COMPRESSBLOCK_BTULTRA_EXTDICT }, { ZSTD_compressBlock_fast_dictMatchState /* default for 0 */, ZSTD_compressBlock_fast_dictMatchState, ZSTD_COMPRESSBLOCK_DOUBLEFAST_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_GREEDY_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_LAZY_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_LAZY2_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_BTLAZY2_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_BTOPT_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_BTULTRA_DICTMATCHSTATE, ZSTD_COMPRESSBLOCK_BTULTRA_DICTMATCHSTATE }, { NULL /* default for 0 */, NULL, NULL, ZSTD_COMPRESSBLOCK_GREEDY_DEDICATEDDICTSEARCH, ZSTD_COMPRESSBLOCK_LAZY_DEDICATEDDICTSEARCH, ZSTD_COMPRESSBLOCK_LAZY2_DEDICATEDDICTSEARCH, NULL, NULL, NULL, NULL } }; ZSTD_BlockCompressor_f selectedCompressor; ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1); assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, (int)strat)); DEBUGLOG(5, "Selected block compressor: dictMode=%d strat=%d rowMatchfinder=%d", (int)dictMode, (int)strat, (int)useRowMatchFinder); if (ZSTD_rowMatchFinderUsed(strat, useRowMatchFinder)) { static const ZSTD_BlockCompressor_f rowBasedBlockCompressors[4][3] = { { ZSTD_COMPRESSBLOCK_GREEDY_ROW, ZSTD_COMPRESSBLOCK_LAZY_ROW, ZSTD_COMPRESSBLOCK_LAZY2_ROW }, { ZSTD_COMPRESSBLOCK_GREEDY_EXTDICT_ROW, ZSTD_COMPRESSBLOCK_LAZY_EXTDICT_ROW, ZSTD_COMPRESSBLOCK_LAZY2_EXTDICT_ROW }, { ZSTD_COMPRESSBLOCK_GREEDY_DICTMATCHSTATE_ROW, ZSTD_COMPRESSBLOCK_LAZY_DICTMATCHSTATE_ROW, ZSTD_COMPRESSBLOCK_LAZY2_DICTMATCHSTATE_ROW }, { ZSTD_COMPRESSBLOCK_GREEDY_DEDICATEDDICTSEARCH_ROW, ZSTD_COMPRESSBLOCK_LAZY_DEDICATEDDICTSEARCH_ROW, ZSTD_COMPRESSBLOCK_LAZY2_DEDICATEDDICTSEARCH_ROW } }; DEBUGLOG(5, "Selecting a row-based matchfinder"); assert(useRowMatchFinder != ZSTD_ps_auto); selectedCompressor = rowBasedBlockCompressors[(int)dictMode][(int)strat - (int)ZSTD_greedy]; } else { selectedCompressor = blockCompressor[(int)dictMode][(int)strat]; } assert(selectedCompressor != NULL); return selectedCompressor; } static void ZSTD_storeLastLiterals(SeqStore_t* seqStorePtr, const BYTE* anchor, size_t lastLLSize) { ZSTD_memcpy(seqStorePtr->lit, anchor, lastLLSize); seqStorePtr->lit += lastLLSize; } void ZSTD_resetSeqStore(SeqStore_t* ssPtr) { ssPtr->lit = ssPtr->litStart; ssPtr->sequences = ssPtr->sequencesStart; ssPtr->longLengthType = ZSTD_llt_none; } /* ZSTD_postProcessSequenceProducerResult() : * Validates and post-processes sequences obtained through the external matchfinder API: * - Checks whether nbExternalSeqs represents an error condition. * - Appends a block delimiter to outSeqs if one is not already present. * See zstd.h for context regarding block delimiters. * Returns the number of sequences after post-processing, or an error code. */ static size_t ZSTD_postProcessSequenceProducerResult( ZSTD_Sequence* outSeqs, size_t nbExternalSeqs, size_t outSeqsCapacity, size_t srcSize ) { RETURN_ERROR_IF( nbExternalSeqs > outSeqsCapacity, sequenceProducer_failed, "External sequence producer returned error code %lu", (unsigned long)nbExternalSeqs ); RETURN_ERROR_IF( nbExternalSeqs == 0 && srcSize > 0, sequenceProducer_failed, "Got zero sequences from external sequence producer for a non-empty src buffer!" ); if (srcSize == 0) { ZSTD_memset(&outSeqs[0], 0, sizeof(ZSTD_Sequence)); return 1; } { ZSTD_Sequence const lastSeq = outSeqs[nbExternalSeqs - 1]; /* We can return early if lastSeq is already a block delimiter. */ if (lastSeq.offset == 0 && lastSeq.matchLength == 0) { return nbExternalSeqs; } /* This error condition is only possible if the external matchfinder * produced an invalid parse, by definition of ZSTD_sequenceBound(). */ RETURN_ERROR_IF( nbExternalSeqs == outSeqsCapacity, sequenceProducer_failed, "nbExternalSeqs == outSeqsCapacity but lastSeq is not a block delimiter!" ); /* lastSeq is not a block delimiter, so we need to append one. */ ZSTD_memset(&outSeqs[nbExternalSeqs], 0, sizeof(ZSTD_Sequence)); return nbExternalSeqs + 1; } } /* ZSTD_fastSequenceLengthSum() : * Returns sum(litLen) + sum(matchLen) + lastLits for *seqBuf*. * Similar to another function in zstd_compress.c (determine_blockSize), * except it doesn't check for a block delimiter to end summation. * Removing the early exit allows the compiler to auto-vectorize (https://godbolt.org/z/cY1cajz9P). * This function can be deleted and replaced by determine_blockSize after we resolve issue #3456. */ static size_t ZSTD_fastSequenceLengthSum(ZSTD_Sequence const* seqBuf, size_t seqBufSize) { size_t matchLenSum, litLenSum, i; matchLenSum = 0; litLenSum = 0; for (i = 0; i < seqBufSize; i++) { litLenSum += seqBuf[i].litLength; matchLenSum += seqBuf[i].matchLength; } return litLenSum + matchLenSum; } /* * Function to validate sequences produced by a block compressor. */ static void ZSTD_validateSeqStore(const SeqStore_t* seqStore, const ZSTD_compressionParameters* cParams) { #if DEBUGLEVEL >= 1 const SeqDef* seq = seqStore->sequencesStart; const SeqDef* const seqEnd = seqStore->sequences; size_t const matchLenLowerBound = cParams->minMatch == 3 ? 3 : 4; for (; seq < seqEnd; ++seq) { const ZSTD_SequenceLength seqLength = ZSTD_getSequenceLength(seqStore, seq); assert(seqLength.matchLength >= matchLenLowerBound); (void)seqLength; (void)matchLenLowerBound; } #else (void)seqStore; (void)cParams; #endif } static size_t ZSTD_transferSequences_wBlockDelim(ZSTD_CCtx* cctx, ZSTD_SequencePosition* seqPos, const ZSTD_Sequence* const inSeqs, size_t inSeqsSize, const void* src, size_t blockSize, ZSTD_ParamSwitch_e externalRepSearch); typedef enum { ZSTDbss_compress, ZSTDbss_noCompress } ZSTD_BuildSeqStore_e; static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize) { ZSTD_MatchState_t* const ms = &zc->blockState.matchState; DEBUGLOG(5, "ZSTD_buildSeqStore (srcSize=%zu)", srcSize); assert(srcSize <= ZSTD_BLOCKSIZE_MAX); /* Assert that we have correctly flushed the ctx params into the ms's copy */ ZSTD_assertEqualCParams(zc->appliedParams.cParams, ms->cParams); /* TODO: See 3090. We reduced MIN_CBLOCK_SIZE from 3 to 2 so to compensate we are adding * additional 1. We need to revisit and change this logic to be more consistent */ if (srcSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1+1) { if (zc->appliedParams.cParams.strategy >= ZSTD_btopt) { ZSTD_ldm_skipRawSeqStoreBytes(&zc->externSeqStore, srcSize); } else { ZSTD_ldm_skipSequences(&zc->externSeqStore, srcSize, zc->appliedParams.cParams.minMatch); } return ZSTDbss_noCompress; /* don't even attempt compression below a certain srcSize */ } ZSTD_resetSeqStore(&(zc->seqStore)); /* required for optimal parser to read stats from dictionary */ ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy; /* tell the optimal parser how we expect to compress literals */ ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode; /* a gap between an attached dict and the current window is not safe, * they must remain adjacent, * and when that stops being the case, the dict must be unset */ assert(ms->dictMatchState == NULL || ms->loadedDictEnd == ms->window.dictLimit); /* limited update after a very long match */ { const BYTE* const base = ms->window.base; const BYTE* const istart = (const BYTE*)src; const U32 curr = (U32)(istart-base); if (sizeof(ptrdiff_t)==8) assert(istart - base < (ptrdiff_t)(U32)(-1)); /* ensure no overflow */ if (curr > ms->nextToUpdate + 384) ms->nextToUpdate = curr - MIN(192, (U32)(curr - ms->nextToUpdate - 384)); } /* select and store sequences */ { ZSTD_dictMode_e const dictMode = ZSTD_matchState_dictMode(ms); size_t lastLLSize; { int i; for (i = 0; i < ZSTD_REP_NUM; ++i) zc->blockState.nextCBlock->rep[i] = zc->blockState.prevCBlock->rep[i]; } if (zc->externSeqStore.pos < zc->externSeqStore.size) { assert(zc->appliedParams.ldmParams.enableLdm == ZSTD_ps_disable); /* External matchfinder + LDM is technically possible, just not implemented yet. * We need to revisit soon and implement it. */ RETURN_ERROR_IF( ZSTD_hasExtSeqProd(&zc->appliedParams), parameter_combination_unsupported, "Long-distance matching with external sequence producer enabled is not currently supported." ); /* Updates ldmSeqStore.pos */ lastLLSize = ZSTD_ldm_blockCompress(&zc->externSeqStore, ms, &zc->seqStore, zc->blockState.nextCBlock->rep, zc->appliedParams.useRowMatchFinder, src, srcSize); assert(zc->externSeqStore.pos <= zc->externSeqStore.size); } else if (zc->appliedParams.ldmParams.enableLdm == ZSTD_ps_enable) { RawSeqStore_t ldmSeqStore = kNullRawSeqStore; /* External matchfinder + LDM is technically possible, just not implemented yet. * We need to revisit soon and implement it. */ RETURN_ERROR_IF( ZSTD_hasExtSeqProd(&zc->appliedParams), parameter_combination_unsupported, "Long-distance matching with external sequence producer enabled is not currently supported." ); ldmSeqStore.seq = zc->ldmSequences; ldmSeqStore.capacity = zc->maxNbLdmSequences; /* Updates ldmSeqStore.size */ FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore, &zc->appliedParams.ldmParams, src, srcSize), ""); /* Updates ldmSeqStore.pos */ lastLLSize = ZSTD_ldm_blockCompress(&ldmSeqStore, ms, &zc->seqStore, zc->blockState.nextCBlock->rep, zc->appliedParams.useRowMatchFinder, src, srcSize); assert(ldmSeqStore.pos == ldmSeqStore.size); } else if (ZSTD_hasExtSeqProd(&zc->appliedParams)) { assert( zc->extSeqBufCapacity >= ZSTD_sequenceBound(srcSize) ); assert(zc->appliedParams.extSeqProdFunc != NULL); { U32 const windowSize = (U32)1 << zc->appliedParams.cParams.windowLog; size_t const nbExternalSeqs = (zc->appliedParams.extSeqProdFunc)( zc->appliedParams.extSeqProdState, zc->extSeqBuf, zc->extSeqBufCapacity, src, srcSize, NULL, 0, /* dict and dictSize, currently not supported */ zc->appliedParams.compressionLevel, windowSize ); size_t const nbPostProcessedSeqs = ZSTD_postProcessSequenceProducerResult( zc->extSeqBuf, nbExternalSeqs, zc->extSeqBufCapacity, srcSize ); /* Return early if there is no error, since we don't need to worry about last literals */ if (!ZSTD_isError(nbPostProcessedSeqs)) { ZSTD_SequencePosition seqPos = {0,0,0}; size_t const seqLenSum = ZSTD_fastSequenceLengthSum(zc->extSeqBuf, nbPostProcessedSeqs); RETURN_ERROR_IF(seqLenSum > srcSize, externalSequences_invalid, "External sequences imply too large a block!"); FORWARD_IF_ERROR( ZSTD_transferSequences_wBlockDelim( zc, &seqPos, zc->extSeqBuf, nbPostProcessedSeqs, src, srcSize, zc->appliedParams.searchForExternalRepcodes ), "Failed to copy external sequences to seqStore!" ); ms->ldmSeqStore = NULL; DEBUGLOG(5, "Copied %lu sequences from external sequence producer to internal seqStore.", (unsigned long)nbExternalSeqs); return ZSTDbss_compress; } /* Propagate the error if fallback is disabled */ if (!zc->appliedParams.enableMatchFinderFallback) { return nbPostProcessedSeqs; } /* Fallback to software matchfinder */ { ZSTD_BlockCompressor_f const blockCompressor = ZSTD_selectBlockCompressor( zc->appliedParams.cParams.strategy, zc->appliedParams.useRowMatchFinder, dictMode); ms->ldmSeqStore = NULL; DEBUGLOG( 5, "External sequence producer returned error code %lu. Falling back to internal parser.", (unsigned long)nbExternalSeqs ); lastLLSize = blockCompressor(ms, &zc->seqStore, zc->blockState.nextCBlock->rep, src, srcSize); } } } else { /* not long range mode and no external matchfinder */ ZSTD_BlockCompressor_f const blockCompressor = ZSTD_selectBlockCompressor( zc->appliedParams.cParams.strategy, zc->appliedParams.useRowMatchFinder, dictMode); ms->ldmSeqStore = NULL; lastLLSize = blockCompressor(ms, &zc->seqStore, zc->blockState.nextCBlock->rep, src, srcSize); } { const BYTE* const lastLiterals = (const BYTE*)src + srcSize - lastLLSize; ZSTD_storeLastLiterals(&zc->seqStore, lastLiterals, lastLLSize); } } ZSTD_validateSeqStore(&zc->seqStore, &zc->appliedParams.cParams); return ZSTDbss_compress; } static size_t ZSTD_copyBlockSequences(SeqCollector* seqCollector, const SeqStore_t* seqStore, const U32 prevRepcodes[ZSTD_REP_NUM]) { const SeqDef* inSeqs = seqStore->sequencesStart; const size_t nbInSequences = (size_t)(seqStore->sequences - inSeqs); const size_t nbInLiterals = (size_t)(seqStore->lit - seqStore->litStart); ZSTD_Sequence* outSeqs = seqCollector->seqIndex == 0 ? seqCollector->seqStart : seqCollector->seqStart + seqCollector->seqIndex; const size_t nbOutSequences = nbInSequences + 1; size_t nbOutLiterals = 0; Repcodes_t repcodes; size_t i; /* Bounds check that we have enough space for every input sequence * and the block delimiter */ assert(seqCollector->seqIndex <= seqCollector->maxSequences); RETURN_ERROR_IF( nbOutSequences > (size_t)(seqCollector->maxSequences - seqCollector->seqIndex), dstSize_tooSmall, "Not enough space to copy sequences"); ZSTD_memcpy(&repcodes, prevRepcodes, sizeof(repcodes)); for (i = 0; i < nbInSequences; ++i) { U32 rawOffset; outSeqs[i].litLength = inSeqs[i].litLength; outSeqs[i].matchLength = inSeqs[i].mlBase + MINMATCH; outSeqs[i].rep = 0; /* Handle the possible single length >= 64K * There can only be one because we add MINMATCH to every match length, * and blocks are at most 128K. */ if (i == seqStore->longLengthPos) { if (seqStore->longLengthType == ZSTD_llt_literalLength) { outSeqs[i].litLength += 0x10000; } else if (seqStore->longLengthType == ZSTD_llt_matchLength) { outSeqs[i].matchLength += 0x10000; } } /* Determine the raw offset given the offBase, which may be a repcode. */ if (OFFBASE_IS_REPCODE(inSeqs[i].offBase)) { const U32 repcode = OFFBASE_TO_REPCODE(inSeqs[i].offBase); assert(repcode > 0); outSeqs[i].rep = repcode; if (outSeqs[i].litLength != 0) { rawOffset = repcodes.rep[repcode - 1]; } else { if (repcode == 3) { assert(repcodes.rep[0] > 1); rawOffset = repcodes.rep[0] - 1; } else { rawOffset = repcodes.rep[repcode]; } } } else { rawOffset = OFFBASE_TO_OFFSET(inSeqs[i].offBase); } outSeqs[i].offset = rawOffset; /* Update repcode history for the sequence */ ZSTD_updateRep(repcodes.rep, inSeqs[i].offBase, inSeqs[i].litLength == 0); nbOutLiterals += outSeqs[i].litLength; } /* Insert last literals (if any exist) in the block as a sequence with ml == off == 0. * If there are no last literals, then we'll emit (of: 0, ml: 0, ll: 0), which is a marker * for the block boundary, according to the API. */ assert(nbInLiterals >= nbOutLiterals); { const size_t lastLLSize = nbInLiterals - nbOutLiterals; outSeqs[nbInSequences].litLength = (U32)lastLLSize; outSeqs[nbInSequences].matchLength = 0; outSeqs[nbInSequences].offset = 0; assert(nbOutSequences == nbInSequences + 1); } seqCollector->seqIndex += nbOutSequences; assert(seqCollector->seqIndex <= seqCollector->maxSequences); return 0; } size_t ZSTD_sequenceBound(size_t srcSize) { const size_t maxNbSeq = (srcSize / ZSTD_MINMATCH_MIN) + 1; const size_t maxNbDelims = (srcSize / ZSTD_BLOCKSIZE_MAX_MIN) + 1; return maxNbSeq + maxNbDelims; } size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, size_t outSeqsSize, const void* src, size_t srcSize) { const size_t dstCapacity = ZSTD_compressBound(srcSize); void* dst; /* Make C90 happy. */ SeqCollector seqCollector; { int targetCBlockSize; FORWARD_IF_ERROR(ZSTD_CCtx_getParameter(zc, ZSTD_c_targetCBlockSize, &targetCBlockSize), ""); RETURN_ERROR_IF(targetCBlockSize != 0, parameter_unsupported, "targetCBlockSize != 0"); } { int nbWorkers; FORWARD_IF_ERROR(ZSTD_CCtx_getParameter(zc, ZSTD_c_nbWorkers, &nbWorkers), ""); RETURN_ERROR_IF(nbWorkers != 0, parameter_unsupported, "nbWorkers != 0"); } dst = ZSTD_customMalloc(dstCapacity, ZSTD_defaultCMem); RETURN_ERROR_IF(dst == NULL, memory_allocation, "NULL pointer!"); seqCollector.collectSequences = 1; seqCollector.seqStart = outSeqs; seqCollector.seqIndex = 0; seqCollector.maxSequences = outSeqsSize; zc->seqCollector = seqCollector; { const size_t ret = ZSTD_compress2(zc, dst, dstCapacity, src, srcSize); ZSTD_customFree(dst, ZSTD_defaultCMem); FORWARD_IF_ERROR(ret, "ZSTD_compress2 failed"); } assert(zc->seqCollector.seqIndex <= ZSTD_sequenceBound(srcSize)); return zc->seqCollector.seqIndex; } size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize) { size_t in = 0; size_t out = 0; for (; in < seqsSize; ++in) { if (sequences[in].offset == 0 && sequences[in].matchLength == 0) { if (in != seqsSize - 1) { sequences[in+1].litLength += sequences[in].litLength; } } else { sequences[out] = sequences[in]; ++out; } } return out; } /* Unrolled loop to read four size_ts of input at a time. Returns 1 if is RLE, 0 if not. */ static int ZSTD_isRLE(const BYTE* src, size_t length) { const BYTE* ip = src; const BYTE value = ip[0]; const size_t valueST = (size_t)((U64)value * 0x0101010101010101ULL); const size_t unrollSize = sizeof(size_t) * 4; const size_t unrollMask = unrollSize - 1; const size_t prefixLength = length & unrollMask; size_t i; if (length == 1) return 1; /* Check if prefix is RLE first before using unrolled loop */ if (prefixLength && ZSTD_count(ip+1, ip, ip+prefixLength) != prefixLength-1) { return 0; } for (i = prefixLength; i != length; i += unrollSize) { size_t u; for (u = 0; u < unrollSize; u += sizeof(size_t)) { if (MEM_readST(ip + i + u) != valueST) { return 0; } } } return 1; } /* Returns true if the given block may be RLE. * This is just a heuristic based on the compressibility. * It may return both false positives and false negatives. */ static int ZSTD_maybeRLE(SeqStore_t const* seqStore) { size_t const nbSeqs = (size_t)(seqStore->sequences - seqStore->sequencesStart); size_t const nbLits = (size_t)(seqStore->lit - seqStore->litStart); return nbSeqs < 4 && nbLits < 10; } static void ZSTD_blockState_confirmRepcodesAndEntropyTables(ZSTD_blockState_t* const bs) { ZSTD_compressedBlockState_t* const tmp = bs->prevCBlock; bs->prevCBlock = bs->nextCBlock; bs->nextCBlock = tmp; } /* Writes the block header */ static void writeBlockHeader(void* op, size_t cSize, size_t blockSize, U32 lastBlock) { U32 const cBlockHeader = cSize == 1 ? lastBlock + (((U32)bt_rle)<<1) + (U32)(blockSize << 3) : lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3); MEM_writeLE24(op, cBlockHeader); DEBUGLOG(5, "writeBlockHeader: cSize: %zu blockSize: %zu lastBlock: %u", cSize, blockSize, lastBlock); } /* ZSTD_buildBlockEntropyStats_literals() : * Builds entropy for the literals. * Stores literals block type (raw, rle, compressed, repeat) and * huffman description table to hufMetadata. * Requires ENTROPY_WORKSPACE_SIZE workspace * @return : size of huffman description table, or an error code */ static size_t ZSTD_buildBlockEntropyStats_literals(void* const src, size_t srcSize, const ZSTD_hufCTables_t* prevHuf, ZSTD_hufCTables_t* nextHuf, ZSTD_hufCTablesMetadata_t* hufMetadata, const int literalsCompressionIsDisabled, void* workspace, size_t wkspSize, int hufFlags) { BYTE* const wkspStart = (BYTE*)workspace; BYTE* const wkspEnd = wkspStart + wkspSize; BYTE* const countWkspStart = wkspStart; unsigned* const countWksp = (unsigned*)workspace; const size_t countWkspSize = (HUF_SYMBOLVALUE_MAX + 1) * sizeof(unsigned); BYTE* const nodeWksp = countWkspStart + countWkspSize; const size_t nodeWkspSize = (size_t)(wkspEnd - nodeWksp); unsigned maxSymbolValue = HUF_SYMBOLVALUE_MAX; unsigned huffLog = LitHufLog; HUF_repeat repeat = prevHuf->repeatMode; DEBUGLOG(5, "ZSTD_buildBlockEntropyStats_literals (srcSize=%zu)", srcSize); /* Prepare nextEntropy assuming reusing the existing table */ ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); if (literalsCompressionIsDisabled) { DEBUGLOG(5, "set_basic - disabled"); hufMetadata->hType = set_basic; return 0; } /* small ? don't even attempt compression (speed opt) */ #ifndef COMPRESS_LITERALS_SIZE_MIN # define COMPRESS_LITERALS_SIZE_MIN 63 /* heuristic */ #endif { size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN; if (srcSize <= minLitSize) { DEBUGLOG(5, "set_basic - too small"); hufMetadata->hType = set_basic; return 0; } } /* Scan input and build symbol stats */ { size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)src, srcSize, workspace, wkspSize); FORWARD_IF_ERROR(largest, "HIST_count_wksp failed"); if (largest == srcSize) { /* only one literal symbol */ DEBUGLOG(5, "set_rle"); hufMetadata->hType = set_rle; return 0; } if (largest <= (srcSize >> 7)+4) { /* heuristic: likely not compressible */ DEBUGLOG(5, "set_basic - no gain"); hufMetadata->hType = set_basic; return 0; } } /* Validate the previous Huffman table */ if (repeat == HUF_repeat_check && !HUF_validateCTable((HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue)) { repeat = HUF_repeat_none; } /* Build Huffman Tree */ ZSTD_memset(nextHuf->CTable, 0, sizeof(nextHuf->CTable)); huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue, nodeWksp, nodeWkspSize, nextHuf->CTable, countWksp, hufFlags); assert(huffLog <= LitHufLog); { size_t const maxBits = HUF_buildCTable_wksp((HUF_CElt*)nextHuf->CTable, countWksp, maxSymbolValue, huffLog, nodeWksp, nodeWkspSize); FORWARD_IF_ERROR(maxBits, "HUF_buildCTable_wksp"); huffLog = (U32)maxBits; } { /* Build and write the CTable */ size_t const newCSize = HUF_estimateCompressedSize( (HUF_CElt*)nextHuf->CTable, countWksp, maxSymbolValue); size_t const hSize = HUF_writeCTable_wksp( hufMetadata->hufDesBuffer, sizeof(hufMetadata->hufDesBuffer), (HUF_CElt*)nextHuf->CTable, maxSymbolValue, huffLog, nodeWksp, nodeWkspSize); /* Check against repeating the previous CTable */ if (repeat != HUF_repeat_none) { size_t const oldCSize = HUF_estimateCompressedSize( (HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue); if (oldCSize < srcSize && (oldCSize <= hSize + newCSize || hSize + 12 >= srcSize)) { DEBUGLOG(5, "set_repeat - smaller"); ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); hufMetadata->hType = set_repeat; return 0; } } if (newCSize + hSize >= srcSize) { DEBUGLOG(5, "set_basic - no gains"); ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); hufMetadata->hType = set_basic; return 0; } DEBUGLOG(5, "set_compressed (hSize=%u)", (U32)hSize); hufMetadata->hType = set_compressed; nextHuf->repeatMode = HUF_repeat_check; return hSize; } } /* ZSTD_buildDummySequencesStatistics(): * Returns a ZSTD_symbolEncodingTypeStats_t with all encoding types as set_basic, * and updates nextEntropy to the appropriate repeatMode. */ static ZSTD_symbolEncodingTypeStats_t ZSTD_buildDummySequencesStatistics(ZSTD_fseCTables_t* nextEntropy) { ZSTD_symbolEncodingTypeStats_t stats = {set_basic, set_basic, set_basic, 0, 0, 0}; nextEntropy->litlength_repeatMode = FSE_repeat_none; nextEntropy->offcode_repeatMode = FSE_repeat_none; nextEntropy->matchlength_repeatMode = FSE_repeat_none; return stats; } /* ZSTD_buildBlockEntropyStats_sequences() : * Builds entropy for the sequences. * Stores symbol compression modes and fse table to fseMetadata. * Requires ENTROPY_WORKSPACE_SIZE wksp. * @return : size of fse tables or error code */ static size_t ZSTD_buildBlockEntropyStats_sequences( const SeqStore_t* seqStorePtr, const ZSTD_fseCTables_t* prevEntropy, ZSTD_fseCTables_t* nextEntropy, const ZSTD_CCtx_params* cctxParams, ZSTD_fseCTablesMetadata_t* fseMetadata, void* workspace, size_t wkspSize) { ZSTD_strategy const strategy = cctxParams->cParams.strategy; size_t const nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart); BYTE* const ostart = fseMetadata->fseTablesBuffer; BYTE* const oend = ostart + sizeof(fseMetadata->fseTablesBuffer); BYTE* op = ostart; unsigned* countWorkspace = (unsigned*)workspace; unsigned* entropyWorkspace = countWorkspace + (MaxSeq + 1); size_t entropyWorkspaceSize = wkspSize - (MaxSeq + 1) * sizeof(*countWorkspace); ZSTD_symbolEncodingTypeStats_t stats; DEBUGLOG(5, "ZSTD_buildBlockEntropyStats_sequences (nbSeq=%zu)", nbSeq); stats = nbSeq != 0 ? ZSTD_buildSequencesStatistics(seqStorePtr, nbSeq, prevEntropy, nextEntropy, op, oend, strategy, countWorkspace, entropyWorkspace, entropyWorkspaceSize) : ZSTD_buildDummySequencesStatistics(nextEntropy); FORWARD_IF_ERROR(stats.size, "ZSTD_buildSequencesStatistics failed!"); fseMetadata->llType = (SymbolEncodingType_e) stats.LLtype; fseMetadata->ofType = (SymbolEncodingType_e) stats.Offtype; fseMetadata->mlType = (SymbolEncodingType_e) stats.MLtype; fseMetadata->lastCountSize = stats.lastCountSize; return stats.size; } /* ZSTD_buildBlockEntropyStats() : * Builds entropy for the block. * Requires workspace size ENTROPY_WORKSPACE_SIZE * @return : 0 on success, or an error code * Note : also employed in superblock */ size_t ZSTD_buildBlockEntropyStats( const SeqStore_t* seqStorePtr, const ZSTD_entropyCTables_t* prevEntropy, ZSTD_entropyCTables_t* nextEntropy, const ZSTD_CCtx_params* cctxParams, ZSTD_entropyCTablesMetadata_t* entropyMetadata, void* workspace, size_t wkspSize) { size_t const litSize = (size_t)(seqStorePtr->lit - seqStorePtr->litStart); int const huf_useOptDepth = (cctxParams->cParams.strategy >= HUF_OPTIMAL_DEPTH_THRESHOLD); int const hufFlags = huf_useOptDepth ? HUF_flags_optimalDepth : 0; entropyMetadata->hufMetadata.hufDesSize = ZSTD_buildBlockEntropyStats_literals(seqStorePtr->litStart, litSize, &prevEntropy->huf, &nextEntropy->huf, &entropyMetadata->hufMetadata, ZSTD_literalsCompressionIsDisabled(cctxParams), workspace, wkspSize, hufFlags); FORWARD_IF_ERROR(entropyMetadata->hufMetadata.hufDesSize, "ZSTD_buildBlockEntropyStats_literals failed"); entropyMetadata->fseMetadata.fseTablesSize = ZSTD_buildBlockEntropyStats_sequences(seqStorePtr, &prevEntropy->fse, &nextEntropy->fse, cctxParams, &entropyMetadata->fseMetadata, workspace, wkspSize); FORWARD_IF_ERROR(entropyMetadata->fseMetadata.fseTablesSize, "ZSTD_buildBlockEntropyStats_sequences failed"); return 0; } /* Returns the size estimate for the literals section (header + content) of a block */ static size_t ZSTD_estimateBlockSize_literal(const BYTE* literals, size_t litSize, const ZSTD_hufCTables_t* huf, const ZSTD_hufCTablesMetadata_t* hufMetadata, void* workspace, size_t wkspSize, int writeEntropy) { unsigned* const countWksp = (unsigned*)workspace; unsigned maxSymbolValue = HUF_SYMBOLVALUE_MAX; size_t literalSectionHeaderSize = 3 + (litSize >= 1 KB) + (litSize >= 16 KB); U32 singleStream = litSize < 256; if (hufMetadata->hType == set_basic) return litSize; else if (hufMetadata->hType == set_rle) return 1; else if (hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat) { size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)literals, litSize, workspace, wkspSize); if (ZSTD_isError(largest)) return litSize; { size_t cLitSizeEstimate = HUF_estimateCompressedSize((const HUF_CElt*)huf->CTable, countWksp, maxSymbolValue); if (writeEntropy) cLitSizeEstimate += hufMetadata->hufDesSize; if (!singleStream) cLitSizeEstimate += 6; /* multi-stream huffman uses 6-byte jump table */ return cLitSizeEstimate + literalSectionHeaderSize; } } assert(0); /* impossible */ return 0; } /* Returns the size estimate for the FSE-compressed symbols (of, ml, ll) of a block */ static size_t ZSTD_estimateBlockSize_symbolType(SymbolEncodingType_e type, const BYTE* codeTable, size_t nbSeq, unsigned maxCode, const FSE_CTable* fseCTable, const U8* additionalBits, short const* defaultNorm, U32 defaultNormLog, U32 defaultMax, void* workspace, size_t wkspSize) { unsigned* const countWksp = (unsigned*)workspace; const BYTE* ctp = codeTable; const BYTE* const ctStart = ctp; const BYTE* const ctEnd = ctStart + nbSeq; size_t cSymbolTypeSizeEstimateInBits = 0; unsigned max = maxCode; HIST_countFast_wksp(countWksp, &max, codeTable, nbSeq, workspace, wkspSize); /* can't fail */ if (type == set_basic) { /* We selected this encoding type, so it must be valid. */ assert(max <= defaultMax); (void)defaultMax; cSymbolTypeSizeEstimateInBits = ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, countWksp, max); } else if (type == set_rle) { cSymbolTypeSizeEstimateInBits = 0; } else if (type == set_compressed || type == set_repeat) { cSymbolTypeSizeEstimateInBits = ZSTD_fseBitCost(fseCTable, countWksp, max); } if (ZSTD_isError(cSymbolTypeSizeEstimateInBits)) { return nbSeq * 10; } while (ctp < ctEnd) { if (additionalBits) cSymbolTypeSizeEstimateInBits += additionalBits[*ctp]; else cSymbolTypeSizeEstimateInBits += *ctp; /* for offset, offset code is also the number of additional bits */ ctp++; } return cSymbolTypeSizeEstimateInBits >> 3; } /* Returns the size estimate for the sequences section (header + content) of a block */ static size_t ZSTD_estimateBlockSize_sequences(const BYTE* ofCodeTable, const BYTE* llCodeTable, const BYTE* mlCodeTable, size_t nbSeq, const ZSTD_fseCTables_t* fseTables, const ZSTD_fseCTablesMetadata_t* fseMetadata, void* workspace, size_t wkspSize, int writeEntropy) { size_t sequencesSectionHeaderSize = 1 /* seqHead */ + 1 /* min seqSize size */ + (nbSeq >= 128) + (nbSeq >= LONGNBSEQ); size_t cSeqSizeEstimate = 0; cSeqSizeEstimate += ZSTD_estimateBlockSize_symbolType(fseMetadata->ofType, ofCodeTable, nbSeq, MaxOff, fseTables->offcodeCTable, NULL, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, workspace, wkspSize); cSeqSizeEstimate += ZSTD_estimateBlockSize_symbolType(fseMetadata->llType, llCodeTable, nbSeq, MaxLL, fseTables->litlengthCTable, LL_bits, LL_defaultNorm, LL_defaultNormLog, MaxLL, workspace, wkspSize); cSeqSizeEstimate += ZSTD_estimateBlockSize_symbolType(fseMetadata->mlType, mlCodeTable, nbSeq, MaxML, fseTables->matchlengthCTable, ML_bits, ML_defaultNorm, ML_defaultNormLog, MaxML, workspace, wkspSize); if (writeEntropy) cSeqSizeEstimate += fseMetadata->fseTablesSize; return cSeqSizeEstimate + sequencesSectionHeaderSize; } /* Returns the size estimate for a given stream of literals, of, ll, ml */ static size_t ZSTD_estimateBlockSize(const BYTE* literals, size_t litSize, const BYTE* ofCodeTable, const BYTE* llCodeTable, const BYTE* mlCodeTable, size_t nbSeq, const ZSTD_entropyCTables_t* entropy, const ZSTD_entropyCTablesMetadata_t* entropyMetadata, void* workspace, size_t wkspSize, int writeLitEntropy, int writeSeqEntropy) { size_t const literalsSize = ZSTD_estimateBlockSize_literal(literals, litSize, &entropy->huf, &entropyMetadata->hufMetadata, workspace, wkspSize, writeLitEntropy); size_t const seqSize = ZSTD_estimateBlockSize_sequences(ofCodeTable, llCodeTable, mlCodeTable, nbSeq, &entropy->fse, &entropyMetadata->fseMetadata, workspace, wkspSize, writeSeqEntropy); return seqSize + literalsSize + ZSTD_blockHeaderSize; } /* Builds entropy statistics and uses them for blocksize estimation. * * @return: estimated compressed size of the seqStore, or a zstd error. */ static size_t ZSTD_buildEntropyStatisticsAndEstimateSubBlockSize(SeqStore_t* seqStore, ZSTD_CCtx* zc) { ZSTD_entropyCTablesMetadata_t* const entropyMetadata = &zc->blockSplitCtx.entropyMetadata; DEBUGLOG(6, "ZSTD_buildEntropyStatisticsAndEstimateSubBlockSize()"); FORWARD_IF_ERROR(ZSTD_buildBlockEntropyStats(seqStore, &zc->blockState.prevCBlock->entropy, &zc->blockState.nextCBlock->entropy, &zc->appliedParams, entropyMetadata, zc->tmpWorkspace, zc->tmpWkspSize), ""); return ZSTD_estimateBlockSize( seqStore->litStart, (size_t)(seqStore->lit - seqStore->litStart), seqStore->ofCode, seqStore->llCode, seqStore->mlCode, (size_t)(seqStore->sequences - seqStore->sequencesStart), &zc->blockState.nextCBlock->entropy, entropyMetadata, zc->tmpWorkspace, zc->tmpWkspSize, (int)(entropyMetadata->hufMetadata.hType == set_compressed), 1); } /* Returns literals bytes represented in a seqStore */ static size_t ZSTD_countSeqStoreLiteralsBytes(const SeqStore_t* const seqStore) { size_t literalsBytes = 0; size_t const nbSeqs = (size_t)(seqStore->sequences - seqStore->sequencesStart); size_t i; for (i = 0; i < nbSeqs; ++i) { SeqDef const seq = seqStore->sequencesStart[i]; literalsBytes += seq.litLength; if (i == seqStore->longLengthPos && seqStore->longLengthType == ZSTD_llt_literalLength) { literalsBytes += 0x10000; } } return literalsBytes; } /* Returns match bytes represented in a seqStore */ static size_t ZSTD_countSeqStoreMatchBytes(const SeqStore_t* const seqStore) { size_t matchBytes = 0; size_t const nbSeqs = (size_t)(seqStore->sequences - seqStore->sequencesStart); size_t i; for (i = 0; i < nbSeqs; ++i) { SeqDef seq = seqStore->sequencesStart[i]; matchBytes += seq.mlBase + MINMATCH; if (i == seqStore->longLengthPos && seqStore->longLengthType == ZSTD_llt_matchLength) { matchBytes += 0x10000; } } return matchBytes; } /* Derives the seqStore that is a chunk of the originalSeqStore from [startIdx, endIdx). * Stores the result in resultSeqStore. */ static void ZSTD_deriveSeqStoreChunk(SeqStore_t* resultSeqStore, const SeqStore_t* originalSeqStore, size_t startIdx, size_t endIdx) { *resultSeqStore = *originalSeqStore; if (startIdx > 0) { resultSeqStore->sequences = originalSeqStore->sequencesStart + startIdx; resultSeqStore->litStart += ZSTD_countSeqStoreLiteralsBytes(resultSeqStore); } /* Move longLengthPos into the correct position if necessary */ if (originalSeqStore->longLengthType != ZSTD_llt_none) { if (originalSeqStore->longLengthPos < startIdx || originalSeqStore->longLengthPos > endIdx) { resultSeqStore->longLengthType = ZSTD_llt_none; } else { resultSeqStore->longLengthPos -= (U32)startIdx; } } resultSeqStore->sequencesStart = originalSeqStore->sequencesStart + startIdx; resultSeqStore->sequences = originalSeqStore->sequencesStart + endIdx; if (endIdx == (size_t)(originalSeqStore->sequences - originalSeqStore->sequencesStart)) { /* This accounts for possible last literals if the derived chunk reaches the end of the block */ assert(resultSeqStore->lit == originalSeqStore->lit); } else { size_t const literalsBytes = ZSTD_countSeqStoreLiteralsBytes(resultSeqStore); resultSeqStore->lit = resultSeqStore->litStart + literalsBytes; } resultSeqStore->llCode += startIdx; resultSeqStore->mlCode += startIdx; resultSeqStore->ofCode += startIdx; } /* * Returns the raw offset represented by the combination of offBase, ll0, and repcode history. * offBase must represent a repcode in the numeric representation of ZSTD_storeSeq(). */ static U32 ZSTD_resolveRepcodeToRawOffset(const U32 rep[ZSTD_REP_NUM], const U32 offBase, const U32 ll0) { U32 const adjustedRepCode = OFFBASE_TO_REPCODE(offBase) - 1 + ll0; /* [ 0 - 3 ] */ assert(OFFBASE_IS_REPCODE(offBase)); if (adjustedRepCode == ZSTD_REP_NUM) { assert(ll0); /* litlength == 0 and offCode == 2 implies selection of first repcode - 1 * This is only valid if it results in a valid offset value, aka > 0. * Note : it may happen that `rep[0]==1` in exceptional circumstances. * In which case this function will return 0, which is an invalid offset. * It's not an issue though, since this value will be * compared and discarded within ZSTD_seqStore_resolveOffCodes(). */ return rep[0] - 1; } return rep[adjustedRepCode]; } /* * ZSTD_seqStore_resolveOffCodes() reconciles any possible divergences in offset history that may arise * due to emission of RLE/raw blocks that disturb the offset history, * and replaces any repcodes within the seqStore that may be invalid. * * dRepcodes are updated as would be on the decompression side. * cRepcodes are updated exactly in accordance with the seqStore. * * Note : this function assumes seq->offBase respects the following numbering |