| 10 10 53 53 9 5 6 5 3 3 5 6 79 79 79 84 84 84 10 6 5 1 4 3 3 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "originator.h" #include "main.h" #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> #include "bat_algo.h" #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "multicast.h" #include "netlink.h" #include "network-coding.h" #include "routing.h" #include "translation-table.h" /* hash class keys */ static struct lock_class_key batadv_orig_hash_lock_class_key; /** * batadv_orig_hash_find() - Find and return originator from orig_hash * @bat_priv: the bat priv with all the soft interface information * @data: mac address of the originator * * Return: orig_node (with increased refcnt), NULL on errors */ struct batadv_orig_node * batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node, *orig_node_tmp = NULL; int index; if (!hash) return NULL; index = batadv_choose_orig(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { if (!batadv_compare_eth(orig_node, data)) continue; if (!kref_get_unless_zero(&orig_node->refcount)) continue; orig_node_tmp = orig_node; break; } rcu_read_unlock(); return orig_node_tmp; } static void batadv_purge_orig(struct work_struct *work); /** * batadv_compare_orig() - comparing function used in the originator hash table * @node: node in the local table * @data2: second object to compare the node to * * Return: true if they are the same originator */ bool batadv_compare_orig(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_orig_node, hash_entry); return batadv_compare_eth(data1, data2); } /** * batadv_orig_node_vlan_get() - get an orig_node_vlan object * @orig_node: the originator serving the VLAN * @vid: the VLAN identifier * * Return: the vlan object identified by vid and belonging to orig_node or NULL * if it does not exist. */ struct batadv_orig_node_vlan * batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_orig_node_vlan *vlan = NULL, *tmp; rcu_read_lock(); hlist_for_each_entry_rcu(tmp, &orig_node->vlan_list, list) { if (tmp->vid != vid) continue; if (!kref_get_unless_zero(&tmp->refcount)) continue; vlan = tmp; break; } rcu_read_unlock(); return vlan; } /** * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding * @vid: the VLAN identifier * * Return: true when either no vlan is set or if VLAN is in correct range, * false otherwise */ static bool batadv_vlan_id_valid(unsigned short vid) { unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK); if (vid == 0) return true; if (!(vid & BATADV_VLAN_HAS_TAG)) return false; if (non_vlan) return false; return true; } /** * batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan * object * @orig_node: the originator serving the VLAN * @vid: the VLAN identifier * * Return: NULL in case of failure or the vlan object identified by vid and * belonging to orig_node otherwise. The object is created and added to the list * if it does not exist. * * The object is returned with refcounter increased by 1. */ struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_orig_node_vlan *vlan; if (!batadv_vlan_id_valid(vid)) return NULL; spin_lock_bh(&orig_node->vlan_list_lock); /* first look if an object for this vid already exists */ vlan = batadv_orig_node_vlan_get(orig_node, vid); if (vlan) goto out; vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC); if (!vlan) goto out; kref_init(&vlan->refcount); vlan->vid = vid; kref_get(&vlan->refcount); hlist_add_head_rcu(&vlan->list, &orig_node->vlan_list); out: spin_unlock_bh(&orig_node->vlan_list_lock); return vlan; } /** * batadv_orig_node_vlan_release() - release originator-vlan object from lists * and queue for free after rcu grace period * @ref: kref pointer of the originator-vlan object */ void batadv_orig_node_vlan_release(struct kref *ref) { struct batadv_orig_node_vlan *orig_vlan; orig_vlan = container_of(ref, struct batadv_orig_node_vlan, refcount); kfree_rcu(orig_vlan, rcu); } /** * batadv_originator_init() - Initialize all originator structures * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure */ int batadv_originator_init(struct batadv_priv *bat_priv) { if (bat_priv->orig_hash) return 0; bat_priv->orig_hash = batadv_hash_new(1024); if (!bat_priv->orig_hash) goto err; batadv_hash_set_lock_class(bat_priv->orig_hash, &batadv_orig_hash_lock_class_key); INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); queue_delayed_work(batadv_event_workqueue, &bat_priv->orig_work, msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); return 0; err: return -ENOMEM; } /** * batadv_neigh_ifinfo_release() - release neigh_ifinfo from lists and queue for * free after rcu grace period * @ref: kref pointer of the neigh_ifinfo */ void batadv_neigh_ifinfo_release(struct kref *ref) { struct batadv_neigh_ifinfo *neigh_ifinfo; neigh_ifinfo = container_of(ref, struct batadv_neigh_ifinfo, refcount); if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_put(neigh_ifinfo->if_outgoing); kfree_rcu(neigh_ifinfo, rcu); } /** * batadv_hardif_neigh_release() - release hardif neigh node from lists and * queue for free after rcu grace period * @ref: kref pointer of the neigh_node */ void batadv_hardif_neigh_release(struct kref *ref) { struct batadv_hardif_neigh_node *hardif_neigh; hardif_neigh = container_of(ref, struct batadv_hardif_neigh_node, refcount); spin_lock_bh(&hardif_neigh->if_incoming->neigh_list_lock); hlist_del_init_rcu(&hardif_neigh->list); spin_unlock_bh(&hardif_neigh->if_incoming->neigh_list_lock); batadv_hardif_put(hardif_neigh->if_incoming); kfree_rcu(hardif_neigh, rcu); } /** * batadv_neigh_node_release() - release neigh_node from lists and queue for * free after rcu grace period * @ref: kref pointer of the neigh_node */ void batadv_neigh_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; neigh_node = container_of(ref, struct batadv_neigh_node, refcount); hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh_node->ifinfo_list, list) { batadv_neigh_ifinfo_put(neigh_ifinfo); } batadv_hardif_neigh_put(neigh_node->hardif_neigh); batadv_hardif_put(neigh_node->if_incoming); kfree_rcu(neigh_node, rcu); } /** * batadv_orig_router_get() - router to the originator depending on iface * @orig_node: the orig node for the router * @if_outgoing: the interface where the payload packet has been received or * the OGM should be sent to * * Return: the neighbor which should be the router for this orig_node/iface. * * The object is returned with refcounter increased by 1. */ struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(orig_ifinfo, &orig_node->ifinfo_list, list) { if (orig_ifinfo->if_outgoing != if_outgoing) continue; router = rcu_dereference(orig_ifinfo->router); break; } if (router && !kref_get_unless_zero(&router->refcount)) router = NULL; rcu_read_unlock(); return router; } /** * batadv_orig_to_router() - get next hop neighbor to an orig address * @bat_priv: the bat priv with all the soft interface information * @orig_addr: the originator MAC address to search the best next hop router for * @if_outgoing: the interface where the payload packet has been received or * the OGM should be sent to * * Return: A neighbor node which is the best router towards the given originator * address. */ struct batadv_neigh_node * batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; orig_node = batadv_orig_hash_find(bat_priv, orig_addr); if (!orig_node) return NULL; neigh_node = batadv_find_router(bat_priv, orig_node, if_outgoing); batadv_orig_node_put(orig_node); return neigh_node; } /** * batadv_orig_ifinfo_get() - find the ifinfo from an orig_node * @orig_node: the orig node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * Return: the requested orig_ifinfo or NULL if not found. * * The object is returned with refcounter increased by 1. */ struct batadv_orig_ifinfo * batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *tmp, *orig_ifinfo = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp, &orig_node->ifinfo_list, list) { if (tmp->if_outgoing != if_outgoing) continue; if (!kref_get_unless_zero(&tmp->refcount)) continue; orig_ifinfo = tmp; break; } rcu_read_unlock(); return orig_ifinfo; } /** * batadv_orig_ifinfo_new() - search and possibly create an orig_ifinfo object * @orig_node: the orig node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * Return: NULL in case of failure or the orig_ifinfo object for the if_outgoing * interface otherwise. The object is created and added to the list * if it does not exist. * * The object is returned with refcounter increased by 1. */ struct batadv_orig_ifinfo * batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *orig_ifinfo; unsigned long reset_time; spin_lock_bh(&orig_node->neigh_list_lock); orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_outgoing); if (orig_ifinfo) goto out; orig_ifinfo = kzalloc(sizeof(*orig_ifinfo), GFP_ATOMIC); if (!orig_ifinfo) goto out; if (if_outgoing != BATADV_IF_DEFAULT) kref_get(&if_outgoing->refcount); reset_time = jiffies - 1; reset_time -= msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_ifinfo->batman_seqno_reset = reset_time; orig_ifinfo->if_outgoing = if_outgoing; INIT_HLIST_NODE(&orig_ifinfo->list); kref_init(&orig_ifinfo->refcount); kref_get(&orig_ifinfo->refcount); hlist_add_head_rcu(&orig_ifinfo->list, &orig_node->ifinfo_list); out: spin_unlock_bh(&orig_node->neigh_list_lock); return orig_ifinfo; } /** * batadv_neigh_ifinfo_get() - find the ifinfo from an neigh_node * @neigh: the neigh node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * The object is returned with refcounter increased by 1. * * Return: the requested neigh_ifinfo or NULL if not found */ struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_ifinfo *neigh_ifinfo = NULL, *tmp_neigh_ifinfo; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_ifinfo, &neigh->ifinfo_list, list) { if (tmp_neigh_ifinfo->if_outgoing != if_outgoing) continue; if (!kref_get_unless_zero(&tmp_neigh_ifinfo->refcount)) continue; neigh_ifinfo = tmp_neigh_ifinfo; break; } rcu_read_unlock(); return neigh_ifinfo; } /** * batadv_neigh_ifinfo_new() - search and possibly create an neigh_ifinfo object * @neigh: the neigh node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * Return: NULL in case of failure or the neigh_ifinfo object for the * if_outgoing interface otherwise. The object is created and added to the list * if it does not exist. * * The object is returned with refcounter increased by 1. */ struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_ifinfo *neigh_ifinfo; spin_lock_bh(&neigh->ifinfo_lock); neigh_ifinfo = batadv_neigh_ifinfo_get(neigh, if_outgoing); if (neigh_ifinfo) goto out; neigh_ifinfo = kzalloc(sizeof(*neigh_ifinfo), GFP_ATOMIC); if (!neigh_ifinfo) goto out; if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&neigh_ifinfo->list); kref_init(&neigh_ifinfo->refcount); neigh_ifinfo->if_outgoing = if_outgoing; kref_get(&neigh_ifinfo->refcount); hlist_add_head_rcu(&neigh_ifinfo->list, &neigh->ifinfo_list); out: spin_unlock_bh(&neigh->ifinfo_lock); return neigh_ifinfo; } /** * batadv_neigh_node_get() - retrieve a neighbour from the list * @orig_node: originator which the neighbour belongs to * @hard_iface: the interface where this neighbour is connected to * @addr: the address of the neighbour * * Looks for and possibly returns a neighbour belonging to this originator list * which is connected through the provided hard interface. * * Return: neighbor when found. Otherwise NULL */ static struct batadv_neigh_node * batadv_neigh_node_get(const struct batadv_orig_node *orig_node, const struct batadv_hard_iface *hard_iface, const u8 *addr) { struct batadv_neigh_node *tmp_neigh_node, *res = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { if (!batadv_compare_eth(tmp_neigh_node->addr, addr)) continue; if (tmp_neigh_node->if_incoming != hard_iface) continue; if (!kref_get_unless_zero(&tmp_neigh_node->refcount)) continue; res = tmp_neigh_node; break; } rcu_read_unlock(); return res; } /** * batadv_hardif_neigh_create() - create a hardif neighbour node * @hard_iface: the interface this neighbour is connected to * @neigh_addr: the interface address of the neighbour to retrieve * @orig_node: originator object representing the neighbour * * Return: the hardif neighbour node if found or created or NULL otherwise. */ static struct batadv_hardif_neigh_node * batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, struct batadv_orig_node *orig_node) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hardif_neigh_node *hardif_neigh; spin_lock_bh(&hard_iface->neigh_list_lock); /* check if neighbor hasn't been added in the meantime */ hardif_neigh = batadv_hardif_neigh_get(hard_iface, neigh_addr); if (hardif_neigh) goto out; hardif_neigh = kzalloc(sizeof(*hardif_neigh), GFP_ATOMIC); if (!hardif_neigh) goto out; kref_get(&hard_iface->refcount); INIT_HLIST_NODE(&hardif_neigh->list); ether_addr_copy(hardif_neigh->addr, neigh_addr); ether_addr_copy(hardif_neigh->orig, orig_node->orig); hardif_neigh->if_incoming = hard_iface; hardif_neigh->last_seen = jiffies; kref_init(&hardif_neigh->refcount); if (bat_priv->algo_ops->neigh.hardif_init) bat_priv->algo_ops->neigh.hardif_init(hardif_neigh); hlist_add_head_rcu(&hardif_neigh->list, &hard_iface->neigh_list); out: spin_unlock_bh(&hard_iface->neigh_list_lock); return hardif_neigh; } /** * batadv_hardif_neigh_get_or_create() - retrieve or create a hardif neighbour * node * @hard_iface: the interface this neighbour is connected to * @neigh_addr: the interface address of the neighbour to retrieve * @orig_node: originator object representing the neighbour * * Return: the hardif neighbour node if found or created or NULL otherwise. */ static struct batadv_hardif_neigh_node * batadv_hardif_neigh_get_or_create(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, struct batadv_orig_node *orig_node) { struct batadv_hardif_neigh_node *hardif_neigh; /* first check without locking to avoid the overhead */ hardif_neigh = batadv_hardif_neigh_get(hard_iface, neigh_addr); if (hardif_neigh) return hardif_neigh; return batadv_hardif_neigh_create(hard_iface, neigh_addr, orig_node); } /** * batadv_hardif_neigh_get() - retrieve a hardif neighbour from the list * @hard_iface: the interface where this neighbour is connected to * @neigh_addr: the address of the neighbour * * Looks for and possibly returns a neighbour belonging to this hard interface. * * Return: neighbor when found. Otherwise NULL */ struct batadv_hardif_neigh_node * batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, const u8 *neigh_addr) { struct batadv_hardif_neigh_node *tmp_hardif_neigh, *hardif_neigh = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_hardif_neigh, &hard_iface->neigh_list, list) { if (!batadv_compare_eth(tmp_hardif_neigh->addr, neigh_addr)) continue; if (!kref_get_unless_zero(&tmp_hardif_neigh->refcount)) continue; hardif_neigh = tmp_hardif_neigh; break; } rcu_read_unlock(); return hardif_neigh; } /** * batadv_neigh_node_create() - create a neigh node object * @orig_node: originator object representing the neighbour * @hard_iface: the interface where the neighbour is connected to * @neigh_addr: the mac address of the neighbour interface * * Allocates a new neigh_node object and initialises all the generic fields. * * Return: the neighbour node if found or created or NULL otherwise. */ static struct batadv_neigh_node * batadv_neigh_node_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr) { struct batadv_neigh_node *neigh_node; struct batadv_hardif_neigh_node *hardif_neigh = NULL; spin_lock_bh(&orig_node->neigh_list_lock); neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); if (neigh_node) goto out; hardif_neigh = batadv_hardif_neigh_get_or_create(hard_iface, neigh_addr, orig_node); if (!hardif_neigh) goto out; neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); if (!neigh_node) goto out; INIT_HLIST_NODE(&neigh_node->list); INIT_HLIST_HEAD(&neigh_node->ifinfo_list); spin_lock_init(&neigh_node->ifinfo_lock); kref_get(&hard_iface->refcount); ether_addr_copy(neigh_node->addr, neigh_addr); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; neigh_node->last_seen = jiffies; /* increment unique neighbor refcount */ kref_get(&hardif_neigh->refcount); neigh_node->hardif_neigh = hardif_neigh; /* extra reference for return */ kref_init(&neigh_node->refcount); kref_get(&neigh_node->refcount); hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", neigh_addr, orig_node->orig, hard_iface->net_dev->name); out: spin_unlock_bh(&orig_node->neigh_list_lock); batadv_hardif_neigh_put(hardif_neigh); return neigh_node; } /** * batadv_neigh_node_get_or_create() - retrieve or create a neigh node object * @orig_node: originator object representing the neighbour * @hard_iface: the interface where the neighbour is connected to * @neigh_addr: the mac address of the neighbour interface * * Return: the neighbour node if found or created or NULL otherwise. */ struct batadv_neigh_node * batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr) { struct batadv_neigh_node *neigh_node; /* first check without locking to avoid the overhead */ neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); if (neigh_node) return neigh_node; return batadv_neigh_node_create(orig_node, hard_iface, neigh_addr); } /** * batadv_hardif_neigh_dump() - Dump to netlink the neighbor infos for a * specific outgoing interface * @msg: message to dump into * @cb: parameters for the dump * * Return: 0 or error value */ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if, *hard_iface; struct net_device *soft_iface; struct batadv_priv *bat_priv; int ret; soft_iface = batadv_netlink_get_softif(cb); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out_put_soft_iface; } hard_iface = batadv_netlink_get_hardif(bat_priv, cb); if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { ret = PTR_ERR(hard_iface); goto out_put_primary_if; } else if (IS_ERR(hard_iface)) { /* => PTR_ERR(hard_iface) == -ENONET * => no hard-iface given, ok */ hard_iface = BATADV_IF_DEFAULT; } if (!bat_priv->algo_ops->neigh.dump) { ret = -EOPNOTSUPP; goto out_put_hard_iface; } bat_priv->algo_ops->neigh.dump(msg, cb, bat_priv, hard_iface); ret = msg->len; out_put_hard_iface: batadv_hardif_put(hard_iface); out_put_primary_if: batadv_hardif_put(primary_if); out_put_soft_iface: dev_put(soft_iface); return ret; } /** * batadv_orig_ifinfo_release() - release orig_ifinfo from lists and queue for * free after rcu grace period * @ref: kref pointer of the orig_ifinfo */ void batadv_orig_ifinfo_release(struct kref *ref) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; orig_ifinfo = container_of(ref, struct batadv_orig_ifinfo, refcount); if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_put(orig_ifinfo->if_outgoing); /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); batadv_neigh_node_put(router); kfree_rcu(orig_ifinfo, rcu); } /** * batadv_orig_node_free_rcu() - free the orig_node * @rcu: rcu pointer of the orig_node */ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { struct batadv_orig_node *orig_node; orig_node = container_of(rcu, struct batadv_orig_node, rcu); batadv_mcast_purge_orig(orig_node); batadv_frag_purge_orig(orig_node, NULL); kfree(orig_node->tt_buff); kfree(orig_node); } /** * batadv_orig_node_release() - release orig_node from lists and queue for * free after rcu grace period * @ref: kref pointer of the orig_node */ void batadv_orig_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_orig_node_vlan *vlan; struct batadv_orig_ifinfo *last_candidate; orig_node = container_of(ref, struct batadv_orig_node, refcount); spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); batadv_neigh_node_put(neigh_node); } hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_put(orig_ifinfo); } last_candidate = orig_node->last_bonding_candidate; orig_node->last_bonding_candidate = NULL; spin_unlock_bh(&orig_node->neigh_list_lock); batadv_orig_ifinfo_put(last_candidate); spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry_safe(vlan, node_tmp, &orig_node->vlan_list, list) { hlist_del_rcu(&vlan->list); batadv_orig_node_vlan_put(vlan); } spin_unlock_bh(&orig_node->vlan_list_lock); /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } /** * batadv_originator_free() - Free all originator structures * @bat_priv: the bat priv with all the soft interface information */ void batadv_originator_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; u32 i; if (!hash) return; cancel_delayed_work_sync(&bat_priv->orig_work); bat_priv->orig_hash = NULL; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { hlist_del_rcu(&orig_node->hash_entry); batadv_orig_node_put(orig_node); } spin_unlock_bh(list_lock); } batadv_hash_destroy(hash); } /** * batadv_orig_node_new() - creates a new orig_node * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the originator * * Creates a new originator object and initialises all the generic fields. * The new object is not added to the originator list. * * Return: the newly created object or NULL on failure. */ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; struct batadv_orig_node_vlan *vlan; unsigned long reset_time; int i; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Creating new originator: %pM\n", addr); orig_node = kzalloc(sizeof(*orig_node), GFP_ATOMIC); if (!orig_node) return NULL; INIT_HLIST_HEAD(&orig_node->neigh_list); INIT_HLIST_HEAD(&orig_node->vlan_list); INIT_HLIST_HEAD(&orig_node->ifinfo_list); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); spin_lock_init(&orig_node->tt_buff_lock); spin_lock_init(&orig_node->tt_lock); spin_lock_init(&orig_node->vlan_list_lock); batadv_nc_init_orig(orig_node); /* extra reference for return */ kref_init(&orig_node->refcount); orig_node->bat_priv = bat_priv; ether_addr_copy(orig_node->orig, addr); batadv_dat_init_orig_node_addr(orig_node); atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; orig_node->last_seen = jiffies; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; #ifdef CONFIG_BATMAN_ADV_MCAST orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4; orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6; orig_node->mcast_flags |= BATADV_MCAST_HAVE_MC_PTYPE_CAPA; INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node); spin_lock_init(&orig_node->mcast_handler_lock); #endif /* create a vlan object for the "untagged" LAN */ vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS); if (!vlan) goto free_orig_node; /* batadv_orig_node_vlan_new() increases the refcounter. * Immediately release vlan since it is not needed anymore in this * context */ batadv_orig_node_vlan_put(vlan); for (i = 0; i < BATADV_FRAG_BUFFER_COUNT; i++) { INIT_HLIST_HEAD(&orig_node->fragments[i].fragment_list); spin_lock_init(&orig_node->fragments[i].lock); orig_node->fragments[i].size = 0; } return orig_node; free_orig_node: kfree(orig_node); return NULL; } /** * batadv_purge_neigh_ifinfo() - purge obsolete ifinfo entries from neighbor * @bat_priv: the bat priv with all the soft interface information * @neigh: orig node which is to be checked */ static void batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh) { struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_hard_iface *if_outgoing; struct hlist_node *node_tmp; spin_lock_bh(&neigh->ifinfo_lock); /* for all ifinfo objects for this neighinator */ hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh->ifinfo_list, list) { if_outgoing = neigh_ifinfo->if_outgoing; /* always keep the default interface */ if (if_outgoing == BATADV_IF_DEFAULT) continue; /* don't purge if the interface is not (going) down */ if (if_outgoing->if_status != BATADV_IF_INACTIVE && if_outgoing->if_status != BATADV_IF_NOT_IN_USE && if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor/ifinfo purge: neighbor %pM, iface: %s\n", neigh->addr, if_outgoing->net_dev->name); hlist_del_rcu(&neigh_ifinfo->list); batadv_neigh_ifinfo_put(neigh_ifinfo); } spin_unlock_bh(&neigh->ifinfo_lock); } /** * batadv_purge_orig_ifinfo() - purge obsolete ifinfo entries from originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked * * Return: true if any ifinfo entry was purged, false otherwise. */ static bool batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_hard_iface *if_outgoing; struct hlist_node *node_tmp; bool ifinfo_purged = false; spin_lock_bh(&orig_node->neigh_list_lock); /* for all ifinfo objects for this originator */ hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { if_outgoing = orig_ifinfo->if_outgoing; /* always keep the default interface */ if (if_outgoing == BATADV_IF_DEFAULT) continue; /* don't purge if the interface is not (going) down */ if (if_outgoing->if_status != BATADV_IF_INACTIVE && if_outgoing->if_status != BATADV_IF_NOT_IN_USE && if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "router/ifinfo purge: originator %pM, iface: %s\n", orig_node->orig, if_outgoing->net_dev->name); ifinfo_purged = true; hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_put(orig_ifinfo); if (orig_node->last_bonding_candidate == orig_ifinfo) { orig_node->last_bonding_candidate = NULL; batadv_orig_ifinfo_put(orig_ifinfo); } } spin_unlock_bh(&orig_node->neigh_list_lock); return ifinfo_purged; } /** * batadv_purge_orig_neighbors() - purges neighbors from originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked * * Return: true if any neighbor was purged, false otherwise */ static bool batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; struct batadv_hard_iface *if_incoming; spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) || if_incoming->if_status == BATADV_IF_INACTIVE || if_incoming->if_status == BATADV_IF_NOT_IN_USE || if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) { if (if_incoming->if_status == BATADV_IF_INACTIVE || if_incoming->if_status == BATADV_IF_NOT_IN_USE || if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", orig_node->orig, neigh_node->addr, if_incoming->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor timeout: originator %pM, neighbor: %pM, last_seen: %u\n", orig_node->orig, neigh_node->addr, jiffies_to_msecs(last_seen)); neigh_purged = true; hlist_del_rcu(&neigh_node->list); batadv_neigh_node_put(neigh_node); } else { /* only necessary if not the whole neighbor is to be * deleted, but some interface has been removed. */ batadv_purge_neigh_ifinfo(bat_priv, neigh_node); } } spin_unlock_bh(&orig_node->neigh_list_lock); return neigh_purged; } /** * batadv_find_best_neighbor() - finds the best neighbor after purging * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked * @if_outgoing: the interface for which the metric should be compared * * Return: the current best neighbor, with refcount increased. */ static struct batadv_neigh_node * batadv_find_best_neighbor(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_node *best = NULL, *neigh; struct batadv_algo_ops *bao = bat_priv->algo_ops; rcu_read_lock(); hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) { if (best && (bao->neigh.cmp(neigh, if_outgoing, best, if_outgoing) <= 0)) continue; if (!kref_get_unless_zero(&neigh->refcount)) continue; batadv_neigh_node_put(best); best = neigh; } rcu_read_unlock(); return best; } /** * batadv_purge_orig_node() - purges obsolete information from an orig_node * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked * * This function checks if the orig_node or substructures of it have become * obsolete, and purges this information if that's the case. * * Return: true if the orig_node is to be removed, false otherwise. */ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_neigh_node *best_neigh_node; struct batadv_hard_iface *hard_iface; bool changed_ifinfo, changed_neigh; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Originator timeout: originator %pM, last_seen %u\n", orig_node->orig, jiffies_to_msecs(orig_node->last_seen)); return true; } changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node); changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node); if (!changed_ifinfo && !changed_neigh) return false; /* first for NULL ... */ best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node, BATADV_IF_DEFAULT); batadv_update_route(bat_priv, orig_node, BATADV_IF_DEFAULT, best_neigh_node); batadv_neigh_node_put(best_neigh_node); /* ... then for all other interfaces. */ rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; if (hard_iface->soft_iface != bat_priv->soft_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node, hard_iface); batadv_update_route(bat_priv, orig_node, hard_iface, best_neigh_node); batadv_neigh_node_put(best_neigh_node); batadv_hardif_put(hard_iface); } rcu_read_unlock(); return false; } /** * batadv_purge_orig_ref() - Purge all outdated originators * @bat_priv: the bat priv with all the soft interface information */ void batadv_purge_orig_ref(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; u32 i; if (!hash) return; /* for all origins... */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; if (hlist_empty(head)) continue; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { if (batadv_purge_orig_node(bat_priv, orig_node)) { batadv_gw_node_delete(bat_priv, orig_node); hlist_del_rcu(&orig_node->hash_entry); batadv_tt_global_del_orig(orig_node->bat_priv, orig_node, -1, "originator timed out"); batadv_orig_node_put(orig_node); continue; } batadv_frag_purge_orig(orig_node, batadv_frag_check_entry); } spin_unlock_bh(list_lock); } batadv_gw_election(bat_priv); } static void batadv_purge_orig(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv *bat_priv; delayed_work = to_delayed_work(work); bat_priv = container_of(delayed_work, struct batadv_priv, orig_work); batadv_purge_orig_ref(bat_priv); queue_delayed_work(batadv_event_workqueue, &bat_priv->orig_work, msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); } /** * batadv_orig_dump() - Dump to netlink the originator infos for a specific * outgoing interface * @msg: message to dump into * @cb: parameters for the dump * * Return: 0 or error value */ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if, *hard_iface; struct net_device *soft_iface; struct batadv_priv *bat_priv; int ret; soft_iface = batadv_netlink_get_softif(cb); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out_put_soft_iface; } hard_iface = batadv_netlink_get_hardif(bat_priv, cb); if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { ret = PTR_ERR(hard_iface); goto out_put_primary_if; } else if (IS_ERR(hard_iface)) { /* => PTR_ERR(hard_iface) == -ENONET * => no hard-iface given, ok */ hard_iface = BATADV_IF_DEFAULT; } if (!bat_priv->algo_ops->orig.dump) { ret = -EOPNOTSUPP; goto out_put_hard_iface; } bat_priv->algo_ops->orig.dump(msg, cb, bat_priv, hard_iface); ret = msg->len; out_put_hard_iface: batadv_hardif_put(hard_iface); out_put_primary_if: batadv_hardif_put(primary_if); out_put_soft_iface: dev_put(soft_iface); return ret; } |
| 151 49 370 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pm_runtime.h - Device run-time power management helper functions. * * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl> */ #ifndef _LINUX_PM_RUNTIME_H #define _LINUX_PM_RUNTIME_H #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm.h> #include <linux/jiffies.h> /* Runtime PM flag argument bits */ #define RPM_ASYNC 0x01 /* Request is asynchronous */ #define RPM_NOWAIT 0x02 /* Don't wait for concurrent state change */ #define RPM_GET_PUT 0x04 /* Increment/decrement the usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). * * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. * * If the underlying dev_pm_ops struct symbol has to be exported, use * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_GPL_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; static inline bool queue_pm_work(struct work_struct *work) { return queue_work(pm_wq, work); } extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); extern int pm_runtime_get_if_active(struct device *dev); extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); extern void pm_runtime_forbid(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); /** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. * * The dependencies of @dev on its children will not be taken into account by * the runtime PM framework going forward if @enable is %true, or they will * be taken into account otherwise. */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } /** * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. * @dev: Target device. */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } /** * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev unless it is 0 already. */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } /** * pm_runtime_suspended - Check whether or not a device is runtime-suspended. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev and its runtime PM status is * %RPM_SUSPENDED, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } /** * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } /** * pm_runtime_status_suspended - Check if runtime PM status is "suspended". * @dev: Target device. * * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false * otherwise, regardless of whether or not runtime PM has been enabled for @dev. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which the * runtime PM status of @dev cannot change. */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } /** * pm_runtime_enabled - Check if runtime PM is enabled. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev. */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } /** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * * Return %true if @dev is a special device without runtime PM callbacks or * %false otherwise. */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } /** * pm_runtime_mark_last_busy - Update the last access time of a device. * @dev: Target device. * * Update the last access time of @dev used by the runtime PM autosuspend * mechanism to the current time as returned by ktime_get_mono_fast_ns(). */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } /** * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. * @dev: Target device. * * Return %true if @dev has been marked as an "IRQ-safe" device (with respect * to runtime PM), in which case its runtime PM callabcks can be expected to * work correctly when invoked from interrupt handlers. */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; } extern u64 pm_runtime_suspended_time(struct device *dev); #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } static inline int __pm_runtime_idle(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_suspend(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_resume(struct device *dev, int rpmflags) { return 1; } static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } static inline int pm_runtime_get_if_active(struct device *dev) { return -EINVAL; } static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, bool use) {} static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ /** * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. * @dev: Target device. * * Invoke the "idle check" callback of @dev and, depending on its return value, * set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend has been enabled for it). */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } /** * pm_runtime_suspend - Suspend a device synchronously. * @dev: Target device. */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } /** * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. * @dev: Target device. * * Set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend is enabled for it) without engaging its "idle check" callback. */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } /** * pm_runtime_resume - Resume a device synchronously. * @dev: Target device. */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } /** * pm_request_idle - Queue up "idle check" execution for a device. * @dev: Target device. * * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev * asynchronously. */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } /** * pm_request_resume - Queue up runtime-resume of a device. * @dev: Target device. */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } /** * pm_request_autosuspend - Queue up autosuspend of a device. * @dev: Target device. * * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev * asynchronously. */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_get - Bump up usage counter and queue up resume of a device. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and queue up a work item to * carry out runtime-resume of it. */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_get_sync - Bump up usage counter of a device and resume it. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of * it synchronously. * * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. * Consider using pm_runtime_resume_and_get() instead of it, especially * if its return value is checked by the caller, as this is likely to result * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } /** * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. * @dev: Target device. * * Resume @dev synchronously and if that is successful, increment its runtime * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been * incremented or a negative error code otherwise. */ static inline int pm_runtime_resume_and_get(struct device *dev) { int ret; ret = __pm_runtime_resume(dev, RPM_GET_PUT); if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } return 0; } /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int __pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, invoke the "idle check" callback of @dev and, depending on its * return value, set up autosuspend of @dev or suspend it (depending on whether * or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_idle() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, carry out runtime-suspend of @dev synchronously. * * The possible return values of this function are the same as for * pm_runtime_suspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending * on whether or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } /** * pm_runtime_set_active - Set runtime PM status to "active". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies * of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } /** * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that * dependencies of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } /** * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * * Prevent the runtime PM framework from working with @dev (by incrementing its * "blocking" counter). * * For each invocation of this function for @dev there must be a matching * pm_runtime_enable() call in order for runtime PM to be enabled for it. */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } /** * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. * @dev: Target device. * * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). * * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() * at driver exit time unless your driver initially enabled pm_runtime * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } /** * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. * @dev: Target device. * * Prevent the runtime PM autosuspend mechanism from being used for @dev which * means that "autosuspend" will be handled as direct runtime-suspend for it * going forward. */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); } #endif |
| 411 21 461 429 32 1 21 18 1419 31 276 432 19 1246 3 1209 8 16 791 2 1008 3 1010 418 76 1291 1163 1058 851 1053 184 59 33 26 59 59 59 33 26 133 41 6 3 87 116 11 104 50 1 49 50 82 3 1905 2 28 322 304 16 1 1 350 2151 1806 1 1 532 3 1 2 647 2284 175 54 2073 26 26 21 3 16 2 6 6 1 21 22 2 7 9 22 30 30 3 28 478 439 41 25 20 1 4 17 1 6 25 25 1 58 70 32 118 4 77 76 101 116 407 407 372 3 48 3 1 2 159 100 129 16 48 48 48 45 3 123 48 153 153 1 118 7 112 37 37 254 263 278 77 24 2 70 77 1 70 76 76 76 76 76 5 103 10 97 56 1 1 136 1 135 55 107 5 103 1 25 2 5 71 907 711 459 473 702 904 1 495 431 65 758 898 378 280 39 279 4 46 408 2 117 429 102 192 102 262 469 624 523 717 687 1 199 529 479 112 83 29 197 17 23 163 6 14 1 2 496 499 21 508 52 1 51 51 51 459 179 51 3 370 45 405 468 2 468 464 17 509 40 3 2 5 523 1 524 529 1238 247 214 56 888 896 241 630 84 75 9 42 32 32 613 66 24 14 4 6 528 529 1 164 7 1 26 1 511 1 2 6 24 516 442 82 223 2 306 277 1 29 31 31 367 111 529 528 529 164 164 125 3 122 57 35 15 81 21 222 217 81 245 245 220 244 261 2 91 221 19 245 57 230 245 55 295 72 15 294 21 10 66 66 52 15 250 264 200 57 15 42 246 45 48 3 332 331 332 259 101 223 14 26 111 94 45 13 124 331 331 379 382 48 426 633 28 1 7 1 53 51 432 1 1 58 9 533 469 523 7 1549 353 108 323 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/xattr.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> * * Fix by Harrison Xing <harrison@mountainviewdata.com>. * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>. * Extended attributes for symlinks and special files added per * suggestion of Luka Renko <luka.renko@hermes.si>. * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, * Red Hat Inc. * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz * and Andreas Gruenbacher <agruen@suse.de>. */ /* * Extended attributes are stored directly in inodes (on file systems with * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl * field contains the block number if an inode uses an additional block. All * attributes must fit in the inode and one additional block. Blocks that * contain the identical set of attributes may be shared among several inodes. * Identical blocks are detected by keeping a cache of blocks that have * recently been accessed. * * The attributes in inodes and on blocks have a different header; the entries * are stored in the same format: * * +------------------+ * | header | * | entry 1 | | * | entry 2 | | growing downwards * | entry 3 | v * | four null bytes | * | . . . | * | value 1 | ^ * | value 3 | | growing upwards * | value 2 | | * +------------------+ * * The header is followed by multiple entry descriptors. In disk blocks, the * entry descriptors are kept sorted. In inodes, they are unsorted. The * attribute values are aligned to the end of the block in no specific order. * * Locking strategy * ---------------- * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem. * EA blocks are only changed if they are exclusive to an inode, so * holding xattr_sem also means that nothing but the EA block's reference * count can change. Multiple writers to the same block are synchronized * by the buffer lock. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "acl.h" #ifdef EXT4_XATTR_DEBUG # define ea_idebug(inode, fmt, ...) \ printk(KERN_DEBUG "inode %s:%lu: " fmt "\n", \ inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) \ printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \ bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__) #else # define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif static void ext4_xattr_block_cache_insert(struct mb_cache *, struct buffer_head *); static struct buffer_head * ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count); static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count); static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, #ifdef CONFIG_EXT4_FS_POSIX_ACL [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler, #endif [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; const struct xattr_handler * const ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY &ext4_xattr_security_handler, #endif &ext4_xattr_hurd_handler, NULL }; #define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_block_cache) #define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_inode_cache) static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode); #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { struct ext4_inode_info *ei = EXT4_I(ea_inode); lockdep_set_subclass(&ea_inode->i_rwsem, 1); (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif static __le32 ext4_xattr_block_csum(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le64 dsk_block_nr = cpu_to_le64(block_nr); __u32 dummy_csum = 0; int offset = offsetof(struct ext4_xattr_header, h_checksum); csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr, sizeof(dsk_block_nr)); csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset); csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset, EXT4_BLOCK_SIZE(inode->i_sb) - offset); return cpu_to_le32(csum); } static int ext4_xattr_block_csum_verify(struct inode *inode, struct buffer_head *bh) { struct ext4_xattr_header *hdr = BHDR(bh); int ret = 1; if (ext4_has_metadata_csum(inode->i_sb)) { lock_buffer(bh); ret = (hdr->h_checksum == ext4_xattr_block_csum(inode, bh->b_blocknr, hdr)); unlock_buffer(bh); } return ret; } static void ext4_xattr_block_csum_set(struct inode *inode, struct buffer_head *bh) { if (ext4_has_metadata_csum(inode->i_sb)) BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode, bh->b_blocknr, BHDR(bh)); } static inline const char *ext4_xattr_prefix(int name_index, struct dentry *dentry) { const struct xattr_handler *handler = NULL; if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map)) handler = ext4_xattr_handler_map[name_index]; if (!xattr_handler_can_list(handler, dentry)) return NULL; return xattr_prefix(handler); } static int check_xattrs(struct inode *inode, struct buffer_head *bh, struct ext4_xattr_entry *entry, void *end, void *value_start, const char *function, unsigned int line) { struct ext4_xattr_entry *e = entry; int err = -EFSCORRUPTED; char *err_str; if (bh) { if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) { err_str = "invalid header"; goto errout; } if (buffer_verified(bh)) return 0; if (!ext4_xattr_block_csum_verify(inode, bh)) { err = -EFSBADCRC; err_str = "invalid checksum"; goto errout; } } else { struct ext4_xattr_ibody_header *header = value_start; header -= 1; if (end - (void *)header < sizeof(*header) + sizeof(u32)) { err_str = "in-inode xattr block too small"; goto errout; } if (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { err_str = "bad magic number in in-inode xattr"; goto errout; } } /* Find the end of the names list */ while (!IS_LAST_ENTRY(e)) { struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) { err_str = "e_name out of bounds"; goto errout; } if (strnlen(e->e_name, e->e_name_len) != e->e_name_len) { err_str = "bad e_name length"; goto errout; } e = next; } /* Check the values */ while (!IS_LAST_ENTRY(entry)) { u32 size = le32_to_cpu(entry->e_value_size); unsigned long ea_ino = le32_to_cpu(entry->e_value_inum); if (!ext4_has_feature_ea_inode(inode->i_sb) && ea_ino) { err_str = "ea_inode specified without ea_inode feature enabled"; goto errout; } if (ea_ino && ((ea_ino == EXT4_ROOT_INO) || !ext4_valid_inum(inode->i_sb, ea_ino))) { err_str = "invalid ea_ino"; goto errout; } if (size > EXT4_XATTR_SIZE_MAX) { err_str = "e_value size too large"; goto errout; } if (size != 0 && entry->e_value_inum == 0) { u16 offs = le16_to_cpu(entry->e_value_offs); void *value; /* * The value cannot overlap the names, and the value * with padding cannot extend beyond 'end'. Check both * the padded and unpadded sizes, since the size may * overflow to 0 when adding padding. */ if (offs > end - value_start) { err_str = "e_value out of bounds"; goto errout; } value = value_start + offs; if (value < (void *)e + sizeof(u32) || size > end - value || EXT4_XATTR_SIZE(size) > end - value) { err_str = "overlapping e_value "; goto errout; } } entry = EXT4_XATTR_NEXT(entry); } if (bh) set_buffer_verified(bh); return 0; errout: if (bh) __ext4_error_inode(inode, function, line, 0, -err, "corrupted xattr block %llu: %s", (unsigned long long) bh->b_blocknr, err_str); else __ext4_error_inode(inode, function, line, 0, -err, "corrupted in-inode xattr: %s", err_str); return err; } static inline int __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh, const char *function, unsigned int line) { return check_xattrs(inode, bh, BFIRST(bh), bh->b_data + bh->b_size, bh->b_data, function, line); } #define ext4_xattr_check_block(inode, bh) \ __ext4_xattr_check_block((inode), (bh), __func__, __LINE__) static inline int __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, void *end, const char *function, unsigned int line) { return check_xattrs(inode, NULL, IFIRST(header), end, IFIRST(header), function, line); } #define xattr_check_inode(inode, header, end) \ __xattr_check_inode((inode), (header), (end), __func__, __LINE__) static int xattr_find_entry(struct inode *inode, struct ext4_xattr_entry **pentry, void *end, int name_index, const char *name, int sorted) { struct ext4_xattr_entry *entry, *next; size_t name_len; int cmp = 1; if (name == NULL) return -EINVAL; name_len = strlen(name); for (entry = *pentry; !IS_LAST_ENTRY(entry); entry = next) { next = EXT4_XATTR_NEXT(entry); if ((void *) next >= end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); return -EFSCORRUPTED; } cmp = name_index - entry->e_name_index; if (!cmp) cmp = name_len - entry->e_name_len; if (!cmp) cmp = memcmp(name, entry->e_name, name_len); if (cmp <= 0 && (sorted || cmp == 0)) break; } *pentry = entry; return cmp ? -ENODATA : 0; } static u32 ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) { return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size); } static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) { return ((u64) inode_get_ctime_sec(ea_inode) << 32) | (u32) inode_peek_iversion_raw(ea_inode); } static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) { inode_set_ctime(ea_inode, (u32)(ref_count >> 32), 0); inode_set_iversion_raw(ea_inode, ref_count & 0xffffffff); } static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) { return (u32) inode_get_atime_sec(ea_inode); } static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) { inode_set_atime(ea_inode, hash, 0); } /* * Read the EA value from an inode. */ static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size) { int blocksize = 1 << ea_inode->i_blkbits; int bh_count = (size + blocksize - 1) >> ea_inode->i_blkbits; int tail_size = (size % blocksize) ?: blocksize; struct buffer_head *bhs_inline[8]; struct buffer_head **bhs = bhs_inline; int i, ret; if (bh_count > ARRAY_SIZE(bhs_inline)) { bhs = kmalloc_array(bh_count, sizeof(*bhs), GFP_NOFS); if (!bhs) return -ENOMEM; } ret = ext4_bread_batch(ea_inode, 0 /* block */, bh_count, true /* wait */, bhs); if (ret) goto free_bhs; for (i = 0; i < bh_count; i++) { /* There shouldn't be any holes in ea_inode. */ if (!bhs[i]) { ret = -EFSCORRUPTED; goto put_bhs; } memcpy((char *)buf + blocksize * i, bhs[i]->b_data, i < bh_count - 1 ? blocksize : tail_size); } ret = 0; put_bhs: for (i = 0; i < bh_count; i++) brelse(bhs[i]); free_bhs: if (bhs != bhs_inline) kfree(bhs); return ret; } #define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode_get_mtime_sec(inode))) static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, u32 ea_inode_hash, struct inode **ea_inode) { struct inode *inode; int err; /* * We have to check for this corruption early as otherwise * iget_locked() could wait indefinitely for the state of our * parent inode. */ if (parent->i_ino == ea_ino) { ext4_error(parent->i_sb, "Parent and EA inode have the same ino %lu", ea_ino); return -EFSCORRUPTED; } inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, "error while reading EA inode %lu err=%d", ea_ino, err); return err; } ext4_xattr_inode_set_class(inode); /* * Check whether this is an old Lustre-style xattr inode. Lustre * implementation does not have hash validation, rather it has a * backpointer from ea_inode to the parent inode. */ if (ea_inode_hash != ext4_xattr_inode_get_hash(inode) && EXT4_XATTR_INODE_GET_PARENT(inode) == parent->i_ino && inode->i_generation == parent->i_generation) { ext4_set_inode_state(inode, EXT4_STATE_LUSTRE_EA_INODE); ext4_xattr_inode_set_ref(inode, 1); } else { inode_lock_nested(inode, I_MUTEX_XATTR); inode->i_flags |= S_NOQUOTA; inode_unlock(inode); } *ea_inode = inode; return 0; } /* Remove entry from mbcache when EA inode is getting evicted */ void ext4_evict_ea_inode(struct inode *inode) { struct mb_cache_entry *oe; if (!EA_INODE_CACHE(inode)) return; /* Wait for entry to get unused so that we can remove it */ while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), ext4_xattr_inode_get_hash(inode), inode->i_ino))) { mb_cache_entry_wait_unused(oe); mb_cache_entry_put(EA_INODE_CACHE(inode), oe); } } static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { u32 hash; /* Verify stored hash matches calculated hash. */ hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size); if (hash != ext4_xattr_inode_get_hash(ea_inode)) return -EFSCORRUPTED; if (entry) { __le32 e_hash, tmp_data; /* Verify entry hash. */ tmp_data = cpu_to_le32(hash); e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, &tmp_data, 1); /* All good? */ if (e_hash == entry->e_hash) return 0; /* * Not good. Maybe the entry hash was calculated * using the buggy signed char version? */ e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len, &tmp_data, 1); /* Still no match - bad */ if (e_hash != entry->e_hash) return -EFSCORRUPTED; /* Let people know about old hash */ pr_warn_once("ext4: filesystem with signed xattr name hash"); } return 0; } /* * Read xattr value from the EA inode. */ static int ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); struct inode *ea_inode; int err; err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ea_inode = NULL; goto out; } if (i_size_read(ea_inode) != size) { ext4_warning_inode(ea_inode, "ea_inode file size=%llu entry size=%zu", i_size_read(ea_inode), size); err = -EFSCORRUPTED; goto out; } err = ext4_xattr_inode_read(ea_inode, buffer, size); if (err) goto out; if (!ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) { err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size); if (err) { ext4_warning_inode(ea_inode, "EA inode hash validation failed"); goto out; } if (ea_inode_cache) mb_cache_entry_create(ea_inode_cache, GFP_NOFS, ext4_xattr_inode_get_hash(ea_inode), ea_inode->i_ino, true /* reusable */); } out: iput(ea_inode); return err; } static int ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct buffer_head *bh = NULL; struct ext4_xattr_entry *entry; size_t size; void *end; int error; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return -ENODATA; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(ea_block_cache, bh); entry = BFIRST(bh); end = bh->b_data + bh->b_size; error = xattr_find_entry(inode, &entry, end, name_index, name, 1); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = bh->b_data + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(bh); return error; } int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; struct ext4_iloc iloc; size_t size; void *end; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return -ENODATA; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; error = xattr_check_inode(inode, header, end); if (error) goto cleanup; entry = IFIRST(header); error = xattr_find_entry(inode, &entry, end, name_index, name, 0); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = (void *)IFIRST(header) + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(iloc.bh); return error; } /* * ext4_xattr_get() * * Copy an extended attribute into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ int ext4_xattr_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { int error; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (strlen(name) > 255) return -ERANGE; down_read(&EXT4_I(inode)->xattr_sem); error = ext4_xattr_ibody_get(inode, name_index, name, buffer, buffer_size); if (error == -ENODATA) error = ext4_xattr_block_get(inode, name_index, name, buffer, buffer_size); up_read(&EXT4_I(inode)->xattr_sem); return error; } static int ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, char *buffer, size_t buffer_size) { size_t rest = buffer_size; for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { const char *prefix; prefix = ext4_xattr_prefix(entry->e_name_index, dentry); if (prefix) { size_t prefix_len = strlen(prefix); size_t size = prefix_len + entry->e_name_len + 1; if (buffer) { if (size > rest) return -ERANGE; memcpy(buffer, prefix, prefix_len); buffer += prefix_len; memcpy(buffer, entry->e_name, entry->e_name_len); buffer += entry->e_name_len; *buffer++ = 0; } rest -= size; } } return buffer_size - rest; /* total size */ } static int ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return 0; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: brelse(bh); return error; } static int ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; struct ext4_iloc iloc; void *end; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return 0; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; error = xattr_check_inode(inode, header, end); if (error) goto cleanup; error = ext4_xattr_list_entries(dentry, IFIRST(header), buffer, buffer_size); cleanup: brelse(iloc.bh); return error; } /* * Inode operation listxattr() * * d_inode(dentry)->i_rwsem: don't care * * Copy a list of attribute names into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ ssize_t ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { int ret, ret2; down_read(&EXT4_I(d_inode(dentry))->xattr_sem); ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; if (buffer) { buffer += ret; buffer_size -= ret; } ret = ext4_xattr_block_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; ret += ret2; errout: up_read(&EXT4_I(d_inode(dentry))->xattr_sem); return ret; } /* * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is * not set, set it. */ static void ext4_xattr_update_super_block(handle_t *handle, struct super_block *sb) { if (ext4_has_feature_xattr(sb)) return; BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, sb, EXT4_SB(sb)->s_sbh, EXT4_JTR_NONE) == 0) { lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); ext4_superblock_csum_set(sb); unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } } int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) { struct ext4_iloc iloc = { .bh = NULL }; struct buffer_head *bh = NULL; struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; qsize_t ea_inode_refs = 0; void *end; int ret; lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem); if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; ret = xattr_check_inode(inode, header, end); if (ret) goto out; for (entry = IFIRST(header); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { ret = PTR_ERR(bh); bh = NULL; goto out; } ret = ext4_xattr_check_block(inode, bh); if (ret) goto out; for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } *usage = ea_inode_refs + 1; ret = 0; out: brelse(iloc.bh); brelse(bh); return ret; } static inline size_t round_up_cluster(struct inode *inode, size_t length) { struct super_block *sb = inode->i_sb; size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits + inode->i_blkbits); size_t mask = ~(cluster_size - 1); return (length + cluster_size - 1) & mask; } static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len) { int err; err = dquot_alloc_inode(inode); if (err) return err; err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len)); if (err) dquot_free_inode(inode); return err; } static void ext4_xattr_inode_free_quota(struct inode *parent, struct inode *ea_inode, size_t len) { if (ea_inode && ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) return; dquot_free_space_nodirty(parent, round_up_cluster(parent, len)); dquot_free_inode(parent); } int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, struct buffer_head *block_bh, size_t value_len, bool is_create) { int credits; int blocks; /* * 1) Owner inode update * 2) Ref count update on old xattr block * 3) new xattr block * 4) block bitmap update for new xattr block * 5) group descriptor for new xattr block * 6) block bitmap update for old xattr block * 7) group descriptor for old block * * 6 & 7 can happen if we have two racing threads T_a and T_b * which are each trying to set an xattr on inodes I_a and I_b * which were both initially sharing an xattr block. */ credits = 7; /* Quota updates. */ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb); /* * In case of inline data, we may push out the data to a block, * so we need to reserve credits for this eventuality */ if (inode && ext4_has_inline_data(inode)) credits += ext4_writepage_trans_blocks(inode) + 1; /* We are done if ea_inode feature is not enabled. */ if (!ext4_has_feature_ea_inode(sb)) return credits; /* New ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks. */ blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; /* Blocks themselves. */ credits += blocks; if (!is_create) { /* Dereference ea_inode holding old xattr value. * Old ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks for old ea_inode. */ blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree for old * ea_inode. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; } /* We may need to clone the existing xattr block in which case we need * to increment ref counts for existing ea_inodes referenced by it. */ if (block_bh) { struct ext4_xattr_entry *entry = BFIRST(block_bh); for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) /* Ref count update on ea_inode. */ credits += 1; } return credits; } static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { struct ext4_iloc iloc; s64 ref_count; int ret; inode_lock_nested(ea_inode, I_MUTEX_XATTR); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); if (ret) goto out; ref_count = ext4_xattr_inode_get_ref(ea_inode); ref_count += ref_change; ext4_xattr_inode_set_ref(ea_inode, ref_count); if (ref_change > 0) { WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld", ea_inode->i_ino, ref_count); if (ref_count == 1) { WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", ea_inode->i_ino, ref_count); if (ref_count == 0) { WARN_ONCE(ea_inode->i_nlink != 1, "EA inode %lu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); } } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: inode_unlock(ea_inode); return ret; } static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, 1); } static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, -1); } static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent, struct ext4_xattr_entry *first) { struct inode *ea_inode; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *failed_entry; unsigned int ea_ino; int err, saved_err; for (entry = first; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) goto cleanup; err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "inc ref error %d", err); iput(ea_inode); goto cleanup; } iput(ea_inode); } return 0; cleanup: saved_err = err; failed_entry = entry; for (entry = first; entry != failed_entry; entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ext4_warning(parent->i_sb, "cleanup ea_ino %u iget error %d", ea_ino, err); continue; } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); iput(ea_inode); } return saved_err; } static int ext4_xattr_restart_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh, bool block_csum, bool dirty) { int error; if (bh && dirty) { if (block_csum) ext4_xattr_block_csum_set(inode, bh); error = ext4_handle_dirty_metadata(handle, NULL, bh); if (error) { ext4_warning(inode->i_sb, "Handle metadata (error %d)", error); return error; } } return 0; } static void ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, struct buffer_head *bh, struct ext4_xattr_entry *first, bool block_csum, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits, bool skip_quota) { struct inode *ea_inode; struct ext4_xattr_entry *entry; bool dirty = false; unsigned int ea_ino; int err; int credits; /* One credit for dec ref on ea_inode, one for orphan list addition, */ credits = 2 + extra_credits; for (entry = first; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) continue; err = ext4_expand_inode_array(ea_inode_array, ea_inode); if (err) { ext4_warning_inode(ea_inode, "Expand inode array err=%d", err); iput(ea_inode); continue; } err = ext4_journal_ensure_credits_fn(handle, credits, credits, ext4_free_metadata_revoke_credits(parent->i_sb, 1), ext4_xattr_restart_fn(handle, parent, bh, block_csum, dirty)); if (err < 0) { ext4_warning_inode(ea_inode, "Ensure credits err=%d", err); continue; } if (err > 0) { err = ext4_journal_get_write_access(handle, parent->i_sb, bh, EXT4_JTR_NONE); if (err) { ext4_warning_inode(ea_inode, "Re-get write access err=%d", err); continue; } } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d", err); continue; } if (!skip_quota) ext4_xattr_inode_free_quota(parent, ea_inode, le32_to_cpu(entry->e_value_size)); /* * Forget about ea_inode within the same transaction that * decrements the ref count. This avoids duplicate decrements in * case the rest of the work spills over to subsequent * transactions. */ entry->e_value_inum = 0; entry->e_value_size = 0; dirty = true; } if (dirty) { /* * Note that we are deliberately skipping csum calculation for * the final update because we do not expect any journal * restarts until xattr block is freed. */ err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) ext4_warning_inode(parent, "handle dirty metadata err=%d", err); } } /* * Release the xattr block BH: If the reference count is > 1, decrement it; * otherwise free the block. */ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, struct buffer_head *bh, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits) { struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); u32 hash, ref; int error = 0; BUFFER_TRACE(bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (error) goto out; retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); if (ref == 1) { ea_bdebug(bh, "refcount now=0; freeing"); /* * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ if (ea_block_cache) { struct mb_cache_entry *oe; oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, bh->b_blocknr); if (oe) { unlock_buffer(bh); mb_cache_entry_wait_unused(oe); mb_cache_entry_put(ea_block_cache, oe); goto retry_ref; } } get_bh(bh); unlock_buffer(bh); if (ext4_has_feature_ea_inode(inode->i_sb)) ext4_xattr_inode_dec_ref_all(handle, inode, bh, BFIRST(bh), true /* block_csum */, ea_inode_array, extra_credits, true /* skip_quota */); ext4_free_blocks(handle, inode, bh, 0, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } else { ref--; BHDR(bh)->h_refcount = cpu_to_le32(ref); if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) { struct mb_cache_entry *ce; if (ea_block_cache) { ce = mb_cache_entry_get(ea_block_cache, hash, bh->b_blocknr); if (ce) { set_bit(MBE_REUSABLE_B, &ce->e_flags); mb_cache_entry_put(ea_block_cache, ce); } } } ext4_xattr_block_csum_set(inode, bh); /* * Beware of this ugliness: Releasing of xattr block references * from different inodes can race and so we have to protect * from a race where someone else frees the block (and releases * its journal_head) before we are done dirtying the buffer. In * nojournal mode this race is harmless and we actually cannot * call ext4_handle_dirty_metadata() with locked buffer as * that function can call sync_dirty_buffer() so for that case * we handle the dirtying after unlocking the buffer. */ if (ext4_handle_valid(handle)) error = ext4_handle_dirty_metadata(handle, inode, bh); unlock_buffer(bh); if (!ext4_handle_valid(handle)) error = ext4_handle_dirty_metadata(handle, inode, bh); if (IS_SYNC(inode)) ext4_handle_sync(handle); dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1)); ea_bdebug(bh, "refcount now=%d; releasing", le32_to_cpu(BHDR(bh)->h_refcount)); } out: ext4_std_error(inode->i_sb, error); return; } /* * Find the available free space for EAs. This also returns the total number of * bytes used by EA entries. */ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, size_t *min_offs, void *base, int *total) { for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < *min_offs) *min_offs = offs; } if (total) *total += EXT4_XATTR_LEN(last->e_name_len); } return (*min_offs - ((void *)last - base) - sizeof(__u32)); } /* * Write the value of the EA in an inode. */ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, const void *buf, int bufsize) { struct buffer_head *bh = NULL; unsigned long block = 0; int blocksize = ea_inode->i_sb->s_blocksize; int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits; int csize, wsize = 0; int ret = 0, ret2 = 0; int retries = 0; retry: while (ret >= 0 && ret < max_blocks) { struct ext4_map_blocks map; map.m_lblk = block += ret; map.m_len = max_blocks -= ret; ret = ext4_map_blocks(handle, ea_inode, &map, EXT4_GET_BLOCKS_CREATE); if (ret <= 0) { ext4_mark_inode_dirty(handle, ea_inode); if (ret == -ENOSPC && ext4_should_retry_alloc(ea_inode->i_sb, &retries)) { ret = 0; goto retry; } break; } } if (ret < 0) return ret; block = 0; while (wsize < bufsize) { brelse(bh); csize = (bufsize - wsize) > blocksize ? blocksize : bufsize - wsize; bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) { WARN_ON_ONCE(1); EXT4_ERROR_INODE(ea_inode, "ext4_getblk() return bh = NULL"); return -EFSCORRUPTED; } ret = ext4_journal_get_write_access(handle, ea_inode->i_sb, bh, EXT4_JTR_NONE); if (ret) goto out; memcpy(bh->b_data, buf, csize); /* * Zero out block tail to avoid writing uninitialized memory * to disk. */ if (csize < blocksize) memset(bh->b_data + csize, 0, blocksize - csize); set_buffer_uptodate(bh); ext4_handle_dirty_metadata(handle, ea_inode, bh); buf += csize; wsize += csize; block += 1; } inode_lock(ea_inode); i_size_write(ea_inode, wsize); ext4_update_i_disksize(ea_inode, wsize); inode_unlock(ea_inode); ret2 = ext4_mark_inode_dirty(handle, ea_inode); if (unlikely(ret2 && !ret)) ret = ret2; out: brelse(bh); return ret; } /* * Create an inode to store the value of a large EA. */ static struct inode *ext4_xattr_inode_create(handle_t *handle, struct inode *inode, u32 hash) { struct inode *ea_inode = NULL; uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; if (inode->i_sb->s_root == NULL) { ext4_warning(inode->i_sb, "refuse to create EA inode when umounting"); WARN_ON(1); return ERR_PTR(-EINVAL); } /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. */ ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG | 0600, NULL, inode->i_ino + 1, owner, EXT4_EA_INODE_FL); if (!IS_ERR(ea_inode)) { ea_inode->i_op = &ext4_file_inode_operations; ea_inode->i_fop = &ext4_file_operations; ext4_set_aops(ea_inode); ext4_xattr_inode_set_class(ea_inode); unlock_new_inode(ea_inode); ext4_xattr_inode_set_ref(ea_inode, 1); ext4_xattr_inode_set_hash(ea_inode, hash); err = ext4_mark_inode_dirty(handle, ea_inode); if (!err) err = ext4_inode_attach_jinode(ea_inode); if (err) { if (ext4_xattr_inode_dec_ref(handle, ea_inode)) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); iput(ea_inode); return ERR_PTR(err); } /* * Xattr inodes are shared therefore quota charging is performed * at a higher level. */ dquot_free_inode(ea_inode); dquot_drop(ea_inode); inode_lock(ea_inode); ea_inode->i_flags |= S_NOQUOTA; inode_unlock(ea_inode); } return ea_inode; } static struct inode * ext4_xattr_inode_cache_find(struct inode *inode, const void *value, size_t value_len, u32 hash) { struct inode *ea_inode; struct mb_cache_entry *ce; struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); void *ea_data; if (!ea_inode_cache) return NULL; ce = mb_cache_entry_find_first(ea_inode_cache, hash); if (!ce) return NULL; WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && !(current->flags & PF_MEMALLOC_NOFS)); ea_data = kvmalloc(value_len, GFP_KERNEL); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); return NULL; } while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, EXT4_IGET_EA_INODE); if (IS_ERR(ea_inode)) goto next_entry; ext4_xattr_inode_set_class(ea_inode); if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && !memcmp(value, ea_data, value_len)) { mb_cache_entry_touch(ea_inode_cache, ce); mb_cache_entry_put(ea_inode_cache, ce); kvfree(ea_data); return ea_inode; } iput(ea_inode); next_entry: ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); return NULL; } /* * Add value of the EA in an inode. */ static struct inode *ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, const void *value, size_t value_len) { struct inode *ea_inode; u32 hash; int err; /* Account inode & space to quota even if sharing... */ err = ext4_xattr_inode_alloc_quota(inode, value_len); if (err) return ERR_PTR(err); hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len); ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash); if (ea_inode) { err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) goto out_err; return ea_inode; } /* Create an inode for the EA value */ ea_inode = ext4_xattr_inode_create(handle, inode, hash); if (IS_ERR(ea_inode)) { ext4_xattr_inode_free_quota(inode, NULL, value_len); return ea_inode; } err = ext4_xattr_inode_write(handle, ea_inode, value, value_len); if (err) { if (ext4_xattr_inode_dec_ref(handle, ea_inode)) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); goto out_err; } if (EA_INODE_CACHE(inode)) mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash, ea_inode->i_ino, true /* reusable */); return ea_inode; out_err: iput(ea_inode); ext4_xattr_inode_free_quota(inode, NULL, value_len); return ERR_PTR(err); } /* * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode * feature is enabled. */ #define EXT4_XATTR_BLOCK_RESERVE(inode) min(i_blocksize(inode)/8, 1024U) static int ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s, handle_t *handle, struct inode *inode, struct inode *new_ea_inode, bool is_block) { struct ext4_xattr_entry *last, *next; struct ext4_xattr_entry *here = s->here; size_t min_offs = s->end - s->base, name_len = strlen(i->name); int in_inode = i->in_inode; struct inode *old_ea_inode = NULL; size_t old_size, new_size; int ret; /* Space used by old and new values. */ old_size = (!s->not_found && !here->e_value_inum) ? EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0; new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0; /* * Optimization for the simple case when old and new values have the * same padded sizes. Not applicable if external inodes are involved. */ if (new_size && new_size == old_size) { size_t offs = le16_to_cpu(here->e_value_offs); void *val = s->base + offs; here->e_value_size = cpu_to_le32(i->value_len); if (i->value == EXT4_ZERO_XATTR_VALUE) { memset(val, 0, new_size); } else { memcpy(val, i->value, i->value_len); /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } goto update_hash; } /* Compute min_offs and last. */ last = s->first; for (; !IS_LAST_ENTRY(last); last = next) { next = EXT4_XATTR_NEXT(last); if ((void *)next >= s->end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); ret = -EFSCORRUPTED; goto out; } if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) min_offs = offs; } } /* Check whether we have enough space. */ if (i->value) { size_t free; free = min_offs - ((void *)last - s->base) - sizeof(__u32); if (!s->not_found) free += EXT4_XATTR_LEN(name_len) + old_size; if (free < EXT4_XATTR_LEN(name_len) + new_size) { ret = -ENOSPC; goto out; } /* * If storing the value in an external inode is an option, * reserve space for xattr entries/names in the external * attribute block so that a long value does not occupy the * whole space and prevent further entries being added. */ if (ext4_has_feature_ea_inode(inode->i_sb) && new_size && is_block && (min_offs + old_size - new_size) < EXT4_XATTR_BLOCK_RESERVE(inode)) { ret = -ENOSPC; goto out; } } /* * Getting access to old and new ea inodes is subject to failures. * Finish that work before doing any modifications to the xattr data. */ if (!s->not_found && here->e_value_inum) { ret = ext4_xattr_inode_iget(inode, le32_to_cpu(here->e_value_inum), le32_to_cpu(here->e_hash), &old_ea_inode); if (ret) { old_ea_inode = NULL; goto out; } /* We are ready to release ref count on the old_ea_inode. */ ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode); if (ret) goto out; ext4_xattr_inode_free_quota(inode, old_ea_inode, le32_to_cpu(here->e_value_size)); } /* No failures allowed past this point. */ if (!s->not_found && here->e_value_size && !here->e_value_inum) { /* Remove the old value. */ void *first_val = s->base + min_offs; size_t offs = le16_to_cpu(here->e_value_offs); void *val = s->base + offs; memmove(first_val + old_size, first_val, val - first_val); memset(first_val, 0, old_size); min_offs += old_size; /* Adjust all value offsets. */ last = s->first; while (!IS_LAST_ENTRY(last)) { size_t o = le16_to_cpu(last->e_value_offs); if (!last->e_value_inum && last->e_value_size && o < offs) last->e_value_offs = cpu_to_le16(o + old_size); last = EXT4_XATTR_NEXT(last); } } if (!i->value) { /* Remove old name. */ size_t size = EXT4_XATTR_LEN(name_len); last = ENTRY((void *)last - size); memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); /* * Update i_inline_off - moved ibody region might contain * system.data attribute. Handling a failure here won't * cause other complications for setting an xattr. */ if (!is_block && ext4_has_inline_data(inode)) { ret = ext4_find_inline_data_nolock(inode); if (ret) { ext4_warning_inode(inode, "unable to update i_inline_off"); goto out; } } } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len); size_t rest = (void *)last - (void *)here + sizeof(__u32); memmove((void *)here + size, here, rest); memset(here, 0, size); here->e_name_index = i->name_index; here->e_name_len = name_len; memcpy(here->e_name, i->name, name_len); } else { /* This is an update, reset value info. */ here->e_value_inum = 0; here->e_value_offs = 0; here->e_value_size = 0; } if (i->value) { /* Insert new value. */ if (in_inode) { here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino); } else if (i->value_len) { void *val = s->base + min_offs - new_size; here->e_value_offs = cpu_to_le16(min_offs - new_size); if (i->value == EXT4_ZERO_XATTR_VALUE) { memset(val, 0, new_size); } else { memcpy(val, i->value, i->value_len); /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } } here->e_value_size = cpu_to_le32(i->value_len); } update_hash: if (i->value) { __le32 hash = 0; /* Entry hash calculation. */ if (in_inode) { __le32 crc32c_hash; /* * Feed crc32c hash instead of the raw value for entry * hash calculation. This is to avoid walking * potentially long value buffer again. */ crc32c_hash = cpu_to_le32( ext4_xattr_inode_get_hash(new_ea_inode)); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, &crc32c_hash, 1); } else if (is_block) { __le32 *value = s->base + le16_to_cpu( here->e_value_offs); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, value, new_size >> 2); } here->e_hash = hash; } if (is_block) ext4_xattr_rehash((struct ext4_xattr_header *)s->base); ret = 0; out: iput(old_ea_inode); return ret; } struct ext4_xattr_block_find { struct ext4_xattr_search s; struct buffer_head *bh; }; static int ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_block_find *bs) { struct super_block *sb = inode->i_sb; int error; ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld", i->name_index, i->name, i->value, (long)i->value_len); if (EXT4_I(inode)->i_file_acl) { /* The inode already has an extended attribute block. */ bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bs->bh)) { error = PTR_ERR(bs->bh); bs->bh = NULL; return error; } ea_bdebug(bs->bh, "b_count=%d, refcount=%d", atomic_read(&(bs->bh->b_count)), le32_to_cpu(BHDR(bs->bh)->h_refcount)); error = ext4_xattr_check_block(inode, bs->bh); if (error) return error; /* Find the named attribute. */ bs->s.base = BHDR(bs->bh); bs->s.first = BFIRST(bs->bh); bs->s.end = bs->bh->b_data + bs->bh->b_size; bs->s.here = bs->s.first; error = xattr_find_entry(inode, &bs->s.here, bs->s.end, i->name_index, i->name, 1); if (error && error != -ENODATA) return error; bs->s.not_found = error; } return 0; } static int ext4_xattr_block_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_block_find *bs) { struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; struct ext4_xattr_search s_copy = bs->s; struct ext4_xattr_search *s = &s_copy; struct mb_cache_entry *ce = NULL; int error = 0; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); struct inode *ea_inode = NULL, *tmp_inode; size_t old_ea_inode_quota = 0; unsigned int ea_ino; #define header(x) ((struct ext4_xattr_header *)(x)) /* If we need EA inode, prepare it before locking the buffer */ if (i->value && i->in_inode) { WARN_ON_ONCE(!i->value_len); ea_inode = ext4_xattr_inode_lookup_create(handle, inode, i->value, i->value_len); if (IS_ERR(ea_inode)) { error = PTR_ERR(ea_inode); ea_inode = NULL; goto cleanup; } } if (s->base) { int offset = (char *)s->here - bs->bh->b_data; BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, sb, bs->bh, EXT4_JTR_NONE); if (error) goto cleanup; lock_buffer(bs->bh); if (header(s->base)->h_refcount == cpu_to_le32(1)) { __u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash); /* * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect modified * block */ if (ea_block_cache) { struct mb_cache_entry *oe; oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, bs->bh->b_blocknr); if (oe) { /* * Xattr block is getting reused. Leave * it alone. */ mb_cache_entry_put(ea_block_cache, oe); goto clone_block; } } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, true /* is_block */); ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) goto bad_block; if (!error) error = ext4_handle_dirty_metadata(handle, inode, bs->bh); if (error) goto cleanup; goto inserted; } clone_block: unlock_buffer(bs->bh); ea_bdebug(bs->bh, "cloning"); s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; s->first = ENTRY(header(s->base)+1); header(s->base)->h_refcount = cpu_to_le32(1); s->here = ENTRY(s->base + offset); s->end = s->base + bs->bh->b_size; /* * If existing entry points to an xattr inode, we need * to prevent ext4_xattr_set_entry() from decrementing * ref count on it because the reference belongs to the * original block. In this case, make the entry look * like it has an empty value. */ if (!s->not_found && s->here->e_value_inum) { ea_ino = le32_to_cpu(s->here->e_value_inum); error = ext4_xattr_inode_iget(inode, ea_ino, le32_to_cpu(s->here->e_hash), &tmp_inode); if (error) goto cleanup; if (!ext4_test_inode_state(tmp_inode, EXT4_STATE_LUSTRE_EA_INODE)) { /* * Defer quota free call for previous * inode until success is guaranteed. */ old_ea_inode_quota = le32_to_cpu( s->here->e_value_size); } iput(tmp_inode); s->here->e_value_inum = 0; s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ s->base = kzalloc(sb->s_blocksize, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); header(s->base)->h_blocks = cpu_to_le32(1); header(s->base)->h_refcount = cpu_to_le32(1); s->first = ENTRY(header(s->base)+1); s->here = ENTRY(header(s->base)+1); s->end = s->base + sb->s_blocksize; } error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, true /* is_block */); if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; inserted: if (!IS_LAST_ENTRY(s->first)) { new_bh = ext4_xattr_block_cache_find(inode, header(s->base), &ce); if (IS_ERR(new_bh)) { error = PTR_ERR(new_bh); new_bh = NULL; goto cleanup; } if (new_bh) { /* We found an identical block in the cache. */ if (new_bh == bs->bh) ea_bdebug(new_bh, "keeping"); else { u32 ref; #ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); #endif /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); if (error) goto cleanup; BUFFER_TRACE(new_bh, "get_write_access"); error = ext4_journal_get_write_access( handle, sb, new_bh, EXT4_JTR_NONE); if (error) goto cleanup_dquot; lock_buffer(new_bh); /* * We have to be careful about races with * adding references to xattr block. Once we * hold buffer lock xattr block's state is * stable so we can check the additional * reference fits. */ ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. */ unlock_buffer(new_bh); dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); brelse(new_bh); mb_cache_entry_put(ea_block_cache, ce); ce = NULL; new_bh = NULL; goto inserted; } BHDR(new_bh)->h_refcount = cpu_to_le32(ref); if (ref == EXT4_XATTR_REFCOUNT_MAX) clear_bit(MBE_REUSABLE_B, &ce->e_flags); ea_bdebug(new_bh, "reusing; refcount now=%d", ref); ext4_xattr_block_csum_set(inode, new_bh); unlock_buffer(new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) goto cleanup_dquot; } mb_cache_entry_touch(ea_block_cache, ce); mb_cache_entry_put(ea_block_cache, ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ ea_bdebug(bs->bh, "keeping this block"); ext4_xattr_block_cache_insert(ea_block_cache, bs->bh); new_bh = bs->bh; get_bh(new_bh); } else { /* We need to allocate a new block */ ext4_fsblk_t goal, block; #ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); #endif goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); block = ext4_new_meta_blocks(handle, inode, goal, 0, NULL, &error); if (error) goto cleanup; ea_idebug(inode, "creating block %llu", (unsigned long long)block); new_bh = sb_getblk(sb, block); if (unlikely(!new_bh)) { error = -ENOMEM; getblk_failed: ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA); goto cleanup; } error = ext4_xattr_inode_inc_ref_all(handle, inode, ENTRY(header(s->base)+1)); if (error) goto getblk_failed; if (ea_inode) { /* Drop the extra ref on ea_inode. */ error = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error) ext4_warning_inode(ea_inode, "dec ref error=%d", error); iput(ea_inode); ea_inode = NULL; } lock_buffer(new_bh); error = ext4_journal_get_create_access(handle, sb, new_bh, EXT4_JTR_NONE); if (error) { unlock_buffer(new_bh); error = -EIO; goto getblk_failed; } memcpy(new_bh->b_data, s->base, new_bh->b_size); ext4_xattr_block_csum_set(inode, new_bh); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); ext4_xattr_block_cache_insert(ea_block_cache, new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) goto cleanup; } } if (old_ea_inode_quota) ext4_xattr_inode_free_quota(inode, NULL, old_ea_inode_quota); /* Update the inode. */ EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; /* Drop the previous xattr block. */ if (bs->bh && bs->bh != new_bh) { struct ext4_xattr_inode_array *ea_inode_array = NULL; ext4_xattr_release_block(handle, inode, bs->bh, &ea_inode_array, 0 /* extra_credits */); ext4_xattr_inode_array_free(ea_inode_array); } error = 0; cleanup: if (ea_inode) { if (error) { int error2; error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error2) ext4_warning_inode(ea_inode, "dec ref error=%d", error2); ext4_xattr_inode_free_quota(inode, ea_inode, i_size_read(ea_inode)); } iput(ea_inode); } if (ce) mb_cache_entry_put(ea_block_cache, ce); brelse(new_bh); if (!(bs->bh && s->base == bs->bh->b_data)) kfree(s->base); return error; cleanup_dquot: dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); goto cleanup; bad_block: EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); goto cleanup; #undef header } int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; int error; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); is->s.here = is->s.first; is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { error = xattr_check_inode(inode, header, is->s.end); if (error) return error; /* Find the named attribute. */ error = xattr_find_entry(inode, &is->s.here, is->s.end, i->name_index, i->name, 0); if (error && error != -ENODATA) return error; is->s.not_found = error; } return 0; } int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_search *s = &is->s; struct inode *ea_inode = NULL; int error; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; /* If we need EA inode, prepare it before locking the buffer */ if (i->value && i->in_inode) { WARN_ON_ONCE(!i->value_len); ea_inode = ext4_xattr_inode_lookup_create(handle, inode, i->value, i->value_len); if (IS_ERR(ea_inode)) return PTR_ERR(ea_inode); } error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, false /* is_block */); if (error) { if (ea_inode) { int error2; error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error2) ext4_warning_inode(ea_inode, "dec ref error=%d", error2); ext4_xattr_inode_free_quota(inode, ea_inode, i_size_read(ea_inode)); iput(ea_inode); } return error; } header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); ext4_set_inode_state(inode, EXT4_STATE_XATTR); } else { header->h_magic = cpu_to_le32(0); ext4_clear_inode_state(inode, EXT4_STATE_XATTR); } iput(ea_inode); return 0; } static int ext4_xattr_value_same(struct ext4_xattr_search *s, struct ext4_xattr_info *i) { void *value; /* When e_value_inum is set the value is stored externally. */ if (s->here->e_value_inum) return 0; if (le32_to_cpu(s->here->e_value_size) != i->value_len) return 0; value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs); return !memcmp(value, i->value, i->value_len); } static struct buffer_head *ext4_xattr_get_block(struct inode *inode) { struct buffer_head *bh; int error; if (!EXT4_I(inode)->i_file_acl) return NULL; bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return bh; error = ext4_xattr_check_block(inode, bh); if (error) { brelse(bh); return ERR_PTR(error); } return bh; } /* * ext4_xattr_set_handle() * * Create, replace or remove an extended attribute for this inode. Value * is NULL to remove an existing extended attribute, and non-NULL to * either replace an existing extended attribute, or create a new extended * attribute. The flags XATTR_REPLACE and XATTR_CREATE * specify that an extended attribute must exist and must not exist * previous to the call, respectively. * * Returns 0, or a negative error number on failure. */ int ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { struct ext4_xattr_info i = { .name_index = name_index, .name = name, .value = value, .value_len = value_len, .in_inode = 0, }; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_block_find bs = { .s = { .not_found = -ENODATA, }, }; int no_expand; int error; if (!name) return -EINVAL; if (strlen(name) > 255) return -ERANGE; ext4_write_lock_xattr(inode, &no_expand); /* Check journal credits under write lock. */ if (ext4_handle_valid(handle)) { struct buffer_head *bh; int credits; bh = ext4_xattr_get_block(inode); if (IS_ERR(bh)) { error = PTR_ERR(bh); goto cleanup; } credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, value_len, flags & XATTR_CREATE); brelse(bh); if (jbd2_handle_buffer_credits(handle) < credits) { error = -ENOSPC; goto cleanup; } WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } error = ext4_reserve_inode_write(handle, inode, &is.iloc); if (error) goto cleanup; if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) { struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc); memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); ext4_clear_inode_state(inode, EXT4_STATE_NEW); } error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto cleanup; if (is.s.not_found) error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; if (is.s.not_found && bs.s.not_found) { error = -ENODATA; if (flags & XATTR_REPLACE) goto cleanup; error = 0; if (!value) goto cleanup; } else { error = -EEXIST; if (flags & XATTR_CREATE) goto cleanup; } if (!value) { if (!is.s.not_found) error = ext4_xattr_ibody_set(handle, inode, &i, &is); else if (!bs.s.not_found) error = ext4_xattr_block_set(handle, inode, &i, &bs); } else { error = 0; /* Xattr value did not change? Save us some work and bail out */ if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i)) goto cleanup; if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i)) goto cleanup; if (ext4_has_feature_ea_inode(inode->i_sb) && (EXT4_XATTR_SIZE(i.value_len) > EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize))) i.in_inode = 1; retry_inode: error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (!error && !bs.s.not_found) { i.value = NULL; error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { brelse(bs.bh); bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; } error = ext4_xattr_block_set(handle, inode, &i, &bs); if (!error && !is.s.not_found) { i.value = NULL; error = ext4_xattr_ibody_set(handle, inode, &i, &is); } else if (error == -ENOSPC) { /* * Xattr does not fit in the block, store at * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; } } } } if (!error) { ext4_xattr_update_super_block(handle, inode->i_sb); inode_set_ctime_current(inode); inode_inc_iversion(inode); if (!value) no_expand = 0; error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); /* * The bh is consumed by ext4_mark_iloc_dirty, even with * error != 0. */ is.iloc.bh = NULL; if (IS_SYNC(inode)) ext4_handle_sync(handle); } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); cleanup: brelse(is.iloc.bh); brelse(bs.bh); ext4_write_unlock_xattr(inode, &no_expand); return error; } int ext4_xattr_set_credits(struct inode *inode, size_t value_len, bool is_create, int *credits) { struct buffer_head *bh; int err; *credits = 0; if (!EXT4_SB(inode->i_sb)->s_journal) return 0; down_read(&EXT4_I(inode)->xattr_sem); bh = ext4_xattr_get_block(inode); if (IS_ERR(bh)) { err = PTR_ERR(bh); } else { *credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, value_len, is_create); brelse(bh); err = 0; } up_read(&EXT4_I(inode)->xattr_sem); return err; } /* * ext4_xattr_set() * * Like ext4_xattr_set_handle, but start from an inode. This extended * attribute modification is a filesystem transaction by itself. * * Returns 0, or a negative error number on failure. */ int ext4_xattr_set(struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { handle_t *handle; struct super_block *sb = inode->i_sb; int error, retries = 0; int credits; error = dquot_initialize(inode); if (error) return error; retry: error = ext4_xattr_set_credits(inode, value_len, flags & XATTR_CREATE, &credits); if (error) return error; handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) { error = PTR_ERR(handle); } else { int error2; error = ext4_xattr_set_handle(handle, inode, name_index, name, value, value_len, flags); ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); error2 = ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) goto retry; if (error == 0) error = error2; } return error; } /* * Shift the EA entries in the inode to create space for the increased * i_extra_isize. */ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry, int value_offs_shift, void *to, void *from, size_t n) { struct ext4_xattr_entry *last = entry; int new_offs; /* We always shift xattr headers further thus offsets get lower */ BUG_ON(value_offs_shift > 0); /* Adjust the value offsets of the entries */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { if (!last->e_value_inum && last->e_value_size) { new_offs = le16_to_cpu(last->e_value_offs) + value_offs_shift; last->e_value_offs = cpu_to_le16(new_offs); } } /* Shift the entries by n bytes */ memmove(to, from, n); } /* * Move xattr pointed to by 'entry' from inode into external xattr block */ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, struct ext4_inode *raw_inode, struct ext4_xattr_entry *entry) { struct ext4_xattr_ibody_find *is = NULL; struct ext4_xattr_block_find *bs = NULL; char *buffer = NULL, *b_entry_name = NULL; size_t value_size = le32_to_cpu(entry->e_value_size); struct ext4_xattr_info i = { .value = NULL, .value_len = 0, .name_index = entry->e_name_index, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); if (!is || !bs || !b_entry_name) { error = -ENOMEM; goto out; } is->s.not_found = -ENODATA; bs->s.not_found = -ENODATA; is->iloc.bh = NULL; bs->bh = NULL; /* Save the entry name and the entry value */ if (entry->e_value_inum) { buffer = kvmalloc(value_size, GFP_NOFS); if (!buffer) { error = -ENOMEM; goto out; } needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); buffer = (void *)IFIRST(header) + value_offs; } memcpy(b_entry_name, entry->e_name, entry->e_name_len); b_entry_name[entry->e_name_len] = '\0'; i.name = b_entry_name; error = ext4_get_inode_loc(inode, &is->iloc); if (error) goto out; error = ext4_xattr_ibody_find(inode, &i, is); if (error) goto out; i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; /* Move ea entry from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; /* Remove the chosen entry from the inode */ i.value = NULL; i.value_len = 0; error = ext4_xattr_ibody_set(handle, inode, &i, is); out: kfree(b_entry_name); if (needs_kvfree && buffer) kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) brelse(bs->bh); kfree(is); kfree(bs); return error; } static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, struct ext4_inode *raw_inode, int isize_diff, size_t ifree, size_t bfree, int *total_ino) { struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); struct ext4_xattr_entry *small_entry; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *last; unsigned int entry_size; /* EA entry size */ unsigned int total_size; /* EA entry size + value size */ unsigned int min_total_size; int error; while (isize_diff > ifree) { entry = NULL; small_entry = NULL; min_total_size = ~0U; last = IFIRST(header); /* Find the entry best suited to be pushed into EA block */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { /* never move system.data out of the inode */ if ((last->e_name_len == 4) && (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) && !memcmp(last->e_name, "data", 4)) continue; total_size = EXT4_XATTR_LEN(last->e_name_len); if (!last->e_value_inum) total_size += EXT4_XATTR_SIZE( le32_to_cpu(last->e_value_size)); if (total_size <= bfree && total_size < min_total_size) { if (total_size + ifree < isize_diff) { small_entry = last; } else { entry = last; min_total_size = total_size; } } } if (entry == NULL) { if (small_entry == NULL) return -ENOSPC; entry = small_entry; } entry_size = EXT4_XATTR_LEN(entry->e_name_len); total_size = entry_size; if (!entry->e_value_inum) total_size += EXT4_XATTR_SIZE( le32_to_cpu(entry->e_value_size)); error = ext4_xattr_move_to_block(handle, inode, raw_inode, entry); if (error) return error; *total_ino -= entry_size; ifree += total_size; bfree -= total_size; } return 0; } /* * Expand an inode by new_extra_isize bytes when EAs are present. * Returns 0 on success or negative error number on failure. */ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; size_t ifree, bfree; int total_ino; void *base, *end; int error = 0, tried_min_extra_isize = 0; int s_min_extra_isize = le16_to_cpu(sbi->s_es->s_min_extra_isize); int isize_diff; /* How much do we need to grow i_extra_isize */ retry: isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) return 0; header = IHDR(inode, raw_inode); /* * Check if enough free space is available in the inode to shift the * entries ahead by new_extra_isize. */ base = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; min_offs = end - base; total_ino = sizeof(struct ext4_xattr_ibody_header) + sizeof(u32); error = xattr_check_inode(inode, header, end); if (error) goto cleanup; ifree = ext4_xattr_free_space(base, &min_offs, base, &total_ino); if (ifree >= isize_diff) goto shift; /* * Enough free space isn't available in the inode, check if * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { struct buffer_head *bh; bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); goto cleanup; } error = ext4_xattr_check_block(inode, bh); if (error) { brelse(bh); goto cleanup; } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base, NULL); brelse(bh); if (bfree + ifree < isize_diff) { if (!tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; goto retry; } error = -ENOSPC; goto cleanup; } } else { bfree = inode->i_sb->s_blocksize; } error = ext4_xattr_make_inode_space(handle, inode, raw_inode, isize_diff, ifree, bfree, &total_ino); if (error) { if (error == -ENOSPC && !tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; goto retry; } goto cleanup; } shift: /* Adjust the offsets and shift the remaining entries ahead */ ext4_xattr_shift_entries(IFIRST(header), EXT4_I(inode)->i_extra_isize - new_extra_isize, (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize, (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; if (ext4_has_inline_data(inode)) error = ext4_find_inline_data_nolock(inode); cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", inode->i_ino); mnt_count = le16_to_cpu(sbi->s_es->s_mnt_count); } return error; } #define EIA_INCR 16 /* must be 2^n */ #define EIA_MASK (EIA_INCR - 1) /* Add the large xattr @inode into @ea_inode_array for deferred iput(). * If @ea_inode_array is new or full it will be grown and the old * contents copied over. */ static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode) { if (*ea_inode_array == NULL) { /* * Start with 15 inodes, so it fits into a power-of-two size. */ (*ea_inode_array) = kmalloc( struct_size(*ea_inode_array, inodes, EIA_MASK), GFP_NOFS); if (*ea_inode_array == NULL) return -ENOMEM; (*ea_inode_array)->count = 0; } else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) { /* expand the array once all 15 + n * 16 slots are full */ struct ext4_xattr_inode_array *new_array = NULL; new_array = kmalloc( struct_size(*ea_inode_array, inodes, (*ea_inode_array)->count + EIA_INCR), GFP_NOFS); if (new_array == NULL) return -ENOMEM; memcpy(new_array, *ea_inode_array, struct_size(*ea_inode_array, inodes, (*ea_inode_array)->count)); kfree(*ea_inode_array); *ea_inode_array = new_array; } (*ea_inode_array)->count++; (*ea_inode_array)->inodes[(*ea_inode_array)->count - 1] = inode; return 0; } /* * ext4_xattr_delete_inode() * * Free extended attribute resources associated with this inode. Traverse * all entries and decrement reference on any xattr inodes associated with this * inode. This is called immediately before an inode is freed. We have exclusive * access to the inode. If an orphan inode is deleted it will also release its * references on xattr block and xattr inodes. */ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits) { struct buffer_head *bh = NULL; struct ext4_xattr_ibody_header *header; struct ext4_iloc iloc = { .bh = NULL }; struct ext4_xattr_entry *entry; struct inode *ea_inode; int error; error = ext4_journal_ensure_credits(handle, extra_credits, ext4_free_metadata_revoke_credits(inode->i_sb, 1)); if (error < 0) { EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error); goto cleanup; } if (ext4_has_feature_ea_inode(inode->i_sb) && ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { error = ext4_get_inode_loc(inode, &iloc); if (error) { EXT4_ERROR_INODE(inode, "inode loc (error %d)", error); goto cleanup; } error = ext4_journal_get_write_access(handle, inode->i_sb, iloc.bh, EXT4_JTR_NONE); if (error) { EXT4_ERROR_INODE(inode, "write access (error %d)", error); goto cleanup; } header = IHDR(inode, ext4_raw_inode(&iloc)); if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC)) ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh, IFIRST(header), false /* block_csum */, ea_inode_array, extra_credits, false /* skip_quota */); } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); if (error == -EIO) { EXT4_ERROR_INODE_ERR(inode, EIO, "block %llu read error", EXT4_I(inode)->i_file_acl); } bh = NULL; goto cleanup; } error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; if (ext4_has_feature_ea_inode(inode->i_sb)) { for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; error = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (error) continue; ext4_xattr_inode_free_quota(inode, ea_inode, le32_to_cpu(entry->e_value_size)); iput(ea_inode); } } ext4_xattr_release_block(handle, inode, bh, ea_inode_array, extra_credits); /* * Update i_file_acl value in the same transaction that releases * block. */ EXT4_I(inode)->i_file_acl = 0; error = ext4_mark_inode_dirty(handle, inode); if (error) { EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)", error); goto cleanup; } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); } error = 0; cleanup: brelse(iloc.bh); brelse(bh); return error; } void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array) { int idx; if (ea_inode_array == NULL) return; for (idx = 0; idx < ea_inode_array->count; ++idx) iput(ea_inode_array->inodes[idx]); kfree(ea_inode_array); } /* * ext4_xattr_block_cache_insert() * * Create a new entry in the extended attribute block cache, and insert * it unless such an entry is already in the cache. */ static void ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache, struct buffer_head *bh) { struct ext4_xattr_header *header = BHDR(bh); __u32 hash = le32_to_cpu(header->h_hash); int reusable = le32_to_cpu(header->h_refcount) < EXT4_XATTR_REFCOUNT_MAX; int error; if (!ea_block_cache) return; error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash, bh->b_blocknr, reusable); if (error) { if (error == -EBUSY) ea_bdebug(bh, "already in cache"); } else ea_bdebug(bh, "inserting [%x]", (int)hash); } /* * ext4_xattr_cmp() * * Compare two extended attribute blocks for equality. * * Returns 0 if the blocks are equal, 1 if they differ. */ static int ext4_xattr_cmp(struct ext4_xattr_header *header1, struct ext4_xattr_header *header2) { struct ext4_xattr_entry *entry1, *entry2; entry1 = ENTRY(header1+1); entry2 = ENTRY(header2+1); while (!IS_LAST_ENTRY(entry1)) { if (IS_LAST_ENTRY(entry2)) return 1; if (entry1->e_hash != entry2->e_hash || entry1->e_name_index != entry2->e_name_index || entry1->e_name_len != entry2->e_name_len || entry1->e_value_size != entry2->e_value_size || entry1->e_value_inum != entry2->e_value_inum || memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) return 1; if (!entry1->e_value_inum && memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), (char *)header2 + le16_to_cpu(entry2->e_value_offs), le32_to_cpu(entry1->e_value_size))) return 1; entry1 = EXT4_XATTR_NEXT(entry1); entry2 = EXT4_XATTR_NEXT(entry2); } if (!IS_LAST_ENTRY(entry2)) return 1; return 0; } /* * ext4_xattr_block_cache_find() * * Find an identical extended attribute block. * * Returns a pointer to the block found, or NULL if such a block was not * found, or an error pointer if an error occurred while reading ea block. */ static struct buffer_head * ext4_xattr_block_cache_find(struct inode *inode, struct ext4_xattr_header *header, struct mb_cache_entry **pce) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (!ea_block_cache) return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { if (PTR_ERR(bh) != -ENOMEM) EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); mb_cache_entry_put(ea_block_cache, ce); return bh; } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { *pce = ce; return bh; } brelse(bh); ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } #define NAME_HASH_SHIFT 5 #define VALUE_HASH_SHIFT 16 /* * ext4_xattr_hash_entry() * * Compute the hash of an extended attribute. */ static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count) { __u32 hash = 0; while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ (unsigned char)*name++; } while (value_count--) { hash = (hash << VALUE_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ le32_to_cpu(*value++); } return cpu_to_le32(hash); } /* * ext4_xattr_hash_entry_signed() * * Compute the hash of an extended attribute incorrectly. */ static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count) { __u32 hash = 0; while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ (signed char)*name++; } while (value_count--) { hash = (hash << VALUE_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ le32_to_cpu(*value++); } return cpu_to_le32(hash); } #undef NAME_HASH_SHIFT #undef VALUE_HASH_SHIFT #define BLOCK_HASH_SHIFT 16 /* * ext4_xattr_rehash() * * Re-compute the extended attribute hash value after an entry has changed. */ static void ext4_xattr_rehash(struct ext4_xattr_header *header) { struct ext4_xattr_entry *here; __u32 hash = 0; here = ENTRY(header+1); while (!IS_LAST_ENTRY(here)) { if (!here->e_hash) { /* Block is not shared if an entry's hash value == 0 */ hash = 0; break; } hash = (hash << BLOCK_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^ le32_to_cpu(here->e_hash); here = EXT4_XATTR_NEXT(here); } header->h_hash = cpu_to_le32(hash); } #undef BLOCK_HASH_SHIFT #define HASH_BUCKET_BITS 10 struct mb_cache * ext4_xattr_create_cache(void) { return mb_cache_create(HASH_BUCKET_BITS); } void ext4_xattr_destroy_cache(struct mb_cache *cache) { if (cache) mb_cache_destroy(cache); } |
| 5 5 12 2 1 5 2 1 1 1 1 1 1 2 1 1 1 5 2 2 37 37 1 66 66 118 118 80 80 108 108 22 22 101 101 | 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(sizeof(*doi_def), GFP_KERNEL); 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; } |
| 8392 137 5883 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vmalloc #if !defined(_TRACE_VMALLOC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VMALLOC_H #include <linux/tracepoint.h> /** * alloc_vmap_area - called when a new vmap allocation occurs * @addr: an allocated address * @size: a requested size * @align: a requested alignment * @vstart: a requested start range * @vend: a requested end range * @failed: an allocation failed or not * * This event is used for a debug purpose, it can give an extra * information for a developer about how often it occurs and which * parameters are passed for further validation. */ TRACE_EVENT(alloc_vmap_area, TP_PROTO(unsigned long addr, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int failed), TP_ARGS(addr, size, align, vstart, vend, failed), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, size) __field(unsigned long, align) __field(unsigned long, vstart) __field(unsigned long, vend) __field(int, failed) ), TP_fast_assign( __entry->addr = addr; __entry->size = size; __entry->align = align; __entry->vstart = vstart; __entry->vend = vend; __entry->failed = failed; ), TP_printk("va_start: %lu size=%lu align=%lu vstart=0x%lx vend=0x%lx failed=%d", __entry->addr, __entry->size, __entry->align, __entry->vstart, __entry->vend, __entry->failed) ); /** * purge_vmap_area_lazy - called when vmap areas were lazily freed * @start: purging start address * @end: purging end address * @npurged: numbed of purged vmap areas * * This event is used for a debug purpose. It gives some * indication about start:end range and how many objects * are released. */ TRACE_EVENT(purge_vmap_area_lazy, TP_PROTO(unsigned long start, unsigned long end, unsigned int npurged), TP_ARGS(start, end, npurged), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned int, npurged) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->npurged = npurged; ), TP_printk("start=0x%lx end=0x%lx num_purged=%u", __entry->start, __entry->end, __entry->npurged) ); /** * free_vmap_area_noflush - called when a vmap area is freed * @va_start: a start address of VA * @nr_lazy: number of current lazy pages * @nr_lazy_max: number of maximum lazy pages * * This event is used for a debug purpose. It gives some * indication about a VA that is released, number of current * outstanding areas and a maximum allowed threshold before * dropping all of them. */ TRACE_EVENT(free_vmap_area_noflush, TP_PROTO(unsigned long va_start, unsigned long nr_lazy, unsigned long nr_lazy_max), TP_ARGS(va_start, nr_lazy, nr_lazy_max), TP_STRUCT__entry( __field(unsigned long, va_start) __field(unsigned long, nr_lazy) __field(unsigned long, nr_lazy_max) ), TP_fast_assign( __entry->va_start = va_start; __entry->nr_lazy = nr_lazy; __entry->nr_lazy_max = nr_lazy_max; ), TP_printk("va_start=0x%lx nr_lazy=%lu nr_lazy_max=%lu", __entry->va_start, __entry->nr_lazy, __entry->nr_lazy_max) ); #endif /* _TRACE_VMALLOC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 255 255 186 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | #include <linux/dcache.h> #include "internal.h" unsigned name_to_int(const struct qstr *qstr) { const char *name = qstr->name; int len = qstr->len; unsigned n = 0; if (len > 1 && *name == '0') goto out; do { unsigned c = *name++ - '0'; if (c > 9) goto out; if (n >= (~0U-9)/10) goto out; n *= 10; n += c; } while (--len > 0); return n; out: return ~0U; } |
| 8 2054 115 55074 119 12323 7614 279 807 332 7153 7153 975 463 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL #define mask_user_address(src) (src) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } /* * Architectures that #define INLINE_COPY_TO_USER use this function * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. * * Rust code always uses the extern definition. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (should_fail_usercopy()) goto fail; if (can_do_masked_user_access()) from = mask_user_address(from); else { if (!access_ok(from, n)) goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); } instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); if (likely(!res)) return 0; fail: memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (!check_copy_size(to, n, false)) return n; #ifdef INLINE_COPY_FROM_USER return _inline_copy_from_user(to, from, n); #else return _copy_from_user(to, from, n); #endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (!check_copy_size(from, n, true)) return n; #ifdef INLINE_COPY_TO_USER return _inline_copy_to_user(to, from, n); #else return _copy_to_user(to, from, n); #endif } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } /** * copy_struct_to_user: copy a struct to userspace * @dst: Destination address, in userspace. This buffer must be @ksize * bytes long. * @usize: (Alleged) size of @dst struct. * @src: Source address, in kernel space. * @ksize: Size of @src struct. * @ignored_trailing: Set to %true if there was a non-zero byte in @src that * userspace cannot see because they are using an smaller struct. * * Copies a struct from kernel space to userspace, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * Some syscalls may wish to make sure that userspace knows about everything in * the struct, and if there is a non-zero value that userspce doesn't know * about, they want to return an error (such as -EMSGSIZE) or have some other * fallback (such as adding a "you're missing some information" flag). If * @ignored_trailing is non-%NULL, it will be set to %true if there was a * non-zero byte that could not be copied to userspace (ie. was past @usize). * * While unconditionally returning an error in this case is the simplest * solution, for maximum backward compatibility you should try to only return * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. * Note that structure sizes can change due to header changes and simple * recompilations without code changes(!), so if you care about * @ignored_trailing you probably want to make sure that any new field data is * associated with a flag. Otherwise you might assume that a program knows * about data it does not. * * @ksize is just sizeof(*src), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) * { * int err; * bool ignored_trailing; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * // ... modify karg somehow ... * * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), * &ignored_trailing); * if (err) * return err; * if (ignored_trailing) * return -EMSGSIZE: * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the kernel is trying to pass userspace a newer * struct than it supports. Thus we only copy the interoperable portions * (@usize) and ignore the rest (but @ignored_trailing is set to %true if * any of the trailing (@ksize - @usize) bytes are non-zero). * * If @usize > @ksize, then the kernel is trying to pass userspace an older * struct than userspace supports. In order to make sure the * unknown-to-the-kernel fields don't contain garbage values, we zero the * trailing (@usize - @ksize) bytes. * * Returns (in all cases, some data may have been copied): * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_to_user(void __user *dst, size_t usize, const void *src, size_t ksize, bool *ignored_trailing) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize > ksize) { if (clear_user(dst + size, rest)) return -EFAULT; } if (ignored_trailing) *ignored_trailing = ksize < usize && memchr_inv(src + size, 0, rest) != NULL; /* Copy the interoperable parts of the struct. */ if (copy_to_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifndef __get_kernel_nofault #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 49 49 48 48 49 438 435 49 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vmscan #if !defined(_TRACE_VMSCAN_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VMSCAN_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <trace/events/mmflags.h> #define RECLAIM_WB_ANON 0x0001u #define RECLAIM_WB_FILE 0x0002u #define RECLAIM_WB_MIXED 0x0010u #define RECLAIM_WB_SYNC 0x0004u /* Unused, all reclaim async */ #define RECLAIM_WB_ASYNC 0x0008u #define RECLAIM_WB_LRU (RECLAIM_WB_ANON|RECLAIM_WB_FILE) #define show_reclaim_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {RECLAIM_WB_ANON, "RECLAIM_WB_ANON"}, \ {RECLAIM_WB_FILE, "RECLAIM_WB_FILE"}, \ {RECLAIM_WB_MIXED, "RECLAIM_WB_MIXED"}, \ {RECLAIM_WB_SYNC, "RECLAIM_WB_SYNC"}, \ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) #define _VMSCAN_THROTTLE_CONGESTED (1 << VMSCAN_THROTTLE_CONGESTED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"}, \ {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ ) TRACE_EVENT(mm_vmscan_kswapd_sleep, TP_PROTO(int nid), TP_ARGS(nid), TP_STRUCT__entry( __field( int, nid ) ), TP_fast_assign( __entry->nid = nid; ), TP_printk("nid=%d", __entry->nid) ); TRACE_EVENT(mm_vmscan_kswapd_wake, TP_PROTO(int nid, int zid, int order), TP_ARGS(nid, zid, order), TP_STRUCT__entry( __field( int, nid ) __field( int, zid ) __field( int, order ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; ), TP_printk("nid=%d order=%d", __entry->nid, __entry->order) ); TRACE_EVENT(mm_vmscan_wakeup_kswapd, TP_PROTO(int nid, int zid, int order, gfp_t gfp_flags), TP_ARGS(nid, zid, order, gfp_flags), TP_STRUCT__entry( __field( int, nid ) __field( int, zid ) __field( int, order ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", __entry->nid, __entry->order, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags), TP_STRUCT__entry( __field( int, order ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("order=%d gfp_flags=%s", __entry->order, show_gfp_flags(__entry->gfp_flags)) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, TP_PROTO(int order, gfp_t gfp_flags), TP_ARGS(order, gfp_flags) ); #endif /* CONFIG_MEMCG */ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed), TP_STRUCT__entry( __field( unsigned long, nr_reclaimed ) ), TP_fast_assign( __entry->nr_reclaimed = nr_reclaimed; ), TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); #ifdef CONFIG_MEMCG DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); #endif /* CONFIG_MEMCG */ TRACE_EVENT(mm_shrink_slab_start, TP_PROTO(struct shrinker *shr, struct shrink_control *sc, long nr_objects_to_shrink, unsigned long cache_items, unsigned long long delta, unsigned long total_scan, int priority), TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan, priority), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) __field(int, priority) ), TP_fast_assign( __entry->shr = shr; __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; __entry->priority = priority; ), TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", __entry->shrink, __entry->shr, __entry->nid, __entry->nr_objects_to_shrink, show_gfp_flags(__entry->gfp_flags), __entry->cache_items, __entry->delta, __entry->total_scan, __entry->priority) ); TRACE_EVENT(mm_shrink_slab_end, TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval, long unused_scan_cnt, long new_scan_cnt, long total_scan), TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt, total_scan), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(int, nid) __field(void *, shrink) __field(long, unused_scan) __field(long, new_scan) __field(int, retval) __field(long, total_scan) ), TP_fast_assign( __entry->shr = shr; __entry->nid = nid; __entry->shrink = shr->scan_objects; __entry->unused_scan = unused_scan_cnt; __entry->new_scan = new_scan_cnt; __entry->retval = shrinker_retval; __entry->total_scan = total_scan; ), TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", __entry->shrink, __entry->shr, __entry->nid, __entry->unused_scan, __entry->new_scan, __entry->total_scan, __entry->retval) ); TRACE_EVENT(mm_vmscan_lru_isolate, TP_PROTO(int highest_zoneidx, int order, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_skipped, unsigned long nr_taken, int lru), TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, lru), TP_STRUCT__entry( __field(int, highest_zoneidx) __field(int, order) __field(unsigned long, nr_requested) __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) __field(int, lru) ), TP_fast_assign( __entry->highest_zoneidx = highest_zoneidx; __entry->order = order; __entry->nr_requested = nr_requested; __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; __entry->lru = lru; ), /* * classzone is previous name of the highest_zoneidx. * Reason not to change it is the ABI requirement of the tracepoint. */ TP_printk("classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", __entry->highest_zoneidx, __entry->order, __entry->nr_requested, __entry->nr_scanned, __entry->nr_skipped, __entry->nr_taken, __print_symbolic(__entry->lru, LRU_NAMES)) ); TRACE_EVENT(mm_vmscan_write_folio, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(int, reclaim_flags) ), TP_fast_assign( __entry->pfn = folio_pfn(folio); __entry->reclaim_flags = trace_reclaim_flags( folio_is_file_lru(folio)); ), TP_printk("page=%p pfn=0x%lx flags=%s", pfn_to_page(__entry->pfn), __entry->pfn, show_reclaim_flags(__entry->reclaim_flags)) ); TRACE_EVENT(mm_vmscan_reclaim_pages, TP_PROTO(int nid, unsigned long nr_scanned, unsigned long nr_reclaimed, struct reclaim_stat *stat), TP_ARGS(nid, nr_scanned, nr_reclaimed, stat), TP_STRUCT__entry( __field(int, nid) __field(unsigned long, nr_scanned) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, nr_congested) __field(unsigned long, nr_immediate) __field(unsigned int, nr_activate0) __field(unsigned int, nr_activate1) __field(unsigned long, nr_ref_keep) __field(unsigned long, nr_unmap_fail) ), TP_fast_assign( __entry->nid = nid; __entry->nr_scanned = nr_scanned; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_dirty = stat->nr_dirty; __entry->nr_writeback = stat->nr_writeback; __entry->nr_congested = stat->nr_congested; __entry->nr_immediate = stat->nr_immediate; __entry->nr_activate0 = stat->nr_activate[0]; __entry->nr_activate1 = stat->nr_activate[1]; __entry->nr_ref_keep = stat->nr_ref_keep; __entry->nr_unmap_fail = stat->nr_unmap_fail; ), TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld", __entry->nid, __entry->nr_scanned, __entry->nr_reclaimed, __entry->nr_dirty, __entry->nr_writeback, __entry->nr_congested, __entry->nr_immediate, __entry->nr_activate0, __entry->nr_activate1, __entry->nr_ref_keep, __entry->nr_unmap_fail) ); TRACE_EVENT(mm_vmscan_lru_shrink_inactive, TP_PROTO(int nid, unsigned long nr_scanned, unsigned long nr_reclaimed, struct reclaim_stat *stat, int priority, int file), TP_ARGS(nid, nr_scanned, nr_reclaimed, stat, priority, file), TP_STRUCT__entry( __field(int, nid) __field(unsigned long, nr_scanned) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, nr_congested) __field(unsigned long, nr_immediate) __field(unsigned int, nr_activate0) __field(unsigned int, nr_activate1) __field(unsigned long, nr_ref_keep) __field(unsigned long, nr_unmap_fail) __field(int, priority) __field(int, reclaim_flags) ), TP_fast_assign( __entry->nid = nid; __entry->nr_scanned = nr_scanned; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_dirty = stat->nr_dirty; __entry->nr_writeback = stat->nr_writeback; __entry->nr_congested = stat->nr_congested; __entry->nr_immediate = stat->nr_immediate; __entry->nr_activate0 = stat->nr_activate[0]; __entry->nr_activate1 = stat->nr_activate[1]; __entry->nr_ref_keep = stat->nr_ref_keep; __entry->nr_unmap_fail = stat->nr_unmap_fail; __entry->priority = priority; __entry->reclaim_flags = trace_reclaim_flags(file); ), TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld priority=%d flags=%s", __entry->nid, __entry->nr_scanned, __entry->nr_reclaimed, __entry->nr_dirty, __entry->nr_writeback, __entry->nr_congested, __entry->nr_immediate, __entry->nr_activate0, __entry->nr_activate1, __entry->nr_ref_keep, __entry->nr_unmap_fail, __entry->priority, show_reclaim_flags(__entry->reclaim_flags)) ); TRACE_EVENT(mm_vmscan_lru_shrink_active, TP_PROTO(int nid, unsigned long nr_taken, unsigned long nr_active, unsigned long nr_deactivated, unsigned long nr_referenced, int priority, int file), TP_ARGS(nid, nr_taken, nr_active, nr_deactivated, nr_referenced, priority, file), TP_STRUCT__entry( __field(int, nid) __field(unsigned long, nr_taken) __field(unsigned long, nr_active) __field(unsigned long, nr_deactivated) __field(unsigned long, nr_referenced) __field(int, priority) __field(int, reclaim_flags) ), TP_fast_assign( __entry->nid = nid; __entry->nr_taken = nr_taken; __entry->nr_active = nr_active; __entry->nr_deactivated = nr_deactivated; __entry->nr_referenced = nr_referenced; __entry->priority = priority; __entry->reclaim_flags = trace_reclaim_flags(file); ), TP_printk("nid=%d nr_taken=%ld nr_active=%ld nr_deactivated=%ld nr_referenced=%ld priority=%d flags=%s", __entry->nid, __entry->nr_taken, __entry->nr_active, __entry->nr_deactivated, __entry->nr_referenced, __entry->priority, show_reclaim_flags(__entry->reclaim_flags)) ); TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_PROTO(int nid, int order, gfp_t gfp_flags), TP_ARGS(nid, order, gfp_flags), TP_STRUCT__entry( __field(int, nid) __field(int, order) __field(unsigned long, gfp_flags) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", __entry->nid, __entry->order, show_gfp_flags(__entry->gfp_flags)) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, TP_PROTO(unsigned long nr_reclaimed), TP_ARGS(nr_reclaimed) ); TRACE_EVENT(mm_vmscan_throttled, TP_PROTO(int nid, int usec_timeout, int usec_delayed, int reason), TP_ARGS(nid, usec_timeout, usec_delayed, reason), TP_STRUCT__entry( __field(int, nid) __field(int, usec_timeout) __field(int, usec_delayed) __field(int, reason) ), TP_fast_assign( __entry->nid = nid; __entry->usec_timeout = usec_timeout; __entry->usec_delayed = usec_delayed; __entry->reason = 1U << reason; ), TP_printk("nid=%d usec_timeout=%d usect_delayed=%d reason=%s", __entry->nid, __entry->usec_timeout, __entry->usec_delayed, show_throttle_flags(__entry->reason)) ); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 33 33 33 31 33 3 30 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Randomness driver for virtio * Copyright (C) 2007, 2008 Rusty Russell IBM Corporation */ #include <asm/barrier.h> #include <linux/err.h> #include <linux/hw_random.h> #include <linux/scatterlist.h> #include <linux/spinlock.h> #include <linux/virtio.h> #include <linux/virtio_rng.h> #include <linux/module.h> #include <linux/slab.h> static DEFINE_IDA(rng_index_ida); struct virtrng_info { struct hwrng hwrng; struct virtqueue *vq; char name[25]; int index; bool hwrng_register_done; bool hwrng_removed; /* data transfer */ struct completion have_data; unsigned int data_avail; unsigned int data_idx; /* minimal size returned by rng_buffer_size() */ #if SMP_CACHE_BYTES < 32 u8 data[32]; #else u8 data[SMP_CACHE_BYTES]; #endif }; static void random_recv_done(struct virtqueue *vq) { struct virtrng_info *vi = vq->vdev->priv; unsigned int len; /* We can get spurious callbacks, e.g. shared IRQs + virtio_pci. */ if (!virtqueue_get_buf(vi->vq, &len)) return; smp_store_release(&vi->data_avail, len); complete(&vi->have_data); } static void request_entropy(struct virtrng_info *vi) { struct scatterlist sg; reinit_completion(&vi->have_data); vi->data_idx = 0; sg_init_one(&sg, vi->data, sizeof(vi->data)); /* There should always be room for one buffer. */ virtqueue_add_inbuf(vi->vq, &sg, 1, vi->data, GFP_KERNEL); virtqueue_kick(vi->vq); } static unsigned int copy_data(struct virtrng_info *vi, void *buf, unsigned int size) { size = min_t(unsigned int, size, vi->data_avail); memcpy(buf, vi->data + vi->data_idx, size); vi->data_idx += size; vi->data_avail -= size; if (vi->data_avail == 0) request_entropy(vi); return size; } static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) { int ret; struct virtrng_info *vi = (struct virtrng_info *)rng->priv; unsigned int chunk; size_t read; if (vi->hwrng_removed) return -ENODEV; read = 0; /* copy available data */ if (smp_load_acquire(&vi->data_avail)) { chunk = copy_data(vi, buf, size); size -= chunk; read += chunk; } if (!wait) return read; /* We have already copied available entropy, * so either size is 0 or data_avail is 0 */ while (size != 0) { /* data_avail is 0 but a request is pending */ ret = wait_for_completion_killable(&vi->have_data); if (ret < 0) return ret; /* if vi->data_avail is 0, we have been interrupted * by a cleanup, but buffer stays in the queue */ if (vi->data_avail == 0) return read; chunk = copy_data(vi, buf + read, size); size -= chunk; read += chunk; } return read; } static void virtio_cleanup(struct hwrng *rng) { struct virtrng_info *vi = (struct virtrng_info *)rng->priv; complete(&vi->have_data); } static int probe_common(struct virtio_device *vdev) { int err, index; struct virtrng_info *vi = NULL; vi = kzalloc(sizeof(struct virtrng_info), GFP_KERNEL); if (!vi) return -ENOMEM; vi->index = index = ida_alloc(&rng_index_ida, GFP_KERNEL); if (index < 0) { err = index; goto err_ida; } sprintf(vi->name, "virtio_rng.%d", index); init_completion(&vi->have_data); vi->hwrng = (struct hwrng) { .read = virtio_read, .cleanup = virtio_cleanup, .priv = (unsigned long)vi, .name = vi->name, }; vdev->priv = vi; /* We expect a single virtqueue. */ vi->vq = virtio_find_single_vq(vdev, random_recv_done, "input"); if (IS_ERR(vi->vq)) { err = PTR_ERR(vi->vq); goto err_find; } virtio_device_ready(vdev); /* we always have a pending entropy request */ request_entropy(vi); return 0; err_find: ida_free(&rng_index_ida, index); err_ida: kfree(vi); return err; } static void remove_common(struct virtio_device *vdev) { struct virtrng_info *vi = vdev->priv; vi->hwrng_removed = true; vi->data_avail = 0; vi->data_idx = 0; complete(&vi->have_data); if (vi->hwrng_register_done) hwrng_unregister(&vi->hwrng); virtio_reset_device(vdev); vdev->config->del_vqs(vdev); ida_free(&rng_index_ida, vi->index); kfree(vi); } static int virtrng_probe(struct virtio_device *vdev) { return probe_common(vdev); } static void virtrng_remove(struct virtio_device *vdev) { remove_common(vdev); } static void virtrng_scan(struct virtio_device *vdev) { struct virtrng_info *vi = vdev->priv; int err; err = hwrng_register(&vi->hwrng); if (!err) vi->hwrng_register_done = true; } static int virtrng_freeze(struct virtio_device *vdev) { remove_common(vdev); return 0; } static int virtrng_restore(struct virtio_device *vdev) { int err; err = probe_common(vdev); if (!err) { struct virtrng_info *vi = vdev->priv; /* * Set hwrng_removed to ensure that virtio_read() * does not block waiting for data before the * registration is complete. */ vi->hwrng_removed = true; err = hwrng_register(&vi->hwrng); if (!err) { vi->hwrng_register_done = true; vi->hwrng_removed = false; } } return err; } static const struct virtio_device_id id_table[] = { { VIRTIO_ID_RNG, VIRTIO_DEV_ANY_ID }, { 0 }, }; static struct virtio_driver virtio_rng_driver = { .driver.name = KBUILD_MODNAME, .id_table = id_table, .probe = virtrng_probe, .remove = virtrng_remove, .scan = virtrng_scan, .freeze = pm_sleep_ptr(virtrng_freeze), .restore = pm_sleep_ptr(virtrng_restore), }; module_virtio_driver(virtio_rng_driver); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio random number driver"); MODULE_LICENSE("GPL"); |
| 2 2 1 2 43 43 1 44 43 1 1 43 43 43 43 43 43 43 36 1 1 1 10 18 18 18 18 36 1 36 10 10 10 10 36 36 1 36 36 36 36 36 36 1 9 9 7 4 3 24 18 6 24 16 4 5 16 3 2 2 13 5 44 1 2 37 3 1 1 1 1 1 32 1 4 2 1 8 25 1 8 2 24 23 7 17 18 18 16 16 16 16 15 1 11 5 16 16 16 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_u32.c Ugly (or Universal) 32bit key Packet Classifier. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * The filters are packed to hash tables of key nodes * with a set of 32bit key/mask pairs at every node. * Nodes reference next level hash tables etc. * * This scheme is the best universal classifier I managed to * invent; it is not super-fast, but it is not slow (provided you * program it correctly), and general enough. And its relative * speed grows as the number of rules becomes larger. * * It seems that it represents the best middle point between * speed and manageability both by human and by machine. * * It is especially useful for link sharing combined with QoS; * pure RSVP doesn't need such a general approach and can use * much simpler (and faster) schemes, sort of cls_rsvp.c. * * nfmark match added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/percpu.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/bitmap.h> #include <linux/netdevice.h> #include <linux/hash.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <linux/idr.h> #include <net/tc_wrapper.h> struct tc_u_knode { struct tc_u_knode __rcu *next; u32 handle; struct tc_u_hnode __rcu *ht_up; struct tcf_exts exts; int ifindex; u8 fshift; struct tcf_result res; struct tc_u_hnode __rcu *ht_down; #ifdef CONFIG_CLS_U32_PERF struct tc_u32_pcnt __percpu *pf; #endif u32 flags; unsigned int in_hw_count; #ifdef CONFIG_CLS_U32_MARK u32 val; u32 mask; u32 __percpu *pcpu_success; #endif struct rcu_work rwork; /* The 'sel' field MUST be the last field in structure to allow for * tc_u32_keys allocated at end of structure. */ struct tc_u32_sel sel; }; struct tc_u_hnode { struct tc_u_hnode __rcu *next; u32 handle; u32 prio; refcount_t refcnt; unsigned int divisor; struct idr handle_idr; bool is_root; struct rcu_head rcu; u32 flags; /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. */ struct tc_u_knode __rcu *ht[]; }; struct tc_u_common { struct tc_u_hnode __rcu *hlist; void *ptr; refcount_t refcnt; struct idr handle_idr; struct hlist_node hnode; long knodes; }; static u32 handle2id(u32 h) { return ((h & 0x80000000) ? ((h >> 20) & 0x7FF) : h); } static u32 id2handle(u32 id) { return (id | 0x800U) << 20; } static inline unsigned int u32_hash_fold(__be32 key, const struct tc_u32_sel *sel, u8 fshift) { unsigned int h = ntohl(key & sel->hmask) >> fshift; return h; } TC_INDIRECT_SCOPE int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct { struct tc_u_knode *knode; unsigned int off; } stack[TC_U32_MAXDEPTH]; struct tc_u_hnode *ht = rcu_dereference_bh(tp->root); unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; int off2 = 0; int sel = 0; #ifdef CONFIG_CLS_U32_PERF int j; #endif int i, r; next_ht: n = rcu_dereference_bh(ht->ht[sel]); next_knode: if (n) { struct tc_u32_key *key = n->sel.keys; #ifdef CONFIG_CLS_U32_PERF __this_cpu_inc(n->pf->rcnt); j = 0; #endif if (tc_skip_sw(n->flags)) { n = rcu_dereference_bh(n->next); goto next_knode; } #ifdef CONFIG_CLS_U32_MARK if ((skb->mark & n->mask) != n->val) { n = rcu_dereference_bh(n->next); goto next_knode; } else { __this_cpu_inc(*n->pcpu_success); } #endif for (i = n->sel.nkeys; i > 0; i--, key++) { int toff = off + key->off + (off2 & key->offmask); __be32 *data, hdata; if (skb_headroom(skb) + toff > INT_MAX) goto out; data = skb_header_pointer(skb, toff, 4, &hdata); if (!data) goto out; if ((*data ^ key->val) & key->mask) { n = rcu_dereference_bh(n->next); goto next_knode; } #ifdef CONFIG_CLS_U32_PERF __this_cpu_inc(n->pf->kcnts[j]); j++; #endif } ht = rcu_dereference_bh(n->ht_down); if (!ht) { check_terminal: if (n->sel.flags & TC_U32_TERMINAL) { *res = n->res; if (!tcf_match_indev(skb, n->ifindex)) { n = rcu_dereference_bh(n->next); goto next_knode; } #ifdef CONFIG_CLS_U32_PERF __this_cpu_inc(n->pf->rhit); #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { n = rcu_dereference_bh(n->next); goto next_knode; } return r; } n = rcu_dereference_bh(n->next); goto next_knode; } /* PUSH */ if (sdepth >= TC_U32_MAXDEPTH) goto deadloop; stack[sdepth].knode = n; stack[sdepth].off = off; sdepth++; ht = rcu_dereference_bh(n->ht_down); sel = 0; if (ht->divisor) { __be32 *data, hdata; data = skb_header_pointer(skb, off + n->sel.hoff, 4, &hdata); if (!data) goto out; sel = ht->divisor & u32_hash_fold(*data, &n->sel, n->fshift); } if (!(n->sel.flags & (TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT))) goto next_ht; if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags & TC_U32_VAROFFSET) { __be16 *data, hdata; data = skb_header_pointer(skb, off + n->sel.offoff, 2, &hdata); if (!data) goto out; off2 += ntohs(n->sel.offmask & *data) >> n->sel.offshift; } off2 &= ~3; } if (n->sel.flags & TC_U32_EAT) { off += off2; off2 = 0; } if (off < skb->len) goto next_ht; } /* POP */ if (sdepth--) { n = stack[sdepth].knode; ht = rcu_dereference_bh(n->ht_up); off = stack[sdepth].off; goto check_terminal; } out: return -1; deadloop: net_warn_ratelimited("cls_u32: dead loop\n"); return -1; } static struct tc_u_hnode *u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) { struct tc_u_hnode *ht; for (ht = rtnl_dereference(tp_c->hlist); ht; ht = rtnl_dereference(ht->next)) if (ht->handle == handle) break; return ht; } static struct tc_u_knode *u32_lookup_key(struct tc_u_hnode *ht, u32 handle) { unsigned int sel; struct tc_u_knode *n = NULL; sel = TC_U32_HASH(handle); if (sel > ht->divisor) goto out; for (n = rtnl_dereference(ht->ht[sel]); n; n = rtnl_dereference(n->next)) if (n->handle == handle) break; out: return n; } static void *u32_get(struct tcf_proto *tp, u32 handle) { struct tc_u_hnode *ht; struct tc_u_common *tp_c = tp->data; if (TC_U32_HTID(handle) == TC_U32_ROOT) ht = rtnl_dereference(tp->root); else ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle)); if (!ht) return NULL; if (TC_U32_KEY(handle) == 0) return ht; return u32_lookup_key(ht, handle); } /* Protected by rtnl lock */ static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) { int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL); if (id < 0) return 0; return id2handle(id); } static struct hlist_head *tc_u_common_hash; #define U32_HASH_SHIFT 10 #define U32_HASH_SIZE (1 << U32_HASH_SHIFT) static void *tc_u_common_ptr(const struct tcf_proto *tp) { struct tcf_block *block = tp->chain->block; /* The block sharing is currently supported only * for classless qdiscs. In that case we use block * for tc_u_common identification. In case the * block is not shared, block->q is a valid pointer * and we can use that. That works for classful qdiscs. */ if (tcf_block_shared(block)) return block; else return block->q; } static struct hlist_head *tc_u_hash(void *key) { return tc_u_common_hash + hash_ptr(key, U32_HASH_SHIFT); } static struct tc_u_common *tc_u_common_find(void *key) { struct tc_u_common *tc; hlist_for_each_entry(tc, tc_u_hash(key), hnode) { if (tc->ptr == key) return tc; } return NULL; } static int u32_init(struct tcf_proto *tp) { struct tc_u_hnode *root_ht; void *key = tc_u_common_ptr(tp); struct tc_u_common *tp_c = tc_u_common_find(key); root_ht = kzalloc(struct_size(root_ht, ht, 1), GFP_KERNEL); if (root_ht == NULL) return -ENOBUFS; refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); if (tp_c == NULL) { tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); if (tp_c == NULL) { kfree(root_ht); return -ENOBUFS; } refcount_set(&tp_c->refcnt, 1); tp_c->ptr = key; INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); hlist_add_head(&tp_c->hnode, tc_u_hash(key)); } else { refcount_inc(&tp_c->refcnt); } RCU_INIT_POINTER(root_ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, root_ht); /* root_ht must be destroyed when tcf_proto is destroyed */ rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; } static void __u32_destroy_key(struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); if (ht && refcount_dec_and_test(&ht->refcnt)) kfree(ht); kfree(n); } static void u32_destroy_key(struct tc_u_knode *n, bool free_pf) { tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); #endif #ifdef CONFIG_CLS_U32_MARK if (free_pf) free_percpu(n->pcpu_success); #endif __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied * version of a tc_u_knode obtained from u32_init_knode(). When * copies are obtained from u32_init_knode() the statistics are * shared between the old and new copies to allow readers to * continue to update the statistics during the copy. To support * this the u32_delete_key_rcu variant does not free the percpu * statistics. */ static void u32_delete_key_work(struct work_struct *work) { struct tc_u_knode *key = container_of(to_rcu_work(work), struct tc_u_knode, rwork); rtnl_lock(); u32_destroy_key(key, false); rtnl_unlock(); } /* u32_delete_key_freepf_rcu is the rcu callback variant * that free's the entire structure including the statistics * percpu variables. Only use this if the key is not a copy * returned by u32_init_knode(). See u32_delete_key_rcu() * for the variant that should be used with keys return from * u32_init_knode() */ static void u32_delete_key_freepf_work(struct work_struct *work) { struct tc_u_knode *key = container_of(to_rcu_work(work), struct tc_u_knode, rwork); rtnl_lock(); u32_destroy_key(key, true); rtnl_unlock(); } static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) { struct tc_u_common *tp_c = tp->data; struct tc_u_knode __rcu **kp; struct tc_u_knode *pkp; struct tc_u_hnode *ht = rtnl_dereference(key->ht_up); if (ht) { kp = &ht->ht[TC_U32_HASH(key->handle)]; for (pkp = rtnl_dereference(*kp); pkp; kp = &pkp->next, pkp = rtnl_dereference(*kp)) { if (pkp == key) { RCU_INIT_POINTER(*kp, key->next); tp_c->knodes--; tcf_unbind_filter(tp, &key->res); idr_remove(&ht->handle_idr, key->handle); tcf_exts_get_net(&key->exts); tcf_queue_work(&key->rwork, u32_delete_key_freepf_work); return 0; } } } WARN_ON(1); return 0; } static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, extack); cls_u32.command = TC_CLSU32_DELETE_HNODE; cls_u32.hnode.divisor = h->divisor; cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false, true); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, u32 flags, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; bool skip_sw = tc_skip_sw(flags); bool offloaded = false; int err; tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack); cls_u32.command = TC_CLSU32_NEW_HNODE; cls_u32.hnode.divisor = h->divisor; cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw, true); if (err < 0) { u32_clear_hw_hnode(tp, h, NULL); return err; } else if (err > 0) { offloaded = true; } if (skip_sw && !offloaded) return -EINVAL; return 0; } static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack); cls_u32.command = TC_CLSU32_DELETE_KNODE; cls_u32.knode.handle = n->handle; tc_setup_cb_destroy(block, tp, TC_SETUP_CLSU32, &cls_u32, false, &n->flags, &n->in_hw_count, true); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32 flags, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; bool skip_sw = tc_skip_sw(flags); int err; tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack); cls_u32.command = TC_CLSU32_REPLACE_KNODE; cls_u32.knode.handle = n->handle; cls_u32.knode.fshift = n->fshift; #ifdef CONFIG_CLS_U32_MARK cls_u32.knode.val = n->val; cls_u32.knode.mask = n->mask; #else cls_u32.knode.val = 0; cls_u32.knode.mask = 0; #endif cls_u32.knode.sel = &n->sel; cls_u32.knode.res = &n->res; cls_u32.knode.exts = &n->exts; if (n->ht_down) cls_u32.knode.link_handle = ht->handle; err = tc_setup_cb_add(block, tp, TC_SETUP_CLSU32, &cls_u32, skip_sw, &n->flags, &n->in_hw_count, true); if (err) { u32_remove_hw_knode(tp, n, NULL); return err; } if (skip_sw && !(n->flags & TCA_CLS_FLAGS_IN_HW)) return -EINVAL; return 0; } static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_knode *n; unsigned int h; for (h = 0; h <= ht->divisor; h++) { while ((n = rtnl_dereference(ht->ht[h])) != NULL) { RCU_INIT_POINTER(ht->ht[h], rtnl_dereference(n->next)); tp_c->knodes--; tcf_unbind_filter(tp, &n->res); u32_remove_hw_knode(tp, n, extack); idr_remove(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) tcf_queue_work(&n->rwork, u32_delete_key_freepf_work); else u32_destroy_key(n, true); } } } static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode __rcu **hn; struct tc_u_hnode *phn; u32_clear_hnode(tp, ht, extack); hn = &tp_c->hlist; for (phn = rtnl_dereference(*hn); phn; hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { u32_clear_hw_hnode(tp, ht, extack); idr_destroy(&ht->handle_idr); idr_remove(&tp_c->handle_idr, handle2id(ht->handle)); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; } } return -ENOENT; } static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); WARN_ON(root_ht == NULL); if (root_ht && refcount_dec_and_test(&root_ht->refcnt)) u32_destroy_hnode(tp, root_ht, extack); if (refcount_dec_and_test(&tp_c->refcnt)) { struct tc_u_hnode *ht; hlist_del(&tp_c->hnode); while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) { u32_clear_hnode(tp, ht, extack); RCU_INIT_POINTER(tp_c->hlist, ht->next); /* u32_destroy_key() will later free ht for us, if it's * still referenced by some knode */ if (refcount_dec_and_test(&ht->refcnt)) kfree_rcu(ht, rcu); } idr_destroy(&tp_c->handle_idr); kfree(tp_c); } tp->data = NULL; } static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = arg; struct tc_u_common *tp_c = tp->data; int ret = 0; if (TC_U32_KEY(ht->handle)) { u32_remove_hw_knode(tp, (struct tc_u_knode *)ht, extack); ret = u32_delete_key(tp, (struct tc_u_knode *)ht); goto out; } if (ht->is_root) { NL_SET_ERR_MSG_MOD(extack, "Not allowed to delete root node"); return -EINVAL; } if (refcount_dec_if_one(&ht->refcnt)) { u32_destroy_hnode(tp, ht, extack); } else { NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); return -EBUSY; } out: *last = refcount_read(&tp_c->refcnt) == 1 && tp_c->knodes == 0; return ret; } static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) { u32 index = htid | 0x800; u32 max = htid | 0xFFF; if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { index = htid + 1; if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) index = max; } return index; } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_CLASSID] = { .type = NLA_U32 }, [TCA_U32_HASH] = { .type = NLA_U32 }, [TCA_U32_LINK] = { .type = NLA_U32 }, [TCA_U32_DIVISOR] = { .type = NLA_U32 }, [TCA_U32_SEL] = { .len = sizeof(struct tc_u32_sel) }, [TCA_U32_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ }, [TCA_U32_MARK] = { .len = sizeof(struct tc_u32_mark) }, [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n, struct nlattr **tb) { if (tb[TCA_U32_CLASSID]) tcf_unbind_filter(tp, &n->res); } static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n, unsigned long base, struct nlattr **tb) { if (tb[TCA_U32_CLASSID]) { n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); tcf_bind_filter(tp, &n->res, base); } } static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { int err, ifindex = -1; err = tcf_exts_validate_ex(net, tp, tb, est, &n->exts, flags, fl_flags, extack); if (err < 0) return err; if (tb[TCA_U32_INDEV]) { ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); if (ifindex < 0) return -EINVAL; } if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; if (TC_U32_KEY(handle)) { NL_SET_ERR_MSG_MOD(extack, "u32 Link handle must be a hash table"); return -EINVAL; } if (handle) { ht_down = u32_lookup_ht(tp->data, handle); if (!ht_down) { NL_SET_ERR_MSG_MOD(extack, "Link hash table not found"); return -EINVAL; } if (ht_down->is_root) { NL_SET_ERR_MSG_MOD(extack, "Not linking to root node"); return -EINVAL; } refcount_inc(&ht_down->refcnt); } ht_old = rtnl_dereference(n->ht_down); rcu_assign_pointer(n->ht_down, ht_down); if (ht_old) refcount_dec(&ht_old->refcnt); } if (ifindex >= 0) n->ifindex = ifindex; return 0; } static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, struct tc_u_knode *n) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; struct tc_u_hnode *ht; if (TC_U32_HTID(n->handle) == TC_U32_ROOT) ht = rtnl_dereference(tp->root); else ht = u32_lookup_ht(tp_c, TC_U32_HTID(n->handle)); ins = &ht->ht[TC_U32_HASH(n->handle)]; /* The node must always exist for it to be replaced if this is not the * case then something went very wrong elsewhere. */ for (pins = rtnl_dereference(*ins); ; ins = &pins->next, pins = rtnl_dereference(*ins)) if (pins->handle == n->handle) break; idr_replace(&ht->handle_idr, n, n->handle); RCU_INIT_POINTER(n->next, pins->next); rcu_assign_pointer(*ins, n); } static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tc_u32_sel *s = &n->sel; struct tc_u_knode *new; new = kzalloc(struct_size(new, sel.keys, s->nkeys), GFP_KERNEL); if (!new) return NULL; RCU_INIT_POINTER(new->next, n->next); new->handle = n->handle; RCU_INIT_POINTER(new->ht_up, n->ht_up); new->ifindex = n->ifindex; new->fshift = n->fshift; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed * a special destroy call must be made to not free the pf memory. */ new->pf = n->pf; #endif #ifdef CONFIG_CLS_U32_MARK new->val = n->val; new->mask = n->mask; /* Similarly success statistics must be moved as pointers */ new->pcpu_success = n->pcpu_success; #endif memcpy(&new->sel, s, struct_size(s, keys, s->nkeys)); if (tcf_exts_init(&new->exts, net, TCA_U32_ACT, TCA_U32_POLICE)) { kfree(new); return NULL; } /* bump reference count as long as we hold pointer to structure */ if (ht) refcount_inc(&ht->refcnt); return new; } static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, u32 flags, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; struct tc_u_knode *n; struct tc_u32_sel *s; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; u32 htid, userflags = 0; size_t sel_size; int err; if (!opt) { if (handle) { NL_SET_ERR_MSG_MOD(extack, "Filter handle requires options"); return -EINVAL; } else { return 0; } } err = nla_parse_nested_deprecated(tb, TCA_U32_MAX, opt, u32_policy, extack); if (err < 0) return err; if (tb[TCA_U32_FLAGS]) { userflags = nla_get_u32(tb[TCA_U32_FLAGS]); if (!tc_flags_valid(userflags)) { NL_SET_ERR_MSG_MOD(extack, "Invalid filter flags"); return -EINVAL; } } n = *arg; if (n) { struct tc_u_knode *new; if (TC_U32_KEY(n->handle) == 0) { NL_SET_ERR_MSG_MOD(extack, "Key node id cannot be zero"); return -EINVAL; } if ((n->flags ^ userflags) & ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW)) { NL_SET_ERR_MSG_MOD(extack, "Key node flags do not match passed flags"); return -EINVAL; } new = u32_init_knode(net, tp, n); if (!new) return -ENOMEM; err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE], flags, new->flags, extack); if (err) { __u32_destroy_key(new); return err; } u32_bind_filter(tp, new, base, tb); err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { u32_unbind_filter(tp, new, tb); if (tb[TCA_U32_LINK]) { struct tc_u_hnode *ht_old; ht_old = rtnl_dereference(n->ht_down); if (ht_old) refcount_inc(&ht_old->refcnt); } __u32_destroy_key(new); return err; } if (!tc_in_hw(new->flags)) new->flags |= TCA_CLS_FLAGS_NOT_IN_HW; tcf_proto_update_usesw(tp, new->flags); u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); tcf_exts_get_net(&n->exts); tcf_queue_work(&n->rwork, u32_delete_key_work); return 0; } if (tb[TCA_U32_DIVISOR]) { unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); if (!is_power_of_2(divisor)) { NL_SET_ERR_MSG_MOD(extack, "Divisor is not a power of 2"); return -EINVAL; } if (divisor-- > 0x100) { NL_SET_ERR_MSG_MOD(extack, "Exceeded maximum 256 hash buckets"); return -EINVAL; } if (TC_U32_KEY(handle)) { NL_SET_ERR_MSG_MOD(extack, "Divisor can only be used on a hash table"); return -EINVAL; } ht = kzalloc(struct_size(ht, ht, divisor + 1), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; if (handle == 0) { handle = gen_new_htid(tp->data, ht); if (handle == 0) { kfree(ht); return -ENOMEM; } } else { err = idr_alloc_u32(&tp_c->handle_idr, ht, &handle, handle, GFP_KERNEL); if (err) { kfree(ht); return err; } } refcount_set(&ht->refcnt, 1); ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; idr_init(&ht->handle_idr); ht->flags = userflags; err = u32_replace_hw_hnode(tp, ht, userflags, extack); if (err) { idr_remove(&tp_c->handle_idr, handle2id(handle)); kfree(ht); return err; } RCU_INIT_POINTER(ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, ht); *arg = ht; return 0; } if (tb[TCA_U32_HASH]) { htid = nla_get_u32(tb[TCA_U32_HASH]); if (TC_U32_HTID(htid) == TC_U32_ROOT) { ht = rtnl_dereference(tp->root); htid = ht->handle; } else { ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid)); if (!ht) { NL_SET_ERR_MSG_MOD(extack, "Specified hash table not found"); return -EINVAL; } } } else { ht = rtnl_dereference(tp->root); htid = ht->handle; } if (ht->divisor < TC_U32_HASH(htid)) { NL_SET_ERR_MSG_MOD(extack, "Specified hash table buckets exceed configured value"); return -EINVAL; } /* At this point, we need to derive the new handle that will be used to * uniquely map the identity of this table match entry. The * identity of the entry that we need to construct is 32 bits made of: * htid(12b):bucketid(8b):node/entryid(12b) * * At this point _we have the table(ht)_ in which we will insert this * entry. We carry the table's id in variable "htid". * Note that earlier code picked the ht selection either by a) the user * providing the htid specified via TCA_U32_HASH attribute or b) when * no such attribute is passed then the root ht, is default to at ID * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. * If OTOH the user passed us the htid, they may also pass a bucketid of * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be * passed via the htid, so even if it was non-zero it will be ignored. * * We may also have a handle, if the user passed one. The handle also * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). * Rule: the bucketid on the handle is ignored even if one was passed; * rather the value on "htid" is always assumed to be the bucketid. */ if (handle) { /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } /* Ok, so far we have a valid htid(12b):bucketid(8b) but we * need to finalize the table entry identification with the last * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for * entries. Rule: nodeid of 0 is reserved only for tables(see * earlier code which processes TC_U32_DIVISOR attribute). * Rule: The nodeid can only be derived from the handle (and not * htid). * Rule: if the handle specified zero for the node id example * 0x60000000, then pick a new nodeid from the pool of IDs * this hash table has been allocating from. * If OTOH it is specified (i.e for example the user passed a * handle such as 0x60000123), then we use it generate our final * handle which is used to uniquely identify the match entry. */ if (!TC_U32_NODE(handle)) { handle = gen_new_kid(ht, htid); } else { handle = htid | TC_U32_NODE(handle); err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, GFP_KERNEL); if (err) return err; } } else { /* The user did not give us a handle; lets just generate one * from the table's pool of nodeids. */ handle = gen_new_kid(ht, htid); } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); err = -EINVAL; goto erridr; } s = nla_data(tb[TCA_U32_SEL]); sel_size = struct_size(s, keys, s->nkeys); if (nla_len(tb[TCA_U32_SEL]) < sel_size) { err = -EINVAL; goto erridr; } n = kzalloc(struct_size(n, sel.keys, s->nkeys), GFP_KERNEL); if (n == NULL) { err = -ENOBUFS; goto erridr; } #ifdef CONFIG_CLS_U32_PERF n->pf = __alloc_percpu(struct_size(n->pf, kcnts, s->nkeys), __alignof__(struct tc_u32_pcnt)); if (!n->pf) { err = -ENOBUFS; goto errfree; } #endif unsafe_memcpy(&n->sel, s, sel_size, /* A composite flex-array structure destination, * which was correctly sized with struct_size(), * bounds-checked against nla_len(), and allocated * above. */); RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; n->flags = userflags; err = tcf_exts_init(&n->exts, net, TCA_U32_ACT, TCA_U32_POLICE); if (err < 0) goto errout; #ifdef CONFIG_CLS_U32_MARK n->pcpu_success = alloc_percpu(u32); if (!n->pcpu_success) { err = -ENOMEM; goto errout; } if (tb[TCA_U32_MARK]) { struct tc_u32_mark *mark; mark = nla_data(tb[TCA_U32_MARK]); n->val = mark->val; n->mask = mark->mask; } #endif err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE], flags, n->flags, extack); u32_bind_filter(tp, n, base, tb); if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; err = u32_replace_hw_knode(tp, n, flags, extack); if (err) goto errunbind; if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; tcf_proto_update_usesw(tp, n->flags); ins = &ht->ht[TC_U32_HASH(handle)]; for (pins = rtnl_dereference(*ins); pins; ins = &pins->next, pins = rtnl_dereference(*ins)) if (TC_U32_NODE(handle) < TC_U32_NODE(pins->handle)) break; RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); tp_c->knodes++; *arg = n; return 0; } errunbind: u32_unbind_filter(tp, n, tb); #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); #endif errout: tcf_exts_destroy(&n->exts); #ifdef CONFIG_CLS_U32_PERF errfree: free_percpu(n->pf); #endif kfree(n); erridr: idr_remove(&ht->handle_idr, handle); return err; } static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; if (arg->stop) return; for (ht = rtnl_dereference(tp_c->hlist); ht; ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; if (!tc_cls_stats_dump(tp, arg, ht)) return; for (h = 0; h <= ht->divisor; h++) { for (n = rtnl_dereference(ht->ht[h]); n; n = rtnl_dereference(n->next)) { if (!tc_cls_stats_dump(tp, arg, n)) return; } } } } static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_cls_u32_offload cls_u32 = {}; int err; tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack); cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE; cls_u32.hnode.divisor = ht->divisor; cls_u32.hnode.handle = ht->handle; cls_u32.hnode.prio = ht->prio; err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv); if (err && add && tc_skip_sw(ht->flags)) return err; return 0; } static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack); cls_u32.command = add ? TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE; cls_u32.knode.handle = n->handle; if (add) { cls_u32.knode.fshift = n->fshift; #ifdef CONFIG_CLS_U32_MARK cls_u32.knode.val = n->val; cls_u32.knode.mask = n->mask; #else cls_u32.knode.val = 0; cls_u32.knode.mask = 0; #endif cls_u32.knode.sel = &n->sel; cls_u32.knode.res = &n->res; cls_u32.knode.exts = &n->exts; if (n->ht_down) cls_u32.knode.link_handle = ht->handle; } return tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSU32, &cls_u32, cb_priv, &n->flags, &n->in_hw_count); } static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; int err; for (ht = rtnl_dereference(tp_c->hlist); ht; ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; /* When adding filters to a new dev, try to offload the * hashtable first. When removing, do the filters before the * hashtable. */ if (add && !tc_skip_hw(ht->flags)) { err = u32_reoffload_hnode(tp, ht, add, cb, cb_priv, extack); if (err) return err; } for (h = 0; h <= ht->divisor; h++) { for (n = rtnl_dereference(ht->ht[h]); n; n = rtnl_dereference(n->next)) { if (tc_skip_hw(n->flags)) continue; err = u32_reoffload_knode(tp, n, add, cb, cb_priv, extack); if (err) return err; } } if (!add && !tc_skip_hw(ht->flags)) u32_reoffload_hnode(tp, ht, add, cb, cb_priv, extack); } return 0; } static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q, unsigned long base) { struct tc_u_knode *n = fh; tc_cls_bind_class(classid, cl, q, &n->res, base); } static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tc_u_knode *n = fh; struct tc_u_hnode *ht_up, *ht_down; struct nlattr *nest; if (n == NULL) return skb->len; t->tcm_handle = n->handle; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (TC_U32_KEY(n->handle) == 0) { struct tc_u_hnode *ht = fh; u32 divisor = ht->divisor + 1; if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor)) goto nla_put_failure; } else { #ifdef CONFIG_CLS_U32_PERF struct tc_u32_pcnt *gpf; int cpu; #endif if (nla_put(skb, TCA_U32_SEL, struct_size(&n->sel, keys, n->sel.nkeys), &n->sel)) goto nla_put_failure; ht_up = rtnl_dereference(n->ht_up); if (ht_up) { u32 htid = n->handle & 0xFFFFF000; if (nla_put_u32(skb, TCA_U32_HASH, htid)) goto nla_put_failure; } if (n->res.classid && nla_put_u32(skb, TCA_U32_CLASSID, n->res.classid)) goto nla_put_failure; ht_down = rtnl_dereference(n->ht_down); if (ht_down && nla_put_u32(skb, TCA_U32_LINK, ht_down->handle)) goto nla_put_failure; if (n->flags && nla_put_u32(skb, TCA_U32_FLAGS, n->flags)) goto nla_put_failure; #ifdef CONFIG_CLS_U32_MARK if ((n->val || n->mask)) { struct tc_u32_mark mark = {.val = n->val, .mask = n->mask, .success = 0}; int cpum; for_each_possible_cpu(cpum) { __u32 cnt = *per_cpu_ptr(n->pcpu_success, cpum); mark.success += cnt; } if (nla_put(skb, TCA_U32_MARK, sizeof(mark), &mark)) goto nla_put_failure; } #endif if (tcf_exts_dump(skb, &n->exts) < 0) goto nla_put_failure; if (n->ifindex) { struct net_device *dev; dev = __dev_get_by_index(net, n->ifindex); if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name)) goto nla_put_failure; } #ifdef CONFIG_CLS_U32_PERF gpf = kzalloc(struct_size(gpf, kcnts, n->sel.nkeys), GFP_KERNEL); if (!gpf) goto nla_put_failure; for_each_possible_cpu(cpu) { int i; struct tc_u32_pcnt *pf = per_cpu_ptr(n->pf, cpu); gpf->rcnt += pf->rcnt; gpf->rhit += pf->rhit; for (i = 0; i < n->sel.nkeys; i++) gpf->kcnts[i] += pf->kcnts[i]; } if (nla_put_64bit(skb, TCA_U32_PCNT, struct_size(gpf, kcnts, n->sel.nkeys), gpf, TCA_U32_PAD)) { kfree(gpf); goto nla_put_failure; } kfree(gpf); #endif } nla_nest_end(skb, nest); if (TC_U32_KEY(n->handle)) if (tcf_exts_dump_stats(skb, &n->exts) < 0) goto nla_put_failure; return skb->len; nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static struct tcf_proto_ops cls_u32_ops __read_mostly = { .kind = "u32", .classify = u32_classify, .init = u32_init, .destroy = u32_destroy, .get = u32_get, .change = u32_change, .delete = u32_delete, .walk = u32_walk, .reoffload = u32_reoffload, .dump = u32_dump, .bind_class = u32_bind_class, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_CLS("u32"); static int __init init_u32(void) { int i, ret; pr_info("u32 classifier\n"); #ifdef CONFIG_CLS_U32_PERF pr_info(" Performance counters on\n"); #endif pr_info(" input device check on\n"); #ifdef CONFIG_NET_CLS_ACT pr_info(" Actions configured\n"); #endif tc_u_common_hash = kvmalloc_array(U32_HASH_SIZE, sizeof(struct hlist_head), GFP_KERNEL); if (!tc_u_common_hash) return -ENOMEM; for (i = 0; i < U32_HASH_SIZE; i++) INIT_HLIST_HEAD(&tc_u_common_hash[i]); ret = register_tcf_proto_ops(&cls_u32_ops); if (ret) kvfree(tc_u_common_hash); return ret; } static void __exit exit_u32(void) { unregister_tcf_proto_ops(&cls_u32_ops); kvfree(tc_u_common_hash); } module_init(init_u32) module_exit(exit_u32) MODULE_DESCRIPTION("Universal 32bit based TC Classifier"); MODULE_LICENSE("GPL"); |
| 2 2 19 17 19 5 3 12 21 1 1 19 7 7 4 15 21 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_meta.c Metadata ematch * * Authors: Thomas Graf <tgraf@suug.ch> * * ========================================================================== * * The metadata ematch compares two meta objects where each object * represents either a meta value stored in the kernel or a static * value provided by userspace. The objects are not provided by * userspace itself but rather a definition providing the information * to build them. Every object is of a certain type which must be * equal to the object it is being compared to. * * The definition of a objects conists of the type (meta type), a * identifier (meta id) and additional type specific information. * The meta id is either TCF_META_TYPE_VALUE for values provided by * userspace or a index to the meta operations table consisting of * function pointers to type specific meta data collectors returning * the value of the requested meta value. * * lvalue rvalue * +-----------+ +-----------+ * | type: INT | | type: INT | * def | id: DEV | | id: VALUE | * | data: | | data: 3 | * +-----------+ +-----------+ * | | * ---> meta_ops[INT][DEV](...) | * | | * ----------- | * V V * +-----------+ +-----------+ * | type: INT | | type: INT | * obj | id: DEV | | id: VALUE | * | data: 2 |<--data got filled out | data: 3 | * +-----------+ +-----------+ * | | * --------------> 2 equals 3 <-------------- * * This is a simplified schema, the complexity varies depending * on the meta type. Obviously, the length of the data must also * be provided for non-numeric types. * * Additionally, type dependent modifiers such as shift operators * or mask may be applied to extend the functionality. As of now, * the variable length type supports shifting the byte string to * the right, eating up any number of octets and thus supporting * wildcard interface name comparisons such as "ppp%" matching * ppp0..9. * * NOTE: Certain meta values depend on other subsystems and are * only available if that subsystem is enabled in the kernel. */ #include <linux/slab.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/if_vlan.h> #include <linux/tc_ematch/tc_em_meta.h> #include <net/dst.h> #include <net/route.h> #include <net/pkt_cls.h> #include <net/sock.h> struct meta_obj { unsigned long value; unsigned int len; }; struct meta_value { struct tcf_meta_val hdr; unsigned long val; unsigned int len; }; struct meta_match { struct meta_value lvalue; struct meta_value rvalue; }; static inline int meta_id(struct meta_value *v) { return TCF_META_ID(v->hdr.kind); } static inline int meta_type(struct meta_value *v) { return TCF_META_TYPE(v->hdr.kind); } #define META_COLLECTOR(FUNC) static void meta_##FUNC(struct sk_buff *skb, \ struct tcf_pkt_info *info, struct meta_value *v, \ struct meta_obj *dst, int *err) /************************************************************************** * System status & misc **************************************************************************/ META_COLLECTOR(int_random) { get_random_bytes(&dst->value, sizeof(dst->value)); } static inline unsigned long fixed_loadavg(int load) { int rnd_load = load + (FIXED_1/200); int rnd_frac = ((rnd_load & (FIXED_1-1)) * 100) >> FSHIFT; return ((rnd_load >> FSHIFT) * 100) + rnd_frac; } META_COLLECTOR(int_loadavg_0) { dst->value = fixed_loadavg(avenrun[0]); } META_COLLECTOR(int_loadavg_1) { dst->value = fixed_loadavg(avenrun[1]); } META_COLLECTOR(int_loadavg_2) { dst->value = fixed_loadavg(avenrun[2]); } /************************************************************************** * Device names & indices **************************************************************************/ static inline int int_dev(struct net_device *dev, struct meta_obj *dst) { if (unlikely(dev == NULL)) return -1; dst->value = dev->ifindex; return 0; } static inline int var_dev(struct net_device *dev, struct meta_obj *dst) { if (unlikely(dev == NULL)) return -1; dst->value = (unsigned long) dev->name; dst->len = strlen(dev->name); return 0; } META_COLLECTOR(int_dev) { *err = int_dev(skb->dev, dst); } META_COLLECTOR(var_dev) { *err = var_dev(skb->dev, dst); } /************************************************************************** * vlan tag **************************************************************************/ META_COLLECTOR(int_vlan_tag) { unsigned short tag; if (skb_vlan_tag_present(skb)) dst->value = skb_vlan_tag_get(skb); else if (!__vlan_get_tag(skb, &tag)) dst->value = tag; else *err = -1; } /************************************************************************** * skb attributes **************************************************************************/ META_COLLECTOR(int_priority) { dst->value = skb->priority; } META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) { dst->value = skb->pkt_type; } META_COLLECTOR(int_pktlen) { dst->value = skb->len; } META_COLLECTOR(int_datalen) { dst->value = skb->data_len; } META_COLLECTOR(int_maclen) { dst->value = skb->mac_len; } META_COLLECTOR(int_rxhash) { dst->value = skb_get_hash(skb); } /************************************************************************** * Netfilter **************************************************************************/ META_COLLECTOR(int_mark) { dst->value = skb->mark; } /************************************************************************** * Traffic Control **************************************************************************/ META_COLLECTOR(int_tcindex) { dst->value = skb->tc_index; } /************************************************************************** * Routing **************************************************************************/ META_COLLECTOR(int_rtclassid) { if (unlikely(skb_dst(skb) == NULL)) *err = -1; else #ifdef CONFIG_IP_ROUTE_CLASSID dst->value = skb_dst(skb)->tclassid; #else dst->value = 0; #endif } META_COLLECTOR(int_rtiif) { if (unlikely(skb_rtable(skb) == NULL)) *err = -1; else dst->value = inet_iif(skb); } /************************************************************************** * Socket Attributes **************************************************************************/ #define skip_nonlocal(skb) \ (unlikely(skb->sk == NULL)) META_COLLECTOR(int_sk_family) { if (skip_nonlocal(skb)) { *err = -1; return; } dst->value = skb->sk->sk_family; } META_COLLECTOR(int_sk_state) { if (skip_nonlocal(skb)) { *err = -1; return; } dst->value = skb->sk->sk_state; } META_COLLECTOR(int_sk_reuse) { if (skip_nonlocal(skb)) { *err = -1; return; } dst->value = skb->sk->sk_reuse; } META_COLLECTOR(int_sk_bound_if) { if (skip_nonlocal(skb)) { *err = -1; return; } /* No error if bound_dev_if is 0, legal userspace check */ dst->value = skb->sk->sk_bound_dev_if; } META_COLLECTOR(var_sk_bound_if) { int bound_dev_if; if (skip_nonlocal(skb)) { *err = -1; return; } bound_dev_if = READ_ONCE(skb->sk->sk_bound_dev_if); if (bound_dev_if == 0) { dst->value = (unsigned long) "any"; dst->len = 3; } else { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(skb->sk), bound_dev_if); *err = var_dev(dev, dst); rcu_read_unlock(); } } META_COLLECTOR(int_sk_refcnt) { if (skip_nonlocal(skb)) { *err = -1; return; } dst->value = refcount_read(&skb->sk->sk_refcnt); } META_COLLECTOR(int_sk_rcvbuf) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_rcvbuf; } META_COLLECTOR(int_sk_shutdown) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_shutdown; } META_COLLECTOR(int_sk_proto) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_protocol; } META_COLLECTOR(int_sk_type) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_type; } META_COLLECTOR(int_sk_rmem_alloc) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk_rmem_alloc_get(sk); } META_COLLECTOR(int_sk_wmem_alloc) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk_wmem_alloc_get(sk); } META_COLLECTOR(int_sk_omem_alloc) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = atomic_read(&sk->sk_omem_alloc); } META_COLLECTOR(int_sk_rcv_qlen) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_receive_queue.qlen; } META_COLLECTOR(int_sk_snd_qlen) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_write_queue.qlen; } META_COLLECTOR(int_sk_wmem_queued) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk_forward_alloc_get(sk); } META_COLLECTOR(int_sk_sndbuf) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_sndbuf; } META_COLLECTOR(int_sk_alloc) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = (__force int) sk->sk_allocation; } META_COLLECTOR(int_sk_hash) { if (skip_nonlocal(skb)) { *err = -1; return; } dst->value = skb->sk->sk_hash; } META_COLLECTOR(int_sk_lingertime) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_lingertime) / HZ; } META_COLLECTOR(int_sk_err_qlen) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_error_queue.qlen; } META_COLLECTOR(int_sk_ack_bl) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_ack_backlog); } META_COLLECTOR(int_sk_max_ack_bl) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_max_ack_backlog); } META_COLLECTOR(int_sk_prio) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_priority); } META_COLLECTOR(int_sk_rcvlowat) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_rcvlowat); } META_COLLECTOR(int_sk_rcvtimeo) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ; } META_COLLECTOR(int_sk_sndtimeo) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ; } META_COLLECTOR(int_sk_sendmsg_off) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_frag.offset; } META_COLLECTOR(int_sk_write_pend) { const struct sock *sk = skb_to_full_sk(skb); if (!sk) { *err = -1; return; } dst->value = sk->sk_write_pending; } /************************************************************************** * Meta value collectors assignment table **************************************************************************/ struct meta_ops { void (*get)(struct sk_buff *, struct tcf_pkt_info *, struct meta_value *, struct meta_obj *, int *); }; #define META_ID(name) TCF_META_ID_##name #define META_FUNC(name) { .get = meta_##name } /* Meta value operations table listing all meta value collectors and * assigns them to a type and meta id. */ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX + 1][TCF_META_ID_MAX + 1] = { [TCF_META_TYPE_VAR] = { [META_ID(DEV)] = META_FUNC(var_dev), [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), }, [TCF_META_TYPE_INT] = { [META_ID(RANDOM)] = META_FUNC(int_random), [META_ID(LOADAVG_0)] = META_FUNC(int_loadavg_0), [META_ID(LOADAVG_1)] = META_FUNC(int_loadavg_1), [META_ID(LOADAVG_2)] = META_FUNC(int_loadavg_2), [META_ID(DEV)] = META_FUNC(int_dev), [META_ID(PRIORITY)] = META_FUNC(int_priority), [META_ID(PROTOCOL)] = META_FUNC(int_protocol), [META_ID(PKTTYPE)] = META_FUNC(int_pkttype), [META_ID(PKTLEN)] = META_FUNC(int_pktlen), [META_ID(DATALEN)] = META_FUNC(int_datalen), [META_ID(MACLEN)] = META_FUNC(int_maclen), [META_ID(NFMARK)] = META_FUNC(int_mark), [META_ID(TCINDEX)] = META_FUNC(int_tcindex), [META_ID(RTCLASSID)] = META_FUNC(int_rtclassid), [META_ID(RTIIF)] = META_FUNC(int_rtiif), [META_ID(SK_FAMILY)] = META_FUNC(int_sk_family), [META_ID(SK_STATE)] = META_FUNC(int_sk_state), [META_ID(SK_REUSE)] = META_FUNC(int_sk_reuse), [META_ID(SK_BOUND_IF)] = META_FUNC(int_sk_bound_if), [META_ID(SK_REFCNT)] = META_FUNC(int_sk_refcnt), [META_ID(SK_RCVBUF)] = META_FUNC(int_sk_rcvbuf), [META_ID(SK_SNDBUF)] = META_FUNC(int_sk_sndbuf), [META_ID(SK_SHUTDOWN)] = META_FUNC(int_sk_shutdown), [META_ID(SK_PROTO)] = META_FUNC(int_sk_proto), [META_ID(SK_TYPE)] = META_FUNC(int_sk_type), [META_ID(SK_RMEM_ALLOC)] = META_FUNC(int_sk_rmem_alloc), [META_ID(SK_WMEM_ALLOC)] = META_FUNC(int_sk_wmem_alloc), [META_ID(SK_OMEM_ALLOC)] = META_FUNC(int_sk_omem_alloc), [META_ID(SK_WMEM_QUEUED)] = META_FUNC(int_sk_wmem_queued), [META_ID(SK_RCV_QLEN)] = META_FUNC(int_sk_rcv_qlen), [META_ID(SK_SND_QLEN)] = META_FUNC(int_sk_snd_qlen), [META_ID(SK_ERR_QLEN)] = META_FUNC(int_sk_err_qlen), [META_ID(SK_FORWARD_ALLOCS)] = META_FUNC(int_sk_fwd_alloc), [META_ID(SK_ALLOCS)] = META_FUNC(int_sk_alloc), [META_ID(SK_HASH)] = META_FUNC(int_sk_hash), [META_ID(SK_LINGERTIME)] = META_FUNC(int_sk_lingertime), [META_ID(SK_ACK_BACKLOG)] = META_FUNC(int_sk_ack_bl), [META_ID(SK_MAX_ACK_BACKLOG)] = META_FUNC(int_sk_max_ack_bl), [META_ID(SK_PRIO)] = META_FUNC(int_sk_prio), [META_ID(SK_RCVLOWAT)] = META_FUNC(int_sk_rcvlowat), [META_ID(SK_RCVTIMEO)] = META_FUNC(int_sk_rcvtimeo), [META_ID(SK_SNDTIMEO)] = META_FUNC(int_sk_sndtimeo), [META_ID(SK_SENDMSG_OFF)] = META_FUNC(int_sk_sendmsg_off), [META_ID(SK_WRITE_PENDING)] = META_FUNC(int_sk_write_pend), [META_ID(VLAN_TAG)] = META_FUNC(int_vlan_tag), [META_ID(RXHASH)] = META_FUNC(int_rxhash), } }; static inline struct meta_ops *meta_ops(struct meta_value *val) { return &__meta_ops[meta_type(val)][meta_id(val)]; } /************************************************************************** * Type specific operations for TCF_META_TYPE_VAR **************************************************************************/ static int meta_var_compare(struct meta_obj *a, struct meta_obj *b) { int r = a->len - b->len; if (r == 0) r = memcmp((void *) a->value, (void *) b->value, a->len); return r; } static int meta_var_change(struct meta_value *dst, struct nlattr *nla) { int len = nla_len(nla); dst->val = (unsigned long)kmemdup(nla_data(nla), len, GFP_KERNEL); if (dst->val == 0UL) return -ENOMEM; dst->len = len; return 0; } static void meta_var_destroy(struct meta_value *v) { kfree((void *) v->val); } static void meta_var_apply_extras(struct meta_value *v, struct meta_obj *dst) { int shift = v->hdr.shift; if (shift && shift < dst->len) dst->len -= shift; } static int meta_var_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { if (v->val && v->len && nla_put(skb, tlv, v->len, (void *) v->val)) goto nla_put_failure; return 0; nla_put_failure: return -1; } /************************************************************************** * Type specific operations for TCF_META_TYPE_INT **************************************************************************/ static int meta_int_compare(struct meta_obj *a, struct meta_obj *b) { /* Let gcc optimize it, the unlikely is not really based on * some numbers but jump free code for mismatches seems * more logical. */ if (unlikely(a->value == b->value)) return 0; else if (a->value < b->value) return -1; else return 1; } static int meta_int_change(struct meta_value *dst, struct nlattr *nla) { if (nla_len(nla) >= sizeof(unsigned long)) { dst->val = *(unsigned long *) nla_data(nla); dst->len = sizeof(unsigned long); } else if (nla_len(nla) == sizeof(u32)) { dst->val = nla_get_u32(nla); dst->len = sizeof(u32); } else return -EINVAL; return 0; } static void meta_int_apply_extras(struct meta_value *v, struct meta_obj *dst) { if (v->hdr.shift) dst->value >>= v->hdr.shift; if (v->val) dst->value &= v->val; } static int meta_int_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { if (v->len == sizeof(unsigned long)) { if (nla_put(skb, tlv, sizeof(unsigned long), &v->val)) goto nla_put_failure; } else if (v->len == sizeof(u32)) { if (nla_put_u32(skb, tlv, v->val)) goto nla_put_failure; } return 0; nla_put_failure: return -1; } /************************************************************************** * Type specific operations table **************************************************************************/ struct meta_type_ops { void (*destroy)(struct meta_value *); int (*compare)(struct meta_obj *, struct meta_obj *); int (*change)(struct meta_value *, struct nlattr *); void (*apply_extras)(struct meta_value *, struct meta_obj *); int (*dump)(struct sk_buff *, struct meta_value *, int); }; static const struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX + 1] = { [TCF_META_TYPE_VAR] = { .destroy = meta_var_destroy, .compare = meta_var_compare, .change = meta_var_change, .apply_extras = meta_var_apply_extras, .dump = meta_var_dump }, [TCF_META_TYPE_INT] = { .compare = meta_int_compare, .change = meta_int_change, .apply_extras = meta_int_apply_extras, .dump = meta_int_dump } }; static inline const struct meta_type_ops *meta_type_ops(struct meta_value *v) { return &__meta_type_ops[meta_type(v)]; } /************************************************************************** * Core **************************************************************************/ static int meta_get(struct sk_buff *skb, struct tcf_pkt_info *info, struct meta_value *v, struct meta_obj *dst) { int err = 0; if (meta_id(v) == TCF_META_ID_VALUE) { dst->value = v->val; dst->len = v->len; return 0; } meta_ops(v)->get(skb, info, v, dst, &err); if (err < 0) return err; if (meta_type_ops(v)->apply_extras) meta_type_ops(v)->apply_extras(v, dst); return 0; } static int em_meta_match(struct sk_buff *skb, struct tcf_ematch *m, struct tcf_pkt_info *info) { int r; struct meta_match *meta = (struct meta_match *) m->data; struct meta_obj l_value, r_value; if (meta_get(skb, info, &meta->lvalue, &l_value) < 0 || meta_get(skb, info, &meta->rvalue, &r_value) < 0) return 0; r = meta_type_ops(&meta->lvalue)->compare(&l_value, &r_value); switch (meta->lvalue.hdr.op) { case TCF_EM_OPND_EQ: return !r; case TCF_EM_OPND_LT: return r < 0; case TCF_EM_OPND_GT: return r > 0; } return 0; } static void meta_delete(struct meta_match *meta) { if (meta) { const struct meta_type_ops *ops = meta_type_ops(&meta->lvalue); if (ops && ops->destroy) { ops->destroy(&meta->lvalue); ops->destroy(&meta->rvalue); } } kfree(meta); } static inline int meta_change_data(struct meta_value *dst, struct nlattr *nla) { if (nla) { if (nla_len(nla) == 0) return -EINVAL; return meta_type_ops(dst)->change(dst, nla); } return 0; } static inline int meta_is_supported(struct meta_value *val) { return !meta_id(val) || meta_ops(val)->get; } static const struct nla_policy meta_policy[TCA_EM_META_MAX + 1] = { [TCA_EM_META_HDR] = { .len = sizeof(struct tcf_meta_hdr) }, }; static int em_meta_change(struct net *net, void *data, int len, struct tcf_ematch *m) { int err; struct nlattr *tb[TCA_EM_META_MAX + 1]; struct tcf_meta_hdr *hdr; struct meta_match *meta = NULL; err = nla_parse_deprecated(tb, TCA_EM_META_MAX, data, len, meta_policy, NULL); if (err < 0) goto errout; err = -EINVAL; if (tb[TCA_EM_META_HDR] == NULL) goto errout; hdr = nla_data(tb[TCA_EM_META_HDR]); if (TCF_META_TYPE(hdr->left.kind) != TCF_META_TYPE(hdr->right.kind) || TCF_META_TYPE(hdr->left.kind) > TCF_META_TYPE_MAX || TCF_META_ID(hdr->left.kind) > TCF_META_ID_MAX || TCF_META_ID(hdr->right.kind) > TCF_META_ID_MAX) goto errout; meta = kzalloc(sizeof(*meta), GFP_KERNEL); if (meta == NULL) { err = -ENOMEM; goto errout; } memcpy(&meta->lvalue.hdr, &hdr->left, sizeof(hdr->left)); memcpy(&meta->rvalue.hdr, &hdr->right, sizeof(hdr->right)); if (!meta_is_supported(&meta->lvalue) || !meta_is_supported(&meta->rvalue)) { err = -EOPNOTSUPP; goto errout; } if (meta_change_data(&meta->lvalue, tb[TCA_EM_META_LVALUE]) < 0 || meta_change_data(&meta->rvalue, tb[TCA_EM_META_RVALUE]) < 0) goto errout; m->datalen = sizeof(*meta); m->data = (unsigned long) meta; err = 0; errout: if (err && meta) meta_delete(meta); return err; } static void em_meta_destroy(struct tcf_ematch *m) { if (m) meta_delete((struct meta_match *) m->data); } static int em_meta_dump(struct sk_buff *skb, struct tcf_ematch *em) { struct meta_match *meta = (struct meta_match *) em->data; struct tcf_meta_hdr hdr; const struct meta_type_ops *ops; memset(&hdr, 0, sizeof(hdr)); memcpy(&hdr.left, &meta->lvalue.hdr, sizeof(hdr.left)); memcpy(&hdr.right, &meta->rvalue.hdr, sizeof(hdr.right)); if (nla_put(skb, TCA_EM_META_HDR, sizeof(hdr), &hdr)) goto nla_put_failure; ops = meta_type_ops(&meta->lvalue); if (ops->dump(skb, &meta->lvalue, TCA_EM_META_LVALUE) < 0 || ops->dump(skb, &meta->rvalue, TCA_EM_META_RVALUE) < 0) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct tcf_ematch_ops em_meta_ops = { .kind = TCF_EM_META, .change = em_meta_change, .match = em_meta_match, .destroy = em_meta_destroy, .dump = em_meta_dump, .owner = THIS_MODULE, .link = LIST_HEAD_INIT(em_meta_ops.link) }; static int __init init_em_meta(void) { return tcf_em_register(&em_meta_ops); } static void __exit exit_em_meta(void) { tcf_em_unregister(&em_meta_ops); } MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata"); MODULE_LICENSE("GPL"); module_init(init_em_meta); module_exit(exit_em_meta); MODULE_ALIAS_TCF_EMATCH(TCF_EM_META); |
| 53 79 53 53 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ #include "hash.h" #include "main.h" #include <linux/gfp.h> #include <linux/lockdep.h> #include <linux/slab.h> /* clears the hash */ static void batadv_hash_init(struct batadv_hashtable *hash) { u32 i; for (i = 0; i < hash->size; i++) { INIT_HLIST_HEAD(&hash->table[i]); spin_lock_init(&hash->list_locks[i]); } atomic_set(&hash->generation, 0); } /** * batadv_hash_destroy() - Free only the hashtable and the hash itself * @hash: hash object to destroy */ void batadv_hash_destroy(struct batadv_hashtable *hash) { kfree(hash->list_locks); kfree(hash->table); kfree(hash); } /** * batadv_hash_new() - Allocates and clears the hashtable * @size: number of hash buckets to allocate * * Return: newly allocated hashtable, NULL on errors */ struct batadv_hashtable *batadv_hash_new(u32 size) { struct batadv_hashtable *hash; hash = kmalloc(sizeof(*hash), GFP_ATOMIC); if (!hash) return NULL; hash->table = kmalloc_array(size, sizeof(*hash->table), GFP_ATOMIC); if (!hash->table) goto free_hash; hash->list_locks = kmalloc_array(size, sizeof(*hash->list_locks), GFP_ATOMIC); if (!hash->list_locks) goto free_table; hash->size = size; batadv_hash_init(hash); return hash; free_table: kfree(hash->table); free_hash: kfree(hash); return NULL; } /** * batadv_hash_set_lock_class() - Set specific lockdep class for hash spinlocks * @hash: hash object to modify * @key: lockdep class key address */ void batadv_hash_set_lock_class(struct batadv_hashtable *hash, struct lock_class_key *key) { u32 i; for (i = 0; i < hash->size; i++) lockdep_set_class(&hash->list_locks[i], key); } |
| 381 198 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> struct fs_struct { int users; spinlock_t lock; seqcount_spinlock_t seq; int umask; int in_exec; struct path root, pwd; } __randomize_layout; extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { spin_lock(&fs->lock); *root = fs->root; path_get(root); spin_unlock(&fs->lock); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { spin_lock(&fs->lock); *pwd = fs->pwd; path_get(pwd); spin_unlock(&fs->lock); } extern bool current_chrooted(void); #endif /* _LINUX_FS_STRUCT_H */ |
| 12 12 1010 192 152 140 136 38 25 1011 1001 16 16 38 38 38 38 13 6 16 1016 1016 16 102 102 9 2 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Process number limiting controller for cgroups. * * Used to allow a cgroup hierarchy to stop any new processes from fork()ing * after a certain limit is reached. * * Since it is trivial to hit the task limit without hitting any kmemcg limits * in place, PIDs are a fundamental resource. As such, PID exhaustion must be * preventable in the scope of a cgroup hierarchy by allowing resource limiting * of the number of tasks in a cgroup. * * In order to use the `pids` controller, set the maximum number of tasks in * pids.max (this is not available in the root cgroup for obvious reasons). The * number of processes currently in the cgroup is given by pids.current. * Organisational operations are not blocked by cgroup policies, so it is * possible to have pids.current > pids.max. However, it is not possible to * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking * would cause a cgroup policy to be violated. * * To set a cgroup to have no limit, set pids.max to "max". This is the default * for all new cgroups (N.B. that PID limits are hierarchical, so the most * stringent limit in the hierarchy is followed). * * pids.current tracks all child cgroup hierarchies, so parent/pids.current is * a superset of parent/child/pids.current. * * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com> */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cgroup.h> #include <linux/slab.h> #include <linux/sched/task.h> #define PIDS_MAX (PID_MAX_LIMIT + 1ULL) #define PIDS_MAX_STR "max" enum pidcg_event { /* Fork failed in subtree because this pids_cgroup limit was hit. */ PIDCG_MAX, /* Fork failed in this pids_cgroup because ancestor limit was hit. */ PIDCG_FORKFAIL, NR_PIDCG_EVENTS, }; struct pids_cgroup { struct cgroup_subsys_state css; /* * Use 64-bit types so that we can safely represent "max" as * %PIDS_MAX = (%PID_MAX_LIMIT + 1). */ atomic64_t counter; atomic64_t limit; int64_t watermark; /* Handles for pids.events[.local] */ struct cgroup_file events_file; struct cgroup_file events_local_file; atomic64_t events[NR_PIDCG_EVENTS]; atomic64_t events_local[NR_PIDCG_EVENTS]; }; static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css) { return container_of(css, struct pids_cgroup, css); } static struct pids_cgroup *parent_pids(struct pids_cgroup *pids) { return css_pids(pids->css.parent); } static struct cgroup_subsys_state * pids_css_alloc(struct cgroup_subsys_state *parent) { struct pids_cgroup *pids; pids = kzalloc(sizeof(struct pids_cgroup), GFP_KERNEL); if (!pids) return ERR_PTR(-ENOMEM); atomic64_set(&pids->limit, PIDS_MAX); return &pids->css; } static void pids_css_free(struct cgroup_subsys_state *css) { kfree(css_pids(css)); } static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids) { /* * This is racy, but we don't need perfectly accurate tallying of * the watermark, and this lets us avoid extra atomic overhead. */ if (nr_pids > READ_ONCE(p->watermark)) WRITE_ONCE(p->watermark, nr_pids); } /** * pids_cancel - uncharge the local pid count * @pids: the pid cgroup state * @num: the number of pids to cancel * * This function will WARN if the pid count goes under 0, because such a case is * a bug in the pids controller proper. */ static void pids_cancel(struct pids_cgroup *pids, int num) { /* * A negative count (or overflow for that matter) is invalid, * and indicates a bug in the `pids` controller proper. */ WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter)); } /** * pids_uncharge - hierarchically uncharge the pid count * @pids: the pid cgroup state * @num: the number of pids to uncharge */ static void pids_uncharge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; for (p = pids; parent_pids(p); p = parent_pids(p)) pids_cancel(p, num); } /** * pids_charge - hierarchically charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge * * This function does *not* follow the pid limit set. It cannot fail and the new * pid count may exceed the limit. This is only used for reverting failed * attaches, where there is no other way out than violating the limit. */ static void pids_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); pids_update_watermark(p, new); } } /** * pids_try_charge - hierarchically try to charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge * @fail: storage of pid cgroup causing the fail * * This function follows the set limit. It will fail if the charge would cause * the new value to exceed the hierarchical limit. Returns 0 if the charge * succeeded, otherwise -EAGAIN. */ static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail) { struct pids_cgroup *p, *q; for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); int64_t limit = atomic64_read(&p->limit); /* * Since new is capped to the maximum number of pid_t, if * p->limit is %PIDS_MAX then we know that this test will never * fail. */ if (new > limit) { *fail = p; goto revert; } /* * Not technically accurate if we go over limit somewhere up * the hierarchy, but that's tolerable for the watermark. */ pids_update_watermark(p, new); } return 0; revert: for (q = pids; q != p; q = parent_pids(q)) pids_cancel(q, num); pids_cancel(p, num); return -EAGAIN; } static int pids_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; cgroup_taskset_for_each(task, dst_css, tset) { struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; /* * No need to pin @old_css between here and cancel_attach() * because cgroup core protects it from being freed before * the migration completes or fails. */ old_css = task_css(task, pids_cgrp_id); old_pids = css_pids(old_css); pids_charge(pids, 1); pids_uncharge(old_pids, 1); } return 0; } static void pids_cancel_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; cgroup_taskset_for_each(task, dst_css, tset) { struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; old_css = task_css(task, pids_cgrp_id); old_pids = css_pids(old_css); pids_charge(old_pids, 1); pids_uncharge(pids, 1); } } static void pids_event(struct pids_cgroup *pids_forking, struct pids_cgroup *pids_over_limit) { struct pids_cgroup *p = pids_forking; /* Only log the first time limit is hit. */ if (atomic64_inc_return(&p->events_local[PIDCG_FORKFAIL]) == 1) { pr_info("cgroup: fork rejected by pids controller in "); pr_cont_cgroup_path(p->css.cgroup); pr_cont("\n"); } if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { cgroup_file_notify(&p->events_local_file); return; } atomic64_inc(&pids_over_limit->events_local[PIDCG_MAX]); cgroup_file_notify(&pids_over_limit->events_local_file); for (p = pids_over_limit; parent_pids(p); p = parent_pids(p)) { atomic64_inc(&p->events[PIDCG_MAX]); cgroup_file_notify(&p->events_file); } } /* * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies * on cgroup_threadgroup_change_begin() held by the copy_process(). */ static int pids_can_fork(struct task_struct *task, struct css_set *cset) { struct pids_cgroup *pids, *pids_over_limit; int err; pids = css_pids(cset->subsys[pids_cgrp_id]); err = pids_try_charge(pids, 1, &pids_over_limit); if (err) pids_event(pids, pids_over_limit); return err; } static void pids_cancel_fork(struct task_struct *task, struct css_set *cset) { struct pids_cgroup *pids; pids = css_pids(cset->subsys[pids_cgrp_id]); pids_uncharge(pids, 1); } static void pids_release(struct task_struct *task) { struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id)); pids_uncharge(pids, 1); } static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_subsys_state *css = of_css(of); struct pids_cgroup *pids = css_pids(css); int64_t limit; int err; buf = strstrip(buf); if (!strcmp(buf, PIDS_MAX_STR)) { limit = PIDS_MAX; goto set_limit; } err = kstrtoll(buf, 0, &limit); if (err) return err; if (limit < 0 || limit >= PIDS_MAX) return -EINVAL; set_limit: /* * Limit updates don't need to be mutex'd, since it isn't * critical that any racing fork()s follow the new limit. */ atomic64_set(&pids->limit, limit); return nbytes; } static int pids_max_show(struct seq_file *sf, void *v) { struct cgroup_subsys_state *css = seq_css(sf); struct pids_cgroup *pids = css_pids(css); int64_t limit = atomic64_read(&pids->limit); if (limit >= PIDS_MAX) seq_printf(sf, "%s\n", PIDS_MAX_STR); else seq_printf(sf, "%lld\n", limit); return 0; } static s64 pids_current_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct pids_cgroup *pids = css_pids(css); return atomic64_read(&pids->counter); } static s64 pids_peak_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct pids_cgroup *pids = css_pids(css); return READ_ONCE(pids->watermark); } static int __pids_events_show(struct seq_file *sf, bool local) { struct pids_cgroup *pids = css_pids(seq_css(sf)); enum pidcg_event pe = PIDCG_MAX; atomic64_t *events; if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { pe = PIDCG_FORKFAIL; local = true; } events = local ? pids->events_local : pids->events; seq_printf(sf, "max %lld\n", (s64)atomic64_read(&events[pe])); return 0; } static int pids_events_show(struct seq_file *sf, void *v) { __pids_events_show(sf, false); return 0; } static int pids_events_local_show(struct seq_file *sf, void *v) { __pids_events_show(sf, true); return 0; } static struct cftype pids_files[] = { { .name = "max", .write = pids_max_write, .seq_show = pids_max_show, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_s64 = pids_peak_read, }, { .name = "events", .seq_show = pids_events_show, .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events.local", .seq_show = pids_events_local_show, .file_offset = offsetof(struct pids_cgroup, events_local_file), .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; static struct cftype pids_files_legacy[] = { { .name = "max", .write = pids_max_write, .seq_show = pids_max_show, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_s64 = pids_peak_read, }, { .name = "events", .seq_show = pids_events_show, .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; struct cgroup_subsys pids_cgrp_subsys = { .css_alloc = pids_css_alloc, .css_free = pids_css_free, .can_attach = pids_can_attach, .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, .release = pids_release, .legacy_cftypes = pids_files_legacy, .dfl_cftypes = pids_files, .threaded = true, }; |
| 5 2 4 6 2 1 2 16 4 13 2 80 11 56 19 2 56 13 45 45 36 10 25 25 25 34 16 3 3 2 6 3 3 3 64 64 13 9 4 50 38 13 12 4 3 2 10 1 35 45 53 27 27 28 25 25 44 1 44 41 13 30 25 29 3 1 2 26 1 1 3 25 37 5 2 2 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Isovalent */ #include <linux/bpf.h> #include <linux/bpf_mprog.h> static int bpf_mprog_link(struct bpf_tuple *tuple, u32 id_or_fd, u32 flags, enum bpf_prog_type type) { struct bpf_link *link = ERR_PTR(-EINVAL); bool id = flags & BPF_F_ID; if (id) link = bpf_link_by_id(id_or_fd); else if (id_or_fd) link = bpf_link_get_from_fd(id_or_fd); if (IS_ERR(link)) return PTR_ERR(link); if (type && link->prog->type != type) { bpf_link_put(link); return -EINVAL; } tuple->link = link; tuple->prog = link->prog; return 0; } static int bpf_mprog_prog(struct bpf_tuple *tuple, u32 id_or_fd, u32 flags, enum bpf_prog_type type) { struct bpf_prog *prog = ERR_PTR(-EINVAL); bool id = flags & BPF_F_ID; if (id) prog = bpf_prog_by_id(id_or_fd); else if (id_or_fd) prog = bpf_prog_get(id_or_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (type && prog->type != type) { bpf_prog_put(prog); return -EINVAL; } tuple->link = NULL; tuple->prog = prog; return 0; } static int bpf_mprog_tuple_relative(struct bpf_tuple *tuple, u32 id_or_fd, u32 flags, enum bpf_prog_type type) { bool link = flags & BPF_F_LINK; bool id = flags & BPF_F_ID; memset(tuple, 0, sizeof(*tuple)); if (link) return bpf_mprog_link(tuple, id_or_fd, flags, type); /* If no relevant flag is set and no id_or_fd was passed, then * tuple link/prog is just NULLed. This is the case when before/ * after selects first/last position without passing fd. */ if (!id && !id_or_fd) return 0; return bpf_mprog_prog(tuple, id_or_fd, flags, type); } static void bpf_mprog_tuple_put(struct bpf_tuple *tuple) { if (tuple->link) bpf_link_put(tuple->link); else if (tuple->prog) bpf_prog_put(tuple->prog); } /* The bpf_mprog_{replace,delete}() operate on exact idx position with the * one exception that for deletion we support delete from front/back. In * case of front idx is -1, in case of back idx is bpf_mprog_total(entry). * Adjustment to first and last entry is trivial. The bpf_mprog_insert() * we have to deal with the following cases: * * idx + before: * * Insert P4 before P3: idx for old array is 1, idx for new array is 2, * hence we adjust target idx for the new array, so that memmove copies * P1 and P2 to the new entry, and we insert P4 into idx 2. Inserting * before P1 would have old idx -1 and new idx 0. * * +--+--+--+ +--+--+--+--+ +--+--+--+--+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| * +--+--+--+ +--+--+--+--+ +--+--+--+--+ * * idx + after: * * Insert P4 after P2: idx for old array is 2, idx for new array is 2. * Again, memmove copies P1 and P2 to the new entry, and we insert P4 * into idx 2. Inserting after P3 would have both old/new idx at 4 aka * bpf_mprog_total(entry). * * +--+--+--+ +--+--+--+--+ +--+--+--+--+ * |P1|P2|P3| ==> |P1|P2| |P3| ==> |P1|P2|P4|P3| * +--+--+--+ +--+--+--+--+ +--+--+--+--+ */ static int bpf_mprog_replace(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_tuple *ntuple, int idx) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; struct bpf_prog *oprog; bpf_mprog_read(entry, idx, &fp, &cp); oprog = READ_ONCE(fp->prog); bpf_mprog_write(fp, cp, ntuple); if (!ntuple->link) { WARN_ON_ONCE(cp->link); bpf_prog_put(oprog); } *entry_new = entry; return 0; } static int bpf_mprog_insert(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_tuple *ntuple, int idx, u32 flags) { int total = bpf_mprog_total(entry); struct bpf_mprog_entry *peer; struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; peer = bpf_mprog_peer(entry); bpf_mprog_entry_copy(peer, entry); if (idx == total) goto insert; else if (flags & BPF_F_BEFORE) idx += 1; bpf_mprog_entry_grow(peer, idx); insert: bpf_mprog_read(peer, idx, &fp, &cp); bpf_mprog_write(fp, cp, ntuple); bpf_mprog_inc(peer); *entry_new = peer; return 0; } static int bpf_mprog_delete(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_tuple *dtuple, int idx) { int total = bpf_mprog_total(entry); struct bpf_mprog_entry *peer; peer = bpf_mprog_peer(entry); bpf_mprog_entry_copy(peer, entry); if (idx == -1) idx = 0; else if (idx == total) idx = total - 1; bpf_mprog_entry_shrink(peer, idx); bpf_mprog_dec(peer); bpf_mprog_mark_for_release(peer, dtuple); *entry_new = peer; return 0; } /* In bpf_mprog_pos_*() we evaluate the target position for the BPF * program/link that needs to be replaced, inserted or deleted for * each "rule" independently. If all rules agree on that position * or existing element, then enact replacement, addition or deletion. * If this is not the case, then the request cannot be satisfied and * we bail out with an error. */ static int bpf_mprog_pos_exact(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; int i; for (i = 0; i < bpf_mprog_total(entry); i++) { bpf_mprog_read(entry, i, &fp, &cp); if (tuple->prog == READ_ONCE(fp->prog)) return tuple->link == cp->link ? i : -EBUSY; } return -ENOENT; } static int bpf_mprog_pos_before(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; int i; for (i = 0; i < bpf_mprog_total(entry); i++) { bpf_mprog_read(entry, i, &fp, &cp); if (tuple->prog == READ_ONCE(fp->prog) && (!tuple->link || tuple->link == cp->link)) return i - 1; } return tuple->prog ? -ENOENT : -1; } static int bpf_mprog_pos_after(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; int i; for (i = 0; i < bpf_mprog_total(entry); i++) { bpf_mprog_read(entry, i, &fp, &cp); if (tuple->prog == READ_ONCE(fp->prog) && (!tuple->link || tuple->link == cp->link)) return i + 1; } return tuple->prog ? -ENOENT : bpf_mprog_total(entry); } int bpf_mprog_attach(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_prog *prog_new, struct bpf_link *link, struct bpf_prog *prog_old, u32 flags, u32 id_or_fd, u64 revision) { struct bpf_tuple rtuple, ntuple = { .prog = prog_new, .link = link, }, otuple = { .prog = prog_old, .link = link, }; int ret, idx = -ERANGE, tidx; if (revision && revision != bpf_mprog_revision(entry)) return -ESTALE; if (bpf_mprog_exists(entry, prog_new)) return -EEXIST; ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags & ~BPF_F_REPLACE, prog_new->type); if (ret) return ret; if (flags & BPF_F_REPLACE) { tidx = bpf_mprog_pos_exact(entry, &otuple); if (tidx < 0) { ret = tidx; goto out; } idx = tidx; } else if (bpf_mprog_total(entry) == bpf_mprog_max()) { ret = -ERANGE; goto out; } if (flags & BPF_F_BEFORE) { tidx = bpf_mprog_pos_before(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < -1 ? tidx : -ERANGE; goto out; } idx = tidx; } if (flags & BPF_F_AFTER) { tidx = bpf_mprog_pos_after(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < 0 ? tidx : -ERANGE; goto out; } idx = tidx; } if (idx < -1) { if (rtuple.prog || flags) { ret = -EINVAL; goto out; } idx = bpf_mprog_total(entry); flags = BPF_F_AFTER; } if (idx >= bpf_mprog_max()) { ret = -ERANGE; goto out; } if (flags & BPF_F_REPLACE) ret = bpf_mprog_replace(entry, entry_new, &ntuple, idx); else ret = bpf_mprog_insert(entry, entry_new, &ntuple, idx, flags); out: bpf_mprog_tuple_put(&rtuple); return ret; } static int bpf_mprog_fetch(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple, int idx) { int total = bpf_mprog_total(entry); struct bpf_mprog_cp *cp; struct bpf_mprog_fp *fp; struct bpf_prog *prog; struct bpf_link *link; if (idx == -1) idx = 0; else if (idx == total) idx = total - 1; bpf_mprog_read(entry, idx, &fp, &cp); prog = READ_ONCE(fp->prog); link = cp->link; /* The deletion request can either be without filled tuple in which * case it gets populated here based on idx, or with filled tuple * where the only thing we end up doing is the WARN_ON_ONCE() assert. * If we hit a BPF link at the given index, it must not be removed * from opts path. */ if (link && !tuple->link) return -EBUSY; WARN_ON_ONCE(tuple->prog && tuple->prog != prog); WARN_ON_ONCE(tuple->link && tuple->link != link); tuple->prog = prog; tuple->link = link; return 0; } int bpf_mprog_detach(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_prog *prog, struct bpf_link *link, u32 flags, u32 id_or_fd, u64 revision) { struct bpf_tuple rtuple, dtuple = { .prog = prog, .link = link, }; int ret, idx = -ERANGE, tidx; if (flags & BPF_F_REPLACE) return -EINVAL; if (revision && revision != bpf_mprog_revision(entry)) return -ESTALE; if (!bpf_mprog_total(entry)) return -ENOENT; ret = bpf_mprog_tuple_relative(&rtuple, id_or_fd, flags, prog ? prog->type : BPF_PROG_TYPE_UNSPEC); if (ret) return ret; if (dtuple.prog) { tidx = bpf_mprog_pos_exact(entry, &dtuple); if (tidx < 0) { ret = tidx; goto out; } idx = tidx; } if (flags & BPF_F_BEFORE) { tidx = bpf_mprog_pos_before(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < -1 ? tidx : -ERANGE; goto out; } idx = tidx; } if (flags & BPF_F_AFTER) { tidx = bpf_mprog_pos_after(entry, &rtuple); if (tidx < -1 || (idx >= -1 && tidx != idx)) { ret = tidx < 0 ? tidx : -ERANGE; goto out; } idx = tidx; } if (idx < -1) { if (rtuple.prog || flags) { ret = -EINVAL; goto out; } idx = bpf_mprog_total(entry); flags = BPF_F_AFTER; } if (idx >= bpf_mprog_max()) { ret = -ERANGE; goto out; } ret = bpf_mprog_fetch(entry, &dtuple, idx); if (ret) goto out; ret = bpf_mprog_delete(entry, entry_new, &dtuple, idx); out: bpf_mprog_tuple_put(&rtuple); return ret; } int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct bpf_mprog_entry *entry) { u32 __user *uprog_flags, *ulink_flags; u32 __user *uprog_id, *ulink_id; struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; struct bpf_prog *prog; const u32 flags = 0; u32 id, count = 0; u64 revision = 1; int i, ret = 0; if (attr->query.query_flags || attr->query.attach_flags) return -EINVAL; if (entry) { revision = bpf_mprog_revision(entry); count = bpf_mprog_total(entry); } if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision))) return -EFAULT; if (copy_to_user(&uattr->query.count, &count, sizeof(count))) return -EFAULT; uprog_id = u64_to_user_ptr(attr->query.prog_ids); uprog_flags = u64_to_user_ptr(attr->query.prog_attach_flags); ulink_id = u64_to_user_ptr(attr->query.link_ids); ulink_flags = u64_to_user_ptr(attr->query.link_attach_flags); if (attr->query.count == 0 || !uprog_id || !count) return 0; if (attr->query.count < count) { count = attr->query.count; ret = -ENOSPC; } for (i = 0; i < bpf_mprog_max(); i++) { bpf_mprog_read(entry, i, &fp, &cp); prog = READ_ONCE(fp->prog); if (!prog) break; id = prog->aux->id; if (copy_to_user(uprog_id + i, &id, sizeof(id))) return -EFAULT; if (uprog_flags && copy_to_user(uprog_flags + i, &flags, sizeof(flags))) return -EFAULT; id = cp->link ? cp->link->id : 0; if (ulink_id && copy_to_user(ulink_id + i, &id, sizeof(id))) return -EFAULT; if (ulink_flags && copy_to_user(ulink_flags + i, &flags, sizeof(flags))) return -EFAULT; if (i + 1 == count) break; } return ret; } |
| 546 546 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Return: >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { unsigned int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * @node: memory node from which to allocate or %NUMA_NO_NODE * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * Return: TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free(mask, cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu based on NUMA distances * @i: index number * @node: local numa_node * * Return: online CPU according to a numa aware policy; local cpus are returned * first, followed by non-local ones, then it wraps around. * * For those who wants to enumerate all CPUs based on their NUMA distances, * i.e. call this function in a loop, like: * * for (i = 0; i < num_online_cpus(); i++) { * cpu = cpumask_local_spread(i, node); * do_something(cpu); * } * * There's a better alternative based on for_each()-like iterators: * * for_each_numa_hop_mask(mask, node) { * for_each_cpu_andnot(cpu, mask, prev) * do_something(cpu); * prev = mask; * } * * It's simpler and more verbose than above. Complexity of iterator-based * enumeration is O(sched_domains_numa_levels * nr_cpu_ids), while * cpumask_local_spread() when called for each cpu is * O(sched_domains_numa_levels * nr_cpu_ids * log(nr_cpu_ids)). */ unsigned int cpumask_local_spread(unsigned int i, int node) { unsigned int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); cpu = sched_numa_find_nth_cpu(cpu_online_mask, i, node); WARN_ON(cpu >= nr_cpu_ids); return cpu; } EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** * cpumask_any_and_distribute - Return an arbitrary cpu within src1p & src2p. * @src1p: first &cpumask for intersection * @src2p: second &cpumask for intersection * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * * Return: >= nr_cpu_ids if the intersection is empty. */ unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { unsigned int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, prev + 1); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_and_distribute); /** * cpumask_any_distribute - Return an arbitrary cpu from srcp * @srcp: &cpumask for selection * * Return: >= nr_cpu_ids if the intersection is empty. */ unsigned int cpumask_any_distribute(const struct cpumask *srcp) { unsigned int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = find_next_bit_wrap(cpumask_bits(srcp), nr_cpumask_bits, prev + 1); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_distribute); |
| 14070 1412 58016 58113 56933 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Access vector cache interface for object managers. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SELINUX_AVC_H_ #define _SELINUX_AVC_H_ #include <linux/stddef.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kdev_t.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/audit.h> #include <linux/lsm_audit.h> #include <linux/in6.h> #include "flask.h" #include "av_permissions.h" #include "security.h" /* * An entry in the AVC. */ struct avc_entry; struct task_struct; struct inode; struct sock; struct sk_buff; /* * AVC statistics */ struct avc_cache_stats { unsigned int lookups; unsigned int misses; unsigned int allocations; unsigned int reclaims; unsigned int frees; }; /* * We only need this data after we have decided to send an audit message. */ struct selinux_audit_data { u32 ssid; u32 tsid; u16 tclass; u32 requested; u32 audited; u32 denied; int result; } __randomize_layout; /* * AVC operations */ void __init avc_init(void); static inline u32 avc_audit_required(u32 requested, struct av_decision *avd, int result, u32 auditdeny, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; /* * auditdeny is TRICKY! Setting a bit in * this field means that ANY denials should NOT be audited if * the policy contains an explicit dontaudit rule for that * permission. Take notice that this is unrelated to the * actual permissions that were denied. As an example lets * assume: * * denied == READ * avd.auditdeny & ACCESS == 0 (not set means explicit rule) * auditdeny & ACCESS == 1 * * We will NOT audit the denial even though the denied * permission was READ and the auditdeny checks were for * ACCESS */ if (auditdeny && !(auditdeny & avd->auditdeny)) audited = 0; } else if (result) audited = denied = requested; else audited = requested & avd->auditallow; *deniedp = denied; return audited; } int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a); /** * avc_audit - Audit the granting or denial of permissions. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions * @avd: access vector decisions * @result: result from avc_has_perm_noaudit * @a: auxiliary audit data * * Audit the granting or denial of permissions in accordance * with the policy. This function is typically called by * avc_has_perm() after a permission check, but can also be * called directly by callers who use avc_has_perm_noaudit() * in order to separate the permission check from the auditing. * For example, this separation is useful when the permission check must * be performed under a lock, to allow the lock to be released * before calling the auditing code. */ static inline int avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, int result, struct common_audit_data *a) { u32 audited, denied; audited = avc_audit_required(requested, avd, result, 0, &denied); if (likely(!audited)) return 0; return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied, result, a); } #define AVC_STRICT 1 /* Ignore permissive mode. */ #define AVC_EXTENDED_PERMS 2 /* update extended permissions */ int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd); int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); #define AVC_EXT_IOCTL (1 << 0) /* Cache entry for an ioctl extended permission */ #define AVC_EXT_NLMSG (1 << 1) /* Cache entry for an nlmsg extended permission */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 base_perm, u8 perm, struct common_audit_data *ad); u32 avc_policy_seqno(void); #define AVC_CALLBACK_GRANT 1 #define AVC_CALLBACK_TRY_REVOKE 2 #define AVC_CALLBACK_REVOKE 4 #define AVC_CALLBACK_RESET 8 #define AVC_CALLBACK_AUDITALLOW_ENABLE 16 #define AVC_CALLBACK_AUDITALLOW_DISABLE 32 #define AVC_CALLBACK_AUDITDENY_ENABLE 64 #define AVC_CALLBACK_AUDITDENY_DISABLE 128 #define AVC_CALLBACK_ADD_XPERMS 256 int avc_add_callback(int (*callback)(u32 event), u32 events); /* Exported to selinuxfs */ int avc_get_hash_stats(char *page); unsigned int avc_get_cache_threshold(void); void avc_set_cache_threshold(unsigned int cache_threshold); #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats); #endif #endif /* _SELINUX_AVC_H_ */ |
| 5 3 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_SCHED_RED_H #define __NET_SCHED_RED_H #include <linux/types.h> #include <linux/bug.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> #include <net/dsfield.h> #include <linux/reciprocal_div.h> /* Random Early Detection (RED) algorithm. ======================================= Source: Sally Floyd and Van Jacobson, "Random Early Detection Gateways for Congestion Avoidance", 1993, IEEE/ACM Transactions on Networking. This file codes a "divisionless" version of RED algorithm as written down in Fig.17 of the paper. Short description. ------------------ When a new packet arrives we calculate the average queue length: avg = (1-W)*avg + W*current_queue_len, W is the filter time constant (chosen as 2^(-Wlog)), it controls the inertia of the algorithm. To allow larger bursts, W should be decreased. if (avg > th_max) -> packet marked (dropped). if (avg < th_min) -> packet passes. if (th_min < avg < th_max) we calculate probability: Pb = max_P * (avg - th_min)/(th_max-th_min) and mark (drop) packet with this probability. Pb changes from 0 (at avg==th_min) to max_P (avg==th_max). max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) is a negative power of two in order arithmetic to contain only shifts. Parameters, settable by user: ----------------------------- qth_min - bytes (should be < qth_max/2) qth_max - bytes (should be at least 2*qth_min and less limit) Wlog - bits (<32) log(1/W). Plog - bits (<32) Plog is related to max_P by formula: max_P = (qth_max-qth_min)/2^Plog; F.e. if qth_max=128K and qth_min=32K, then Plog=22 corresponds to max_P=0.02 Scell_log Stab Lookup table for log((1-W)^(t/t_ave). NOTES: Upper bound on W. ----------------- If you want to allow bursts of L packets of size S, you should choose W: L + 1 - th_min/S < (1-(1-W)^L)/W th_min/S = 32 th_min/S = 4 log(W) L -1 33 -2 35 -3 39 -4 46 -5 57 -6 75 -7 101 -8 135 -9 190 etc. */ /* * Adaptative RED : An Algorithm for Increasing the Robustness of RED's AQM * (Sally FLoyd, Ramakrishna Gummadi, and Scott Shenker) August 2001 * * Every 500 ms: * if (avg > target and max_p <= 0.5) * increase max_p : max_p += alpha; * else if (avg < target and max_p >= 0.01) * decrease max_p : max_p *= beta; * * target :[qth_min + 0.4*(qth_min - qth_max), * qth_min + 0.6*(qth_min - qth_max)]. * alpha : min(0.01, max_p / 4) * beta : 0.9 * max_P is a Q0.32 fixed point number (with 32 bits mantissa) * max_P between 0.01 and 0.5 (1% - 50%) [ Its no longer a negative power of two ] */ #define RED_ONE_PERCENT ((u32)DIV_ROUND_CLOSEST(1ULL<<32, 100)) #define MAX_P_MIN (1 * RED_ONE_PERCENT) #define MAX_P_MAX (50 * RED_ONE_PERCENT) #define MAX_P_ALPHA(val) min(MAX_P_MIN, val / 4) #define RED_STAB_SIZE 256 #define RED_STAB_MASK (RED_STAB_SIZE - 1) struct red_stats { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ u32 forced_drop; /* Forced drops, qavg > max_thresh */ u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ }; struct red_parms { /* Parameters */ u32 qth_min; /* Min avg length threshold: Wlog scaled */ u32 qth_max; /* Max avg length threshold: Wlog scaled */ u32 Scell_max; u32 max_P; /* probability, [0 .. 1.0] 32 scaled */ /* reciprocal_value(max_P / qth_delta) */ struct reciprocal_value max_P_reciprocal; u32 qth_delta; /* max_th - min_th */ u32 target_min; /* min_th + 0.4*(max_th - min_th) */ u32 target_max; /* min_th + 0.6*(max_th - min_th) */ u8 Scell_log; u8 Wlog; /* log(W) */ u8 Plog; /* random number bits */ u8 Stab[RED_STAB_SIZE]; }; struct red_vars { /* Variables */ int qcount; /* Number of packets since last random number generation */ u32 qR; /* Cached random number */ unsigned long qavg; /* Average queue length: Wlog scaled */ ktime_t qidlestart; /* Start of current idle period */ }; static inline u32 red_maxp(u8 Plog) { return Plog < 32 ? (~0U >> Plog) : ~0U; } static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; v->qcount = -1; } static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log, u8 *stab) { if (fls(qth_min) + Wlog >= 32) return false; if (fls(qth_max) + Wlog >= 32) return false; if (Scell_log >= 32) return false; if (qth_max < qth_min) return false; if (stab) { int i; for (i = 0; i < RED_STAB_SIZE; i++) if (stab[i] >= 32) return false; } return true; } static inline int red_get_flags(unsigned char qopt_flags, unsigned char historic_mask, struct nlattr *flags_attr, unsigned char supported_mask, struct nla_bitfield32 *p_flags, unsigned char *p_userbits, struct netlink_ext_ack *extack) { struct nla_bitfield32 flags; if (qopt_flags && flags_attr) { NL_SET_ERR_MSG_MOD(extack, "flags should be passed either through qopt, or through a dedicated attribute"); return -EINVAL; } if (flags_attr) { flags = nla_get_bitfield32(flags_attr); } else { flags.selector = historic_mask; flags.value = qopt_flags & historic_mask; } *p_flags = flags; *p_userbits = qopt_flags & ~historic_mask; return 0; } static inline int red_validate_flags(unsigned char flags, struct netlink_ext_ack *extack) { if ((flags & TC_RED_NODROP) && !(flags & TC_RED_ECN)) { NL_SET_ERR_MSG_MOD(extack, "nodrop mode is only meaningful with ECN"); return -EINVAL; } return 0; } static inline void red_set_parms(struct red_parms *p, u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog, u8 Scell_log, u8 *stab, u32 max_P) { int delta = qth_max - qth_min; u32 max_p_delta; WRITE_ONCE(p->qth_min, qth_min << Wlog); WRITE_ONCE(p->qth_max, qth_max << Wlog); WRITE_ONCE(p->Wlog, Wlog); WRITE_ONCE(p->Plog, Plog); if (delta <= 0) delta = 1; p->qth_delta = delta; if (!max_P) { max_P = red_maxp(Plog); max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */ } WRITE_ONCE(p->max_P, max_P); max_p_delta = max_P / delta; max_p_delta = max(max_p_delta, 1U); p->max_P_reciprocal = reciprocal_value(max_p_delta); /* RED Adaptative target : * [min_th + 0.4*(min_th - max_th), * min_th + 0.6*(min_th - max_th)]. */ delta /= 5; p->target_min = qth_min + 2*delta; p->target_max = qth_min + 3*delta; WRITE_ONCE(p->Scell_log, Scell_log); p->Scell_max = (255 << Scell_log); if (stab) memcpy(p->Stab, stab, sizeof(p->Stab)); } static inline int red_is_idling(const struct red_vars *v) { return v->qidlestart != 0; } static inline void red_start_of_idle_period(struct red_vars *v) { v->qidlestart = ktime_get(); } static inline void red_end_of_idle_period(struct red_vars *v) { v->qidlestart = 0; } static inline void red_restart(struct red_vars *v) { red_end_of_idle_period(v); v->qavg = 0; v->qcount = -1; } static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms *p, const struct red_vars *v) { s64 delta = ktime_us_delta(ktime_get(), v->qidlestart); long us_idle = min_t(s64, delta, p->Scell_max); int shift; /* * The problem: ideally, average length queue recalculation should * be done over constant clock intervals. This is too expensive, so * that the calculation is driven by outgoing packets. * When the queue is idle we have to model this clock by hand. * * SF+VJ proposed to "generate": * * m = idletime / (average_pkt_size / bandwidth) * * dummy packets as a burst after idle time, i.e. * * v->qavg *= (1-W)^m * * This is an apparently overcomplicated solution (f.e. we have to * precompute a table to make this calculation in reasonable time) * I believe that a simpler model may be used here, * but it is field for experiments. */ shift = p->Stab[(us_idle >> p->Scell_log) & RED_STAB_MASK]; if (shift) return v->qavg >> shift; else { /* Approximate initial part of exponent with linear function: * * (1-W)^m ~= 1-mW + ... * * Seems, it is the best solution to * problem of too coarse exponent tabulation. */ us_idle = (v->qavg * (u64)us_idle) >> p->Scell_log; if (us_idle < (v->qavg >> 1)) return v->qavg - us_idle; else return v->qavg >> 1; } } static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p, const struct red_vars *v, unsigned int backlog) { /* * NOTE: v->qavg is fixed point number with point at Wlog. * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; * * --ANK (980924) */ return v->qavg + (backlog - (v->qavg >> p->Wlog)); } static inline unsigned long red_calc_qavg(const struct red_parms *p, const struct red_vars *v, unsigned int backlog) { if (!red_is_idling(v)) return red_calc_qavg_no_idle_time(p, v, backlog); else return red_calc_qavg_from_idle_time(p, v); } static inline u32 red_random(const struct red_parms *p) { return reciprocal_divide(get_random_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, const struct red_vars *v, unsigned long qavg) { /* The formula used below causes questions. OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed point at Wlog, two lines below have the following floating point equivalent: max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount Any questions? --ANK (980924) */ return !(((qavg - p->qth_min) >> p->Wlog) * v->qcount < v->qR); } enum { RED_BELOW_MIN_THRESH, RED_BETWEEN_TRESH, RED_ABOVE_MAX_TRESH, }; static inline int red_cmp_thresh(const struct red_parms *p, unsigned long qavg) { if (qavg < p->qth_min) return RED_BELOW_MIN_THRESH; else if (qavg >= p->qth_max) return RED_ABOVE_MAX_TRESH; else return RED_BETWEEN_TRESH; } enum { RED_DONT_MARK, RED_PROB_MARK, RED_HARD_MARK, }; static inline int red_action(const struct red_parms *p, struct red_vars *v, unsigned long qavg) { switch (red_cmp_thresh(p, qavg)) { case RED_BELOW_MIN_THRESH: v->qcount = -1; return RED_DONT_MARK; case RED_BETWEEN_TRESH: if (++v->qcount) { if (red_mark_probability(p, v, qavg)) { v->qcount = 0; v->qR = red_random(p); return RED_PROB_MARK; } } else v->qR = red_random(p); return RED_DONT_MARK; case RED_ABOVE_MAX_TRESH: v->qcount = -1; return RED_HARD_MARK; } BUG(); return RED_DONT_MARK; } static inline void red_adaptative_algo(struct red_parms *p, struct red_vars *v) { unsigned long qavg; u32 max_p_delta; qavg = v->qavg; if (red_is_idling(v)) qavg = red_calc_qavg_from_idle_time(p, v); /* v->qavg is fixed point number with point at Wlog */ qavg >>= p->Wlog; if (qavg > p->target_max && p->max_P <= MAX_P_MAX) p->max_P += MAX_P_ALPHA(p->max_P); /* maxp = maxp + alpha */ else if (qavg < p->target_min && p->max_P >= MAX_P_MIN) p->max_P = (p->max_P/10)*9; /* maxp = maxp * Beta */ max_p_delta = DIV_ROUND_CLOSEST(p->max_P, p->qth_delta); max_p_delta = max(max_p_delta, 1U); p->max_P_reciprocal = reciprocal_value(max_p_delta); } #endif |
| 26 26 1 25 26 9 60 59 16 16 77 77 77 70 24 46 39 7 46 46 46 46 7 46 88 88 98 98 81 17 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "socket.h" #include "timers.h" #include "device.h" #include "ratelimiter.h" #include "peer.h" #include "messages.h" #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> #include <net/dst_metadata.h> #include <net/gso.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> #include <net/addrconf.h> static LIST_HEAD(device_list); static int wg_open(struct net_device *dev) { struct in_device *dev_v4 = __in_dev_get_rtnl(dev); struct inet6_dev *dev_v6 = __in6_dev_get(dev); struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; int ret; if (dev_v4) { /* At some point we might put this check near the ip_rt_send_ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar * to the current secpath check. */ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; } if (dev_v6) dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; mutex_lock(&wg->device_update_lock); ret = wg_socket_init(wg, wg->incoming_port); if (ret < 0) goto out; list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_send_staged_packets(peer); if (peer->persistent_keepalive_interval) wg_packet_send_keepalive(peer); } out: mutex_unlock(&wg->device_update_lock); return ret; } static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; /* If the machine is constantly suspending and resuming, as part of * its normal operation rather than as a somewhat rare event, then we * don't actually want to clear keys. */ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)) return 0; if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE) return 0; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { del_timer(&peer->timer_zero_key_material); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); } mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); rcu_barrier(); return 0; } static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification }; static int wg_vm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_noise_expire_current_peer_keypairs(peer); mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); return 0; } static struct notifier_block vm_notifier = { .notifier_call = wg_vm_notification }; static int wg_stop(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; struct sk_buff *skb; mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_purge_staged_packets(peer); wg_timers_stop(peer); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); } mutex_unlock(&wg->device_update_lock); while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL) kfree_skb(skb); atomic_set(&wg->handshake_queue_len, 0); wg_socket_reinit(wg, NULL, NULL); return 0; } static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct sk_buff_head packets; struct wg_peer *peer; struct sk_buff *next; sa_family_t family; u32 mtu; int ret; if (unlikely(!wg_check_packet_protocol(skb))) { ret = -EPROTONOSUPPORT; net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); goto err; } peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb); if (unlikely(!peer)) { ret = -ENOKEY; if (skb->protocol == htons(ETH_P_IP)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n", dev->name, &ip_hdr(skb)->daddr); else if (skb->protocol == htons(ETH_P_IPV6)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", dev->name, &ipv6_hdr(skb)->daddr); goto err_icmp; } family = READ_ONCE(peer->endpoint.addr.sa_family); if (unlikely(family != AF_INET && family != AF_INET6)) { ret = -EDESTADDRREQ; net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n", dev->name, peer->internal_id); goto err_peer; } mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { skb_mark_not_on_list(skb); } else { struct sk_buff *segs = skb_gso_segment(skb, 0); if (IS_ERR(segs)) { ret = PTR_ERR(segs); goto err_peer; } dev_kfree_skb(skb); skb = segs; } skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) continue; /* We only need to keep the original dst around for icmp, * so at this point we're in a position to drop it. */ skb_dst_drop(skb); PACKET_CB(skb)->mtu = mtu; __skb_queue_tail(&packets, skb); } spin_lock_bh(&peer->staged_packet_queue.lock); /* If the queue is getting too big, we start removing the oldest packets * until it's small again. We do this before adding the new packet, so * we don't remove GSO segments that are in excess. */ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); DEV_STATS_INC(dev, tx_dropped); } skb_queue_splice_tail(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); wg_packet_send_staged_packets(peer); wg_peer_put(peer); return NETDEV_TX_OK; err_peer: wg_peer_put(peer); err_icmp: if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } static const struct net_device_ops netdev_ops = { .ndo_open = wg_open, .ndo_stop = wg_stop, .ndo_start_xmit = wg_xmit, }; static void wg_destruct(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); rtnl_lock(); list_del(&wg->device_list); rtnl_unlock(); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg->incoming_port = 0; wg_socket_reinit(wg, NULL, NULL); /* The final references are cleared in the below calls to destroy_workqueue. */ wg_peer_remove_all(wg); destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); wg_packet_queue_free(&wg->handshake_queue, true); wg_packet_queue_free(&wg->decrypt_queue, false); wg_packet_queue_free(&wg->encrypt_queue, false); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); pr_debug("%s: Interface destroyed\n", dev->name); free_netdev(dev); } static const struct device_type device_type = { .name = KBUILD_MODNAME }; static void wg_setup(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->hard_header_len = 0; dev->addr_len = 0; dev->needed_headroom = DATA_PACKET_HEAD_ROOM; dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE); dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; dev->mtu = ETH_DATA_LEN - overhead; dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; SET_NETDEV_DEVTYPE(dev, &device_type); /* We need to keep the dst around in case of icmp replies. */ netif_keep_dst(dev); netif_set_tso_max_size(dev, GSO_MAX_SIZE); wg->dev = dev; } static int wg_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct wg_device *wg = netdev_priv(dev); int ret = -ENOMEM; rcu_assign_pointer(wg->creating_net, src_net); init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); wg_allowedips_init(&wg->peer_allowedips); wg_cookie_checker_init(&wg->cookie_checker, wg); INIT_LIST_HEAD(&wg->peer_list); wg->device_update_gen = 1; wg->peer_hashtable = wg_pubkey_hashtable_alloc(); if (!wg->peer_hashtable) return ret; wg->index_hashtable = wg_index_hashtable_alloc(); if (!wg->index_hashtable) goto err_free_peer_hashtable; wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_receive_wq) goto err_free_index_hashtable; wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_send_wq) goto err_destroy_handshake_receive; wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name); if (!wg->packet_crypt_wq) goto err_destroy_handshake_send; ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_destroy_packet_crypt; ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_free_encrypt_queue; ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker, MAX_QUEUED_INCOMING_HANDSHAKES); if (ret < 0) goto err_free_decrypt_queue; ret = wg_ratelimiter_init(); if (ret < 0) goto err_free_handshake_queue; ret = register_netdevice(dev); if (ret < 0) goto err_uninit_ratelimiter; list_add(&wg->device_list, &device_list); /* We wait until the end to assign priv_destructor, so that * register_netdevice doesn't call it for us if it fails. */ dev->priv_destructor = wg_destruct; pr_debug("%s: Interface created\n", dev->name); return ret; err_uninit_ratelimiter: wg_ratelimiter_uninit(); err_free_handshake_queue: wg_packet_queue_free(&wg->handshake_queue, false); err_free_decrypt_queue: wg_packet_queue_free(&wg->decrypt_queue, false); err_free_encrypt_queue: wg_packet_queue_free(&wg->encrypt_queue, false); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: destroy_workqueue(wg->handshake_send_wq); err_destroy_handshake_receive: destroy_workqueue(wg->handshake_receive_wq); err_free_index_hashtable: kvfree(wg->index_hashtable); err_free_peer_hashtable: kvfree(wg->peer_hashtable); return ret; } static struct rtnl_link_ops link_ops __read_mostly = { .kind = KBUILD_MODNAME, .priv_size = sizeof(struct wg_device), .setup = wg_setup, .newlink = wg_newlink, }; static void wg_netns_pre_exit(struct net *net) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { if (rcu_access_pointer(wg->creating_net) == net) { pr_debug("%s: Creating namespace exiting\n", wg->dev->name); netif_carrier_off(wg->dev); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg_socket_reinit(wg, NULL, NULL); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_socket_clear_peer_endpoint_src(peer); mutex_unlock(&wg->device_update_lock); } } rtnl_unlock(); } static struct pernet_operations pernet_ops = { .pre_exit = wg_netns_pre_exit }; int __init wg_device_init(void) { int ret; ret = register_pm_notifier(&pm_notifier); if (ret) return ret; ret = register_random_vmfork_notifier(&vm_notifier); if (ret) goto error_pm; ret = register_pernet_device(&pernet_ops); if (ret) goto error_vm; ret = rtnl_link_register(&link_ops); if (ret) goto error_pernet; return 0; error_pernet: unregister_pernet_device(&pernet_ops); error_vm: unregister_random_vmfork_notifier(&vm_notifier); error_pm: unregister_pm_notifier(&pm_notifier); return ret; } void wg_device_uninit(void) { rtnl_link_unregister(&link_ops); unregister_pernet_device(&pernet_ops); unregister_random_vmfork_notifier(&vm_notifier); unregister_pm_notifier(&pm_notifier); rcu_barrier(); } |
| 502 502 7 21 3 25 19 2 1 4 9 14 14 7 4 10 14 7 7 7 9 7 7 7 6 57 1 296 25 273 30 28 28 28 28 28 28 28 502 502 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 fragment reassembly for connection tracking * * Copyright (C)2004 USAGI/WIDE Project * * Author: * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * * Based on: net/ipv6/reassembly.c */ #define pr_fmt(fmt) "IPv6-nf: " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <net/ipv6_frag.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #include <linux/sysctl.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/kernel.h> #include <linux/module.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netns/generic.h> static const char nf_frags_cache_name[] = "nf-frags"; static unsigned int nf_frag_pernet_id __read_mostly; static struct inet_frags nf_frags; static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) { return net_generic(net, nf_frag_pernet_id); } #ifdef CONFIG_SYSCTL static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_frag6_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "nf_conntrack_frag6_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; static int nf_ct_frag6_sysctl_register(struct net *net) { struct nft_ct_frag6_pernet *nf_frag; struct ctl_table *table; struct ctl_table_header *hdr; table = nf_ct_frag6_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; } nf_frag = nf_frag_pernet(net); table[0].data = &nf_frag->fqdir->timeout; table[1].data = &nf_frag->fqdir->low_thresh; table[1].extra2 = &nf_frag->fqdir->high_thresh; table[2].data = &nf_frag->fqdir->high_thresh; table[2].extra1 = &nf_frag->fqdir->low_thresh; hdr = register_net_sysctl_sz(net, "net/netfilter", table, ARRAY_SIZE(nf_ct_frag6_sysctl_table)); if (hdr == NULL) goto err_reg; nf_frag->nf_frag_frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); const struct ctl_table *table; table = nf_frag->nf_frag_frags_hdr->ctl_table_arg; unregister_net_sysctl_table(nf_frag->nf_frag_frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { } #endif static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev); static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); } static void nf_ct_frag6_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; fq = container_of(frag, struct frag_queue, q); ip6frag_expire_frag_queue(fq->q.fqdir->net, fq); } /* Creation primitives. */ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, const struct ipv6hdr *hdr, int iif) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); struct frag_v6_compare_key key = { .id = id, .saddr = hdr->saddr, .daddr = hdr->daddr, .user = user, .iif = iif, }; struct inet_frag_queue *q; if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL))) key.iif = 0; q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; return container_of(q, struct frag_queue, q); } static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { unsigned int payload_len; struct net_device *dev; struct sk_buff *prev; int offset, end, err; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) { pr_debug("Already completed\n"); goto err; } payload_len = ntohs(ipv6_hdr(skb)->payload_len); offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (payload_len - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { pr_debug("offset is too large.\n"); return -EINVAL; } ecn = ip6_frag_ecn(ipv6_hdr(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) { const unsigned char *nh = skb_network_header(skb); skb->csum = csum_sub(skb->csum, csum_partial(nh, (u8 *)(fhdr + 1) - nh, 0)); } /* Is this the final fragment? */ if (!(fhdr->frag_off & htons(IP6_MF))) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { pr_debug("already received last fragment\n"); goto err; } fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. * Required by the RFC. */ if (end & 0x7) { /* RFC2460 says always send parameter problem in * this case. -DaveM */ pr_debug("end of fragment not rounded to 8 bytes.\n"); inet_frag_kill(&fq->q); return -EPROTO; } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) { pr_debug("last packet already reached.\n"); goto err; } fq->q.len = end; } } if (end == offset) goto err; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) { pr_debug("queue: message is too short.\n"); goto err; } if (pskb_trim_rcsum(skb, end - offset)) { pr_debug("Can't trim\n"); goto err; } /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); prev = fq->q.fragments_tail; err = inet_frag_queue_insert(&fq->q, skb, offset, end); if (err) { if (err == IPFRAG_DUP) { /* No error for duplicates, pretend they got queued. */ kfree_skb_reason(skb, SKB_DROP_REASON_DUP_FRAG); return -EINPROGRESS; } goto insert_error; } if (dev) fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.tstamp_type = skb->tstamp_type; fq->q.meat += skb->len; fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; add_frag_mem_limit(fq->q.fqdir, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. */ if (offset == 0) { fq->nhoffset = nhoff; fq->q.flags |= INET_FRAG_FIRST_IN; } if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; err = nf_ct_frag6_reasm(fq, skb, prev, dev); skb->_skb_refdst = orefdst; /* After queue has assumed skb ownership, only 0 or * -EINPROGRESS must be returned. */ return err ? -EINPROGRESS : 0; } skb_dst_drop(skb); skb_orphan(skb); return -EINPROGRESS; insert_error: inet_frag_kill(&fq->q); err: skb_dst_drop(skb); return -EINVAL; } /* * Check if this packet is complete. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) { void *reasm_data; int payload_len; u8 ecn; inet_frag_kill(&fq->q); ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) goto err; reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto err; payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); goto err; } /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; memmove(skb->head + sizeof(struct frag_hdr), skb->head, (skb->data - skb->head) - sizeof(struct frag_hdr)); skb->mac_header += sizeof(struct frag_hdr); skb->network_header += sizeof(struct frag_hdr); skb_reset_transport_header(skb); inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->ignore_df = 1; skb->dev = dev; ipv6_hdr(skb)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_partial(skb_network_header(skb), skb_network_header_len(skb), skb->csum); fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; return 0; err: inet_frag_kill(&fq->q); return -EINVAL; } /* * find the header just before Fragment Header. * * if success return 0 and set ... * (*prevhdrp): the value of "Next Header Field" in the header * just before Fragment Header. * (*prevhoff): the offset of "Next Header Field" in the header * just before Fragment Header. * (*fhoff) : the offset of Fragment Header. * * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c * */ static int find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) { u8 nexthdr = ipv6_hdr(skb)->nexthdr; const int netoff = skb_network_offset(skb); u8 prev_nhoff = netoff + offsetof(struct ipv6hdr, nexthdr); int start = netoff + sizeof(struct ipv6hdr); int len = skb->len - start; u8 prevhdr = NEXTHDR_IPV6; while (nexthdr != NEXTHDR_FRAGMENT) { struct ipv6_opt_hdr hdr; int hdrlen; if (!ipv6_ext_hdr(nexthdr)) { return -1; } if (nexthdr == NEXTHDR_NONE) { pr_debug("next header is none\n"); return -1; } if (len < (int)sizeof(struct ipv6_opt_hdr)) { pr_debug("too short\n"); return -1; } if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) BUG(); if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(&hdr); else hdrlen = ipv6_optlen(&hdr); prevhdr = nexthdr; prev_nhoff = start; nexthdr = hdr.nexthdr; len -= hdrlen; start += hdrlen; } if (len < 0) return -1; *prevhdrp = prevhdr; *prevhoff = prev_nhoff; *fhoff = start; return 0; } int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; u8 nexthdr = NEXTHDR_FRAGMENT; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; u8 prevhdr; /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) return 0; /* Discard the first fragment if it does not include all headers * RFC 8200, Section 4.5 */ if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { pr_debug("Drop incomplete fragment\n"); return 0; } if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; skb_set_transport_header(skb, fhoff); hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); return -ENOMEM; } spin_lock_bh(&fq->q.lock); ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); if (ret == -EPROTO) { skb->transport_header = savethdr; ret = 0; } spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q); return ret; } EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); static int nf_ct_net_init(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); int res; res = fqdir_init(&nf_frag->fqdir, &nf_frags, net); if (res < 0) return res; nf_frag->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; nf_frag->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; nf_frag->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = nf_ct_frag6_sysctl_register(net); if (res < 0) fqdir_exit(nf_frag->fqdir); return res; } static void nf_ct_net_pre_exit(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); fqdir_pre_exit(nf_frag->fqdir); } static void nf_ct_net_exit(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); nf_ct_frags6_sysctl_unregister(net); fqdir_exit(nf_frag->fqdir); } static struct pernet_operations nf_ct_net_ops = { .init = nf_ct_net_init, .pre_exit = nf_ct_net_pre_exit, .exit = nf_ct_net_exit, .id = &nf_frag_pernet_id, .size = sizeof(struct nft_ct_frag6_pernet), }; static const struct rhashtable_params nfct_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .hashfn = ip6frag_key_hashfn, .obj_hashfn = ip6frag_obj_hashfn, .obj_cmpfn = ip6frag_obj_cmpfn, .automatic_shrinking = true, }; int nf_ct_frag6_init(void) { int ret = 0; nf_frags.constructor = ip6frag_init; nf_frags.destructor = NULL; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.frags_cache_name = nf_frags_cache_name; nf_frags.rhash_params = nfct_rhash_params; ret = inet_frags_init(&nf_frags); if (ret) goto out; ret = register_pernet_subsys(&nf_ct_net_ops); if (ret) inet_frags_fini(&nf_frags); out: return ret; } void nf_ct_frag6_cleanup(void) { unregister_pernet_subsys(&nf_ct_net_ops); inet_frags_fini(&nf_frags); } |
| 270 6 41 73 265 296 73 73 296 296 296 296 1 36 36 36 36 72 28 31 14 73 40 40 37 1 5 6 43 1 1 1 2 35 43 1 2 2 38 1 3 2 8 26 34 31 1 2 1 29 2 1 50 6 1 1 2 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 2 2 8 6 1 1 83 83 6 39 15 20 3 3 3 5 15 3 1 2 2 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * binfmt_misc.c * * Copyright (C) 1997 Richard Günther * * binfmt_misc detects binaries via a magic or filename extension and invokes * a specified wrapper. See Documentation/admin-guide/binfmt-misc.rst for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/magic.h> #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/string_helpers.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/uaccess.h> #include "internal.h" #ifdef DEBUG # define USE_DEBUG 1 #else # define USE_DEBUG 0 #endif enum { VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */ }; enum {Enabled, Magic}; #define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) #define MISC_FMT_OPEN_BINARY (1UL << 30) #define MISC_FMT_CREDENTIALS (1UL << 29) #define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; unsigned long flags; /* type, status, etc. */ int offset; /* offset of magic */ int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; refcount_t users; /* sync removal with load_misc_binary() */ } Node; static struct file_system_type bm_fs_type; /* * Max length of the register string. Determined by: * - 7 delimiters * - name: ~50 bytes * - type: 1 byte * - offset: 3 bytes (has to be smaller than BINPRM_BUF_SIZE) * - magic: 128 bytes (512 in escaped form) * - mask: 128 bytes (512 in escaped form) * - interp: ~50 bytes * - flags: 5 bytes * Round that up a bit, and then back off to hold the internal data * (like struct Node). */ #define MAX_REGISTER_LENGTH 1920 /** * search_binfmt_handler - search for a binary handler for @bprm * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Search for a binary type handler for @bprm in the list of registered binary * type handlers. * * Return: binary type list entry on success, NULL on failure */ static Node *search_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { char *p = strrchr(bprm->interp, '.'); Node *e; /* Walk all the registered handlers. */ list_for_each_entry(e, &misc->entries, list) { char *s; int j; /* Make sure this one is currently enabled. */ if (!test_bit(Enabled, &e->flags)) continue; /* Do matching based on extension if applicable. */ if (!test_bit(Magic, &e->flags)) { if (p && !strcmp(e->magic, p + 1)) return e; continue; } /* Do matching based on magic & mask. */ s = bprm->buf + e->offset; if (e->mask) { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j]) & e->mask[j]) break; } else { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j])) break; } if (j == e->size) return e; } return NULL; } /** * get_binfmt_handler - try to find a binary type handler * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Try to find a binfmt handler for the binary type. If one is found take a * reference to protect against removal via bm_{entry,status}_write(). * * Return: binary type list entry on success, NULL on failure */ static Node *get_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { Node *e; read_lock(&misc->entries_lock); e = search_binfmt_handler(misc, bprm); if (e) refcount_inc(&e->users); read_unlock(&misc->entries_lock); return e; } /** * put_binfmt_handler - put binary handler node * @e: node to put * * Free node syncing with load_misc_binary() and defer final free to * load_misc_binary() in case it is using the binary type handler we were * requested to remove. */ static void put_binfmt_handler(Node *e) { if (refcount_dec_and_test(&e->users)) { if (e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); kfree(e); } } /** * load_binfmt_misc - load the binfmt_misc of the caller's user namespace * * To be called in load_misc_binary() to load the relevant struct binfmt_misc. * If a user namespace doesn't have its own binfmt_misc mount it can make use * of its ancestor's binfmt_misc handlers. This mimicks the behavior of * pre-namespaced binfmt_misc where all registered binfmt_misc handlers where * available to all user and user namespaces on the system. * * Return: the binfmt_misc instance of the caller's user namespace */ static struct binfmt_misc *load_binfmt_misc(void) { const struct user_namespace *user_ns; struct binfmt_misc *misc; user_ns = current_user_ns(); while (user_ns) { /* Pairs with smp_store_release() in bm_fill_super(). */ misc = smp_load_acquire(&user_ns->binfmt_misc); if (misc) return misc; user_ns = user_ns->parent; } return &init_binfmt_misc; } /* * the loader itself */ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; int retval = -ENOEXEC; struct binfmt_misc *misc; misc = load_binfmt_misc(); if (!misc->enabled) return retval; fmt = get_binfmt_handler(misc, bprm); if (!fmt) return retval; /* Need to be able to load the file after exec */ retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) goto ret; if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) { bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0; } else { retval = remove_arg_zero(bprm); if (retval) goto ret; } if (fmt->flags & MISC_FMT_OPEN_BINARY) bprm->have_execfd = 1; /* make argv[1] be the path to the binary */ retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) goto ret; bprm->argc++; /* add the interp as argv[0] */ retval = copy_string_kernel(fmt->interpreter, bprm); if (retval < 0) goto ret; bprm->argc++; /* Update interp in case binfmt_script needs it. */ retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto ret; if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) goto ret; bprm->interpreter = interp_file; if (fmt->flags & MISC_FMT_CREDENTIALS) bprm->execfd_creds = 1; retval = 0; ret: /* * If we actually put the node here all concurrent calls to * load_misc_binary() will have finished. We also know * that for the refcount to be zero someone must have concurently * removed the binary type handler from the list and it's our job to * free it. */ put_binfmt_handler(fmt); return retval; } /* Command parsers */ /* * parses and copies one argument enclosed in del from *sp to *dp, * recognising the \x special. * returns pointer to the copied argument or NULL in case of an * error (and sets err) or null argument length. */ static char *scanarg(char *s, char del) { char c; while ((c = *s++) != del) { if (c == '\\' && *s == 'x') { s++; if (!isxdigit(*s++)) return NULL; if (!isxdigit(*s++)) return NULL; } } s[-1] ='\0'; return s; } static char *check_special_flags(char *sfs, Node *e) { char *p = sfs; int cont = 1; /* special flags */ while (cont) { switch (*p) { case 'P': pr_debug("register: flag: P (preserve argv0)\n"); p++; e->flags |= MISC_FMT_PRESERVE_ARGV0; break; case 'O': pr_debug("register: flag: O (open binary)\n"); p++; e->flags |= MISC_FMT_OPEN_BINARY; break; case 'C': pr_debug("register: flag: C (preserve creds)\n"); p++; /* this flags also implies the open-binary flag */ e->flags |= (MISC_FMT_CREDENTIALS | MISC_FMT_OPEN_BINARY); break; case 'F': pr_debug("register: flag: F: open interpreter file now\n"); p++; e->flags |= MISC_FMT_OPEN_FILE; break; default: cont = 0; } } return p; } /* * This registers a new binary format, it recognises the syntax * ':name:type:offset:magic:mask:interpreter:flags' * where the ':' is the IFS, that can be chosen with the first char */ static Node *create_entry(const char __user *buffer, size_t count) { Node *e; int memsize, err; char *buf, *p; char del; pr_debug("register: received %zu bytes\n", count); /* some sanity checks */ err = -EINVAL; if ((count < 11) || (count > MAX_REGISTER_LENGTH)) goto out; err = -ENOMEM; memsize = sizeof(Node) + count + 8; e = kmalloc(memsize, GFP_KERNEL_ACCOUNT); if (!e) goto out; p = buf = (char *)e + sizeof(Node); memset(e, 0, sizeof(Node)); if (copy_from_user(buf, buffer, count)) goto efault; del = *p++; /* delimeter */ pr_debug("register: delim: %#x {%c}\n", del, del); /* Pad the buffer with the delim to simplify parsing below. */ memset(buf + count, del, 8); /* Parse the 'name' field. */ e->name = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->name[0] || !strcmp(e->name, ".") || !strcmp(e->name, "..") || strchr(e->name, '/')) goto einval; pr_debug("register: name: {%s}\n", e->name); /* Parse the 'type' field. */ switch (*p++) { case 'E': pr_debug("register: type: E (extension)\n"); e->flags = 1 << Enabled; break; case 'M': pr_debug("register: type: M (magic)\n"); e->flags = (1 << Enabled) | (1 << Magic); break; default: goto einval; } if (*p++ != del) goto einval; if (test_bit(Magic, &e->flags)) { /* Handle the 'M' (magic) format. */ char *s; /* Parse the 'offset' field. */ s = strchr(p, del); if (!s) goto einval; *s = '\0'; if (p != s) { int r = kstrtoint(p, 10, &e->offset); if (r != 0 || e->offset < 0) goto einval; } p = s; if (*p++) goto einval; pr_debug("register: offset: %#x\n", e->offset); /* Parse the 'magic' field. */ e->magic = p; p = scanarg(p, del); if (!p) goto einval; if (!e->magic[0]) goto einval; if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[raw]: ", DUMP_PREFIX_NONE, e->magic, p - e->magic); /* Parse the 'mask' field. */ e->mask = p; p = scanarg(p, del); if (!p) goto einval; if (!e->mask[0]) { e->mask = NULL; pr_debug("register: mask[raw]: none\n"); } else if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[raw]: ", DUMP_PREFIX_NONE, e->mask, p - e->mask); /* * Decode the magic & mask fields. * Note: while we might have accepted embedded NUL bytes from * above, the unescape helpers here will stop at the first one * it encounters. */ e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX); if (e->mask && string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto einval; if (e->size > BINPRM_BUF_SIZE || BINPRM_BUF_SIZE - e->size < e->offset) goto einval; pr_debug("register: magic/mask length: %i\n", e->size); if (USE_DEBUG) { print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[decoded]: ", DUMP_PREFIX_NONE, e->magic, e->size); if (e->mask) { int i; char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT); print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[decoded]: ", DUMP_PREFIX_NONE, e->mask, e->size); if (masked) { for (i = 0; i < e->size; ++i) masked[i] = e->magic[i] & e->mask[i]; print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[masked]: ", DUMP_PREFIX_NONE, masked, e->size); kfree(masked); } } } } else { /* Handle the 'E' (extension) format. */ /* Skip the 'offset' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; /* Parse the 'magic' field. */ e->magic = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->magic[0] || strchr(e->magic, '/')) goto einval; pr_debug("register: extension: {%s}\n", e->magic); /* Skip the 'mask' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; } /* Parse the 'interpreter' field. */ e->interpreter = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->interpreter[0]) goto einval; pr_debug("register: interpreter: {%s}\n", e->interpreter); /* Parse the 'flags' field. */ p = check_special_flags(p, e); if (*p == '\n') p++; if (p != buf + count) goto einval; return e; out: return ERR_PTR(err); efault: kfree(e); return ERR_PTR(-EFAULT); einval: kfree(e); return ERR_PTR(-EINVAL); } /* * Set status of entry/binfmt_misc: * '1' enables, '0' disables and '-1' clears entry/binfmt_misc */ static int parse_command(const char __user *buffer, size_t count) { char s[4]; if (count > 3) return -EINVAL; if (copy_from_user(s, buffer, count)) return -EFAULT; if (!count) return 0; if (s[count - 1] == '\n') count--; if (count == 1 && s[0] == '0') return 1; if (count == 1 && s[0] == '1') return 2; if (count == 2 && s[0] == '-' && s[1] == '1') return 3; return -EINVAL; } /* generic stuff */ static void entry_status(Node *e, char *page) { char *dp = page; const char *status = "disabled"; if (test_bit(Enabled, &e->flags)) status = "enabled"; if (!VERBOSE_STATUS) { sprintf(page, "%s\n", status); return; } dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter); /* print the special flags */ dp += sprintf(dp, "flags: "); if (e->flags & MISC_FMT_PRESERVE_ARGV0) *dp++ = 'P'; if (e->flags & MISC_FMT_OPEN_BINARY) *dp++ = 'O'; if (e->flags & MISC_FMT_CREDENTIALS) *dp++ = 'C'; if (e->flags & MISC_FMT_OPEN_FILE) *dp++ = 'F'; *dp++ = '\n'; if (!test_bit(Magic, &e->flags)) { sprintf(dp, "extension .%s\n", e->magic); } else { dp += sprintf(dp, "offset %i\nmagic ", e->offset); dp = bin2hex(dp, e->magic, e->size); if (e->mask) { dp += sprintf(dp, "\nmask "); dp = bin2hex(dp, e->mask, e->size); } *dp++ = '\n'; *dp = '\0'; } } static struct inode *bm_get_inode(struct super_block *sb, int mode) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; simple_inode_init_ts(inode); } return inode; } /** * i_binfmt_misc - retrieve struct binfmt_misc from a binfmt_misc inode * @inode: inode of the relevant binfmt_misc instance * * This helper retrieves struct binfmt_misc from a binfmt_misc inode. This can * be done without any memory barriers because we are guaranteed that * user_ns->binfmt_misc is fully initialized. It was fully initialized when the * binfmt_misc mount was first created. * * Return: struct binfmt_misc of the relevant binfmt_misc instance */ static struct binfmt_misc *i_binfmt_misc(struct inode *inode) { return inode->i_sb->s_user_ns->binfmt_misc; } /** * bm_evict_inode - cleanup data associated with @inode * @inode: inode to which the data is attached * * Cleanup the binary type handler data associated with @inode if a binary type * entry is removed or the filesystem is unmounted and the super block is * shutdown. * * If the ->evict call was not caused by a super block shutdown but by a write * to remove the entry or all entries via bm_{entry,status}_write() the entry * will have already been removed from the list. We keep the list_empty() check * to make that explicit. */ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; clear_inode(inode); if (e) { struct binfmt_misc *misc; misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); if (!list_empty(&e->list)) list_del_init(&e->list); write_unlock(&misc->entries_lock); put_binfmt_handler(e); } } /** * unlink_binfmt_dentry - remove the dentry for the binary type handler * @dentry: dentry associated with the binary type handler * * Do the actual filesystem work to remove a dentry for a registered binary * type handler. Since binfmt_misc only allows simple files to be created * directly under the root dentry of the filesystem we ensure that we are * indeed passed a dentry directly beneath the root dentry, that the inode * associated with the root dentry is locked, and that it is a regular file we * are asked to remove. */ static void unlink_binfmt_dentry(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; struct inode *inode, *parent_inode; /* All entries are immediate descendants of the root dentry. */ if (WARN_ON_ONCE(dentry->d_sb->s_root != parent)) return; /* We only expect to be called on regular files. */ inode = d_inode(dentry); if (WARN_ON_ONCE(!S_ISREG(inode->i_mode))) return; /* The parent inode must be locked. */ parent_inode = d_inode(parent); if (WARN_ON_ONCE(!inode_is_locked(parent_inode))) return; if (simple_positive(dentry)) { dget(dentry); simple_unlink(parent_inode, dentry); d_delete(dentry); dput(dentry); } } /** * remove_binfmt_handler - remove a binary type handler * @misc: handle to binfmt_misc instance * @e: binary type handler to remove * * Remove a binary type handler from the list of binary type handlers and * remove its associated dentry. This is called from * binfmt_{entry,status}_write(). In the future, we might want to think about * adding a proper ->unlink() method to binfmt_misc instead of forcing caller's * to use writes to files in order to delete binary type handlers. But it has * worked for so long that it's not a pressing issue. */ static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e) { write_lock(&misc->entries_lock); list_del_init(&e->list); write_unlock(&misc->entries_lock); unlink_binfmt_dentry(e->dentry); } /* /<entry> */ static ssize_t bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { Node *e = file_inode(file)->i_private; ssize_t res; char *page; page = (char *) __get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; entry_status(e, page); res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page)); free_page((unsigned long) page); return res; } static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); Node *e = inode->i_private; int res = parse_command(buffer, count); switch (res) { case 1: /* Disable this handler. */ clear_bit(Enabled, &e->flags); break; case 2: /* Enable this handler. */ set_bit(Enabled, &e->flags); break; case 3: /* Delete this handler. */ inode = d_inode(inode->i_sb->s_root); inode_lock(inode); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ if (!list_empty(&e->list)) remove_binfmt_handler(i_binfmt_misc(inode), e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_entry_operations = { .read = bm_entry_read, .write = bm_entry_write, .llseek = default_llseek, }; /* /register */ static ssize_t bm_register_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { Node *e; struct inode *inode; struct super_block *sb = file_inode(file)->i_sb; struct dentry *root = sb->s_root, *dentry; struct binfmt_misc *misc; int err = 0; struct file *f = NULL; e = create_entry(buffer, count); if (IS_ERR(e)) return PTR_ERR(e); if (e->flags & MISC_FMT_OPEN_FILE) { const struct cred *old_cred; /* * Now that we support unprivileged binfmt_misc mounts make * sure we use the credentials that the register @file was * opened with to also open the interpreter. Before that this * didn't matter much as only a privileged process could open * the register file. */ old_cred = override_creds(file->f_cred); f = open_exec(e->interpreter); revert_creds(old_cred); if (IS_ERR(f)) { pr_notice("register: failed to install interpreter file %s\n", e->interpreter); kfree(e); return PTR_ERR(f); } e->interp_file = f; } inode_lock(d_inode(root)); dentry = lookup_one_len(e->name, root, strlen(e->name)); err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out; err = -EEXIST; if (d_really_is_positive(dentry)) goto out2; inode = bm_get_inode(sb, S_IFREG | 0644); err = -ENOMEM; if (!inode) goto out2; refcount_set(&e->users, 1); e->dentry = dget(dentry); inode->i_private = e; inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); list_add(&e->list, &misc->entries); write_unlock(&misc->entries_lock); err = 0; out2: dput(dentry); out: inode_unlock(d_inode(root)); if (err) { if (f) filp_close(f, NULL); kfree(e); return err; } return count; } static const struct file_operations bm_register_operations = { .write = bm_register_write, .llseek = noop_llseek, }; /* /status */ static ssize_t bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { struct binfmt_misc *misc; char *s; misc = i_binfmt_misc(file_inode(file)); s = misc->enabled ? "enabled\n" : "disabled\n"; return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s)); } static ssize_t bm_status_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct binfmt_misc *misc; int res = parse_command(buffer, count); Node *e, *next; struct inode *inode; misc = i_binfmt_misc(file_inode(file)); switch (res) { case 1: /* Disable all handlers. */ misc->enabled = false; break; case 2: /* Enable all handlers. */ misc->enabled = true; break; case 3: /* Delete all handlers. */ inode = d_inode(file_inode(file)->i_sb->s_root); inode_lock(inode); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ list_for_each_entry_safe(e, next, &misc->entries, list) remove_binfmt_handler(misc, e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_status_operations = { .read = bm_status_read, .write = bm_status_write, .llseek = default_llseek, }; /* Superblock handling */ static void bm_put_super(struct super_block *sb) { struct user_namespace *user_ns = sb->s_fs_info; sb->s_fs_info = NULL; put_user_ns(user_ns); } static const struct super_operations s_ops = { .statfs = simple_statfs, .evict_inode = bm_evict_inode, .put_super = bm_put_super, }; static int bm_fill_super(struct super_block *sb, struct fs_context *fc) { int err; struct user_namespace *user_ns = sb->s_user_ns; struct binfmt_misc *misc; static const struct tree_descr bm_files[] = { [2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO}, [3] = {"register", &bm_register_operations, S_IWUSR}, /* last one */ {""} }; if (WARN_ON(user_ns != current_user_ns())) return -EINVAL; /* * Lazily allocate a new binfmt_misc instance for this namespace, i.e. * do it here during the first mount of binfmt_misc. We don't need to * waste memory for every user namespace allocation. It's likely much * more common to not mount a separate binfmt_misc instance than it is * to mount one. * * While multiple superblocks can exist they are keyed by userns in * s_fs_info for binfmt_misc. Hence, the vfs guarantees that * bm_fill_super() is called exactly once whenever a binfmt_misc * superblock for a userns is created. This in turn lets us conclude * that when a binfmt_misc superblock is created for the first time for * a userns there's no one racing us. Therefore we don't need any * barriers when we dereference binfmt_misc. */ misc = user_ns->binfmt_misc; if (!misc) { /* * If it turns out that most user namespaces actually want to * register their own binary type handler and therefore all * create their own separate binfmt_misc mounts we should * consider turning this into a kmem cache. */ misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); if (!misc) return -ENOMEM; INIT_LIST_HEAD(&misc->entries); rwlock_init(&misc->entries_lock); /* Pairs with smp_load_acquire() in load_binfmt_misc(). */ smp_store_release(&user_ns->binfmt_misc, misc); } /* * When the binfmt_misc superblock for this userns is shutdown * ->enabled might have been set to false and we don't reinitialize * ->enabled again in put_super() as someone might already be mounting * binfmt_misc again. It also would be pointless since by the time * ->put_super() is called we know that the binary type list for this * bintfmt_misc mount is empty making load_misc_binary() return * -ENOEXEC independent of whether ->enabled is true. Instead, if * someone mounts binfmt_misc for the first time or again we simply * reset ->enabled to true. */ misc->enabled = true; err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files); if (!err) sb->s_op = &s_ops; return err; } static void bm_free(struct fs_context *fc) { if (fc->s_fs_info) put_user_ns(fc->s_fs_info); } static int bm_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, bm_fill_super, get_user_ns(fc->user_ns)); } static const struct fs_context_operations bm_context_ops = { .free = bm_free, .get_tree = bm_get_tree, }; static int bm_init_fs_context(struct fs_context *fc) { fc->ops = &bm_context_ops; return 0; } static struct linux_binfmt misc_format = { .module = THIS_MODULE, .load_binary = load_misc_binary, }; static struct file_system_type bm_fs_type = { .owner = THIS_MODULE, .name = "binfmt_misc", .init_fs_context = bm_init_fs_context, .fs_flags = FS_USERNS_MOUNT, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("binfmt_misc"); static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); return err; } static void __exit exit_misc_binfmt(void) { unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } core_initcall(init_misc_binfmt); module_exit(exit_misc_binfmt); MODULE_DESCRIPTION("Kernel support for miscellaneous binaries"); MODULE_LICENSE("GPL"); |
| 112 121 1 1 117 2 2 5 112 112 112 112 112 112 76 76 32 32 8 2 3 3 1 6 1 5 5 5 2 2 1 4 15 16 4 12 12 13 9 1 1 1 2 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; 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 address family and sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/stringify.h> #include <linux/sched/signal.h> #include <asm/ioctls.h> #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> #include "leds.h" #include "selftest.h" /* Bluetooth sockets */ #define BT_MAX_PROTO (BTPROTO_LAST + 1) static const struct net_proto_family *bt_proto[BT_MAX_PROTO]; static DEFINE_RWLOCK(bt_proto_lock); static struct lock_class_key bt_lock_key[BT_MAX_PROTO]; static const char *const bt_key_strings[BT_MAX_PROTO] = { "sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP", "sk_lock-AF_BLUETOOTH-BTPROTO_HCI", "sk_lock-AF_BLUETOOTH-BTPROTO_SCO", "sk_lock-AF_BLUETOOTH-BTPROTO_RFCOMM", "sk_lock-AF_BLUETOOTH-BTPROTO_BNEP", "sk_lock-AF_BLUETOOTH-BTPROTO_CMTP", "sk_lock-AF_BLUETOOTH-BTPROTO_HIDP", "sk_lock-AF_BLUETOOTH-BTPROTO_AVDTP", "sk_lock-AF_BLUETOOTH-BTPROTO_ISO", }; static struct lock_class_key bt_slock_key[BT_MAX_PROTO]; static const char *const bt_slock_key_strings[BT_MAX_PROTO] = { "slock-AF_BLUETOOTH-BTPROTO_L2CAP", "slock-AF_BLUETOOTH-BTPROTO_HCI", "slock-AF_BLUETOOTH-BTPROTO_SCO", "slock-AF_BLUETOOTH-BTPROTO_RFCOMM", "slock-AF_BLUETOOTH-BTPROTO_BNEP", "slock-AF_BLUETOOTH-BTPROTO_CMTP", "slock-AF_BLUETOOTH-BTPROTO_HIDP", "slock-AF_BLUETOOTH-BTPROTO_AVDTP", "slock-AF_BLUETOOTH-BTPROTO_ISO", }; void bt_sock_reclassify_lock(struct sock *sk, int proto) { BUG_ON(!sk); BUG_ON(!sock_allow_reclassification(sk)); sock_lock_init_class_and_name(sk, bt_slock_key_strings[proto], &bt_slock_key[proto], bt_key_strings[proto], &bt_lock_key[proto]); } EXPORT_SYMBOL(bt_sock_reclassify_lock); int bt_sock_register(int proto, const struct net_proto_family *ops) { int err = 0; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; write_lock(&bt_proto_lock); if (bt_proto[proto]) err = -EEXIST; else bt_proto[proto] = ops; write_unlock(&bt_proto_lock); return err; } EXPORT_SYMBOL(bt_sock_register); void bt_sock_unregister(int proto) { if (proto < 0 || proto >= BT_MAX_PROTO) return; write_lock(&bt_proto_lock); bt_proto[proto] = NULL; write_unlock(&bt_proto_lock); } EXPORT_SYMBOL(bt_sock_unregister); static int bt_sock_create(struct net *net, struct socket *sock, int proto, int kern) { int err; if (net != &init_net) return -EAFNOSUPPORT; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; if (!bt_proto[proto]) request_module("bt-proto-%d", proto); err = -EPROTONOSUPPORT; read_lock(&bt_proto_lock); if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { err = bt_proto[proto]->create(net, sock, proto, kern); if (!err) bt_sock_reclassify_lock(sock->sk, proto); module_put(bt_proto[proto]->owner); } read_unlock(&bt_proto_lock); return err; } struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern) { struct sock *sk; sk = sk_alloc(net, PF_BLUETOOTH, prio, prot, kern); if (!sk) return NULL; sock_init_data(sock, sk); INIT_LIST_HEAD(&bt_sk(sk)->accept_q); sock_reset_flag(sk, SOCK_ZAPPED); sk->sk_protocol = proto; sk->sk_state = BT_OPEN; /* Init peer information so it can be properly monitored */ if (!kern) { spin_lock(&sk->sk_peer_lock); sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); spin_unlock(&sk->sk_peer_lock); } return sk; } EXPORT_SYMBOL(bt_sock_alloc); void bt_sock_link(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_add_node(sk, &l->head); write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_link); void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_del_node_init(sk); write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_unlink); bool bt_sock_linked(struct bt_sock_list *l, struct sock *s) { struct sock *sk; if (!l || !s) return false; read_lock(&l->lock); sk_for_each(sk, &l->head) { if (s == sk) { read_unlock(&l->lock); return true; } } read_unlock(&l->lock); return false; } EXPORT_SYMBOL(bt_sock_linked); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { const struct cred *old_cred; struct pid *old_pid; BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); if (bh) bh_lock_sock_nested(sk); else lock_sock_nested(sk, SINGLE_DEPTH_NESTING); list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; /* Copy credentials from parent since for incoming connections the * socket is allocated by the kernel. */ spin_lock(&sk->sk_peer_lock); old_pid = sk->sk_peer_pid; old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(parent->sk_peer_pid); sk->sk_peer_cred = get_cred(parent->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); put_pid(old_pid); put_cred(old_cred); if (bh) bh_unlock_sock(sk); else release_sock(sk); sk_acceptq_added(parent); } EXPORT_SYMBOL(bt_accept_enqueue); /* Calling function must hold the sk lock. * bt_sk(sk)->parent must be non-NULL meaning sk is in the parent list. */ void bt_accept_unlink(struct sock *sk) { BT_DBG("sk %p state %d", sk, sk->sk_state); list_del_init(&bt_sk(sk)->accept_q); sk_acceptq_removed(bt_sk(sk)->parent); bt_sk(sk)->parent = NULL; sock_put(sk); } EXPORT_SYMBOL(bt_accept_unlink); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) { struct bt_sock *s, *n; struct sock *sk; BT_DBG("parent %p", parent); restart: list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; /* Prevent early freeing of sk due to unlink and sock_kill */ sock_hold(sk); lock_sock(sk); /* Check sk has not already been unlinked via * bt_accept_unlink() due to serialisation caused by sk locking */ if (!bt_sk(sk)->parent) { BT_DBG("sk %p, already unlinked", sk); release_sock(sk); sock_put(sk); /* Restart the loop as sk is no longer in the list * and also avoid a potential infinite loop because * list_for_each_entry_safe() is not thread safe. */ goto restart; } /* sk is safely in the parent list so reduce reference count */ sock_put(sk); /* FIXME: Is this check still needed */ if (sk->sk_state == BT_CLOSED) { bt_accept_unlink(sk); release_sock(sk); continue; } if (sk->sk_state == BT_CONNECTED || !newsock || test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) { bt_accept_unlink(sk); if (newsock) sock_graft(sk, newsock); release_sock(sk); return sk; } release_sock(sk); } return NULL; } EXPORT_SYMBOL(bt_accept_dequeue); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; size_t copied; size_t skblen; int err; BT_DBG("sock %p sk %p len %zu", sock, sk, len); if (flags & MSG_OOB) return -EOPNOTSUPP; skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; return err; } skblen = skb->len; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err == 0) { sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name && bt_sk(sk)->skb_msg_name) bt_sk(sk)->skb_msg_name(skb, msg->msg_name, &msg->msg_namelen); if (test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags)) { u8 pkt_status = hci_skb_pkt_status(skb); put_cmsg(msg, SOL_BLUETOOTH, BT_SCM_PKT_STATUS, sizeof(pkt_status), &pkt_status); } } skb_free_datagram(sk, skb); if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; } EXPORT_SYMBOL(bt_sock_recvmsg); static long bt_sock_data_wait(struct sock *sk, long timeo) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(sk_sleep(sk), &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (!skb_queue_empty(&sk->sk_receive_queue)) break; if (sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN)) break; if (signal_pending(current) || !timeo) break; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return timeo; } int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int err = 0; size_t target, copied = 0; long timeo; if (flags & MSG_OOB) return -EOPNOTSUPP; BT_DBG("sk %p size %zu", sk, size); lock_sock(sk); target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb; int chunk; skb = skb_dequeue(&sk->sk_receive_queue); if (!skb) { if (copied >= target) break; err = sock_error(sk); if (err) break; if (sk->sk_shutdown & RCV_SHUTDOWN) break; err = -EAGAIN; if (!timeo) break; timeo = bt_sock_data_wait(sk, timeo); if (signal_pending(current)) { err = sock_intr_errno(timeo); goto out; } continue; } chunk = min_t(unsigned int, skb->len, size); if (skb_copy_datagram_msg(skb, 0, msg, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); if (!copied) copied = -EFAULT; break; } copied += chunk; size -= chunk; sock_recv_cmsgs(msg, sk, skb); if (!(flags & MSG_PEEK)) { int skb_len = skb_headlen(skb); if (chunk <= skb_len) { __skb_pull(skb, chunk); } else { struct sk_buff *frag; __skb_pull(skb, skb_len); chunk -= skb_len; skb_walk_frags(skb, frag) { if (chunk <= frag->len) { /* Pulling partial data */ skb->len -= chunk; skb->data_len -= chunk; __skb_pull(frag, chunk); break; } else if (frag->len) { /* Pulling all frag data */ chunk -= frag->len; skb->len -= frag->len; skb->data_len -= frag->len; __skb_pull(frag, frag->len); } } } if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); break; } kfree_skb(skb); } else { /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); break; } } while (size); out: release_sock(sk); return copied ? : err; } EXPORT_SYMBOL(bt_sock_stream_recvmsg); static inline __poll_t bt_accept_poll(struct sock *parent) { struct bt_sock *s, *n; struct sock *sk; list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; if (sk->sk_state == BT_CONNECTED || (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && sk->sk_state == BT_CONNECT2)) return EPOLLIN | EPOLLRDNORM; } return 0; } __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask = 0; poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) mask |= EPOLLHUP; if (sk->sk_state == BT_CONNECT || sk->sk_state == BT_CONNECT2 || sk->sk_state == BT_CONFIG) return mask; if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } EXPORT_SYMBOL(bt_sock_poll); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; struct sk_buff *skb; long amount; int err; BT_DBG("sk %p cmd %x arg %lx", sk, cmd, arg); switch (cmd) { case TIOCOUTQ: if (sk->sk_state == BT_LISTEN) return -EINVAL; amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; err = put_user(amount, (int __user *)arg); break; case TIOCINQ: if (sk->sk_state == BT_LISTEN) return -EINVAL; spin_lock(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; spin_unlock(&sk->sk_receive_queue.lock); err = put_user(amount, (int __user *)arg); break; default: err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(bt_sock_ioctl); /* This function expects the sk lock to be held when called */ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) { DECLARE_WAITQUEUE(wait, current); int err = 0; BT_DBG("sk %p", sk); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (sk->sk_state != state) { if (!timeo) { err = -EINPROGRESS; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_state); /* This function expects the sk lock to be held when called */ int bt_sock_wait_ready(struct sock *sk, unsigned int msg_flags) { DECLARE_WAITQUEUE(wait, current); unsigned long timeo; int err = 0; BT_DBG("sk %p", sk); timeo = sock_sndtimeo(sk, !!(msg_flags & MSG_DONTWAIT)); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags)) { if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_ready); #ifdef CONFIG_PROC_FS static void *bt_seq_start(struct seq_file *seq, loff_t *pos) __acquires(seq->private->l->lock) { struct bt_sock_list *l = pde_data(file_inode(seq->file)); read_lock(&l->lock); return seq_hlist_start_head(&l->head, *pos); } static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bt_sock_list *l = pde_data(file_inode(seq->file)); return seq_hlist_next(v, &l->head, pos); } static void bt_seq_stop(struct seq_file *seq, void *v) __releases(seq->private->l->lock) { struct bt_sock_list *l = pde_data(file_inode(seq->file)); read_unlock(&l->lock); } static int bt_seq_show(struct seq_file *seq, void *v) { struct bt_sock_list *l = pde_data(file_inode(seq->file)); if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk RefCnt Rmem Wmem User Inode Parent"); if (l->custom_seq_show) { seq_putc(seq, ' '); l->custom_seq_show(seq, v); } seq_putc(seq, '\n'); } else { struct sock *sk = sk_entry(v); struct bt_sock *bt = bt_sk(sk); seq_printf(seq, "%pK %-6d %-6u %-6u %-6u %-6lu %-6lu", sk, refcount_read(&sk->sk_refcnt), sk_rmem_alloc_get(sk), sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), bt->parent ? sock_i_ino(bt->parent) : 0LU); if (l->custom_seq_show) { seq_putc(seq, ' '); l->custom_seq_show(seq, v); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations bt_seq_ops = { .start = bt_seq_start, .next = bt_seq_next, .stop = bt_seq_stop, .show = bt_seq_show, }; int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (*seq_show)(struct seq_file *, void *)) { sk_list->custom_seq_show = seq_show; if (!proc_create_seq_data(name, 0, net->proc_net, &bt_seq_ops, sk_list)) return -ENOMEM; return 0; } void bt_procfs_cleanup(struct net *net, const char *name) { remove_proc_entry(name, net->proc_net); } #else int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (*seq_show)(struct seq_file *, void *)) { return 0; } void bt_procfs_cleanup(struct net *net, const char *name) { } #endif EXPORT_SYMBOL(bt_procfs_init); EXPORT_SYMBOL(bt_procfs_cleanup); static const struct net_proto_family bt_sock_family_ops = { .owner = THIS_MODULE, .family = PF_BLUETOOTH, .create = bt_sock_create, }; struct dentry *bt_debugfs; EXPORT_SYMBOL_GPL(bt_debugfs); #define VERSION __stringify(BT_SUBSYS_VERSION) "." \ __stringify(BT_SUBSYS_REVISION) static int __init bt_init(void) { int err; sock_skb_cb_check_size(sizeof(struct bt_skb_cb)); BT_INFO("Core ver %s", VERSION); err = bt_selftest(); if (err < 0) return err; bt_debugfs = debugfs_create_dir("bluetooth", NULL); bt_leds_init(); err = bt_sysfs_init(); if (err < 0) goto cleanup_led; err = sock_register(&bt_sock_family_ops); if (err) goto cleanup_sysfs; BT_INFO("HCI device and connection manager initialized"); err = hci_sock_init(); if (err) goto unregister_socket; err = l2cap_init(); if (err) goto cleanup_socket; err = sco_init(); if (err) goto cleanup_cap; err = mgmt_init(); if (err) goto cleanup_sco; return 0; cleanup_sco: sco_exit(); cleanup_cap: l2cap_exit(); cleanup_socket: hci_sock_cleanup(); unregister_socket: sock_unregister(PF_BLUETOOTH); cleanup_sysfs: bt_sysfs_cleanup(); cleanup_led: bt_leds_cleanup(); debugfs_remove_recursive(bt_debugfs); return err; } static void __exit bt_exit(void) { iso_exit(); mgmt_exit(); sco_exit(); l2cap_exit(); hci_sock_cleanup(); sock_unregister(PF_BLUETOOTH); bt_sysfs_cleanup(); bt_leds_cleanup(); debugfs_remove_recursive(bt_debugfs); } subsys_initcall(bt_init); module_exit(bt_exit); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth Core ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_BLUETOOTH); |
| 19 19 6 6 58 40 52 17 17 1 1 7 6 1 6 7 15 8 8 1 3 3 4 14 8 6 5 1 6 15 15 14 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * The HSR spec says never to forward the same frame twice on the same * interface. A frame is identified by its source MAC address and its HSR * sequence number. This code keeps track of senders and their sequence numbers * to allow filtering of duplicate frames, and to detect HSR ring errors. * Same code handles filtering of duplicates for PRP as well. */ #include <linux/if_ether.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/rculist.h> #include "hsr_main.h" #include "hsr_framereg.h" #include "hsr_netlink.h" /* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b, * false otherwise. */ static bool seq_nr_after(u16 a, u16 b) { /* Remove inconsistency where * seq_nr_after(a, b) == seq_nr_before(a, b) */ if ((int)b - a == 32768) return false; return (((s16)(b - a)) < 0); } #define seq_nr_before(a, b) seq_nr_after((b), (a)) #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr) { if (!hsr->redbox || !is_valid_ether_addr(hsr->macaddress_redbox)) return false; return ether_addr_equal(addr, hsr->macaddress_redbox); } bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { struct hsr_self_node *sn; bool ret = false; rcu_read_lock(); sn = rcu_dereference(hsr->self_node); if (!sn) { WARN_ONCE(1, "HSR: No self node\n"); goto out; } if (ether_addr_equal(addr, sn->macaddress_A) || ether_addr_equal(addr, sn->macaddress_B)) ret = true; out: rcu_read_unlock(); return ret; } /* Search for mac entry. Caller must hold rcu read lock. */ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, const unsigned char addr[ETH_ALEN]) { struct hsr_node *node; list_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, addr)) return node; } return NULL; } /* Check if node for a given MAC address is already present in data base */ bool hsr_is_node_in_db(struct list_head *node_db, const unsigned char addr[ETH_ALEN]) { return !!find_node_by_addr_A(node_db, addr); } /* Helper for device init; the self_node is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ int hsr_create_self_node(struct hsr_priv *hsr, const unsigned char addr_a[ETH_ALEN], const unsigned char addr_b[ETH_ALEN]) { struct hsr_self_node *sn, *old; sn = kmalloc(sizeof(*sn), GFP_KERNEL); if (!sn) return -ENOMEM; ether_addr_copy(sn->macaddress_A, addr_a); ether_addr_copy(sn->macaddress_B, addr_b); spin_lock_bh(&hsr->list_lock); old = rcu_replace_pointer(hsr->self_node, sn, lockdep_is_held(&hsr->list_lock)); spin_unlock_bh(&hsr->list_lock); if (old) kfree_rcu(old, rcu_head); return 0; } void hsr_del_self_node(struct hsr_priv *hsr) { struct hsr_self_node *old; spin_lock_bh(&hsr->list_lock); old = rcu_replace_pointer(hsr->self_node, NULL, lockdep_is_held(&hsr->list_lock)); spin_unlock_bh(&hsr->list_lock); if (old) kfree_rcu(old, rcu_head); } void hsr_del_nodes(struct list_head *node_db) { struct hsr_node *node; struct hsr_node *tmp; list_for_each_entry_safe(node, tmp, node_db, mac_list) kfree(node); } void prp_handle_san_frame(bool san, enum hsr_port_type port, struct hsr_node *node) { /* Mark if the SAN node is over LAN_A or LAN_B */ if (port == HSR_PT_SLAVE_A) { node->san_a = true; return; } if (port == HSR_PT_SLAVE_B) node->san_b = true; } /* Allocate an hsr_node and add it to node_db. 'addr' is the node's address_A; * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. */ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, struct list_head *node_db, unsigned char addr[], u16 seq_out, bool san, enum hsr_port_type rx_port) { struct hsr_node *new_node, *node; unsigned long now; int i; new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); if (!new_node) return NULL; ether_addr_copy(new_node->macaddress_A, addr); spin_lock_init(&new_node->seq_out_lock); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; for (i = 0; i < HSR_PT_PORTS; i++) { new_node->time_in[i] = now; new_node->time_out[i] = now; } for (i = 0; i < HSR_PT_PORTS; i++) new_node->seq_out[i] = seq_out; if (san && hsr->proto_ops->handle_san_frame) hsr->proto_ops->handle_san_frame(san, rx_port, new_node); spin_lock_bh(&hsr->list_lock); list_for_each_entry_rcu(node, node_db, mac_list, lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) goto out; } list_add_tail_rcu(&new_node->mac_list, node_db); spin_unlock_bh(&hsr->list_lock); return new_node; out: spin_unlock_bh(&hsr->list_lock); kfree(new_node); return node; } void prp_update_san_info(struct hsr_node *node, bool is_sup) { if (!is_sup) return; node->san_a = false; node->san_b = false; } /* Get the hsr_node from which 'skb' was sent. */ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, struct sk_buff *skb, bool is_sup, enum hsr_port_type rx_port) { struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; struct prp_rct *rct; bool san = false; u16 seq_out; if (!skb_mac_header_was_set(skb)) return NULL; ethhdr = (struct ethhdr *)skb_mac_header(skb); list_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); return node; } if (ether_addr_equal(node->macaddress_B, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); return node; } } /* Check if required node is not in proxy nodes table */ list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); return node; } } /* Everyone may create a node entry, connected node to a HSR/PRP * device. */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { /* Check if skb contains hsr_ethhdr */ if (skb->mac_len < sizeof(struct hsr_ethhdr)) return NULL; /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ seq_out = hsr_get_skb_sequence_nr(skb) - 1; } else { rct = skb_get_PRP_rct(skb); if (rct && prp_check_lsdu_size(skb, rct, is_sup)) { seq_out = prp_get_skb_sequence_nr(rct); } else { if (rx_port != HSR_PT_MASTER) san = true; seq_out = HSR_SEQNR_START; } } return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out, san, rx_port); } /* Use the Supervision frame's info about an eventual macaddress_B for merging * nodes that has previously had their macaddress_B registered as a separate * node. */ void hsr_handle_sup_frame(struct hsr_frame_info *frame) { struct hsr_node *node_curr = frame->node_src; struct hsr_port *port_rcv = frame->port_rcv; struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_sup_tlv; struct hsr_node *node_real; struct sk_buff *skb = NULL; struct list_head *node_db; struct ethhdr *ethhdr; int i; unsigned int pull_size = 0; unsigned int total_pull_size = 0; /* Here either frame->skb_hsr or frame->skb_prp should be * valid as supervision frame always will have protocol * header info. */ if (frame->skb_hsr) skb = frame->skb_hsr; else if (frame->skb_prp) skb = frame->skb_prp; else if (frame->skb_std) skb = frame->skb_std; if (!skb) return; /* Leave the ethernet header. */ pull_size = sizeof(struct ethhdr); skb_pull(skb, pull_size); total_pull_size += pull_size; ethhdr = (struct ethhdr *)skb_mac_header(skb); /* And leave the HSR tag. */ if (ethhdr->h_proto == htons(ETH_P_HSR)) { pull_size = sizeof(struct hsr_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; } /* And leave the HSR sup tag. */ pull_size = sizeof(struct hsr_sup_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; /* get HSR sup payload */ hsr_sp = (struct hsr_sup_payload *)skb->data; /* Merge node_curr (registered on macaddress_B) into node_real */ node_db = &port_rcv->hsr->node_db; node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, HSR_SEQNR_START - 1, true, port_rcv->type); if (!node_real) goto done; /* No mem */ if (node_real == node_curr) /* Node has already been merged */ goto done; /* Leave the first HSR sup payload. */ pull_size = sizeof(struct hsr_sup_payload); skb_pull(skb, pull_size); total_pull_size += pull_size; /* Get second supervision tlv */ hsr_sup_tlv = (struct hsr_sup_tlv *)skb->data; /* And check if it is a redbox mac TLV */ if (hsr_sup_tlv->HSR_TLV_type == PRP_TLV_REDBOX_MAC) { /* We could stop here after pushing hsr_sup_payload, * or proceed and allow macaddress_B and for redboxes. */ /* Sanity check length */ if (hsr_sup_tlv->HSR_TLV_length != 6) goto done; /* Leave the second HSR sup tlv. */ pull_size = sizeof(struct hsr_sup_tlv); skb_pull(skb, pull_size); total_pull_size += pull_size; /* Get redbox mac address. */ hsr_sp = (struct hsr_sup_payload *)skb->data; /* Check if redbox mac and node mac are equal. */ if (!ether_addr_equal(node_real->macaddress_A, hsr_sp->macaddress_A)) { /* This is a redbox supervision frame for a VDAN! */ goto done; } } ether_addr_copy(node_real->macaddress_B, ethhdr->h_source); spin_lock_bh(&node_real->seq_out_lock); for (i = 0; i < HSR_PT_PORTS; i++) { if (!node_curr->time_in_stale[i] && time_after(node_curr->time_in[i], node_real->time_in[i])) { node_real->time_in[i] = node_curr->time_in[i]; node_real->time_in_stale[i] = node_curr->time_in_stale[i]; } if (seq_nr_after(node_curr->seq_out[i], node_real->seq_out[i])) node_real->seq_out[i] = node_curr->seq_out[i]; } spin_unlock_bh(&node_real->seq_out_lock); node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); if (!node_curr->removed) { list_del_rcu(&node_curr->mac_list); node_curr->removed = true; kfree_rcu(node_curr, rcu_head); } spin_unlock_bh(&hsr->list_lock); done: /* Push back here */ skb_push(skb, total_pull_size); } /* 'skb' is a frame meant for this host, that is to be passed to upper layers. * * If the frame was sent by a node's B interface, replace the source * address with that node's "official" address (macaddress_A) so that upper * layers recognize where it came from. */ void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); return; } memcpy(ð_hdr(skb)->h_source, node->macaddress_A, ETH_ALEN); } /* 'skb' is a frame meant for another host. * 'port' is the outgoing interface * * Substitute the target (dest) MAC address if necessary, so the it matches the * recipient interface MAC address, regardless of whether that is the * recipient's A or B interface. * This is needed to keep the packets flowing through switches that learn on * which "side" the different interfaces are. */ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, struct hsr_port *port) { struct hsr_node *node_dst; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); return; } if (!is_unicast_ether_addr(eth_hdr(skb)->h_dest)) return; node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst && port->hsr->redbox) node_dst = find_node_by_addr_A(&port->hsr->proxy_node_db, eth_hdr(skb)->h_dest); if (!node_dst) { if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } if (port->type != node_dst->addr_B_port) return; if (is_valid_ether_addr(node_dst->macaddress_B)) ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B); } void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, u16 sequence_nr) { /* Don't register incoming frames without a valid sequence number. This * ensures entries of restarted nodes gets pruned so that they can * re-register and resume communications. */ if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && seq_nr_before(sequence_nr, node->seq_out[port->type])) return; node->time_in[port->type] = jiffies; node->time_in_stale[port->type] = false; } /* 'skb' is a HSR Ethernet frame (with a HSR tag inserted), with a valid * ethhdr->h_source address and skb->mac_header set. * * Return: * 1 if frame can be shown to have been sent recently on this interface, * 0 otherwise, or * negative error code on error */ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr) { spin_lock_bh(&node->seq_out_lock); if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) && time_is_after_jiffies(node->time_out[port->type] + msecs_to_jiffies(HSR_ENTRY_FORGET_TIME))) { spin_unlock_bh(&node->seq_out_lock); return 1; } node->time_out[port->type] = jiffies; node->seq_out[port->type] = sequence_nr; spin_unlock_bh(&node->seq_out_lock); return 0; } static struct hsr_port *get_late_port(struct hsr_priv *hsr, struct hsr_node *node) { if (node->time_in_stale[HSR_PT_SLAVE_A]) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (node->time_in_stale[HSR_PT_SLAVE_B]) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (time_after(node->time_in[HSR_PT_SLAVE_B], node->time_in[HSR_PT_SLAVE_A] + msecs_to_jiffies(MAX_SLAVE_DIFF))) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (time_after(node->time_in[HSR_PT_SLAVE_A], node->time_in[HSR_PT_SLAVE_B] + msecs_to_jiffies(MAX_SLAVE_DIFF))) return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); return NULL; } /* Remove stale sequence_nr records. Called by timer every * HSR_LIFE_CHECK_INTERVAL (two seconds or so). */ void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; spin_lock_bh(&hsr->list_lock); list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] * nor time_in[HSR_PT_SLAVE_B], will ever be updated for * the master port. Thus the master node will be repeatedly * pruned leading to packet loss. */ if (hsr_addr_is_self(hsr, node->macaddress_A)) continue; /* Shorthand */ time_a = node->time_in[HSR_PT_SLAVE_A]; time_b = node->time_in[HSR_PT_SLAVE_B]; /* Check for timestamps old enough to risk wrap-around */ if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2)) node->time_in_stale[HSR_PT_SLAVE_A] = true; if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2)) node->time_in_stale[HSR_PT_SLAVE_B] = true; /* Get age of newest frame from node. * At least one time_in is OK here; nodes get pruned long * before both time_ins can get stale */ timestamp = time_a; if (node->time_in_stale[HSR_PT_SLAVE_A] || (!node->time_in_stale[HSR_PT_SLAVE_B] && time_after(time_b, time_a))) timestamp = time_b; /* Warn of ring error only as long as we get frames at all */ if (time_is_after_jiffies(timestamp + msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) { rcu_read_lock(); port = get_late_port(hsr, node); if (port) hsr_nl_ringerror(hsr, node->macaddress_A, port); rcu_read_unlock(); } /* Prune old entries */ if (time_is_before_jiffies(timestamp + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { hsr_nl_nodedown(hsr, node->macaddress_A); if (!node->removed) { list_del_rcu(&node->mac_list); node->removed = true; /* Note that we need to free this entry later: */ kfree_rcu(node, rcu_head); } } } spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); } void hsr_prune_proxy_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_proxy_timer); unsigned long timestamp; struct hsr_node *node; struct hsr_node *tmp; spin_lock_bh(&hsr->list_lock); list_for_each_entry_safe(node, tmp, &hsr->proxy_node_db, mac_list) { /* Don't prune RedBox node. */ if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; timestamp = node->time_in[HSR_PT_INTERLINK]; /* Prune old entries */ if (time_is_before_jiffies(timestamp + msecs_to_jiffies(HSR_PROXY_NODE_FORGET_TIME))) { hsr_nl_nodedown(hsr, node->macaddress_A); if (!node->removed) { list_del_rcu(&node->mac_list); node->removed = true; /* Note that we need to free this entry later: */ kfree_rcu(node, rcu_head); } } } spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { struct hsr_node *node; if (!_pos) { node = list_first_or_null_rcu(&hsr->node_db, struct hsr_node, mac_list); if (node) ether_addr_copy(addr, node->macaddress_A); return node; } node = _pos; list_for_each_entry_continue_rcu(node, &hsr->node_db, mac_list) { ether_addr_copy(addr, node->macaddress_A); return node; } return NULL; } int hsr_get_node_data(struct hsr_priv *hsr, const unsigned char *addr, unsigned char addr_b[ETH_ALEN], unsigned int *addr_b_ifindex, int *if1_age, u16 *if1_seq, int *if2_age, u16 *if2_seq) { struct hsr_node *node; struct hsr_port *port; unsigned long tdiff; node = find_node_by_addr_A(&hsr->node_db, addr); if (!node) return -ENOENT; ether_addr_copy(addr_b, node->macaddress_B); tdiff = jiffies - node->time_in[HSR_PT_SLAVE_A]; if (node->time_in_stale[HSR_PT_SLAVE_A]) *if1_age = INT_MAX; #if HZ <= MSEC_PER_SEC else if (tdiff > msecs_to_jiffies(INT_MAX)) *if1_age = INT_MAX; #endif else *if1_age = jiffies_to_msecs(tdiff); tdiff = jiffies - node->time_in[HSR_PT_SLAVE_B]; if (node->time_in_stale[HSR_PT_SLAVE_B]) *if2_age = INT_MAX; #if HZ <= MSEC_PER_SEC else if (tdiff > msecs_to_jiffies(INT_MAX)) *if2_age = INT_MAX; #endif else *if2_age = jiffies_to_msecs(tdiff); /* Present sequence numbers as if they were incoming on interface */ *if1_seq = node->seq_out[HSR_PT_SLAVE_B]; *if2_seq = node->seq_out[HSR_PT_SLAVE_A]; if (node->addr_B_port != HSR_PT_NONE) { port = hsr_port_get_hsr(hsr, node->addr_B_port); *addr_b_ifindex = port->dev->ifindex; } else { *addr_b_ifindex = -1; } return 0; } |
| 832 834 829 834 2 78 167 76 439 603 2121 553 1153 99 72 389 174 175 20 6 20 459 459 255 304 80 224 224 35 202 224 247 246 235 235 20 20 479 759 45 832 367 465 35 432 63 55 1 7 1384 8 329 330 8 330 330 330 55 1868 1096 1848 55 1742 190 1845 1848 47 1800 13 1093 1051 1866 329 330 2 2180 455 2180 2184 1 1 1 94 243 1689 76 2270 26 2 3 1035 979 61 826 628 2185 3 238 4 4 2400 2398 2401 4 67 215 213 2 148 2128 2184 2184 2140 1803 1692 2117 1152 62 62 1000 2119 2211 3 4 38 38 32 7 4 1 3 100 55 530 777 627 611 573 661 100 378 485 299 100 100 6 57 36 1230 564 948 2 1210 33 56 67 67 67 1243 1039 1244 190 19 50 1209 947 261 1033 2133 1661 78 2135 2117 101 217 192 217 32 215 217 217 217 758 434 329 142 217 328 1712 1570 141 1714 483 483 833 20 28 7 721 79 885 64 9 780 2 308 46 45 44 47 46 885 580 92 952 15 998 1008 445 559 1008 1001 442 561 1005 444 562 12 1008 590 241 341 29 30 417 415 559 563 141 141 91 91 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/memfd.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/secretmem.h> #include <linux/sched/signal.h> #include <linux/rwsem.h> #include <linux/hugetlb.h> #include <linux/migrate.h> #include <linux/mm_inline.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include "internal.h" struct follow_page_context { struct dev_pagemap *pgmap; unsigned int page_mask; }; static inline void sanity_check_pinned_pages(struct page **pages, unsigned long npages) { if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; /* * We only pin anonymous pages if they are exclusive. Once pinned, we * can no longer turn them possibly shared and PageAnonExclusive() will * stick around until the page is freed. * * We'd like to verify that our pinned anonymous pages are still mapped * exclusively. The issue with anon THP is that we don't know how * they are/were mapped when pinning them. However, for anon * THP we can assume that either the given page (PTE-mapped THP) or * the head page (PMD-mapped THP) should be PageAnonExclusive(). If * neither is the case, there is certainly something wrong. */ for (; npages; npages--, pages++) { struct page *page = *pages; struct folio *folio; if (!page) continue; folio = page_folio(page); if (is_zero_page(page) || !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); else /* Either a PTE-mapped or a PMD-mapped THP. */ VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && !PageAnonExclusive(page), page); } } /* * Return the folio with ref appropriately incremented, * or NULL if that failed. */ static inline struct folio *try_get_folio(struct page *page, int refs) { struct folio *folio; retry: folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; if (unlikely(!folio_ref_try_add(folio, refs))) return NULL; /* * At this point we have a stable reference to the folio; but it * could be that between calling page_folio() and the refcount * increment, the folio was split, in which case we'd end up * holding a reference on a folio that has nothing to do with the page * we were given anymore. * So now that the folio is stable, recheck that the page still * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } return folio; } static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; } if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); } /** * try_grab_folio() - add a folio's refcount by a flag-dependent amount * @folio: pointer to folio to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same * time. * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. * * It is called when we have a stable reference for the folio, typically in * GUP slow path. */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags) { if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO; if (flags & FOLL_GET) folio_ref_add(folio, refs); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_folio(folio)) return 0; /* * Increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { folio_ref_add(folio, refs); atomic_add(refs, &folio->_pincount); } else { folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS); } node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); } return 0; } /** * unpin_user_page() - release a dma-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so * that such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. */ void unpin_user_page(struct page *page) { sanity_check_pinned_pages(&page, 1); gup_put_folio(page_folio(page), 1, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_page); /** * unpin_folio() - release a dma-pinned folio * @folio: pointer to folio to be released * * Folios that were pinned via memfd_pin_folios() or other similar routines * must be released either using unpin_folio() or unpin_folios(). */ void unpin_folio(struct folio *folio) { gup_put_folio(folio, 1, FOLL_PIN); } EXPORT_SYMBOL_GPL(unpin_folio); /** * folio_add_pin - Try to get an additional pin on a pinned folio * @folio: The folio to be pinned * * Get an additional pin on a folio we already have a pin on. Makes no change * if the folio is a zero_page. */ void folio_add_pin(struct folio *folio) { if (is_zero_folio(folio)) return; /* * Similar to try_grab_folio(): be sure to *also* increment the normal * page refcount field at least once, so that the page really is * pinned. */ if (folio_test_large(folio)) { WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); folio_ref_inc(folio); atomic_inc(&folio->_pincount); } else { WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } } static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { struct page *next = nth_page(start, i); struct folio *folio = page_folio(next); unsigned int nr = 1; if (folio_test_large(folio)) nr = min_t(unsigned int, npages - i, folio_nr_pages(folio) - folio_page_idx(folio, next)); *ntails = nr; return folio; } static inline struct folio *gup_folio_next(struct page **list, unsigned long npages, unsigned long i, unsigned int *ntails) { struct folio *folio = page_folio(list[i]); unsigned int nr; for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio) break; } *ntails = nr - i; return folio; } /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page" refers to a page that has had one of the get_user_pages() * variants called on that page. * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously * listed as clean. In any case, releases all pages using unpin_user_page(), * possibly via unpin_user_pages(), for the non-dirty case. * * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; if (!make_dirty) { unpin_user_pages(pages, npages); return; } sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key * cases: * * 1) This code sees the page as already dirty, so it * skips the call to set_page_dirty(). That could happen * because clear_page_dirty_for_io() called * folio_mkclean(), followed by set_page_dirty(). * However, now the page is going to get written back, * which meets the original intention of setting it * dirty, so all is well: clear_page_dirty_for_io() goes * on to call TestClearPageDirty(), and write the page * back. * * 2) This code sees the page as clean, so it calls * set_page_dirty(). The page stays dirty, despite being * written back, so it gets written back again in the * next writeback cycle. This is harmless. */ if (!folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages_dirty_lock); /** * unpin_user_page_range_dirty_lock() - release and optionally dirty * gup-pinned page range * * @page: the starting page of a range maybe marked dirty, and definitely released. * @npages: number of consecutive pages to release. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page range" refers to a range of pages that has had one of the * pin_user_pages() variants called on that page. * * For the page ranges defined by [page .. page+npages], make that range (or * its head pages, if a compound page) dirty, if @make_dirty is true, and if the * page range was previously listed as clean. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; for (i = 0; i < npages; i += nr) { folio = gup_folio_range_next(page, npages, i, &nr); if (make_dirty && !folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * Don't perform any sanity checks because we might have raced with * fork() and some anonymous pages might now actually be shared -- * which is why we're unpinning after all. */ for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } /** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details. */ void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here. */ if (WARN_ON(IS_ERR_VALUE(npages))) return; sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { if (!pages[i]) { nr = 1; continue; } folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages); /** * unpin_user_folio() - release pages of a folio * @folio: pointer to folio to be released * @npages: number of pages of same folio * * Release npages of the folio */ void unpin_user_folio(struct folio *folio, unsigned long npages) { gup_put_folio(folio, npages, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_folio); /** * unpin_folios() - release an array of gup-pinned folios. * @folios: array of folios to be marked dirty and released. * @nfolios: number of folios in the @folios array. * * For each folio in the @folios array, release the folio using gup_put_folio. * * Please see the unpin_folio() documentation for details. */ void unpin_folios(struct folio **folios, unsigned long nfolios) { unsigned long i = 0, j; /* * If this WARN_ON() fires, then the system *might* be leaking folios * (by leaving them pinned), but probably not. More likely, gup/pup * returned a hard -ERRNO error to the caller, who erroneously passed * it here. */ if (WARN_ON(IS_ERR_VALUE(nfolios))) return; while (i < nfolios) { for (j = i + 1; j < nfolios; j++) if (folios[i] != folios[j]) break; if (folios[i]) gup_put_folio(folios[i], j - i, FOLL_PIN); i = j; } } EXPORT_SYMBOL_GPL(unpin_folios); /* * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's * lifecycle. Avoid setting the bit unless necessary, or it might cause write * cache bouncing on large SMP machines for concurrent pinned gups. */ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) { if (!test_bit(MMF_HAS_PINNED, mm_flags)) set_bit(MMF_HAS_PINNED, mm_flags); } #ifdef CONFIG_MMU #ifdef CONFIG_HAVE_GUP_FAST static int record_subpages(struct page *page, unsigned long sz, unsigned long addr, unsigned long end, struct page **pages) { struct page *start_page; int nr; start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) pages[nr] = nth_page(start_page, nr); return nr; } /** * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. * @page: pointer to page to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. * * Return: The folio containing @page (with refcount appropriately * incremented) for success, or NULL upon failure. If neither FOLL_GET * nor FOLL_PIN was set, that's considered failure, and furthermore, * a likely bug in the caller, so a warning is also emitted. * * It uses add ref unless zero to elevate the folio refcount and must be called * in fast path only. */ static struct folio *try_grab_folio_fast(struct page *page, int refs, unsigned int flags) { struct folio *folio; /* Raise warn if it is not called in fast GUP */ VM_WARN_ON_ONCE(!irqs_disabled()); if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL; if (flags & FOLL_GET) return try_get_folio(page, refs); /* FOLL_PIN is set */ /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return page_folio(page); folio = try_get_folio(page, refs); if (!folio) return NULL; /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. */ if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); return NULL; } /* * When pinning a large folio, use an exact count to track it. * * However, be sure to *also* increment the normal folio * refcount field at least once, so that the folio really * is pinned. That's why the refcount from the earlier * try_get_folio() is left intact. */ if (folio_test_large(folio)) atomic_add(refs, &folio->_pincount); else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory * barrier in folio_try_share_anon_rmap_*(). */ smp_mb__after_atomic(); node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); return folio; } #endif /* CONFIG_HAVE_GUP_FAST */ /* Common code for can_follow_write_* */ static inline bool can_follow_write_common(struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ return page && PageAnon(page) && PageAnonExclusive(page); } static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) { if (!(flags & FOLL_DUMP)) return NULL; /* * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ if (is_vm_hugetlb_page(vma)) { struct hstate *h = hstate_vma(vma); if (!hugetlbfs_pagecache_present(h, vma, address)) return ERR_PTR(-EFAULT); } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); } return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES /* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */ static inline bool can_follow_write_pud(pud_t pud, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pud is writable, we can write to the page. */ if (pud_write(pud)) return true; return can_follow_write_common(page, vma, flags); } static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; struct page *page; pud_t pud = *pudp; unsigned long pfn = pud_pfn(pud); int ret; assert_spin_locked(pud_lockptr(mm, pudp)); if (!pud_present(pud)) return NULL; if ((flags & FOLL_WRITE) && !can_follow_write_pud(pud, pfn_to_page(pfn), vma, flags)) return NULL; pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && pud_devmap(pud)) { /* * device mapped pages can only be returned if the caller * will manage the page reference count. * * At least one of FOLL_GET | FOLL_PIN must be set, so * assert that here: */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); if (flags & FOLL_TOUCH) touch_pud(vma, addr, pudp, flags & FOLL_WRITE); ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); if (!ctx->pgmap) return ERR_PTR(-EFAULT); } page = pfn_to_page(pfn); if (!pud_devmap(pud) && !pud_write(pud) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); else ctx->page_mask = HPAGE_PUD_NR - 1; return page; } /* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) return true; if (!can_follow_write_common(page, vma, flags)) return false; /* ... and a write-fault isn't required for other reasons. */ if (pmd_needs_soft_dirty_wp(vma, pmd)) return false; return !userfaultfd_huge_pmd_wp(vma, pmd); } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; pmd_t pmdval = *pmd; struct page *page; int ret; assert_spin_locked(pmd_lockptr(mm, pmd)); page = pmd_page(pmdval); if ((flags & FOLL_WRITE) && !can_follow_write_pmd(pmdval, page, vma, flags)) return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) return ERR_PTR(-EFAULT); if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) return NULL; if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); ret = try_grab_folio(page_folio(page), 1, flags); if (ret) return ERR_PTR(ret); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; ctx->page_mask = HPAGE_PMD_NR - 1; return page; } #else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { return NULL; } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) { if (flags & FOLL_TOUCH) { pte_t orig_entry = ptep_get(pte); pte_t entry = orig_entry; if (flags & FOLL_WRITE) entry = pte_mkdirty(entry); entry = pte_mkyoung(entry); if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); } } /* Proper page table entry exists, but no corresponding struct page */ return -EEXIST; } /* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ static inline bool can_follow_write_pte(pte_t pte, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pte is writable, we can write to the page. */ if (pte_write(pte)) return true; if (!can_follow_write_common(page, vma, flags)) return false; /* ... and a write-fault isn't required for other reasons. */ if (pte_needs_soft_dirty_wp(vma, pte)) return false; return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; struct folio *folio; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; int ret; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); /* * We only care about anon pages in can_follow_write_pte() and don't * have to worry about pte_devmap() because they are never anon. */ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) { page = NULL; goto out; } if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN * case since they are only valid while holding the pgmap * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } folio = page_folio(page); if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); /* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */ ret = try_grab_folio(folio, 1, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; } /* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details. */ if (flags & FOLL_PIN) { ret = arch_make_folio_accessible(folio); if (ret) { unpin_user_page(page); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !folio_test_dirty(folio)) folio_mark_dirty(folio); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * folio_mark_accessed(). */ folio_mark_accessed(folio); } out: pte_unmap_unlock(ptep, ptl); return page; no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, unsigned int flags, struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); pmdval = *pmd; if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); return no_page_table(vma, flags, address); } if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); return page; } static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, unsigned int flags, struct follow_page_context *ctx) { pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); if (pud_leaf(pud)) { ptl = pud_lock(mm, pudp); page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (unlikely(pud_bad(pud))) return no_page_table(vma, flags, address); return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, unsigned int flags, struct follow_page_context *ctx) { p4d_t *p4dp, p4d; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); BUILD_BUG_ON(p4d_leaf(p4d)); if (!p4d_present(p4d) || p4d_bad(p4d)) return no_page_table(vma, flags, address); return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * * When getting an anonymous page and the caller has to trigger unsharing * of a shared anonymous page first, -EMLINK is returned. The caller should * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only * relevant with FOLL_PIN and !FOLL_WRITE. * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; struct page *page; vma_pgtable_walk_begin(vma); ctx->page_mask = 0; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address); else page = follow_p4d_mask(vma, address, pgd, flags, ctx); vma_pgtable_walk_end(vma); return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, unsigned int gup_flags, struct vm_area_struct **vma, struct page **page) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t entry; int ret = -EFAULT; /* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) return -EFAULT; if (address > TASK_SIZE) pgd = pgd_offset_k(address); else pgd = pgd_offset_gate(mm, address); if (pgd_none(*pgd)) return -EFAULT; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return -EFAULT; pud = pud_offset(p4d, address); if (pud_none(*pud)) return -EFAULT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; pte = pte_offset_map(pmd, address); if (!pte) return -EFAULT; entry = ptep_get(pte); if (pte_none(entry)) goto unmap; *vma = get_gate_vma(mm); if (!page) goto out; *page = vm_normal_page(*vma, address, entry); if (!*page) { if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap; *page = pte_page(entry); } ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap; out: ret = 0; unmap: pte_unmap(pte); return ret; } /* * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set * to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int flags, bool unshare, int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; if (flags & FOLL_NOFAULT) return -EFAULT; if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; if (flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals. */ if (flags & FOLL_INTERRUPTIBLE) fault_flags |= FAULT_FLAG_INTERRUPTIBLE; } if (flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } if (unshare) { fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this. */ WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); *locked = 0; /* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_. */ return -EAGAIN; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, flags); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; } return 0; } /* * Writing to file-backed mappings which require folio dirty tracking using GUP * is a fundamentally broken operation, as kernel write access to GUP mappings * do not adhere to the semantics expected by a file system. * * Consider the following scenario:- * * 1. A folio is written to via GUP which write-faults the memory, notifying * the file system and dirtying the folio. * 2. Later, writeback is triggered, resulting in the folio being cleaned and * the PTE being marked read-only. * 3. The GUP caller writes to the folio, as it is mapped read/write via the * direct mapping. * 4. The GUP caller, now done with the page, unpins it and sets it dirty * (though it does not have to). * * This results in both data being written to a folio without writenotify, and * the folio being dirtied unexpectedly (if the caller decides to do so). */ static bool writable_file_mapping_allowed(struct vm_area_struct *vma, unsigned long gup_flags) { /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow. */ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true; /* * If the VMA does not require dirty tracking then no problematic write * can occur either. */ return !vma_needs_dirty_tracking(vma); } static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) { vm_flags_t vm_flags = vma->vm_flags; int write = (gup_flags & FOLL_WRITE); int foreign = (gup_flags & FOLL_REMOTE); bool vma_anon = vma_is_anonymous(vma); if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; if ((gup_flags & FOLL_ANON) && !vma_anon) return -EFAULT; if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP; if (vma_is_secretmem(vma)) return -EFAULT; if (write) { if (!vma_anon && !writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT; if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it. */ if (!is_cow_mapping(vm_flags)) return -EFAULT; } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set? */ if (!(vm_flags & VM_MAYREAD)) return -EFAULT; } /* * gups are always data accesses, not instruction * fetches, so execute=false here */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return -EFAULT; return 0; } /* * This is "vma_lookup()", but with a warning if we would have * historically expanded the stack in the GUP code. */ static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, unsigned long addr) { #ifdef CONFIG_STACK_GROWSUP return vma_lookup(mm, addr); #else static volatile unsigned long next_warn; struct vm_area_struct *vma; unsigned long now, next; vma = find_vma(mm, addr); if (!vma || (addr >= vma->vm_start)) return vma; /* Only warn for half-way relevant accesses */ if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; if (vma->vm_start - addr > 65536) return NULL; /* Let's not warn more than once an hour.. */ now = jiffies; next = next_warn; if (next && time_before(now, next)) return NULL; next_warn = now + 60*60*HZ; /* Let people know things may have changed. */ pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n", current->comm, task_pid_nr(current), vma->vm_start, vma->vm_end, addr); dump_stack(); return NULL; #endif } /** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * -- 0 return value is possible when the fault would need to be retried. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If * the page is written to, set_page_dirty (or set_page_dirty_lock, as * appropriate) must be called after the page is finished with, and * before put_page is called. * * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may * be released. If this happens *@locked will be set to 0 on return. * * A caller using such a combination of @gup_flags must therefore hold the * mmap_lock for reading only, and recognize when it's been released. Otherwise, * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); do { struct page *page; unsigned int page_increm; /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { /* * MADV_POPULATE_(READ|WRITE) wants to handle VMA * lookups+error reporting differently. */ if (gup_flags & FOLL_MADV_POPULATE) { vma = vma_lookup(mm, start); if (!vma) { ret = -ENOMEM; goto out; } if (check_vma_flags(vma, gup_flags)) { ret = -EINVAL; goto out; } goto retry; } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, pages ? &page : NULL); if (ret) goto out; ctx.page_mask = 0; goto next_page; } if (!vma) { ret = -EFAULT; goto out; } ret = check_vma_flags(vma, gup_flags); if (ret) goto out; } retry: /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { ret = -EINTR; goto out; } cond_resched(); page = follow_page_mask(vma, start, gup_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) { ret = faultin_page(vma, start, gup_flags, PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: case -EAGAIN: ret = 0; fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out; } BUG(); } else if (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding * struct page. If the caller expects **pages to be * filled in, bail out now, because that can't be done * for this page. */ if (pages) { ret = PTR_ERR(page); goto out; } } else if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } next_page: page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; if (pages) { struct page *subpage; unsigned int j; /* * This must be a large folio (and doesn't need to * be the whole folio; it can be part of it), do * the refcount work for all the subpages too. * * NOTE: here the page may not be the head page * e.g. when start addr is not thp-size aligned. * try_grab_folio() should have taken care of tail * pages. */ if (page_increm > 1) { struct folio *folio = page_folio(page); /* * Since we already hold refcount on the * large folio, this should never fail. */ if (try_grab_folio(folio, page_increm - 1, gup_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ gup_put_folio(folio, 1, gup_flags); ret = -EFAULT; goto out; } } for (j = 0; j < page_increm; j++) { subpage = nth_page(page, j); pages[i + j] = subpage; flush_anon_page(vma, subpage, start + j * PAGE_SIZE); flush_dcache_page(subpage); } } i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); out: if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags) { bool write = !!(fault_flags & FAULT_FLAG_WRITE); bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE); vm_flags_t vm_flags = write ? VM_WRITE : VM_READ; if (!(vm_flags & vma->vm_flags)) return false; /* * The architecture might have a hardware protection * mechanism other than read/write that can deny access. * * gup always represents data access, not instruction * fetches, so execute=false here: */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return false; return true; } /** * fixup_user_fault() - manually resolve a user page fault * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller * does not allow retry. If NULL, the caller must guarantee * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() * section), this returns -EFAULT, and we want to resolve the user fault before * trying again. * * Typically this is meant to be used by the futex code. * * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; vm_fault_t ret; address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; if ((fault_flags & FAULT_FLAG_KILLABLE) && fatal_signal_pending(current)) return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); /* * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is * specified, it'll also respond to generic signals. The caller of GUP * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption. */ static bool gup_signal_pending(unsigned int flags) { if (fatal_signal_pending(current)) return true; if (!(flags & FOLL_INTERRUPTIBLE)) return false; return signal_pending(current); } /* * Locking: (*locked == 1) means that the mmap_lock has already been acquired by * the caller. This function may drop the mmap_lock. If it does so, then it will * set (*locked = 0). * * (*locked == 0) means that the caller expects this function to acquire and * drop the mmap_lock. Therefore, the value of *locked will still be zero when * the function returns, even though it may have changed temporarily during * function execution. * * Please note that this function, unlike __get_user_pages(), will not return 0 * for nr_pages > 0, unless FOLL_NOWAIT is used. */ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int flags) { long ret, pages_done; bool must_unlock = false; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } else mmap_assert_locked(mm); if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough. */ if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET; pages_done = 0; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); } if (ret > 0) { nr_pages -= ret; pages_done += ret; if (!nr_pages) break; } if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT. */ if (!pages_done) pages_done = ret; break; } /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts. */ if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; /* The lock was temporarily dropped, so we must unlock later */ must_unlock = true; retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever. */ if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; } ret = mmap_read_lock_killable(mm); if (ret) { BUG_ON(ret > 0); if (!pages_done) pages_done = ret; break; } *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); goto retry; } if (ret != 1) { BUG_ON(ret > 1); if (!pages_done) pages_done = ret; break; } nr_pages--; pages_done++; if (!nr_pages) break; if (likely(pages)) pages++; start += PAGE_SIZE; } if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state. */ mmap_read_unlock(mm); *locked = 0; } /* * Failing to pin anything implies something has gone wrong (except when * FOLL_NOWAIT is specified). */ if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) return -EFAULT; return pages_done; } /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma * @start: start address * @end: end address * @locked: whether the mmap_lock is still held * * This takes care of mlocking the pages too if VM_LOCKED is set. * * Return either number of pages pinned in the vma, or a negative error * code on error. * * vma->vm_mm->mmap_lock must be held. * * If @locked is NULL, it may be held for read or write and will * be unperturbed. * * If @locked is non-NULL, it must held for read only and may be * released. If it's released, *@locked will be set to 0. */ long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked) { struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here. */ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages; /* ... similarly, we've never faulted in PROT_NONE pages */ if (!vma_is_accessible(vma)) return -EFAULT; gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. * * Otherwise, do a read fault, and use FOLL_FORCE in case it's not * readable (ie write-only or executable). */ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; else gup_flags |= FOLL_FORCE; if (locked) gup_flags |= FOLL_UNLOCKABLE; /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, locked ? locked : &local_locked); lru_add_drain(); return ret; } /* * faultin_page_range() - populate (prefault) page tables inside the * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * * Returns either number of processed pages in the MM, or a negative error * code on error (see __get_user_pages()). Note that this function reports * errors related to VMAs, such as incompatible mappings, as expected by * MADV_POPULATE_(READ|WRITE). * * The range must be page-aligned. * * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked) { unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); mmap_assert_locked(mm); /* * FOLL_TOUCH: Mark page accessed and thereby young; will also mark * the page dirty with FOLL_WRITE -- which doesn't make a * difference with !FOLL_FORCE, because the page is writable * in the page table. * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, gup_flags); lru_add_drain(); return ret; } /* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap * flags. VMAs must be already marked with the desired vm_flags, and * mmap_lock must not be held. */ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0; end = start + len; for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA. */ if (!locked) { locked = 1; mmap_read_lock(mm); vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) vma = find_vma_intersection(mm, vma->vm_end, end); if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked. */ ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) { ret = 0; continue; /* continue at next VMA */ } break; } nend = nstart + ret * PAGE_SIZE; ret = 0; } if (locked) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ } #else /* CONFIG_MMU */ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int foll_flags) { struct vm_area_struct *vma; bool must_unlock = false; unsigned long vm_flags; long i; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. */ vm_flags = (foll_flags & FOLL_WRITE) ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (foll_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) break; /* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) break; if (pages) { pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } start = (start + PAGE_SIZE) & PAGE_MASK; } if (must_unlock && *locked) { mmap_read_unlock(mm); *locked = 0; } return i ? : -EFAULT; } #endif /* !CONFIG_MMU */ /** * fault_in_writeable - fault in userspace address range for writing * @uaddr: start of address range * @size: size of address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_writeable(char __user *uaddr, size_t size) { char __user *start = uaddr, *end; if (unlikely(size == 0)) return 0; if (!user_write_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_put_user(0, uaddr, out); uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_put_user(0, uaddr, out); uaddr += PAGE_SIZE; } out: user_write_access_end(); if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_writeable); /** * fault_in_subpage_writeable - fault in an address range for writing * @uaddr: start of address range * @size: size of address range * * Fault in a user address range for writing while checking for permissions at * sub-page granularity (e.g. arm64 MTE). This function should be used when * the caller cannot guarantee forward progress of a copy_to_user() loop. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) { size_t faulted_in; /* * Attempt faulting in at page granularity first for page table * permission checking. The arch-specific probe_subpage_writeable() * functions may not check for this. */ faulted_in = size - fault_in_writeable(uaddr, size); if (faulted_in) faulted_in -= probe_subpage_writeable(uaddr, faulted_in); return size - faulted_in; } EXPORT_SYMBOL(fault_in_subpage_writeable); /* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range * @size: length of address range * * Faults in an address range for writing. This is primarily useful when we * already know that some or all of the pages in the address range aren't in * memory. * * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of * time. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; bool unlocked = false; if (unlikely(size == 0)) return 0; end = PAGE_ALIGN(start + size); if (end < start) end = 0; mmap_read_lock(mm); do { if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; start = (start + PAGE_SIZE) & PAGE_MASK; } while (start != end); mmap_read_unlock(mm); if (size > (unsigned long)uaddr - start) return size - ((unsigned long)uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); /** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range * @size: size of user address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_readable(const char __user *uaddr, size_t size) { const char __user *start = uaddr, *end; volatile char c; if (unlikely(size == 0)) return 0; if (!user_read_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_get_user(c, uaddr, out); uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_get_user(c, uaddr, out); uaddr += PAGE_SIZE; } out: user_read_access_end(); (void)c; if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_readable); /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * * Returns struct page pointer of user page pinned for dump, * to be freed afterwards by put_page(). * * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself). */ #ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsigned long addr) { struct page *page; int locked = 0; int ret; ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked, FOLL_FORCE | FOLL_DUMP | FOLL_GET); return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ #ifdef CONFIG_MIGRATION /* * An array of either pages or folios ("pofs"). Although it may seem tempting to * avoid this complication, by simply interpreting a list of folios as a list of * pages, that approach won't work in the longer term, because eventually the * layouts of struct page and struct folio will become completely different. * Furthermore, this pof approach avoids excessive page_folio() calls. */ struct pages_or_folios { union { struct page **pages; struct folio **folios; void **entries; }; bool has_folios; long nr_entries; }; static struct folio *pofs_get_folio(struct pages_or_folios *pofs, long i) { if (pofs->has_folios) return pofs->folios[i]; return page_folio(pofs->pages[i]); } static void pofs_clear_entry(struct pages_or_folios *pofs, long i) { pofs->entries[i] = NULL; } static void pofs_unpin(struct pages_or_folios *pofs) { if (pofs->has_folios) unpin_folios(pofs->folios, pofs->nr_entries); else unpin_user_pages(pofs->pages, pofs->nr_entries); } /* * Returns the number of collected folios. Return value is always >= 0. */ static void collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs) { struct folio *prev_folio = NULL; bool drain_allow = true; unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); if (folio == prev_folio) continue; prev_folio = folio; if (folio_is_longterm_pinnable(folio)) continue; if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { folio_isolate_hugetlb(folio, movable_folio_list); continue; } if (!folio_test_lru(folio) && drain_allow) { lru_add_drain_all(); drain_allow = false; } if (!folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_folio_list); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } } /* * Unpins all folios and migrates device coherent folios and movable_folio_list. * Returns -EAGAIN if all folios were successfully migrated or -errno for * failure (or partial success). */ static int migrate_longterm_unpinnable_folios(struct list_head *movable_folio_list, struct pages_or_folios *pofs) { int ret; unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); if (folio_is_device_coherent(folio)) { /* * Migration will fail if the folio is pinned, so * convert the pin on the source folio to a normal * reference. */ pofs_clear_entry(pofs, i); folio_get(folio); gup_put_folio(folio, 1, FOLL_PIN); if (migrate_device_coherent_folio(folio)) { ret = -EBUSY; goto err; } continue; } /* * We can't migrate folios with unexpected references, so drop * the reference obtained by __get_user_pages_locked(). * Migrating folios have been added to movable_folio_list after * calling folio_isolate_lru() which takes a reference so the * folio won't be freed if it's migrating. */ unpin_folio(folio); pofs_clear_entry(pofs, i); } if (!list_empty(movable_folio_list)) { struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_folio_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_LONGTERM_PIN, NULL)) { ret = -ENOMEM; goto err; } } putback_movable_pages(movable_folio_list); return -EAGAIN; err: pofs_unpin(pofs); putback_movable_pages(movable_folio_list); return ret; } static long check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) { LIST_HEAD(movable_folio_list); collect_longterm_unpinnable_folios(&movable_folio_list, pofs); if (list_empty(&movable_folio_list)) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); } /* * Check whether all folios are *allowed* to be pinned indefinitely (long term). * Rather confusingly, all folios in the range are required to be pinned via * FOLL_PIN, before calling this routine. * * Return values: * * 0: if everything is OK and all folios in the range are allowed to be pinned, * then this routine leaves all folios pinned and returns zero for success. * * -EAGAIN: if any folios in the range are not allowed to be pinned, then this * routine will migrate those folios away, unpin all the folios in the range. If * migration of the entire set of folios succeeds, then -EAGAIN is returned. The * caller should re-pin the entire range with FOLL_PIN and then call this * routine again. * * -ENOMEM, or any other -errno: if an error *other* than -EAGAIN occurs, this * indicates a migration failure. The caller should give up, and propagate the * error back up the call stack. The caller does not need to unpin any folios in * that case, because this routine will do the unpinning. */ static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { struct pages_or_folios pofs = { .folios = folios, .has_folios = true, .nr_entries = nr_folios, }; return check_and_migrate_movable_pages_or_folios(&pofs); } /* * Return values and behavior are the same as those for * check_and_migrate_movable_folios(). */ static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { struct pages_or_folios pofs = { .pages = pages, .has_folios = false, .nr_entries = nr_pages, }; return check_and_migrate_movable_pages_or_folios(&pofs); } #else static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { return 0; } static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { return 0; } #endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int gup_flags) { unsigned int flags; long rc, nr_pinned_pages; if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); flags = memalloc_pin_save(); do { nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); if (nr_pinned_pages <= 0) { rc = nr_pinned_pages; break; } /* FOLL_LONGTERM implies FOLL_PIN */ rc = check_and_migrate_movable_pages(nr_pinned_pages, pages); } while (rc == -EAGAIN); memalloc_pin_restore(flags); return rc ? rc : nr_pinned_pages; } /* * Check that the given flags are valid for the exported gup/pup interface, and * update them with the required flags that the caller must have set. */ static bool is_valid_gup_args(struct page **pages, int *locked, unsigned int *gup_flags_p, unsigned int to_set) { unsigned int gup_flags = *gup_flags_p; /* * These flags not allowed to be specified externally to the gup * interfaces: * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only, set in (get|pin)_user_pages_remote() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) return false; gup_flags |= to_set; if (locked) { /* At the external interface locked must be set */ if (WARN_ON_ONCE(*locked != 1)) return false; gup_flags |= FOLL_UNLOCKABLE; } /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return false; /* LONGTERM can only be specified when pinning */ if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM))) return false; /* Pages input must be given if using GET/PIN */ if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) return false; /* We want to allow the pgmap to be hot-unplugged at all times */ if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))) return false; *gup_flags_p = gup_flags; return true; } #ifdef CONFIG_MMU /** * get_user_pages_remote() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held for read or write. * * get_user_pages_remote walks a process's page tables and takes a reference * to each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must * be called after the page is finished with, and before put_page is called. * * get_user_pages_remote is typically used for fewer-copy IO operations, * to get a handle on the memory by some means other than accesses * via the user virtual addresses. The pages may be submitted for * DMA to devices or accessed via their kernel linear mapping (via the * kmap APIs). Care should be taken to use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. * * get_user_pages_remote should be phased out in favor of * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; return __get_user_pages_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { return 0; } #endif /* !CONFIG_MMU */ /** * get_user_pages() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to * the current task, and doesn't allow passing of a locked parameter. We also * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages); /* * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags * (e.g. FOLL_FORCE) are not required. */ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked); /* * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be * protected from page table pages being freed from under it, and should * block any THP splits. * * One way to achieve this is to have the walker disable interrupts, and * rely on IPIs from the TLB flushing code blocking before the page table * pages are freed. This is unsuitable for architectures that do not need * to broadcast an IPI when invalidating TLBs. * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * * Before activating this code, please be aware that the following assumptions * are currently made: * * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * * *) access_ok is sufficient to validate userspace address ranges. * * The last two assumptions can be relaxed by the addition of helper functions. * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * * GUP-fast must reject all secretmem folios. * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing * so. * * This function cannot be as thorough as that one as the VMA is not available * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { bool reject_file_backed = false; struct address_space *mapping; bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) reject_file_backed = true; /* We hold a folio reference, so we can safely access folio fields. */ /* secretmem folios are always order-0 folios. */ if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) check_secretmem = true; if (!reject_file_backed && !check_secretmem) return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; /* * GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods * cannot proceed, which means no actions performed under RCU can * proceed either. * * inodes and thus their mappings are freed under RCU, which means the * mapping cannot be freed beneath us and thus we can safely dereference * it. */ lockdep_assert_irqs_disabled(); /* * However, there may be operations which _alter_ the mapping, so ensure * we read it once and only once. */ mapping = READ_ONCE(folio->mapping); /* * The mapping may have been truncated, in any case we cannot determine * if this mapping is safe - fall back to slow path to determine how to * proceed. */ if (!mapping) return false; /* Anonymous folios pose no problem. */ mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; if (mapping_flags) return mapping_flags & PAGE_MAPPING_ANON; /* * At this point, we know the mapping is non-null and points to an * address_space object. */ if (check_secretmem && secretmem_mapping(mapping)) return false; /* The only remaining allowed file system is shmem. */ return !reject_file_backed || shmem_mapping(mapping); } static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { struct folio *folio = page_folio(pages[--(*nr)]); folio_clear_referenced(folio); gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * * To pin the page, GUP-fast needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy * with GUP-fast, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * * For THP collapse, it's a bit more complicated because GUP-fast may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; ptem = ptep = pte_offset_map(&pmd, addr); if (!ptep) return 0; do { pte_t pte = ptep_get_lockless(ptep); struct page *page; struct folio *folio; /* * Always fallback to ordinary GUP on PROT_NONE-mapped pages: * pte_access_permitted() better should reject these pages * either way: otherwise, GUP-fast might succeed in * cases where ordinary GUP would fail due to VMA access * permissions. */ if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) goto pte_unmap; if (pte_devmap(pte)) { if (unlikely(flags & FOLL_LONGTERM)) goto pte_unmap; pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); folio = try_grab_folio_fast(page, 1, flags); if (!folio) goto pte_unmap; if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please * see Documentation/core-api/pin_user_pages.rst for * details. */ if (flags & FOLL_PIN) { ret = arch_make_folio_accessible(folio); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; pte_unmap: if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); return ret; } #else /* * If we can't determine whether or not a pte is special, then fail immediately * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not * to be special. * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio = try_grab_folio_fast(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap); return addr == end; } static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } #endif static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pmd_special(orig)) return 0; if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, pages, nr); } page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pud_special(orig)) return 0; if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, pages, nr); } page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int refs; struct page *page; struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) return 0; if (unlikely(pmd_leaf(pmd))) { /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; if (unlikely(pud_leaf(pud))) { if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, pages, nr)) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); if (!p4d_present(p4d)) return 0; BUILD_BUG_ON(p4d_leaf(p4d)); if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pgd_t *pgdp; pgdp = pgd_offset(current->mm, addr); do { pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; if (unlikely(pgd_leaf(pgd))) { if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, pages, nr)) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } #endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* * Check if it's allowed to use get_user_pages_fast_only() for the range, or * we need to fall back to the slow version: */ static bool gup_fast_permitted(unsigned long start, unsigned long end) { return true; } #endif static unsigned long gup_fast(unsigned long start, unsigned long end, unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; if (gup_flags & FOLL_PIN) { if (!raw_seqcount_try_begin(¤t->mm->write_protect_seq, seq)) return 0; } /* * Disable interrupts. The nested form is used, in order to allow full, * general purpose use of this routine. * * With interrupts disabled, we block page table pages from being freed * from under us. See struct mmu_table_batch comments in * include/asm-generic/tlb.h for more details. * * We do not adopt an rcu_read_lock() here as we also want to block IPIs * that come from THPs splitting. */ local_irq_save(flags); gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * When pinning pages for DMA there could be a concurrent write protect * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); } } return nr_pinned; } static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; int locked = 0; int ret; if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; /* Slow path: try to get the remaining pages with get_user_pages */ start += nr_pinned << PAGE_SHIFT; pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, &locked, gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so * returning -errno is not an option */ if (nr_pinned) return nr_pinned; return ret; } return ret + nr_pinned; } /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. * * If the architecture does not support this function, simply return with no * pages pinned. * * Careful, careful! COW breaking can go either way, so a non-write * access can get ambiguous page results. If you call this function without * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, * because gup fast is always a "pin with a +1 page refcount" request. * * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Attempt to pin user pages in memory without taking mm->mmap_lock. * If not successful, it will fall back to taking the lock and * calling get_user_pages(). * * Returns number of pages pinned. This may be fewer than the number requested. * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns * -errno. */ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * The caller may or may not have explicitly set FOLL_GET; either way is * OK. However, internally (within mm/gup.c), gup fast variants must set * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" * request. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See * get_user_pages_fast() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); /** * pin_user_pages_remote() - pin pages of a remote process * * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See * get_user_pages_remote() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE)) return 0; return __gup_longterm_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_remote); /** * pin_user_pages() - pin user pages in memory for use by other devices * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); /* * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_unlocked); /** * memfd_pin_folios() - pin folios associated with a memfd * @memfd: the memfd whose folios are to be pinned * @start: the first memfd offset * @end: the last memfd offset (inclusive) * @folios: array that receives pointers to the folios pinned * @max_folios: maximum number of entries in @folios * @offset: the offset into the first folio * * Attempt to pin folios associated with a memfd in the contiguous range * [start, end]. Given that a memfd is either backed by shmem or hugetlb, * the folios can either be found in the page cache or need to be allocated * if necessary. Once the folios are located, they are all pinned via * FOLL_PIN and @offset is populatedwith the offset into the first folio. * And, eventually, these pinned folios must be released either using * unpin_folios() or unpin_folio(). * * It must be noted that the folios may be pinned for an indefinite amount * of time. And, in most cases, the duration of time they may stay pinned * would be controlled by the userspace. This behavior is effectively the * same as using FOLL_LONGTERM with other GUP APIs. * * Returns number of folios pinned, which could be less than @max_folios * as it depends on the folio sizes that cover the range [start, end]. * If no folios were pinned, it returns -errno. */ long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset) { unsigned int flags, nr_folios, nr_found; unsigned int i, pgshift = PAGE_SHIFT; pgoff_t start_idx, end_idx, next_idx; struct folio *folio = NULL; struct folio_batch fbatch; struct hstate *h; long ret = -EINVAL; if (start < 0 || start > end || !max_folios) return -EINVAL; if (!memfd) return -EINVAL; if (!shmem_file(memfd) && !is_file_hugepages(memfd)) return -EINVAL; if (end >= i_size_read(file_inode(memfd))) return -EINVAL; if (is_file_hugepages(memfd)) { h = hstate_file(memfd); pgshift = huge_page_shift(h); } flags = memalloc_pin_save(); do { nr_folios = 0; start_idx = start >> pgshift; end_idx = end >> pgshift; if (is_file_hugepages(memfd)) { start_idx <<= huge_page_order(h); end_idx <<= huge_page_order(h); } folio_batch_init(&fbatch); while (start_idx <= end_idx && nr_folios < max_folios) { /* * In most cases, we should be able to find the folios * in the page cache. If we cannot find them for some * reason, we try to allocate them and add them to the * page cache. */ nr_found = filemap_get_folios_contig(memfd->f_mapping, &start_idx, end_idx, &fbatch); if (folio) { folio_put(folio); folio = NULL; } next_idx = 0; for (i = 0; i < nr_found; i++) { /* * As there can be multiple entries for a * given folio in the batch returned by * filemap_get_folios_contig(), the below * check is to ensure that we pin and return a * unique set of folios between start and end. */ if (next_idx && next_idx != folio_index(fbatch.folios[i])) continue; folio = page_folio(&fbatch.folios[i]->page); if (try_grab_folio(folio, 1, FOLL_PIN)) { folio_batch_release(&fbatch); ret = -EINVAL; goto err; } if (nr_folios == 0) *offset = offset_in_folio(folio, start); folios[nr_folios] = folio; next_idx = folio_next_index(folio); if (++nr_folios == max_folios) break; } folio = NULL; folio_batch_release(&fbatch); if (!nr_found) { folio = memfd_alloc_folio(memfd, start_idx); if (IS_ERR(folio)) { ret = PTR_ERR(folio); if (ret != -EEXIST) goto err; folio = NULL; } } } ret = check_and_migrate_movable_folios(nr_folios, folios); } while (ret == -EAGAIN); memalloc_pin_restore(flags); return ret ? ret : nr_folios; err: memalloc_pin_restore(flags); unpin_folios(folios, nr_folios); return ret; } EXPORT_SYMBOL_GPL(memfd_pin_folios); /** * folio_add_pins() - add pins to an already-pinned folio * @folio: the folio to add more pins to * @pins: number of pins to add * * Try to add more pins to an already-pinned folio. The semantics * of the pin (e.g., FOLL_WRITE) follow any existing pin and cannot * be changed. * * This function is helpful when having obtained a pin on a large folio * using memfd_pin_folios(), but wanting to logically unpin parts * (e.g., individual pages) of the folio later, for example, using * unpin_user_page_range_dirty_lock(). * * This is not the right interface to initially pin a folio. */ int folio_add_pins(struct folio *folio, unsigned int pins) { VM_WARN_ON_ONCE(!folio_maybe_dma_pinned(folio)); return try_grab_folio(folio, pins, FOLL_PIN); } EXPORT_SYMBOL_GPL(folio_add_pins); |
| 69 2 67 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2006 Patrick McHardy <kaber@trash.net> * * Based on ipt_random and ipt_nth by Fabrice MARIE <fabrice@netfilter.org>. */ #include <linux/init.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/netfilter/xt_statistic.h> #include <linux/netfilter/x_tables.h> #include <linux/module.h> struct xt_statistic_priv { atomic_t count; } ____cacheline_aligned_in_smp; MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Xtables: statistics-based matching (\"Nth\", random)"); MODULE_ALIAS("ipt_statistic"); MODULE_ALIAS("ip6t_statistic"); static bool statistic_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_statistic_info *info = par->matchinfo; bool ret = info->flags & XT_STATISTIC_INVERT; int nval, oval; switch (info->mode) { case XT_STATISTIC_MODE_RANDOM: if ((get_random_u32() & 0x7FFFFFFF) < info->u.random.probability) ret = !ret; break; case XT_STATISTIC_MODE_NTH: do { oval = atomic_read(&info->master->count); nval = (oval == info->u.nth.every) ? 0 : oval + 1; } while (atomic_cmpxchg(&info->master->count, oval, nval) != oval); if (nval == 0) ret = !ret; break; } return ret; } static int statistic_mt_check(const struct xt_mtchk_param *par) { struct xt_statistic_info *info = par->matchinfo; if (info->mode > XT_STATISTIC_MODE_MAX || info->flags & ~XT_STATISTIC_MASK) return -EINVAL; info->master = kzalloc(sizeof(*info->master), GFP_KERNEL); if (info->master == NULL) return -ENOMEM; atomic_set(&info->master->count, info->u.nth.count); return 0; } static void statistic_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_statistic_info *info = par->matchinfo; kfree(info->master); } static struct xt_match xt_statistic_mt_reg __read_mostly = { .name = "statistic", .revision = 0, .family = NFPROTO_UNSPEC, .match = statistic_mt, .checkentry = statistic_mt_check, .destroy = statistic_mt_destroy, .matchsize = sizeof(struct xt_statistic_info), .usersize = offsetof(struct xt_statistic_info, master), .me = THIS_MODULE, }; static int __init statistic_mt_init(void) { return xt_register_match(&xt_statistic_mt_reg); } static void __exit statistic_mt_exit(void) { xt_unregister_match(&xt_statistic_mt_reg); } module_init(statistic_mt_init); module_exit(statistic_mt_exit); |
| 24 1 23 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <net/ip.h> #include <net/tcp.h> #include <net/route.h> #include <net/dst.h> #include <net/netfilter/ipv4/nf_reject.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> static int nf_reject_iphdr_validate(struct sk_buff *skb) { struct iphdr *iph; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return 0; iph = ip_hdr(skb); if (iph->ihl < 5 || iph->version != 4) return 0; len = ntohs(iph->tot_len); if (skb->len < len) return 0; else if (len < (iph->ihl*4)) return 0; if (!pskb_may_pull(skb, iph->ihl*4)) return 0; return 1; } struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook) { const struct tcphdr *oth; struct sk_buff *nskb; struct iphdr *niph; struct tcphdr _oth; if (!nf_reject_iphdr_validate(oldskb)) return NULL; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); if (!oth) return NULL; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return NULL; nskb->dev = (struct net_device *)dev; skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); niph->tot_len = htons(nskb->len); ip_send_check(niph); return nskb; } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset); struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook, u8 code) { struct sk_buff *nskb; struct iphdr *niph; struct icmphdr *icmph; unsigned int len; int dataoff; __wsum csum; u8 proto; if (!nf_reject_iphdr_validate(oldskb)) return NULL; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; /* RFC says return as much as we can without exceeding 576 bytes. */ len = min_t(unsigned int, 536, oldskb->len); if (!pskb_may_pull(oldskb, len)) return NULL; if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) return NULL; dataoff = ip_hdrlen(oldskb); proto = ip_hdr(oldskb)->protocol; if (!skb_csum_unnecessary(oldskb) && nf_reject_verify_csum(oldskb, dataoff, proto) && nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) return NULL; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + LL_MAX_HEADER + len, GFP_ATOMIC); if (!nskb) return NULL; nskb->dev = (struct net_device *)dev; skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); skb_reset_transport_header(nskb); icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); icmph->type = ICMP_DEST_UNREACH; icmph->code = code; skb_put_data(nskb, skb_network_header(oldskb), len); csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0); icmph->checksum = csum_fold(csum); niph->tot_len = htons(nskb->len); ip_send_check(niph); return nskb; } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach); const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook) { const struct tcphdr *oth; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; if (ip_hdr(oldskb)->protocol != IPPROTO_TCP) return NULL; oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb), sizeof(struct tcphdr), _oth); if (oth == NULL) return NULL; /* No RST for RST. */ if (oth->rst) return NULL; /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return NULL; return oth; } EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_get); struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, __u8 protocol, int ttl) { struct iphdr *niph, *oiph = ip_hdr(oldskb); skb_reset_network_header(nskb); niph = skb_put(nskb, sizeof(struct iphdr)); niph->version = 4; niph->ihl = sizeof(struct iphdr) / 4; niph->tos = 0; niph->id = 0; niph->frag_off = htons(IP_DF); niph->protocol = protocol; niph->check = 0; niph->saddr = oiph->daddr; niph->daddr = oiph->saddr; niph->ttl = ttl; nskb->protocol = htons(ETH_P_IP); return niph; } EXPORT_SYMBOL_GPL(nf_reject_iphdr_put); void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth) { struct iphdr *niph = ip_hdr(nskb); struct tcphdr *tcph; skb_reset_transport_header(nskb); tcph = skb_put_zero(nskb, sizeof(struct tcphdr)); tcph->source = oth->dest; tcph->dest = oth->source; tcph->doff = sizeof(struct tcphdr) / 4; if (oth->ack) { tcph->seq = oth->ack_seq; } else { tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + oldskb->len - ip_hdrlen(oldskb) - (oth->doff << 2)); tcph->ack = 1; } tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); } EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) { struct dst_entry *dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(struct flowi)); fl.u.ip4.daddr = ip_hdr(skb_in)->saddr; nf_ip_route(dev_net(skb_in->dev), &dst, &fl, false); if (!dst) return -1; skb_dst_set(skb_in, dst); return 0; } /* Send RST reply */ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { const struct tcphdr *oth; struct sk_buff *nskb; struct tcphdr _oth; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); if (!oth) return; if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return; /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); nskb->mark = IP4_REPLY_MARK(net, oldskb->mark); skb_reserve(nskb, LL_MAX_HEADER); nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); if (ip_route_me_harder(net, sk, nskb, RTN_UNSPEC)) goto free_nskb; /* "Never happens" */ if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; nf_ct_attach(nskb, oldskb); nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on * the RST will be ours, instead of the destination's. This confuses * some routers/firewalls, and they drop the packet. So we need to * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); struct iphdr *niph = ip_hdr(nskb); struct net_device *br_indev; br_indev = nf_bridge_get_physindev(oldskb, net); if (!br_indev) goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); ip_send_check(niph); if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), oeth->h_source, oeth->h_dest, nskb->len) < 0) goto free_nskb; dev_queue_xmit(nskb); } else #endif ip_local_out(net, nskb->sk, nskb); return; free_nskb: kfree_skb(nskb); } EXPORT_SYMBOL_GPL(nf_send_reset); void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) { struct iphdr *iph = ip_hdr(skb_in); int dataoff = ip_hdrlen(skb_in); u8 proto = iph->protocol; if (iph->frag_off & htons(IP_OFFSET)) return; if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(skb_in, dataoff, proto)) { icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); return; } if (nf_ip_checksum(skb_in, hook, dataoff, proto) == 0) icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); } EXPORT_SYMBOL_GPL(nf_send_unreach); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv4 packet rejection core"); |
| 6 6 5 24 24 23 7 1 1 7 14 14 1 13 4 4 3 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C)2003,2004 USAGI/WIDE Project * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_tunnel __rcu *tunnel6_handlers __read_mostly; static struct xfrm6_tunnel __rcu *tunnel46_handlers __read_mostly; static struct xfrm6_tunnel __rcu *tunnelmpls6_handlers __read_mostly; static DEFINE_MUTEX(tunnel6_mutex); static inline int xfrm6_tunnel_mpls_supported(void) { return IS_ENABLED(CONFIG_MPLS); } int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family) { struct xfrm6_tunnel __rcu **pprev; struct xfrm6_tunnel *t; int ret = -EEXIST; int priority = handler->priority; mutex_lock(&tunnel6_mutex); switch (family) { case AF_INET6: pprev = &tunnel6_handlers; break; case AF_INET: pprev = &tunnel46_handlers; break; case AF_MPLS: pprev = &tunnelmpls6_handlers; break; default: goto err; } for (; (t = rcu_dereference_protected(*pprev, lockdep_is_held(&tunnel6_mutex))) != NULL; pprev = &t->next) { if (t->priority > priority) break; if (t->priority == priority) goto err; } handler->next = *pprev; rcu_assign_pointer(*pprev, handler); ret = 0; err: mutex_unlock(&tunnel6_mutex); return ret; } EXPORT_SYMBOL(xfrm6_tunnel_register); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) { struct xfrm6_tunnel __rcu **pprev; struct xfrm6_tunnel *t; int ret = -ENOENT; mutex_lock(&tunnel6_mutex); switch (family) { case AF_INET6: pprev = &tunnel6_handlers; break; case AF_INET: pprev = &tunnel46_handlers; break; case AF_MPLS: pprev = &tunnelmpls6_handlers; break; default: goto err; } for (; (t = rcu_dereference_protected(*pprev, lockdep_is_held(&tunnel6_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } err: mutex_unlock(&tunnel6_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_tunnel_deregister); #define for_each_tunnel_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int tunnelmpls6_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for_each_tunnel_rcu(tunnelmpls6_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int tunnel6_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } #if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) static int tunnel6_rcv_cb(struct sk_buff *skb, u8 proto, int err) { struct xfrm6_tunnel __rcu *head; struct xfrm6_tunnel *handler; int ret; head = (proto == IPPROTO_IPV6) ? tunnel6_handlers : tunnel46_handlers; for_each_tunnel_rcu(head, handler) { if (handler->cb_handler) { ret = handler->cb_handler(skb, err); if (ret <= 0) return ret; } } return 0; } static const struct xfrm_input_afinfo tunnel6_input_afinfo = { .family = AF_INET6, .is_ipip = true, .callback = tunnel6_rcv_cb, }; #endif static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int tunnelmpls6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnelmpls6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol tunnel6_protocol = { .handler = tunnel6_rcv, .err_handler = tunnel6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static const struct inet6_protocol tunnel46_protocol = { .handler = tunnel46_rcv, .err_handler = tunnel46_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static const struct inet6_protocol tunnelmpls6_protocol = { .handler = tunnelmpls6_rcv, .err_handler = tunnelmpls6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static int __init tunnel6_init(void) { if (inet6_add_protocol(&tunnel6_protocol, IPPROTO_IPV6)) { pr_err("%s: can't add protocol\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&tunnel46_protocol, IPPROTO_IPIP)) { pr_err("%s: can't add protocol\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); return -EAGAIN; } if (xfrm6_tunnel_mpls_supported() && inet6_add_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS)) { pr_err("%s: can't add protocol\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); return -EAGAIN; } #if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) if (xfrm_input_register_afinfo(&tunnel6_input_afinfo)) { pr_err("%s: can't add input afinfo\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); if (xfrm6_tunnel_mpls_supported()) inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS); return -EAGAIN; } #endif return 0; } static void __exit tunnel6_fini(void) { #if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) if (xfrm_input_unregister_afinfo(&tunnel6_input_afinfo)) pr_err("%s: can't remove input afinfo\n", __func__); #endif if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) pr_err("%s: can't remove protocol\n", __func__); if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) pr_err("%s: can't remove protocol\n", __func__); if (xfrm6_tunnel_mpls_supported() && inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS)) pr_err("%s: can't remove protocol\n", __func__); } module_init(tunnel6_init); module_exit(tunnel6_fini); MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver"); MODULE_LICENSE("GPL"); |
| 29894 14912 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC_H #define _ASM_X86_ATOMIC_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> #include <asm/barrier.h> /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. */ static __always_inline int arch_atomic_read(const atomic_t *v) { /* * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here, * it's non-inlined function that increases binary size and stack usage. */ return __READ_ONCE((v)->counter); } static __always_inline void arch_atomic_set(atomic_t *v, int i) { __WRITE_ONCE(v->counter, i); } static __always_inline void arch_atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline void arch_atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i); } #define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_dec arch_atomic_dec static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e); } #define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e); } #define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i); } #define arch_atomic_add_negative arch_atomic_add_negative static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } #define arch_atomic_add_return arch_atomic_add_return #define arch_atomic_sub_return(i, v) arch_atomic_add_return(-(i), v) static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); } #define arch_atomic_fetch_add arch_atomic_fetch_add #define arch_atomic_fetch_sub(i, v) arch_atomic_fetch_add(-(i), v) static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { return arch_cmpxchg(&v->counter, old, new); } #define arch_atomic_cmpxchg arch_atomic_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { return arch_try_cmpxchg(&v->counter, old, new); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg static __always_inline int arch_atomic_xchg(atomic_t *v, int new) { return arch_xchg(&v->counter, new); } #define arch_atomic_xchg arch_atomic_xchg static __always_inline void arch_atomic_and(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "andl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i)); return val; } #define arch_atomic_fetch_and arch_atomic_fetch_and static __always_inline void arch_atomic_or(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "orl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i)); return val; } #define arch_atomic_fetch_or arch_atomic_fetch_or static __always_inline void arch_atomic_xor(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "xorl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i)); return val; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else # include <asm/atomic64_64.h> #endif #endif /* _ASM_X86_ATOMIC_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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/arch/x86_64/mm/init.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2000 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2002,2003 Andi Kleen <ak@suse.de> */ #include <linux/signal.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/ptrace.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/initrd.h> #include <linux/pagemap.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/pci.h> #include <linux/pfn.h> #include <linux/poison.h> #include <linux/dma-mapping.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/memremap.h> #include <linux/nmi.h> #include <linux/gfp.h> #include <linux/kcore.h> #include <linux/bootmem_info.h> #include <asm/processor.h> #include <asm/bios_ebda.h> #include <linux/uaccess.h> #include <asm/pgalloc.h> #include <asm/dma.h> #include <asm/fixmap.h> #include <asm/e820/api.h> #include <asm/apic.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/smp.h> #include <asm/sections.h> #include <asm/kdebug.h> #include <asm/numa.h> #include <asm/set_memory.h> #include <asm/init.h> #include <asm/uv/uv.h> #include <asm/setup.h> #include <asm/ftrace.h> #include "mm_internal.h" #include "ident_map.c" #define DEFINE_POPULATE(fname, type1, type2, init) \ static inline void fname##_init(struct mm_struct *mm, \ type1##_t *arg1, type2##_t *arg2, bool init) \ { \ if (init) \ fname##_safe(mm, arg1, arg2); \ else \ fname(mm, arg1, arg2); \ } DEFINE_POPULATE(p4d_populate, p4d, pud, init) DEFINE_POPULATE(pgd_populate, pgd, p4d, init) DEFINE_POPULATE(pud_populate, pud, pmd, init) DEFINE_POPULATE(pmd_populate_kernel, pmd, pte, init) #define DEFINE_ENTRY(type1, type2, init) \ static inline void set_##type1##_init(type1##_t *arg1, \ type2##_t arg2, bool init) \ { \ if (init) \ set_##type1##_safe(arg1, arg2); \ else \ set_##type1(arg1, arg2); \ } DEFINE_ENTRY(p4d, p4d, init) DEFINE_ENTRY(pud, pud, init) DEFINE_ENTRY(pmd, pmd, init) DEFINE_ENTRY(pte, pte, init) static inline pgprot_t prot_sethuge(pgprot_t prot) { WARN_ON_ONCE(pgprot_val(prot) & _PAGE_PAT); return __pgprot(pgprot_val(prot) | _PAGE_PSE); } /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the * physical space so we can cache the place of the first one and move * around without checking the pgd every time. */ /* Bits supported by the hardware: */ pteval_t __supported_pte_mask __read_mostly = ~0; /* Bits allowed in normal kernel mappings: */ pteval_t __default_kernel_pte_mask __read_mostly = ~0; EXPORT_SYMBOL_GPL(__supported_pte_mask); /* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */ EXPORT_SYMBOL(__default_kernel_pte_mask); int force_personality32; /* * noexec32=on|off * Control non executable heap for 32bit processes. * * on PROT_READ does not imply PROT_EXEC for 32-bit processes (default) * off PROT_READ implies PROT_EXEC */ static int __init nonx32_setup(char *str) { if (!strcmp(str, "on")) force_personality32 &= ~READ_IMPLIES_EXEC; else if (!strcmp(str, "off")) force_personality32 |= READ_IMPLIES_EXEC; return 1; } __setup("noexec32=", nonx32_setup); static void sync_global_pgds_l5(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { const pgd_t *pgd_ref = pgd_offset_k(addr); struct page *page; /* Check for overflow */ if (addr < start) break; if (pgd_none(*pgd_ref)) continue; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(addr); /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); if (pgd_none(*pgd)) set_pgd(pgd, *pgd_ref); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } static void sync_global_pgds_l4(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { pgd_t *pgd_ref = pgd_offset_k(addr); const p4d_t *p4d_ref; struct page *page; /* * With folded p4d, pgd_none() is always false, we need to * handle synchronization on p4d level. */ MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref)); p4d_ref = p4d_offset(pgd_ref, addr); if (p4d_none(*p4d_ref)) continue; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; p4d_t *p4d; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(addr); p4d = p4d_offset(pgd, addr); /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); if (!p4d_none(*p4d_ref) && !p4d_none(*p4d)) BUG_ON(p4d_pgtable(*p4d) != p4d_pgtable(*p4d_ref)); if (p4d_none(*p4d)) set_p4d(p4d, *p4d_ref); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } /* * When memory was added make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ static void sync_global_pgds(unsigned long start, unsigned long end) { if (pgtable_l5_enabled()) sync_global_pgds_l5(start, end); else sync_global_pgds_l4(start, end); } /* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. */ static __ref void *spp_getpage(void) { void *ptr; if (after_bootmem) ptr = (void *) get_zeroed_page(GFP_ATOMIC); else ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) { panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem ? "after bootmem" : ""); } pr_debug("spp_getpage %p\n", ptr); return ptr; } static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr) { if (pgd_none(*pgd)) { p4d_t *p4d = (p4d_t *)spp_getpage(); pgd_populate(&init_mm, pgd, p4d); if (p4d != p4d_offset(pgd, 0)) printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", p4d, p4d_offset(pgd, 0)); } return p4d_offset(pgd, vaddr); } static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr) { if (p4d_none(*p4d)) { pud_t *pud = (pud_t *)spp_getpage(); p4d_populate(&init_mm, p4d, pud); if (pud != pud_offset(p4d, 0)) printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", pud, pud_offset(p4d, 0)); } return pud_offset(p4d, vaddr); } static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) { if (pud_none(*pud)) { pmd_t *pmd = (pmd_t *) spp_getpage(); pud_populate(&init_mm, pud, pmd); if (pmd != pmd_offset(pud, 0)) printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n", pmd, pmd_offset(pud, 0)); } return pmd_offset(pud, vaddr); } static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr) { if (pmd_none(*pmd)) { pte_t *pte = (pte_t *) spp_getpage(); pmd_populate_kernel(&init_mm, pmd, pte); if (pte != pte_offset_kernel(pmd, 0)) printk(KERN_ERR "PAGETABLE BUG #03!\n"); } return pte_offset_kernel(pmd, vaddr); } static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) { pmd_t *pmd = fill_pmd(pud, vaddr); pte_t *pte = fill_pte(pmd, vaddr); set_pte(pte, new_pte); /* * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) { p4d_t *p4d = p4d_page + p4d_index(vaddr); pud_t *pud = fill_pud(p4d, vaddr); __set_pte_vaddr(pud, vaddr, new_pte); } void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) { pud_t *pud = pud_page + pud_index(vaddr); __set_pte_vaddr(pud, vaddr, new_pte); } void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; p4d_t *p4d_page; pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval)); pgd = pgd_offset_k(vaddr); if (pgd_none(*pgd)) { printk(KERN_ERR "PGD FIXMAP MISSING, it should be setup in head.S!\n"); return; } p4d_page = p4d_offset(pgd, 0); set_pte_vaddr_p4d(p4d_page, vaddr, pteval); } pmd_t * __init populate_extra_pmd(unsigned long vaddr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(vaddr); p4d = fill_p4d(pgd, vaddr); pud = fill_pud(p4d, vaddr); return fill_pmd(pud, vaddr); } pte_t * __init populate_extra_pte(unsigned long vaddr) { pmd_t *pmd; pmd = populate_extra_pmd(vaddr); return fill_pte(pmd, vaddr); } /* * Create large page table mappings for a range of physical addresses. */ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, enum page_cache_mode cache) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgprot_t prot; pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) | protval_4k_2_large(cachemode2protval(cache)); BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK)); for (; size; phys += PMD_SIZE, size -= PMD_SIZE) { pgd = pgd_offset_k((unsigned long)__va(phys)); if (pgd_none(*pgd)) { p4d = (p4d_t *) spp_getpage(); set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE | _PAGE_USER)); } p4d = p4d_offset(pgd, (unsigned long)__va(phys)); if (p4d_none(*p4d)) { pud = (pud_t *) spp_getpage(); set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE | _PAGE_USER)); } pud = pud_offset(p4d, (unsigned long)__va(phys)); if (pud_none(*pud)) { pmd = (pmd_t *) spp_getpage(); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); } pmd = pmd_offset(pud, phys); BUG_ON(!pmd_none(*pmd)); set_pmd(pmd, __pmd(phys | pgprot_val(prot))); } } void __init init_extra_mapping_wb(unsigned long phys, unsigned long size) { __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB); } void __init init_extra_mapping_uc(unsigned long phys, unsigned long size) { __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC); } /* * The head.S code sets up the kernel high mapping: * * from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text) * * phys_base holds the negative offset to the kernel, which is added * to the compile time generated pmds. This results in invalid pmds up * to the point where we hit the physaddr 0 mapping. * * We limit the mappings to the region from _text to _brk_end. _brk_end * is rounded up to the 2MB boundary. This catches the invalid pmds as * well, as they are located before _text: */ void __init cleanup_highmap(void) { unsigned long vaddr = __START_KERNEL_map; unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE; unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1; pmd_t *pmd = level2_kernel_pgt; /* * Native path, max_pfn_mapped is not set yet. * Xen has valid max_pfn_mapped set in * arch/x86/xen/mmu.c:xen_setup_kernel_pagetable(). */ if (max_pfn_mapped) vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT); for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; if (vaddr < (unsigned long) _text || vaddr > end) set_pmd(pmd, __pmd(0)); } } /* * Create PTE level page table mapping for physical addresses. * It returns the last physical address mapped. */ static unsigned long __meminit phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, pgprot_t prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; pte_t *pte; int i; pte = pte_page + pte_index(paddr); i = pte_index(paddr); for (; i < PTRS_PER_PTE; i++, paddr = paddr_next, pte++) { paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_RESERVED_KERN) && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_ACPI)) set_pte_init(pte, __pte(0), init); continue; } /* * We will re-use the existing mapping. * Xen for example has some special requirements, like mapping * pagetable pages as RO. So assume someone who pre-setup * these mappings are more intelligent. */ if (!pte_none(*pte)) { if (!after_bootmem) pages++; continue; } if (0) pr_info(" pte=%p addr=%lx pte=%016lx\n", pte, paddr, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte); pages++; set_pte_init(pte, pfn_pte(paddr >> PAGE_SHIFT, prot), init); paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE; } update_page_count(PG_LEVEL_4K, pages); return paddr_last; } /* * Create PMD level page table mapping for physical addresses. The virtual * and physical address have to be aligned at this level. * It returns the last physical address mapped. */ static unsigned long __meminit phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; int i = pmd_index(paddr); for (; i < PTRS_PER_PMD; i++, paddr = paddr_next) { pmd_t *pmd = pmd_page + pmd_index(paddr); pte_t *pte; pgprot_t new_prot = prot; paddr_next = (paddr & PMD_MASK) + PMD_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_RESERVED_KERN) && !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_ACPI)) set_pmd_init(pmd, __pmd(0), init); continue; } if (!pmd_none(*pmd)) { if (!pmd_leaf(*pmd)) { spin_lock(&init_mm.page_table_lock); pte = (pte_t *)pmd_page_vaddr(*pmd); paddr_last = phys_pte_init(pte, paddr, paddr_end, prot, init); spin_unlock(&init_mm.page_table_lock); continue; } /* * If we are ok with PG_LEVEL_2M mapping, then we will * use the existing mapping, * * Otherwise, we will split the large page mapping but * use the same existing protection bits except for * large page, so that we don't violate Intel's TLB * Application note (317080) which says, while changing * the page sizes, new and old translations should * not differ with respect to page frame and * attributes. */ if (page_size_mask & (1 << PG_LEVEL_2M)) { if (!after_bootmem) pages++; paddr_last = paddr_next; continue; } new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd)); } if (page_size_mask & (1<<PG_LEVEL_2M)) { pages++; spin_lock(&init_mm.page_table_lock); set_pmd_init(pmd, pfn_pmd(paddr >> PAGE_SHIFT, prot_sethuge(prot)), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; continue; } pte = alloc_low_page(); paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot, init); spin_lock(&init_mm.page_table_lock); pmd_populate_kernel_init(&init_mm, pmd, pte, init); spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_2M, pages); return paddr_last; } /* * Create PUD level page table mapping for physical addresses. The virtual * and physical address do not have to be aligned at this level. KASLR can * randomize virtual addresses up to this level. * It returns the last physical address mapped. */ static unsigned long __meminit phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t _prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; unsigned long vaddr = (unsigned long)__va(paddr); int i = pud_index(vaddr); for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) { pud_t *pud; pmd_t *pmd; pgprot_t prot = _prot; vaddr = (unsigned long)__va(paddr); pud = pud_page + pud_index(vaddr); paddr_next = (paddr & PUD_MASK) + PUD_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_RESERVED_KERN) && !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_ACPI)) set_pud_init(pud, __pud(0), init); continue; } if (!pud_none(*pud)) { if (!pud_leaf(*pud)) { pmd = pmd_offset(pud, 0); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, page_size_mask, prot, init); continue; } /* * If we are ok with PG_LEVEL_1G mapping, then we will * use the existing mapping. * * Otherwise, we will split the gbpage mapping but use * the same existing protection bits except for large * page, so that we don't violate Intel's TLB * Application note (317080) which says, while changing * the page sizes, new and old translations should * not differ with respect to page frame and * attributes. */ if (page_size_mask & (1 << PG_LEVEL_1G)) { if (!after_bootmem) pages++; paddr_last = paddr_next; continue; } prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud)); } if (page_size_mask & (1<<PG_LEVEL_1G)) { pages++; spin_lock(&init_mm.page_table_lock); set_pud_init(pud, pfn_pud(paddr >> PAGE_SHIFT, prot_sethuge(prot)), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; continue; } pmd = alloc_low_page(); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); pud_populate_init(&init_mm, pud, pmd, init); spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_1G, pages); return paddr_last; } static unsigned long __meminit phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot, bool init) { unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last; paddr_last = paddr_end; vaddr = (unsigned long)__va(paddr); vaddr_end = (unsigned long)__va(paddr_end); if (!pgtable_l5_enabled()) return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask, prot, init); for (; vaddr < vaddr_end; vaddr = vaddr_next) { p4d_t *p4d = p4d_page + p4d_index(vaddr); pud_t *pud; vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE; paddr = __pa(vaddr); if (paddr >= paddr_end) { paddr_next = __pa(vaddr_next); if (!after_bootmem && !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RESERVED_KERN) && !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_ACPI)) set_p4d_init(p4d, __p4d(0), init); continue; } if (!p4d_none(*p4d)) { pud = pud_offset(p4d, 0); paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), page_size_mask, prot, init); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); p4d_populate_init(&init_mm, p4d, pud, init); spin_unlock(&init_mm.page_table_lock); } return paddr_last; } static unsigned long __meminit __kernel_physical_mapping_init(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot, bool init) { bool pgd_changed = false; unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last; paddr_last = paddr_end; vaddr = (unsigned long)__va(paddr_start); vaddr_end = (unsigned long)__va(paddr_end); vaddr_start = vaddr; for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); p4d_t *p4d; vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; if (pgd_val(*pgd)) { p4d = (p4d_t *)pgd_page_vaddr(*pgd); paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask, prot, init); continue; } p4d = alloc_low_page(); paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); if (pgtable_l5_enabled()) pgd_populate_init(&init_mm, pgd, p4d, init); else p4d_populate_init(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d, init); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } if (pgd_changed) sync_global_pgds(vaddr_start, vaddr_end - 1); return paddr_last; } /* * Create page table mapping for the physical memory for specific physical * addresses. Note that it can only be used to populate non-present entries. * The virtual and physical addresses have to be aligned on PMD level * down. It returns the last physical address mapped. */ unsigned long __meminit kernel_physical_mapping_init(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot) { return __kernel_physical_mapping_init(paddr_start, paddr_end, page_size_mask, prot, true); } /* * This function is similar to kernel_physical_mapping_init() above with the * exception that it uses set_{pud,pmd}() instead of the set_{pud,pte}_safe() * when updating the mapping. The caller is responsible to flush the TLBs after * the function returns. */ unsigned long __meminit kernel_physical_mapping_change(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask) { return __kernel_physical_mapping_init(paddr_start, paddr_end, page_size_mask, PAGE_KERNEL, false); } #ifndef CONFIG_NUMA void __init initmem_init(void) { memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); } #endif void __init paging_init(void) { sparse_init(); /* * clear the default setting with node 0 * note: don't use nodes_clear here, that is really clearing when * numa support is not compiled in, and later node_set_state * will not set it back. */ node_clear_state(0, N_MEMORY); node_clear_state(0, N_NORMAL_MEMORY); zone_sizes_init(); } #ifdef CONFIG_SPARSEMEM_VMEMMAP #define PAGE_UNUSED 0xFD /* * The unused vmemmap range, which was not yet memset(PAGE_UNUSED), ranges * from unused_pmd_start to next PMD_SIZE boundary. */ static unsigned long unused_pmd_start __meminitdata; static void __meminit vmemmap_flush_unused_pmd(void) { if (!unused_pmd_start) return; /* * Clears (unused_pmd_start, PMD_END] */ memset((void *)unused_pmd_start, PAGE_UNUSED, ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start); unused_pmd_start = 0; } #ifdef CONFIG_MEMORY_HOTPLUG /* Returns true if the PMD is completely unused and thus it can be freed */ static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end) { unsigned long start = ALIGN_DOWN(addr, PMD_SIZE); /* * Flush the unused range cache to ensure that memchr_inv() will work * for the whole range. */ vmemmap_flush_unused_pmd(); memset((void *)addr, PAGE_UNUSED, end - addr); return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE); } #endif static void __meminit __vmemmap_use_sub_pmd(unsigned long start) { /* * As we expect to add in the same granularity as we remove, it's * sufficient to mark only some piece used to block the memmap page from * getting removed when removing some other adjacent memmap (just in * case the first memmap never gets initialized e.g., because the memory * block never gets onlined). */ memset((void *)start, 0, sizeof(struct page)); } static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end) { /* * We only optimize if the new used range directly follows the * previously unused range (esp., when populating consecutive sections). */ if (unused_pmd_start == start) { if (likely(IS_ALIGNED(end, PMD_SIZE))) unused_pmd_start = 0; else unused_pmd_start = end; return; } /* * If the range does not contiguously follows previous one, make sure * to mark the unused range of the previous one so it can be removed. */ vmemmap_flush_unused_pmd(); __vmemmap_use_sub_pmd(start); } static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end) { const unsigned long page = ALIGN_DOWN(start, PMD_SIZE); vmemmap_flush_unused_pmd(); /* * Could be our memmap page is filled with PAGE_UNUSED already from a * previous remove. Make sure to reset it. */ __vmemmap_use_sub_pmd(start); /* * Mark with PAGE_UNUSED the unused parts of the new memmap range */ if (!IS_ALIGNED(start, PMD_SIZE)) memset((void *)page, PAGE_UNUSED, start - page); /* * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of * consecutive sections. Remember for the last added PMD where the * unused range begins. */ if (!IS_ALIGNED(end, PMD_SIZE)) unused_pmd_start = end; } #endif /* * Memory hotplug specific functions */ #ifdef CONFIG_MEMORY_HOTPLUG /* * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need * updating. */ static void update_end_of_memory_vars(u64 start, u64 size) { unsigned long end_pfn = PFN_UP(start + size); if (end_pfn > max_pfn) { max_pfn = end_pfn; max_low_pfn = end_pfn; high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; } } int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; if (WARN_ON_ONCE(end > DIRECT_MAP_PHYSMEM_END)) return -ERANGE; ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); /* update max_pfn, max_low_pfn and high_memory */ update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); return ret; } int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; init_memory_mapping(start, start + size, params->pgprot); return add_pages(nid, start_pfn, nr_pages, params); } static void free_reserved_pages(struct page *page, unsigned long nr_pages) { while (nr_pages--) free_reserved_page(page++); } static void __meminit free_pagetable(struct page *page, int order) { /* bootmem page has reserved flag */ if (PageReserved(page)) { unsigned long nr_pages = 1 << order; #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE enum bootmem_type type = bootmem_type(page); if (type == SECTION_INFO || type == MIX_SECTION_INFO) { while (nr_pages--) put_page_bootmem(page++); } else { free_reserved_pages(page, nr_pages); } #else free_reserved_pages(page, nr_pages); #endif } else { free_pages((unsigned long)page_address(page), order); } } static void __meminit free_hugepage_table(struct page *page, struct vmem_altmap *altmap) { if (altmap) vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE); else free_pagetable(page, get_order(PMD_SIZE)); } static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) { pte_t *pte; int i; for (i = 0; i < PTRS_PER_PTE; i++) { pte = pte_start + i; if (!pte_none(*pte)) return; } /* free a pte table */ free_pagetable(pmd_page(*pmd), 0); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) { pmd_t *pmd; int i; for (i = 0; i < PTRS_PER_PMD; i++) { pmd = pmd_start + i; if (!pmd_none(*pmd)) return; } /* free a pmd table */ free_pagetable(pud_page(*pud), 0); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); } static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) { pud_t *pud; int i; for (i = 0; i < PTRS_PER_PUD; i++) { pud = pud_start + i; if (!pud_none(*pud)) return; } /* free a pud table */ free_pagetable(p4d_page(*p4d), 0); spin_lock(&init_mm.page_table_lock); p4d_clear(p4d); spin_unlock(&init_mm.page_table_lock); } static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, bool direct) { unsigned long next, pages = 0; pte_t *pte; phys_addr_t phys_addr; pte = pte_start + pte_index(addr); for (; addr < end; addr = next, pte++) { next = (addr + PAGE_SIZE) & PAGE_MASK; if (next > end) next = end; if (!pte_present(*pte)) continue; /* * We mapped [0,1G) memory as identity mapping when * initializing, in arch/x86/kernel/head_64.S. These * pagetables cannot be removed. */ phys_addr = pte_val(*pte) + (addr & PAGE_MASK); if (phys_addr < (phys_addr_t)0x40000000) return; if (!direct) free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); spin_unlock(&init_mm.page_table_lock); /* For non-direct mapping, pages means nothing. */ pages++; } /* Call free_pte_table() in remove_pmd_table(). */ flush_tlb_all(); if (direct) update_page_count(PG_LEVEL_4K, -pages); } static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, bool direct, struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte_base; pmd_t *pmd; pmd = pmd_start + pmd_index(addr); for (; addr < end; addr = next, pmd++) { next = pmd_addr_end(addr, end); if (!pmd_present(*pmd)) continue; if (pmd_leaf(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE)) { if (!direct) free_hugepage_table(pmd_page(*pmd), altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); pages++; } #ifdef CONFIG_SPARSEMEM_VMEMMAP else if (vmemmap_pmd_is_unused(addr, next)) { free_hugepage_table(pmd_page(*pmd), altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } #endif continue; } pte_base = (pte_t *)pmd_page_vaddr(*pmd); remove_pte_table(pte_base, addr, next, direct); free_pte_table(pte_base, pmd); } /* Call free_pmd_table() in remove_pud_table(). */ if (direct) update_page_count(PG_LEVEL_2M, -pages); } static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pmd_t *pmd_base; pud_t *pud; pud = pud_start + pud_index(addr); for (; addr < end; addr = next, pud++) { next = pud_addr_end(addr, end); if (!pud_present(*pud)) continue; if (pud_leaf(*pud) && IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); pages++; continue; } pmd_base = pmd_offset(pud, 0); remove_pmd_table(pmd_base, addr, next, direct, altmap); free_pmd_table(pmd_base, pud); } if (direct) update_page_count(PG_LEVEL_1G, -pages); } static void __meminit remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pud_t *pud_base; p4d_t *p4d; p4d = p4d_start + p4d_index(addr); for (; addr < end; addr = next, p4d++) { next = p4d_addr_end(addr, end); if (!p4d_present(*p4d)) continue; BUILD_BUG_ON(p4d_leaf(*p4d)); pud_base = pud_offset(p4d, 0); remove_pud_table(pud_base, addr, next, altmap, direct); /* * For 4-level page tables we do not want to free PUDs, but in the * 5-level case we should free them. This code will have to change * to adapt for boot-time switching between 4 and 5 level page tables. */ if (pgtable_l5_enabled()) free_pud_table(pud_base, p4d); } if (direct) update_page_count(PG_LEVEL_512G, -pages); } /* start and end are both virtual address. */ static void __meminit remove_pagetable(unsigned long start, unsigned long end, bool direct, struct vmem_altmap *altmap) { unsigned long next; unsigned long addr; pgd_t *pgd; p4d_t *p4d; for (addr = start; addr < end; addr = next) { next = pgd_addr_end(addr, end); pgd = pgd_offset_k(addr); if (!pgd_present(*pgd)) continue; p4d = p4d_offset(pgd, 0); remove_p4d_table(p4d, addr, next, altmap, direct); } flush_tlb_all(); } void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); remove_pagetable(start, end, false, altmap); } static void __meminit kernel_physical_mapping_remove(unsigned long start, unsigned long end) { start = (unsigned long)__va(start); end = (unsigned long)__va(end); remove_pagetable(start, end, true, NULL); } void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ static struct kcore_list kcore_vsyscall; static void __init register_page_bootmem_info(void) { #if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP) int i; for_each_online_node(i) register_page_bootmem_info_node(NODE_DATA(i)); #endif } /* * Pre-allocates page-table pages for the vmalloc area in the kernel page-table. * Only the level which needs to be synchronized between all page-tables is * allocated because the synchronization can be expensive. */ static void __init preallocate_vmalloc_pages(void) { unsigned long addr; const char *lvl; for (addr = VMALLOC_START; addr <= VMEMORY_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; lvl = "p4d"; p4d = p4d_alloc(&init_mm, pgd, addr); if (!p4d) goto failed; if (pgtable_l5_enabled()) continue; /* * The goal here is to allocate all possibly required * hardware page tables pointed to by the top hardware * level. * * On 4-level systems, the P4D layer is folded away and * the above code does no preallocation. Below, go down * to the pud _software_ level to ensure the second * hardware level is allocated on 4-level systems too. */ lvl = "pud"; pud = pud_alloc(&init_mm, p4d, addr); if (!pud) goto failed; } return; failed: /* * The pages have to be there now or they will be missing in * process page-tables later. */ panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl); } void __init mem_init(void) { pci_iommu_alloc(); /* clear_bss() already clear the empty_zero_page */ /* this will put all memory onto the freelists */ memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been * initialized, and memblock_free_all() initializes all the reserved * deferred pages for us. */ register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ if (get_gate_vma(&init_mm)) kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); preallocate_vmalloc_pages(); } int kernel_set_to_readonly; void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long rodata_start = PFN_ALIGN(__start_rodata); unsigned long end = (unsigned long)__end_rodata_hpage_align; unsigned long text_end = PFN_ALIGN(_etext); unsigned long rodata_end = PFN_ALIGN(__end_rodata); unsigned long all_end; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); kernel_set_to_readonly = 1; /* * The rodata/data/bss/brk section (but not the kernel text!) * should also be not-executable. * * We align all_end to PMD_SIZE because the existing mapping * is a full PMD. If we would align _brk_end to PAGE_SIZE we * split the PMD and the reminder between _brk_end and the end * of the PMD will remain mapped executable. * * Any PMD which was setup after the one which covers _brk_end * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); set_ftrace_ops_ro(); #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); set_memory_rw(start, (end-start) >> PAGE_SHIFT); printk(KERN_INFO "Testing CPA: again\n"); set_memory_ro(start, (end-start) >> PAGE_SHIFT); #endif free_kernel_image_pages("unused kernel image (text/rodata gap)", (void *)text_end, (void *)rodata_start); free_kernel_image_pages("unused kernel image (rodata/data gap)", (void *)rodata_end, (void *)_sdata); } /* * Block size is the minimum amount of memory which can be hotplugged or * hotremoved. It must be power of two and must be equal or larger than * MIN_MEMORY_BLOCK_SIZE. */ #define MAX_BLOCK_SIZE (2UL << 30) /* Amount of ram needed to start using large blocks */ #define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30) /* Adjustable memory block size */ static unsigned long set_memory_block_size; int __init set_memory_block_size_order(unsigned int order) { unsigned long size = 1UL << order; if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE) return -EINVAL; set_memory_block_size = size; return 0; } static unsigned long probe_memory_block_size(void) { unsigned long boot_mem_end = max_pfn << PAGE_SHIFT; unsigned long bz; /* If memory block size has been set, then use it */ bz = set_memory_block_size; if (bz) goto done; /* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */ if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) { bz = MIN_MEMORY_BLOCK_SIZE; goto done; } /* * Use max block size to minimize overhead on bare metal, where * alignment for memory hotplug isn't a concern. */ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { bz = MAX_BLOCK_SIZE; goto done; } /* Find the largest allowed block size that aligns to memory end */ for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) { if (IS_ALIGNED(boot_mem_end, bz)) break; } done: pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20); return bz; } static unsigned long memory_block_size_probed; unsigned long memory_block_size_bytes(void) { if (!memory_block_size_probed) memory_block_size_probed = probe_memory_block_size(); return memory_block_size_probed; } #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. */ static long __meminitdata addr_start, addr_end; static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, unsigned long addr, unsigned long next) { pte_t entry; entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL_LARGE); set_pmd(pmd, __pmd(pte_val(entry))); /* check to see if we have contiguous blocks */ if (p_end != p || node_start != node) { if (p_start) pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); addr_start = addr; node_start = node; p_start = p; } addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; if (!IS_ALIGNED(addr, PMD_SIZE) || !IS_ALIGNED(next, PMD_SIZE)) vmemmap_use_new_sub_pmd(addr, next); } int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next) { int large = pmd_leaf(*pmd); if (pmd_leaf(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); vmemmap_use_sub_pmd(addr, next); } return large; } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { int err; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); if (end - start < PAGES_PER_SECTION * sizeof(struct page)) err = vmemmap_populate_basepages(start, end, node, NULL); else if (boot_cpu_has(X86_FEATURE_PSE)) err = vmemmap_populate_hugepages(start, end, node, altmap); else if (altmap) { pr_err_once("%s: no cpu support for altmap allocations\n", __func__); err = -ENOMEM; } else err = vmemmap_populate_basepages(start, end, node, NULL); if (!err) sync_global_pgds(start, end - 1); return err; } #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long nr_pages) { unsigned long addr = (unsigned long)start_page; unsigned long end = (unsigned long)(start_page + nr_pages); unsigned long next; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; unsigned int nr_pmd_pages; struct page *page; for (; addr < end; addr = next) { pte_t *pte = NULL; pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; } get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO); p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; } get_page_bootmem(section_nr, p4d_page(*p4d), MIX_SECTION_INFO); pud = pud_offset(p4d, addr); if (pud_none(*pud)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; } get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); if (!boot_cpu_has(X86_FEATURE_PSE)) { next = (addr + PAGE_SIZE) & PAGE_MASK; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) continue; get_page_bootmem(section_nr, pmd_page(*pmd), MIX_SECTION_INFO); pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) continue; get_page_bootmem(section_nr, pte_page(*pte), SECTION_INFO); } else { next = pmd_addr_end(addr, end); pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) continue; nr_pmd_pages = 1 << get_order(PMD_SIZE); page = pmd_page(*pmd); while (nr_pmd_pages--) get_page_bootmem(section_nr, page++, SECTION_INFO); } } } #endif void __meminit vmemmap_populate_print_last(void) { if (p_start) { pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); p_start = NULL; p_end = NULL; node_start = 0; } } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NET_TIMESTAMPING_H_ #define _LINUX_NET_TIMESTAMPING_H_ #include <uapi/linux/net_tstamp.h> #define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ SOF_TIMESTAMPING_TX_SOFTWARE | \ SOF_TIMESTAMPING_SOFTWARE) #define SOF_TIMESTAMPING_HARDWARE_MASK (SOF_TIMESTAMPING_RX_HARDWARE | \ SOF_TIMESTAMPING_TX_HARDWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) enum hwtstamp_source { HWTSTAMP_SOURCE_UNSPEC, HWTSTAMP_SOURCE_NETDEV, HWTSTAMP_SOURCE_PHYLIB, }; /** * struct hwtstamp_provider_desc - hwtstamp provider description * * @index: index of the hwtstamp provider. * @qualifier: hwtstamp provider qualifier. */ struct hwtstamp_provider_desc { int index; enum hwtstamp_provider_qualifier qualifier; }; /** * struct hwtstamp_provider - hwtstamp provider object * * @rcu_head: RCU callback used to free the struct. * @source: source of the hwtstamp provider. * @phydev: pointer of the phydev source in case a PTP coming from phylib * @desc: hwtstamp provider description. */ struct hwtstamp_provider { struct rcu_head rcu_head; enum hwtstamp_source source; struct phy_device *phydev; struct hwtstamp_provider_desc desc; }; /** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * * @flags: see struct hwtstamp_config * @tx_type: see struct hwtstamp_config * @rx_filter: see struct hwtstamp_config * @ifr: pointer to ifreq structure from the original ioctl request, to pass to * a legacy implementation of a lower driver * @copied_to_user: request was passed to a legacy implementation which already * copied the ioctl request back to user space * @source: indication whether timestamps should come from the netdev or from * an attached phylib PHY * @qualifier: qualifier of the hwtstamp provider * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config * exposed to the %SIOCGHWTSTAMP and %SIOCSHWTSTAMP ioctl UAPI. */ struct kernel_hwtstamp_config { int flags; int tx_type; int rx_filter; struct ifreq *ifr; bool copied_to_user; enum hwtstamp_source source; enum hwtstamp_provider_qualifier qualifier; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, const struct hwtstamp_config *cfg) { kernel_cfg->flags = cfg->flags; kernel_cfg->tx_type = cfg->tx_type; kernel_cfg->rx_filter = cfg->rx_filter; } static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg, const struct kernel_hwtstamp_config *kernel_cfg) { cfg->flags = kernel_cfg->flags; cfg->tx_type = kernel_cfg->tx_type; cfg->rx_filter = kernel_cfg->rx_filter; } static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a, const struct kernel_hwtstamp_config *b) { return a->flags != b->flags || a->tx_type != b->tx_type || a->rx_filter != b->rx_filter; } #endif /* _LINUX_NET_TIMESTAMPING_H_ */ |
| 192 82 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Symmetric key ciphers. * * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_SKCIPHER_H #define _CRYPTO_INTERNAL_SKCIPHER_H #include <crypto/algapi.h> #include <crypto/internal/cipher.h> #include <crypto/skcipher.h> #include <linux/types.h> /* * Set this if your algorithm is sync but needs a reqsize larger * than MAX_SYNC_SKCIPHER_REQSIZE. * * Reuse bit that is specific to hash algorithms. */ #define CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE CRYPTO_ALG_OPTIONAL_KEY struct aead_request; struct rtattr; struct skcipher_instance { void (*free)(struct skcipher_instance *inst); union { struct { char head[offsetof(struct skcipher_alg, base)]; struct crypto_instance base; } s; struct skcipher_alg alg; }; }; struct lskcipher_instance { void (*free)(struct lskcipher_instance *inst); union { struct { char head[offsetof(struct lskcipher_alg, co.base)]; struct crypto_instance base; } s; struct lskcipher_alg alg; }; }; struct crypto_skcipher_spawn { struct crypto_spawn base; }; struct crypto_lskcipher_spawn { struct crypto_spawn base; }; struct skcipher_walk { union { struct { void *addr; } virt; } src, dst; struct scatter_walk in; unsigned int nbytes; struct scatter_walk out; unsigned int total; u8 *page; u8 *buffer; u8 *oiv; void *iv; unsigned int ivsize; int flags; unsigned int blocksize; unsigned int stride; unsigned int alignmask; }; static inline struct crypto_instance *skcipher_crypto_instance( struct skcipher_instance *inst) { return &inst->s.base; } static inline struct crypto_instance *lskcipher_crypto_instance( struct lskcipher_instance *inst) { return &inst->s.base; } static inline struct skcipher_instance *skcipher_alg_instance( struct crypto_skcipher *skcipher) { return container_of(crypto_skcipher_alg(skcipher), struct skcipher_instance, alg); } static inline struct lskcipher_instance *lskcipher_alg_instance( struct crypto_lskcipher *lskcipher) { return container_of(crypto_lskcipher_alg(lskcipher), struct lskcipher_instance, alg); } static inline void *skcipher_instance_ctx(struct skcipher_instance *inst) { return crypto_instance_ctx(skcipher_crypto_instance(inst)); } static inline void *lskcipher_instance_ctx(struct lskcipher_instance *inst) { return crypto_instance_ctx(lskcipher_crypto_instance(inst)); } static inline void skcipher_request_complete(struct skcipher_request *req, int err) { crypto_request_complete(&req->base, err); } int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); int crypto_grab_lskcipher(struct crypto_lskcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline void crypto_drop_lskcipher(struct crypto_lskcipher_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct lskcipher_alg *crypto_lskcipher_spawn_alg( struct crypto_lskcipher_spawn *spawn) { return container_of(spawn->base.alg, struct lskcipher_alg, co.base); } static inline struct skcipher_alg_common *crypto_spawn_skcipher_alg_common( struct crypto_skcipher_spawn *spawn) { return container_of(spawn->base.alg, struct skcipher_alg_common, base); } static inline struct lskcipher_alg *crypto_spawn_lskcipher_alg( struct crypto_lskcipher_spawn *spawn) { return crypto_lskcipher_spawn_alg(spawn); } static inline struct crypto_skcipher *crypto_spawn_skcipher( struct crypto_skcipher_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_lskcipher *crypto_spawn_lskcipher( struct crypto_lskcipher_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline void crypto_skcipher_set_reqsize( struct crypto_skcipher *skcipher, unsigned int reqsize) { skcipher->reqsize = reqsize; } static inline void crypto_skcipher_set_reqsize_dma( struct crypto_skcipher *skcipher, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); skcipher->reqsize = reqsize; } int crypto_register_skcipher(struct skcipher_alg *alg); void crypto_unregister_skcipher(struct skcipher_alg *alg); int crypto_register_skciphers(struct skcipher_alg *algs, int count); void crypto_unregister_skciphers(struct skcipher_alg *algs, int count); int skcipher_register_instance(struct crypto_template *tmpl, struct skcipher_instance *inst); int crypto_register_lskcipher(struct lskcipher_alg *alg); void crypto_unregister_lskcipher(struct lskcipher_alg *alg); int crypto_register_lskciphers(struct lskcipher_alg *algs, int count); void crypto_unregister_lskciphers(struct lskcipher_alg *algs, int count); int lskcipher_register_instance(struct crypto_template *tmpl, struct lskcipher_instance *inst); int skcipher_walk_done(struct skcipher_walk *walk, int res); int skcipher_walk_virt(struct skcipher_walk *walk, struct skcipher_request *req, bool atomic); int skcipher_walk_aead_encrypt(struct skcipher_walk *walk, struct aead_request *req, bool atomic); int skcipher_walk_aead_decrypt(struct skcipher_walk *walk, struct aead_request *req, bool atomic); static inline void skcipher_walk_abort(struct skcipher_walk *walk) { skcipher_walk_done(walk, -ECANCELED); } static inline void *crypto_skcipher_ctx(struct crypto_skcipher *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void *crypto_lskcipher_ctx(struct crypto_lskcipher *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void *crypto_skcipher_ctx_dma(struct crypto_skcipher *tfm) { return crypto_tfm_ctx_dma(&tfm->base); } static inline void *skcipher_request_ctx(struct skcipher_request *req) { return req->__ctx; } static inline void *skcipher_request_ctx_dma(struct skcipher_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(skcipher_request_ctx(req), align); } static inline u32 skcipher_request_flags(struct skcipher_request *req) { return req->base.flags; } /* Helpers for simple block cipher modes of operation */ struct skcipher_ctx_simple { struct crypto_cipher *cipher; /* underlying block cipher */ }; static inline struct crypto_cipher * skcipher_cipher_simple(struct crypto_skcipher *tfm) { struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); return ctx->cipher; } struct skcipher_instance *skcipher_alloc_instance_simple( struct crypto_template *tmpl, struct rtattr **tb); static inline struct crypto_alg *skcipher_ialg_simple( struct skcipher_instance *inst) { struct crypto_cipher_spawn *spawn = skcipher_instance_ctx(inst); return crypto_spawn_cipher_alg(spawn); } static inline struct crypto_lskcipher *lskcipher_cipher_simple( struct crypto_lskcipher *tfm) { struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm); return *ctx; } struct lskcipher_instance *lskcipher_alloc_instance_simple( struct crypto_template *tmpl, struct rtattr **tb); static inline struct lskcipher_alg *lskcipher_ialg_simple( struct lskcipher_instance *inst) { struct crypto_lskcipher_spawn *spawn = lskcipher_instance_ctx(inst); return crypto_lskcipher_spawn_alg(spawn); } #endif /* _CRYPTO_INTERNAL_SKCIPHER_H */ |
| 5 4 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2021 Facebook */ #ifndef __MMAP_UNLOCK_WORK_H__ #define __MMAP_UNLOCK_WORK_H__ #include <linux/irq_work.h> /* irq_work to run mmap_read_unlock() in irq_work */ struct mmap_unlock_irq_work { struct irq_work irq_work; struct mm_struct *mm; }; DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); /* * We cannot do mmap_read_unlock() when the irq is disabled, because of * risk to deadlock with rq_lock. To look up vma when the irqs are * disabled, we need to run mmap_read_unlock() in irq_work. We use a * percpu variable to do the irq_work. If the irq_work is already used * by another lookup, we fall over. */ static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr) { struct mmap_unlock_irq_work *work = NULL; bool irq_work_busy = false; if (irqs_disabled()) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { work = this_cpu_ptr(&mmap_unlock_work); if (irq_work_is_busy(&work->irq_work)) { /* cannot queue more up_read, fallback */ irq_work_busy = true; } } else { /* * PREEMPT_RT does not allow to trylock mmap sem in * interrupt disabled context. Force the fallback code. */ irq_work_busy = true; } } *work_ptr = work; return irq_work_busy; } static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm) { if (!work) { mmap_read_unlock(mm); } else { work->mm = mm; /* The lock will be released once we're out of interrupt * context. Tell lockdep that we've released it now so * it doesn't complain that we forgot to release it. */ rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); irq_work_queue(&work->irq_work); } } #endif /* __MMAP_UNLOCK_WORK_H__ */ |
| 41 75 31 75 75 86 86 86 76 75 75 106 106 75 75 75 85 107 1 106 75 75 31 31 31 4 2 2 2 2 2 118 32 86 86 85 84 2 85 85 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 | /* * Public API and common code for kernel->userspace relay file support. * * See Documentation/filesystems/relay.rst for an overview. * * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com) * * Moved to kernel/relay.c by Paul Mundt, 2006. * November 2006 - CPU hotplug support by Mathieu Desnoyers * (mathieu.desnoyers@polymtl.ca) * * This file is released under the GPL. */ #include <linux/errno.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/string.h> #include <linux/relay.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/cpu.h> #include <linux/splice.h> /* list of open channels, for cpu hotplug */ static DEFINE_MUTEX(relay_channels_mutex); static LIST_HEAD(relay_channels); /* * fault() vm_op implementation for relay file mapping. */ static vm_fault_t relay_buf_fault(struct vm_fault *vmf) { struct page *page; struct rchan_buf *buf = vmf->vma->vm_private_data; pgoff_t pgoff = vmf->pgoff; if (!buf) return VM_FAULT_OOM; page = vmalloc_to_page(buf->start + (pgoff << PAGE_SHIFT)); if (!page) return VM_FAULT_SIGBUS; get_page(page); vmf->page = page; return 0; } /* * vm_ops for relay file mappings. */ static const struct vm_operations_struct relay_file_mmap_ops = { .fault = relay_buf_fault, }; /* * allocate an array of pointers of struct page */ static struct page **relay_alloc_page_array(unsigned int n_pages) { return kvcalloc(n_pages, sizeof(struct page *), GFP_KERNEL); } /* * free an array of pointers of struct page */ static void relay_free_page_array(struct page **array) { kvfree(array); } /** * relay_mmap_buf: - mmap channel buffer to process address space * @buf: relay channel buffer * @vma: vm_area_struct describing memory to be mapped * * Returns 0 if ok, negative on error * * Caller should already have grabbed mmap_lock. */ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) { unsigned long length = vma->vm_end - vma->vm_start; if (!buf) return -EBADF; if (length != (unsigned long)buf->chan->alloc_size) return -EINVAL; vma->vm_ops = &relay_file_mmap_ops; vm_flags_set(vma, VM_DONTEXPAND); vma->vm_private_data = buf; return 0; } /** * relay_alloc_buf - allocate a channel buffer * @buf: the buffer struct * @size: total size of the buffer * * Returns a pointer to the resulting buffer, %NULL if unsuccessful. The * passed in size will get page aligned, if it isn't already. */ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size) { void *mem; unsigned int i, j, n_pages; *size = PAGE_ALIGN(*size); n_pages = *size >> PAGE_SHIFT; buf->page_array = relay_alloc_page_array(n_pages); if (!buf->page_array) return NULL; for (i = 0; i < n_pages; i++) { buf->page_array[i] = alloc_page(GFP_KERNEL); if (unlikely(!buf->page_array[i])) goto depopulate; set_page_private(buf->page_array[i], (unsigned long)buf); } mem = vmap(buf->page_array, n_pages, VM_MAP, PAGE_KERNEL); if (!mem) goto depopulate; memset(mem, 0, *size); buf->page_count = n_pages; return mem; depopulate: for (j = 0; j < i; j++) __free_page(buf->page_array[j]); relay_free_page_array(buf->page_array); return NULL; } /** * relay_create_buf - allocate and initialize a channel buffer * @chan: the relay channel * * Returns channel buffer if successful, %NULL otherwise. */ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t), GFP_KERNEL); if (!buf->padding) goto free_buf; buf->start = relay_alloc_buf(buf, &chan->alloc_size); if (!buf->start) goto free_buf; buf->chan = chan; kref_get(&buf->chan->kref); return buf; free_buf: kfree(buf->padding); kfree(buf); return NULL; } /** * relay_destroy_channel - free the channel struct * @kref: target kernel reference that contains the relay channel * * Should only be called from kref_put(). */ static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); free_percpu(chan->buf); kfree(chan); } /** * relay_destroy_buf - destroy an rchan_buf struct and associated buffer * @buf: the buffer struct */ static void relay_destroy_buf(struct rchan_buf *buf) { struct rchan *chan = buf->chan; unsigned int i; if (likely(buf->start)) { vunmap(buf->start); for (i = 0; i < buf->page_count; i++) __free_page(buf->page_array[i]); relay_free_page_array(buf->page_array); } *per_cpu_ptr(chan->buf, buf->cpu) = NULL; kfree(buf->padding); kfree(buf); kref_put(&chan->kref, relay_destroy_channel); } /** * relay_remove_buf - remove a channel buffer * @kref: target kernel reference that contains the relay buffer * * Removes the file from the filesystem, which also frees the * rchan_buf_struct and the channel buffer. Should only be called from * kref_put(). */ static void relay_remove_buf(struct kref *kref) { struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref); relay_destroy_buf(buf); } /** * relay_buf_empty - boolean, is the channel buffer empty? * @buf: channel buffer * * Returns 1 if the buffer is empty, 0 otherwise. */ static int relay_buf_empty(struct rchan_buf *buf) { return (buf->subbufs_produced - buf->subbufs_consumed) ? 0 : 1; } /** * relay_buf_full - boolean, is the channel buffer full? * @buf: channel buffer * * Returns 1 if the buffer is full, 0 otherwise. */ int relay_buf_full(struct rchan_buf *buf) { size_t ready = buf->subbufs_produced - buf->subbufs_consumed; return (ready >= buf->chan->n_subbufs) ? 1 : 0; } EXPORT_SYMBOL_GPL(relay_buf_full); /* * High-level relay kernel API and associated functions. */ static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding) { if (!buf->chan->cb->subbuf_start) return !relay_buf_full(buf); return buf->chan->cb->subbuf_start(buf, subbuf, prev_subbuf, prev_padding); } /** * wakeup_readers - wake up readers waiting on a channel * @work: contains the channel buffer * * This is the function used to defer reader waking */ static void wakeup_readers(struct irq_work *work) { struct rchan_buf *buf; buf = container_of(work, struct rchan_buf, wakeup_work); wake_up_interruptible(&buf->read_wait); } /** * __relay_reset - reset a channel buffer * @buf: the channel buffer * @init: 1 if this is a first-time initialization * * See relay_reset() for description of effect. */ static void __relay_reset(struct rchan_buf *buf, unsigned int init) { size_t i; if (init) { init_waitqueue_head(&buf->read_wait); kref_init(&buf->kref); init_irq_work(&buf->wakeup_work, wakeup_readers); } else { irq_work_sync(&buf->wakeup_work); } buf->subbufs_produced = 0; buf->subbufs_consumed = 0; buf->bytes_consumed = 0; buf->finalized = 0; buf->data = buf->start; buf->offset = 0; for (i = 0; i < buf->chan->n_subbufs; i++) buf->padding[i] = 0; relay_subbuf_start(buf, buf->data, NULL, 0); } /** * relay_reset - reset the channel * @chan: the channel * * This has the effect of erasing all data from all channel buffers * and restarting the channel in its initial state. The buffers * are not freed, so any mappings are still in effect. * * NOTE. Care should be taken that the channel isn't actually * being used by anything when this call is made. */ void relay_reset(struct rchan *chan) { struct rchan_buf *buf; unsigned int i; if (!chan) return; if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) { __relay_reset(buf, 0); return; } mutex_lock(&relay_channels_mutex); for_each_possible_cpu(i) if ((buf = *per_cpu_ptr(chan->buf, i))) __relay_reset(buf, 0); mutex_unlock(&relay_channels_mutex); } EXPORT_SYMBOL_GPL(relay_reset); static inline void relay_set_buf_dentry(struct rchan_buf *buf, struct dentry *dentry) { buf->dentry = dentry; d_inode(buf->dentry)->i_size = buf->early_bytes; } static struct dentry *relay_create_buf_file(struct rchan *chan, struct rchan_buf *buf, unsigned int cpu) { struct dentry *dentry; char *tmpname; tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL); if (!tmpname) return NULL; snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu); /* Create file in fs */ dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, buf, &chan->is_global); if (IS_ERR(dentry)) dentry = NULL; kfree(tmpname); return dentry; } /* * relay_open_buf - create a new relay channel buffer * * used by relay_open() and CPU hotplug. */ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) { struct rchan_buf *buf; struct dentry *dentry; if (chan->is_global) return *per_cpu_ptr(chan->buf, 0); buf = relay_create_buf(chan); if (!buf) return NULL; if (chan->has_base_filename) { dentry = relay_create_buf_file(chan, buf, cpu); if (!dentry) goto free_buf; relay_set_buf_dentry(buf, dentry); } else { /* Only retrieve global info, nothing more, nothing less */ dentry = chan->cb->create_buf_file(NULL, NULL, S_IRUSR, buf, &chan->is_global); if (IS_ERR_OR_NULL(dentry)) goto free_buf; } buf->cpu = cpu; __relay_reset(buf, 1); if(chan->is_global) { *per_cpu_ptr(chan->buf, 0) = buf; buf->cpu = 0; } return buf; free_buf: relay_destroy_buf(buf); return NULL; } /** * relay_close_buf - close a channel buffer * @buf: channel buffer * * Marks the buffer finalized and restores the default callbacks. * The channel buffer and channel buffer data structure are then freed * automatically when the last reference is given up. */ static void relay_close_buf(struct rchan_buf *buf) { buf->finalized = 1; irq_work_sync(&buf->wakeup_work); buf->chan->cb->remove_buf_file(buf->dentry); kref_put(&buf->kref, relay_remove_buf); } int relay_prepare_cpu(unsigned int cpu) { struct rchan *chan; struct rchan_buf *buf; mutex_lock(&relay_channels_mutex); list_for_each_entry(chan, &relay_channels, list) { if (*per_cpu_ptr(chan->buf, cpu)) continue; buf = relay_open_buf(chan, cpu); if (!buf) { pr_err("relay: cpu %d buffer creation failed\n", cpu); mutex_unlock(&relay_channels_mutex); return -ENOMEM; } *per_cpu_ptr(chan->buf, cpu) = buf; } mutex_unlock(&relay_channels_mutex); return 0; } /** * relay_open - create a new relay channel * @base_filename: base name of files to create, %NULL for buffering only * @parent: dentry of parent directory, %NULL for root directory or buffer * @subbuf_size: size of sub-buffers * @n_subbufs: number of sub-buffers * @cb: client callback functions * @private_data: user-defined data * * Returns channel pointer if successful, %NULL otherwise. * * Creates a channel buffer for each cpu using the sizes and * attributes specified. The created channel buffer files * will be named base_filename0...base_filenameN-1. File * permissions will be %S_IRUSR. * * If opening a buffer (@parent = NULL) that you later wish to register * in a filesystem, call relay_late_setup_files() once the @parent dentry * is available. */ struct rchan *relay_open(const char *base_filename, struct dentry *parent, size_t subbuf_size, size_t n_subbufs, const struct rchan_callbacks *cb, void *private_data) { unsigned int i; struct rchan *chan; struct rchan_buf *buf; if (!(subbuf_size && n_subbufs)) return NULL; if (subbuf_size > UINT_MAX / n_subbufs) return NULL; if (!cb || !cb->create_buf_file || !cb->remove_buf_file) return NULL; chan = kzalloc(sizeof(struct rchan), GFP_KERNEL); if (!chan) return NULL; chan->buf = alloc_percpu(struct rchan_buf *); if (!chan->buf) { kfree(chan); return NULL; } chan->version = RELAYFS_CHANNEL_VERSION; chan->n_subbufs = n_subbufs; chan->subbuf_size = subbuf_size; chan->alloc_size = PAGE_ALIGN(subbuf_size * n_subbufs); chan->parent = parent; chan->private_data = private_data; if (base_filename) { chan->has_base_filename = 1; strscpy(chan->base_filename, base_filename, NAME_MAX); } chan->cb = cb; kref_init(&chan->kref); mutex_lock(&relay_channels_mutex); for_each_online_cpu(i) { buf = relay_open_buf(chan, i); if (!buf) goto free_bufs; *per_cpu_ptr(chan->buf, i) = buf; } list_add(&chan->list, &relay_channels); mutex_unlock(&relay_channels_mutex); return chan; free_bufs: for_each_possible_cpu(i) { if ((buf = *per_cpu_ptr(chan->buf, i))) relay_close_buf(buf); } kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); return NULL; } EXPORT_SYMBOL_GPL(relay_open); struct rchan_percpu_buf_dispatcher { struct rchan_buf *buf; struct dentry *dentry; }; /* Called in atomic context. */ static void __relay_set_buf_dentry(void *info) { struct rchan_percpu_buf_dispatcher *p = info; relay_set_buf_dentry(p->buf, p->dentry); } /** * relay_late_setup_files - triggers file creation * @chan: channel to operate on * @base_filename: base name of files to create * @parent: dentry of parent directory, %NULL for root directory * * Returns 0 if successful, non-zero otherwise. * * Use to setup files for a previously buffer-only channel created * by relay_open() with a NULL parent dentry. * * For example, this is useful for perfomring early tracing in kernel, * before VFS is up and then exposing the early results once the dentry * is available. */ int relay_late_setup_files(struct rchan *chan, const char *base_filename, struct dentry *parent) { int err = 0; unsigned int i, curr_cpu; unsigned long flags; struct dentry *dentry; struct rchan_buf *buf; struct rchan_percpu_buf_dispatcher disp; if (!chan || !base_filename) return -EINVAL; strscpy(chan->base_filename, base_filename, NAME_MAX); mutex_lock(&relay_channels_mutex); /* Is chan already set up? */ if (unlikely(chan->has_base_filename)) { mutex_unlock(&relay_channels_mutex); return -EEXIST; } chan->has_base_filename = 1; chan->parent = parent; if (chan->is_global) { err = -EINVAL; buf = *per_cpu_ptr(chan->buf, 0); if (!WARN_ON_ONCE(!buf)) { dentry = relay_create_buf_file(chan, buf, 0); if (dentry && !WARN_ON_ONCE(!chan->is_global)) { relay_set_buf_dentry(buf, dentry); err = 0; } } mutex_unlock(&relay_channels_mutex); return err; } curr_cpu = get_cpu(); /* * The CPU hotplug notifier ran before us and created buffers with * no files associated. So it's safe to call relay_setup_buf_file() * on all currently online CPUs. */ for_each_online_cpu(i) { buf = *per_cpu_ptr(chan->buf, i); if (unlikely(!buf)) { WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n"); err = -EINVAL; break; } dentry = relay_create_buf_file(chan, buf, i); if (unlikely(!dentry)) { err = -EINVAL; break; } if (curr_cpu == i) { local_irq_save(flags); relay_set_buf_dentry(buf, dentry); local_irq_restore(flags); } else { disp.buf = buf; disp.dentry = dentry; smp_mb(); /* relay_channels_mutex must be held, so wait. */ err = smp_call_function_single(i, __relay_set_buf_dentry, &disp, 1); } if (unlikely(err)) break; } put_cpu(); mutex_unlock(&relay_channels_mutex); return err; } EXPORT_SYMBOL_GPL(relay_late_setup_files); /** * relay_switch_subbuf - switch to a new sub-buffer * @buf: channel buffer * @length: size of current event * * Returns either the length passed in or 0 if full. * * Performs sub-buffer-switch tasks such as invoking callbacks, * updating padding counts, waking up readers, etc. */ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) { void *old, *new; size_t old_subbuf, new_subbuf; if (unlikely(length > buf->chan->subbuf_size)) goto toobig; if (buf->offset != buf->chan->subbuf_size + 1) { buf->prev_padding = buf->chan->subbuf_size - buf->offset; old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; buf->padding[old_subbuf] = buf->prev_padding; buf->subbufs_produced++; if (buf->dentry) d_inode(buf->dentry)->i_size += buf->chan->subbuf_size - buf->padding[old_subbuf]; else buf->early_bytes += buf->chan->subbuf_size - buf->padding[old_subbuf]; smp_mb(); if (waitqueue_active(&buf->read_wait)) { /* * Calling wake_up_interruptible() from here * will deadlock if we happen to be logging * from the scheduler (trying to re-grab * rq->lock), so defer it. */ irq_work_queue(&buf->wakeup_work); } } old = buf->data; new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; new = buf->start + new_subbuf * buf->chan->subbuf_size; buf->offset = 0; if (!relay_subbuf_start(buf, new, old, buf->prev_padding)) { buf->offset = buf->chan->subbuf_size + 1; return 0; } buf->data = new; buf->padding[new_subbuf] = 0; if (unlikely(length + buf->offset > buf->chan->subbuf_size)) goto toobig; return length; toobig: buf->chan->last_toobig = length; return 0; } EXPORT_SYMBOL_GPL(relay_switch_subbuf); /** * relay_subbufs_consumed - update the buffer's sub-buffers-consumed count * @chan: the channel * @cpu: the cpu associated with the channel buffer to update * @subbufs_consumed: number of sub-buffers to add to current buf's count * * Adds to the channel buffer's consumed sub-buffer count. * subbufs_consumed should be the number of sub-buffers newly consumed, * not the total consumed. * * NOTE. Kernel clients don't need to call this function if the channel * mode is 'overwrite'. */ void relay_subbufs_consumed(struct rchan *chan, unsigned int cpu, size_t subbufs_consumed) { struct rchan_buf *buf; if (!chan || cpu >= NR_CPUS) return; buf = *per_cpu_ptr(chan->buf, cpu); if (!buf || subbufs_consumed > chan->n_subbufs) return; if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed) buf->subbufs_consumed = buf->subbufs_produced; else buf->subbufs_consumed += subbufs_consumed; } EXPORT_SYMBOL_GPL(relay_subbufs_consumed); /** * relay_close - close the channel * @chan: the channel * * Closes all channel buffers and frees the channel. */ void relay_close(struct rchan *chan) { struct rchan_buf *buf; unsigned int i; if (!chan) return; mutex_lock(&relay_channels_mutex); if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) relay_close_buf(buf); else for_each_possible_cpu(i) if ((buf = *per_cpu_ptr(chan->buf, i))) relay_close_buf(buf); if (chan->last_toobig) printk(KERN_WARNING "relay: one or more items not logged " "[item size (%zd) > sub-buffer size (%zd)]\n", chan->last_toobig, chan->subbuf_size); list_del(&chan->list); kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); } EXPORT_SYMBOL_GPL(relay_close); /** * relay_flush - close the channel * @chan: the channel * * Flushes all channel buffers, i.e. forces buffer switch. */ void relay_flush(struct rchan *chan) { struct rchan_buf *buf; unsigned int i; if (!chan) return; if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) { relay_switch_subbuf(buf, 0); return; } mutex_lock(&relay_channels_mutex); for_each_possible_cpu(i) if ((buf = *per_cpu_ptr(chan->buf, i))) relay_switch_subbuf(buf, 0); mutex_unlock(&relay_channels_mutex); } EXPORT_SYMBOL_GPL(relay_flush); /** * relay_file_open - open file op for relay files * @inode: the inode * @filp: the file * * Increments the channel buffer refcount. */ static int relay_file_open(struct inode *inode, struct file *filp) { struct rchan_buf *buf = inode->i_private; kref_get(&buf->kref); filp->private_data = buf; return nonseekable_open(inode, filp); } /** * relay_file_mmap - mmap file op for relay files * @filp: the file * @vma: the vma describing what to map * * Calls upon relay_mmap_buf() to map the file into user space. */ static int relay_file_mmap(struct file *filp, struct vm_area_struct *vma) { struct rchan_buf *buf = filp->private_data; return relay_mmap_buf(buf, vma); } /** * relay_file_poll - poll file op for relay files * @filp: the file * @wait: poll table * * Poll implemention. */ static __poll_t relay_file_poll(struct file *filp, poll_table *wait) { __poll_t mask = 0; struct rchan_buf *buf = filp->private_data; if (buf->finalized) return EPOLLERR; if (filp->f_mode & FMODE_READ) { poll_wait(filp, &buf->read_wait, wait); if (!relay_buf_empty(buf)) mask |= EPOLLIN | EPOLLRDNORM; } return mask; } /** * relay_file_release - release file op for relay files * @inode: the inode * @filp: the file * * Decrements the channel refcount, as the filesystem is * no longer using it. */ static int relay_file_release(struct inode *inode, struct file *filp) { struct rchan_buf *buf = filp->private_data; kref_put(&buf->kref, relay_remove_buf); return 0; } /* * relay_file_read_consume - update the consumed count for the buffer */ static void relay_file_read_consume(struct rchan_buf *buf, size_t read_pos, size_t bytes_consumed) { size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t read_subbuf; if (buf->subbufs_produced == buf->subbufs_consumed && buf->offset == buf->bytes_consumed) return; if (buf->bytes_consumed + bytes_consumed > subbuf_size) { relay_subbufs_consumed(buf->chan, buf->cpu, 1); buf->bytes_consumed = 0; } buf->bytes_consumed += bytes_consumed; if (!read_pos) read_subbuf = buf->subbufs_consumed % n_subbufs; else read_subbuf = read_pos / buf->chan->subbuf_size; if (buf->bytes_consumed + buf->padding[read_subbuf] == subbuf_size) { if ((read_subbuf == buf->subbufs_produced % n_subbufs) && (buf->offset == subbuf_size)) return; relay_subbufs_consumed(buf->chan, buf->cpu, 1); buf->bytes_consumed = 0; } } /* * relay_file_read_avail - boolean, are there unconsumed bytes available? */ static int relay_file_read_avail(struct rchan_buf *buf) { size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t produced = buf->subbufs_produced; size_t consumed; relay_file_read_consume(buf, 0, 0); consumed = buf->subbufs_consumed; if (unlikely(buf->offset > subbuf_size)) { if (produced == consumed) return 0; return 1; } if (unlikely(produced - consumed >= n_subbufs)) { consumed = produced - n_subbufs + 1; buf->subbufs_consumed = consumed; buf->bytes_consumed = 0; } produced = (produced % n_subbufs) * subbuf_size + buf->offset; consumed = (consumed % n_subbufs) * subbuf_size + buf->bytes_consumed; if (consumed > produced) produced += n_subbufs * subbuf_size; if (consumed == produced) { if (buf->offset == subbuf_size && buf->subbufs_produced > buf->subbufs_consumed) return 1; return 0; } return 1; } /** * relay_file_read_subbuf_avail - return bytes available in sub-buffer * @read_pos: file read position * @buf: relay channel buffer */ static size_t relay_file_read_subbuf_avail(size_t read_pos, struct rchan_buf *buf) { size_t padding, avail = 0; size_t read_subbuf, read_offset, write_subbuf, write_offset; size_t subbuf_size = buf->chan->subbuf_size; write_subbuf = (buf->data - buf->start) / subbuf_size; write_offset = buf->offset > subbuf_size ? subbuf_size : buf->offset; read_subbuf = read_pos / subbuf_size; read_offset = read_pos % subbuf_size; padding = buf->padding[read_subbuf]; if (read_subbuf == write_subbuf) { if (read_offset + padding < write_offset) avail = write_offset - (read_offset + padding); } else avail = (subbuf_size - padding) - read_offset; return avail; } /** * relay_file_read_start_pos - find the first available byte to read * @buf: relay channel buffer * * If the read_pos is in the middle of padding, return the * position of the first actually available byte, otherwise * return the original value. */ static size_t relay_file_read_start_pos(struct rchan_buf *buf) { size_t read_subbuf, padding, padding_start, padding_end; size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) % (n_subbufs * subbuf_size); read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; padding_start = (read_subbuf + 1) * subbuf_size - padding; padding_end = (read_subbuf + 1) * subbuf_size; if (read_pos >= padding_start && read_pos < padding_end) { read_subbuf = (read_subbuf + 1) % n_subbufs; read_pos = read_subbuf * subbuf_size; } return read_pos; } /** * relay_file_read_end_pos - return the new read position * @read_pos: file read position * @buf: relay channel buffer * @count: number of bytes to be read */ static size_t relay_file_read_end_pos(struct rchan_buf *buf, size_t read_pos, size_t count) { size_t read_subbuf, padding, end_pos; size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; if (read_pos % subbuf_size + count + padding == subbuf_size) end_pos = (read_subbuf + 1) * subbuf_size; else end_pos = read_pos + count; if (end_pos >= subbuf_size * n_subbufs) end_pos = 0; return end_pos; } static ssize_t relay_file_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct rchan_buf *buf = filp->private_data; size_t read_start, avail; size_t written = 0; int ret; if (!count) return 0; inode_lock(file_inode(filp)); do { void *from; if (!relay_file_read_avail(buf)) break; read_start = relay_file_read_start_pos(buf); avail = relay_file_read_subbuf_avail(read_start, buf); if (!avail) break; avail = min(count, avail); from = buf->start + read_start; ret = avail; if (copy_to_user(buffer, from, avail)) break; buffer += ret; written += ret; count -= ret; relay_file_read_consume(buf, read_start, ret); *ppos = relay_file_read_end_pos(buf, read_start, ret); } while (count); inode_unlock(file_inode(filp)); return written; } const struct file_operations relay_file_operations = { .open = relay_file_open, .poll = relay_file_poll, .mmap = relay_file_mmap, .read = relay_file_read, .release = relay_file_release, }; EXPORT_SYMBOL_GPL(relay_file_operations); |
| 157 128 25 26 25 128 38 144 142 8 98 4 95 1 1 2 1 2 1 2 4 3 175 170 6 99 25 78 45 31 3 3 11 11 3 3 2 4 11 8 6 11 9 2 6 3 3 67 67 38 1 1 1 32 5 157 123 4 1 6 4 4 51 67 67 81 78 7 81 1 72 5 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * Added support for a Unix98-style ptmx device. * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998 * */ #include <linux/module.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/fcntl.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/major.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/device.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/devpts_fs.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/ioctl.h> #include <linux/compat.h> #include "tty.h" #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP # define tty_debug_hangup(tty, f, args...) tty_debug(tty, f, ##args) #else # define tty_debug_hangup(tty, f, args...) do {} while (0) #endif #ifdef CONFIG_UNIX98_PTYS static struct tty_driver *ptm_driver; static struct tty_driver *pts_driver; static DEFINE_MUTEX(devpts_mutex); #endif static void pty_close(struct tty_struct *tty, struct file *filp) { if (tty->driver->subtype == PTY_TYPE_MASTER) WARN_ON(tty->count > 1); else { if (tty_io_error(tty)) return; if (tty->count > 2) return; } set_bit(TTY_IO_ERROR, &tty->flags); wake_up_interruptible(&tty->read_wait); wake_up_interruptible(&tty->write_wait); spin_lock_irq(&tty->ctrl.lock); tty->ctrl.packet = false; spin_unlock_irq(&tty->ctrl.lock); /* Review - krefs on tty_link ?? */ if (!tty->link) return; set_bit(TTY_OTHER_CLOSED, &tty->link->flags); wake_up_interruptible(&tty->link->read_wait); wake_up_interruptible(&tty->link->write_wait); if (tty->driver->subtype == PTY_TYPE_MASTER) { set_bit(TTY_OTHER_CLOSED, &tty->flags); #ifdef CONFIG_UNIX98_PTYS if (tty->driver == ptm_driver) { mutex_lock(&devpts_mutex); if (tty->link->driver_data) devpts_pty_kill(tty->link->driver_data); mutex_unlock(&devpts_mutex); } #endif tty_vhangup(tty->link); } } /* * The unthrottle routine is called by the line discipline to signal * that it can receive more characters. For PTY's, the TTY_THROTTLED * flag is always set, to force the line discipline to always call the * unthrottle routine when there are fewer than TTY_THRESHOLD_UNTHROTTLE * characters in the queue. This is necessary since each time this * happens, we need to wake up any sleeping processes that could be * (1) trying to send data to the pty, or (2) waiting in wait_until_sent() * for the pty buffer to be drained. */ static void pty_unthrottle(struct tty_struct *tty) { tty_wakeup(tty->link); set_bit(TTY_THROTTLED, &tty->flags); } /** * pty_write - write to a pty * @tty: the tty we write from * @buf: kernel buffer of data * @c: bytes to write * * Our "hardware" write method. Data is coming from the ldisc which * may be in a non sleeping state. We simply throw this at the other * end of the link as if we were an IRQ handler receiving stuff for * the other side of the pty/tty pair. */ static ssize_t pty_write(struct tty_struct *tty, const u8 *buf, size_t c) { struct tty_struct *to = tty->link; if (tty->flow.stopped || !c) return 0; return tty_insert_flip_string_and_push_buffer(to->port, buf, c); } /** * pty_write_room - write space * @tty: tty we are writing from * * Report how many bytes the ldisc can send into the queue for * the other device. */ static unsigned int pty_write_room(struct tty_struct *tty) { if (tty->flow.stopped) return 0; return tty_buffer_space_avail(tty->link->port); } /* Set the lock flag on a pty */ static int pty_set_lock(struct tty_struct *tty, int __user *arg) { int val; if (get_user(val, arg)) return -EFAULT; if (val) set_bit(TTY_PTY_LOCK, &tty->flags); else clear_bit(TTY_PTY_LOCK, &tty->flags); return 0; } static int pty_get_lock(struct tty_struct *tty, int __user *arg) { int locked = test_bit(TTY_PTY_LOCK, &tty->flags); return put_user(locked, arg); } /* Set the packet mode on a pty */ static int pty_set_pktmode(struct tty_struct *tty, int __user *arg) { int pktmode; if (get_user(pktmode, arg)) return -EFAULT; spin_lock_irq(&tty->ctrl.lock); if (pktmode) { if (!tty->ctrl.packet) { tty->link->ctrl.pktstatus = 0; smp_mb(); tty->ctrl.packet = true; } } else tty->ctrl.packet = false; spin_unlock_irq(&tty->ctrl.lock); return 0; } /* Get the packet mode of a pty */ static int pty_get_pktmode(struct tty_struct *tty, int __user *arg) { int pktmode = tty->ctrl.packet; return put_user(pktmode, arg); } /* Send a signal to the slave */ static int pty_signal(struct tty_struct *tty, int sig) { struct pid *pgrp; if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP) return -EINVAL; if (tty->link) { pgrp = tty_get_pgrp(tty->link); if (pgrp) kill_pgrp(pgrp, sig, 1); put_pid(pgrp); } return 0; } static void pty_flush_buffer(struct tty_struct *tty) { struct tty_struct *to = tty->link; if (!to) return; tty_buffer_flush(to, NULL); if (to->ctrl.packet) { spin_lock_irq(&tty->ctrl.lock); tty->ctrl.pktstatus |= TIOCPKT_FLUSHWRITE; wake_up_interruptible(&to->read_wait); spin_unlock_irq(&tty->ctrl.lock); } } static int pty_open(struct tty_struct *tty, struct file *filp) { if (!tty || !tty->link) return -ENODEV; if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) goto out; if (test_bit(TTY_PTY_LOCK, &tty->link->flags)) goto out; if (tty->driver->subtype == PTY_TYPE_SLAVE && tty->link->count != 1) goto out; clear_bit(TTY_IO_ERROR, &tty->flags); clear_bit(TTY_OTHER_CLOSED, &tty->link->flags); set_bit(TTY_THROTTLED, &tty->flags); return 0; out: set_bit(TTY_IO_ERROR, &tty->flags); return -EIO; } static void pty_set_termios(struct tty_struct *tty, const struct ktermios *old_termios) { /* See if packet mode change of state. */ if (tty->link && tty->link->ctrl.packet) { int extproc = (old_termios->c_lflag & EXTPROC) | L_EXTPROC(tty); int old_flow = ((old_termios->c_iflag & IXON) && (old_termios->c_cc[VSTOP] == '\023') && (old_termios->c_cc[VSTART] == '\021')); int new_flow = (I_IXON(tty) && STOP_CHAR(tty) == '\023' && START_CHAR(tty) == '\021'); if ((old_flow != new_flow) || extproc) { spin_lock_irq(&tty->ctrl.lock); if (old_flow != new_flow) { tty->ctrl.pktstatus &= ~(TIOCPKT_DOSTOP | TIOCPKT_NOSTOP); if (new_flow) tty->ctrl.pktstatus |= TIOCPKT_DOSTOP; else tty->ctrl.pktstatus |= TIOCPKT_NOSTOP; } if (extproc) tty->ctrl.pktstatus |= TIOCPKT_IOCTL; spin_unlock_irq(&tty->ctrl.lock); wake_up_interruptible(&tty->link->read_wait); } } tty->termios.c_cflag &= ~(CSIZE | PARENB); tty->termios.c_cflag |= (CS8 | CREAD); } /** * pty_resize - resize event * @tty: tty being resized * @ws: window size being set. * * Update the termios variables and send the necessary signals to * peform a terminal resize correctly */ static int pty_resize(struct tty_struct *tty, struct winsize *ws) { struct pid *pgrp, *rpgrp; struct tty_struct *pty = tty->link; /* For a PTY we need to lock the tty side */ mutex_lock(&tty->winsize_mutex); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; /* Signal the foreground process group of both ptys */ pgrp = tty_get_pgrp(tty); rpgrp = tty_get_pgrp(pty); if (pgrp) kill_pgrp(pgrp, SIGWINCH, 1); if (rpgrp != pgrp && rpgrp) kill_pgrp(rpgrp, SIGWINCH, 1); put_pid(pgrp); put_pid(rpgrp); tty->winsize = *ws; pty->winsize = *ws; /* Never used so will go away soon */ done: mutex_unlock(&tty->winsize_mutex); return 0; } /** * pty_start - start() handler * pty_stop - stop() handler * @tty: tty being flow-controlled * * Propagates the TIOCPKT status to the master pty. * * NB: only the master pty can be in packet mode so only the slave * needs start()/stop() handlers */ static void pty_start(struct tty_struct *tty) { unsigned long flags; if (tty->link && tty->link->ctrl.packet) { spin_lock_irqsave(&tty->ctrl.lock, flags); tty->ctrl.pktstatus &= ~TIOCPKT_STOP; tty->ctrl.pktstatus |= TIOCPKT_START; spin_unlock_irqrestore(&tty->ctrl.lock, flags); wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } } static void pty_stop(struct tty_struct *tty) { unsigned long flags; if (tty->link && tty->link->ctrl.packet) { spin_lock_irqsave(&tty->ctrl.lock, flags); tty->ctrl.pktstatus &= ~TIOCPKT_START; tty->ctrl.pktstatus |= TIOCPKT_STOP; spin_unlock_irqrestore(&tty->ctrl.lock, flags); wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } } /** * pty_common_install - set up the pty pair * @driver: the pty driver * @tty: the tty being instantiated * @legacy: true if this is BSD style * * Perform the initial set up for the tty/pty pair. Called from the * tty layer when the port is first opened. * * Locking: the caller must hold the tty_mutex */ static int pty_common_install(struct tty_driver *driver, struct tty_struct *tty, bool legacy) { struct tty_struct *o_tty; struct tty_port *ports[2]; int idx = tty->index; int retval = -ENOMEM; /* Opening the slave first has always returned -EIO */ if (driver->subtype != PTY_TYPE_MASTER) return -EIO; ports[0] = kmalloc(sizeof **ports, GFP_KERNEL); ports[1] = kmalloc(sizeof **ports, GFP_KERNEL); if (!ports[0] || !ports[1]) goto err; if (!try_module_get(driver->other->owner)) { /* This cannot in fact currently happen */ goto err; } o_tty = alloc_tty_struct(driver->other, idx); if (!o_tty) goto err_put_module; tty_set_lock_subclass(o_tty); lockdep_set_subclass(&o_tty->termios_rwsem, TTY_LOCK_SLAVE); if (legacy) { /* We always use new tty termios data so we can do this the easy way .. */ tty_init_termios(tty); tty_init_termios(o_tty); driver->other->ttys[idx] = o_tty; driver->ttys[idx] = tty; } else { memset(&tty->termios_locked, 0, sizeof(tty->termios_locked)); tty->termios = driver->init_termios; memset(&o_tty->termios_locked, 0, sizeof(tty->termios_locked)); o_tty->termios = driver->other->init_termios; } /* * Everything allocated ... set up the o_tty structure. */ tty_driver_kref_get(driver->other); /* Establish the links in both directions */ tty->link = o_tty; o_tty->link = tty; tty_port_init(ports[0]); tty_port_init(ports[1]); tty_buffer_set_limit(ports[0], 8192); tty_buffer_set_limit(ports[1], 8192); o_tty->port = ports[0]; tty->port = ports[1]; o_tty->port->itty = o_tty; tty_buffer_set_lock_subclass(o_tty->port); tty_driver_kref_get(driver); tty->count++; o_tty->count++; return 0; err_put_module: module_put(driver->other->owner); err: kfree(ports[0]); kfree(ports[1]); return retval; } static void pty_cleanup(struct tty_struct *tty) { tty_port_put(tty->port); } /* Traditional BSD devices */ #ifdef CONFIG_LEGACY_PTYS static int pty_install(struct tty_driver *driver, struct tty_struct *tty) { return pty_common_install(driver, tty, true); } static void pty_remove(struct tty_driver *driver, struct tty_struct *tty) { struct tty_struct *pair = tty->link; driver->ttys[tty->index] = NULL; if (pair) pair->driver->ttys[pair->index] = NULL; } static int pty_bsd_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { switch (cmd) { case TIOCSPTLCK: /* Set PT Lock (disallow slave open) */ return pty_set_lock(tty, (int __user *) arg); case TIOCGPTLCK: /* Get PT Lock status */ return pty_get_lock(tty, (int __user *)arg); case TIOCPKT: /* Set PT packet mode */ return pty_set_pktmode(tty, (int __user *)arg); case TIOCGPKT: /* Get PT packet mode */ return pty_get_pktmode(tty, (int __user *)arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); case TIOCGPTN: /* TTY returns ENOTTY, but glibc expects EINVAL here */ return -EINVAL; } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT static long pty_bsd_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { /* * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ return pty_bsd_ioctl(tty, cmd, (unsigned long)compat_ptr(arg)); } #else #define pty_bsd_compat_ioctl NULL #endif static int legacy_count = CONFIG_LEGACY_PTY_COUNT; /* * not really modular, but the easiest way to keep compat with existing * bootargs behaviour is to continue using module_param here. */ module_param(legacy_count, int, 0); /* * The master side of a pty can do TIOCSPTLCK and thus * has pty_bsd_ioctl. */ static const struct tty_operations master_pty_ops_bsd = { .install = pty_install, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .ioctl = pty_bsd_ioctl, .compat_ioctl = pty_bsd_compat_ioctl, .cleanup = pty_cleanup, .resize = pty_resize, .remove = pty_remove }; static const struct tty_operations slave_pty_ops_bsd = { .install = pty_install, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .set_termios = pty_set_termios, .cleanup = pty_cleanup, .resize = pty_resize, .start = pty_start, .stop = pty_stop, .remove = pty_remove }; static void __init legacy_pty_init(void) { struct tty_driver *pty_driver, *pty_slave_driver; if (legacy_count <= 0) return; pty_driver = tty_alloc_driver(legacy_count, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(pty_driver)) panic("Couldn't allocate pty driver"); pty_slave_driver = tty_alloc_driver(legacy_count, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(pty_slave_driver)) panic("Couldn't allocate pty slave driver"); pty_driver->driver_name = "pty_master"; pty_driver->name = "pty"; pty_driver->major = PTY_MASTER_MAJOR; pty_driver->minor_start = 0; pty_driver->type = TTY_DRIVER_TYPE_PTY; pty_driver->subtype = PTY_TYPE_MASTER; pty_driver->init_termios = tty_std_termios; pty_driver->init_termios.c_iflag = 0; pty_driver->init_termios.c_oflag = 0; pty_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pty_driver->init_termios.c_lflag = 0; pty_driver->init_termios.c_ispeed = 38400; pty_driver->init_termios.c_ospeed = 38400; pty_driver->other = pty_slave_driver; tty_set_operations(pty_driver, &master_pty_ops_bsd); pty_slave_driver->driver_name = "pty_slave"; pty_slave_driver->name = "ttyp"; pty_slave_driver->major = PTY_SLAVE_MAJOR; pty_slave_driver->minor_start = 0; pty_slave_driver->type = TTY_DRIVER_TYPE_PTY; pty_slave_driver->subtype = PTY_TYPE_SLAVE; pty_slave_driver->init_termios = tty_std_termios; pty_slave_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pty_slave_driver->init_termios.c_ispeed = 38400; pty_slave_driver->init_termios.c_ospeed = 38400; pty_slave_driver->other = pty_driver; tty_set_operations(pty_slave_driver, &slave_pty_ops_bsd); if (tty_register_driver(pty_driver)) panic("Couldn't register pty driver"); if (tty_register_driver(pty_slave_driver)) panic("Couldn't register pty slave driver"); } #else static inline void legacy_pty_init(void) { } #endif /* Unix98 devices */ #ifdef CONFIG_UNIX98_PTYS static struct cdev ptmx_cdev; /** * ptm_open_peer - open the peer of a pty * @master: the open struct file of the ptmx device node * @tty: the master of the pty being opened * @flags: the flags for open * * Provide a race free way for userspace to open the slave end of a pty * (where they have the master fd and cannot access or trust the mount * namespace /dev/pts was mounted inside). */ int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) { int fd; struct file *filp; int retval = -EINVAL; struct path path; if (tty->driver != ptm_driver) return -EIO; fd = get_unused_fd_flags(flags); if (fd < 0) { retval = fd; goto err; } /* Compute the slave's path */ path.mnt = devpts_mntget(master, tty->driver_data); if (IS_ERR(path.mnt)) { retval = PTR_ERR(path.mnt); goto err_put; } path.dentry = tty->link->driver_data; filp = dentry_open(&path, flags, current_cred()); mntput(path.mnt); if (IS_ERR(filp)) { retval = PTR_ERR(filp); goto err_put; } fd_install(fd, filp); return fd; err_put: put_unused_fd(fd); err: return retval; } static int pty_unix98_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { switch (cmd) { case TIOCSPTLCK: /* Set PT Lock (disallow slave open) */ return pty_set_lock(tty, (int __user *)arg); case TIOCGPTLCK: /* Get PT Lock status */ return pty_get_lock(tty, (int __user *)arg); case TIOCPKT: /* Set PT packet mode */ return pty_set_pktmode(tty, (int __user *)arg); case TIOCGPKT: /* Get PT packet mode */ return pty_get_pktmode(tty, (int __user *)arg); case TIOCGPTN: /* Get PT Number */ return put_user(tty->index, (unsigned int __user *)arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT static long pty_unix98_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { /* * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ return pty_unix98_ioctl(tty, cmd, cmd == TIOCSIG ? arg : (unsigned long)compat_ptr(arg)); } #else #define pty_unix98_compat_ioctl NULL #endif /** * ptm_unix98_lookup - find a pty master * @driver: ptm driver * @file: unused * @idx: tty index * * Look up a pty master device. Called under the tty_mutex for now. * This provides our locking. */ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, struct file *file, int idx) { /* Master must be open via /dev/ptmx */ return ERR_PTR(-EIO); } /** * pts_unix98_lookup - find a pty slave * @driver: pts driver * @file: file pointer to tty * @idx: tty index * * Look up a pty master device. Called under the tty_mutex for now. * This provides our locking for the tty pointer. */ static struct tty_struct *pts_unix98_lookup(struct tty_driver *driver, struct file *file, int idx) { struct tty_struct *tty; mutex_lock(&devpts_mutex); tty = devpts_get_priv(file->f_path.dentry); mutex_unlock(&devpts_mutex); /* Master must be open before slave */ if (!tty) return ERR_PTR(-EIO); return tty; } static int pty_unix98_install(struct tty_driver *driver, struct tty_struct *tty) { return pty_common_install(driver, tty, false); } /* this is called once with whichever end is closed last */ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) { struct pts_fs_info *fsi; if (tty->driver->subtype == PTY_TYPE_MASTER) fsi = tty->driver_data; else fsi = tty->link->driver_data; if (fsi) { devpts_kill_index(fsi, tty->index); devpts_release(fsi); } } static void pty_show_fdinfo(struct tty_struct *tty, struct seq_file *m) { seq_printf(m, "tty-index:\t%d\n", tty->index); } static const struct tty_operations ptm_unix98_ops = { .lookup = ptm_unix98_lookup, .install = pty_unix98_install, .remove = pty_unix98_remove, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .ioctl = pty_unix98_ioctl, .compat_ioctl = pty_unix98_compat_ioctl, .resize = pty_resize, .cleanup = pty_cleanup, .show_fdinfo = pty_show_fdinfo, }; static const struct tty_operations pty_unix98_ops = { .lookup = pts_unix98_lookup, .install = pty_unix98_install, .remove = pty_unix98_remove, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .set_termios = pty_set_termios, .start = pty_start, .stop = pty_stop, .cleanup = pty_cleanup, }; /** * ptmx_open - open a unix 98 pty master * @inode: inode of device file * @filp: file pointer to tty * * Allocate a unix98 pty master device from the ptmx driver. * * Locking: tty_mutex protects the init_dev work. tty->count should * protect the rest. * allocated_ptys_lock handles the list of free pty numbers */ static int ptmx_open(struct inode *inode, struct file *filp) { struct pts_fs_info *fsi; struct tty_struct *tty; struct dentry *dentry; int retval; int index; nonseekable_open(inode, filp); /* We refuse fsnotify events on ptmx, since it's a shared resource */ file_set_fsnotify_mode(filp, FMODE_NONOTIFY); retval = tty_alloc_file(filp); if (retval) return retval; fsi = devpts_acquire(filp); if (IS_ERR(fsi)) { retval = PTR_ERR(fsi); goto out_free_file; } /* find a device that is not in use. */ mutex_lock(&devpts_mutex); index = devpts_new_index(fsi); mutex_unlock(&devpts_mutex); retval = index; if (index < 0) goto out_put_fsi; mutex_lock(&tty_mutex); tty = tty_init_dev(ptm_driver, index); /* The tty returned here is locked so we can safely drop the mutex */ mutex_unlock(&tty_mutex); retval = PTR_ERR(tty); if (IS_ERR(tty)) goto out; /* * From here on out, the tty is "live", and the index and * fsi will be killed/put by the tty_release() */ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = fsi; tty_add_file(tty, filp); dentry = devpts_pty_new(fsi, index, tty->link); if (IS_ERR(dentry)) { retval = PTR_ERR(dentry); goto err_release; } tty->link->driver_data = dentry; retval = ptm_driver->ops->open(tty, filp); if (retval) goto err_release; tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); tty_unlock(tty); return 0; err_release: tty_unlock(tty); // This will also put-ref the fsi tty_release(inode, filp); return retval; out: devpts_kill_index(fsi, index); out_put_fsi: devpts_release(fsi); out_free_file: tty_free_file(filp); return retval; } static struct file_operations ptmx_fops __ro_after_init; static void __init unix98_pty_init(void) { ptm_driver = tty_alloc_driver(NR_UNIX98_PTY_MAX, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV | TTY_DRIVER_DEVPTS_MEM | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(ptm_driver)) panic("Couldn't allocate Unix98 ptm driver"); pts_driver = tty_alloc_driver(NR_UNIX98_PTY_MAX, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV | TTY_DRIVER_DEVPTS_MEM | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(pts_driver)) panic("Couldn't allocate Unix98 pts driver"); ptm_driver->driver_name = "pty_master"; ptm_driver->name = "ptm"; ptm_driver->major = UNIX98_PTY_MASTER_MAJOR; ptm_driver->minor_start = 0; ptm_driver->type = TTY_DRIVER_TYPE_PTY; ptm_driver->subtype = PTY_TYPE_MASTER; ptm_driver->init_termios = tty_std_termios; ptm_driver->init_termios.c_iflag = 0; ptm_driver->init_termios.c_oflag = 0; ptm_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; ptm_driver->init_termios.c_lflag = 0; ptm_driver->init_termios.c_ispeed = 38400; ptm_driver->init_termios.c_ospeed = 38400; ptm_driver->other = pts_driver; tty_set_operations(ptm_driver, &ptm_unix98_ops); pts_driver->driver_name = "pty_slave"; pts_driver->name = "pts"; pts_driver->major = UNIX98_PTY_SLAVE_MAJOR; pts_driver->minor_start = 0; pts_driver->type = TTY_DRIVER_TYPE_PTY; pts_driver->subtype = PTY_TYPE_SLAVE; pts_driver->init_termios = tty_std_termios; pts_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pts_driver->init_termios.c_ispeed = 38400; pts_driver->init_termios.c_ospeed = 38400; pts_driver->other = ptm_driver; tty_set_operations(pts_driver, &pty_unix98_ops); if (tty_register_driver(ptm_driver)) panic("Couldn't register Unix98 ptm driver"); if (tty_register_driver(pts_driver)) panic("Couldn't register Unix98 pts driver"); /* Now create the /dev/ptmx special device */ tty_default_fops(&ptmx_fops); ptmx_fops.open = ptmx_open; cdev_init(&ptmx_cdev, &ptmx_fops); if (cdev_add(&ptmx_cdev, MKDEV(TTYAUX_MAJOR, 2), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 2), 1, "/dev/ptmx") < 0) panic("Couldn't register /dev/ptmx driver"); device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 2), NULL, "ptmx"); } #else static inline void unix98_pty_init(void) { } #endif static int __init pty_init(void) { legacy_pty_init(); unix98_pty_init(); return 0; } device_initcall(pty_init); |
| 233 273 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NLS_H #define _LINUX_NLS_H #include <linux/init.h> /* Unicode has changed over the years. Unicode code points no longer * fit into 16 bits; as of Unicode 5 valid code points range from 0 * to 0x10ffff (17 planes, where each plane holds 65536 code points). * * The original decision to represent Unicode characters as 16-bit * wchar_t values is now outdated. But plane 0 still includes the * most commonly used characters, so we will retain it. The newer * 32-bit unicode_t type can be used when it is necessary to * represent the full Unicode character set. */ /* Plane-0 Unicode character */ typedef u16 wchar_t; #define MAX_WCHAR_T 0xffff /* Arbitrary Unicode character */ typedef u32 unicode_t; struct nls_table { const char *charset; const char *alias; int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen); int (*char2uni) (const unsigned char *rawstring, int boundlen, wchar_t *uni); const unsigned char *charset2lower; const unsigned char *charset2upper; struct module *owner; struct nls_table *next; }; /* this value hold the maximum octet of charset */ #define NLS_MAX_CHARSET_SIZE 6 /* for UTF-8 */ /* Byte order for UTF-16 strings */ enum utf16_endian { UTF16_HOST_ENDIAN, UTF16_LITTLE_ENDIAN, UTF16_BIG_ENDIAN }; /* nls_base.c */ extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); extern struct nls_table *load_nls(const char *charset); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); #define register_nls(nls) __register_nls((nls), THIS_MODULE) extern int utf8_to_utf32(const u8 *s, int len, unicode_t *pu); extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen); extern int utf8s_to_utf16s(const u8 *s, int len, enum utf16_endian endian, wchar_t *pwcs, int maxlen); extern int utf16s_to_utf8s(const wchar_t *pwcs, int len, enum utf16_endian endian, u8 *s, int maxlen); static inline unsigned char nls_tolower(struct nls_table *t, unsigned char c) { unsigned char nc = t->charset2lower[c]; return nc ? nc : c; } static inline unsigned char nls_toupper(struct nls_table *t, unsigned char c) { unsigned char nc = t->charset2upper[c]; return nc ? nc : c; } static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1, const unsigned char *s2, int len) { while (len--) { if (nls_tolower(t, *s1++) != nls_tolower(t, *s2++)) return 1; } return 0; } /* * nls_nullsize - return length of null character for codepage * @codepage - codepage for which to return length of NULL terminator * * Since we can't guarantee that the null terminator will be a particular * length, we have to check against the codepage. If there's a problem * determining it, assume a single-byte NULL terminator. */ static inline int nls_nullsize(const struct nls_table *codepage) { int charlen; char tmp[NLS_MAX_CHARSET_SIZE]; charlen = codepage->uni2char(0, tmp, NLS_MAX_CHARSET_SIZE); return charlen > 0 ? charlen : 1; } #define MODULE_ALIAS_NLS(name) MODULE_ALIAS("nls_" __stringify(name)) #endif /* _LINUX_NLS_H */ |
| 16 5 16 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Based on net/mac80211/trace.h */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mac802154 #if !defined(__MAC802154_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) #define __MAC802154_DRIVER_TRACE #include <linux/tracepoint.h> #include <net/mac802154.h> #include "ieee802154_i.h" #define MAXNAME 32 #define LOCAL_ENTRY __array(char, wpan_phy_name, MAXNAME) #define LOCAL_ASSIGN strscpy(__entry->wpan_phy_name, \ wpan_phy_name(local->hw.phy), MAXNAME) #define LOCAL_PR_FMT "%s" #define LOCAL_PR_ARG __entry->wpan_phy_name #define CCA_ENTRY __field(enum nl802154_cca_modes, cca_mode) \ __field(enum nl802154_cca_opts, cca_opt) #define CCA_ASSIGN \ do { \ (__entry->cca_mode) = cca->mode; \ (__entry->cca_opt) = cca->opt; \ } while (0) #define CCA_PR_FMT "cca_mode: %d, cca_opt: %d" #define CCA_PR_ARG __entry->cca_mode, __entry->cca_opt #define BOOL_TO_STR(bo) (bo) ? "true" : "false" /* Tracing for driver callbacks */ DECLARE_EVENT_CLASS(local_only_evt4, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local), TP_STRUCT__entry( LOCAL_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; ), TP_printk(LOCAL_PR_FMT, LOCAL_PR_ARG) ); DEFINE_EVENT(local_only_evt4, 802154_drv_return_void, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); TRACE_EVENT(802154_drv_return_int, TP_PROTO(struct ieee802154_local *local, int ret), TP_ARGS(local, ret), TP_STRUCT__entry( LOCAL_ENTRY __field(int, ret) ), TP_fast_assign( LOCAL_ASSIGN; __entry->ret = ret; ), TP_printk(LOCAL_PR_FMT ", returned: %d", LOCAL_PR_ARG, __entry->ret) ); DEFINE_EVENT(local_only_evt4, 802154_drv_start, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); DEFINE_EVENT(local_only_evt4, 802154_drv_stop, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); TRACE_EVENT(802154_drv_set_channel, TP_PROTO(struct ieee802154_local *local, u8 page, u8 channel), TP_ARGS(local, page, channel), TP_STRUCT__entry( LOCAL_ENTRY __field(u8, page) __field(u8, channel) ), TP_fast_assign( LOCAL_ASSIGN; __entry->page = page; __entry->channel = channel; ), TP_printk(LOCAL_PR_FMT ", page: %d, channel: %d", LOCAL_PR_ARG, __entry->page, __entry->channel) ); TRACE_EVENT(802154_drv_set_cca_mode, TP_PROTO(struct ieee802154_local *local, const struct wpan_phy_cca *cca), TP_ARGS(local, cca), TP_STRUCT__entry( LOCAL_ENTRY CCA_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; CCA_ASSIGN; ), TP_printk(LOCAL_PR_FMT ", " CCA_PR_FMT, LOCAL_PR_ARG, CCA_PR_ARG) ); TRACE_EVENT(802154_drv_set_cca_ed_level, TP_PROTO(struct ieee802154_local *local, s32 mbm), TP_ARGS(local, mbm), TP_STRUCT__entry( LOCAL_ENTRY __field(s32, mbm) ), TP_fast_assign( LOCAL_ASSIGN; __entry->mbm = mbm; ), TP_printk(LOCAL_PR_FMT ", ed level: %d", LOCAL_PR_ARG, __entry->mbm) ); TRACE_EVENT(802154_drv_set_tx_power, TP_PROTO(struct ieee802154_local *local, s32 power), TP_ARGS(local, power), TP_STRUCT__entry( LOCAL_ENTRY __field(s32, power) ), TP_fast_assign( LOCAL_ASSIGN; __entry->power = power; ), TP_printk(LOCAL_PR_FMT ", mbm: %d", LOCAL_PR_ARG, __entry->power) ); TRACE_EVENT(802154_drv_set_lbt_mode, TP_PROTO(struct ieee802154_local *local, bool mode), TP_ARGS(local, mode), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, mode) ), TP_fast_assign( LOCAL_ASSIGN; __entry->mode = mode; ), TP_printk(LOCAL_PR_FMT ", lbt mode: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->mode)) ); TRACE_EVENT(802154_drv_set_short_addr, TP_PROTO(struct ieee802154_local *local, __le16 short_addr), TP_ARGS(local, short_addr), TP_STRUCT__entry( LOCAL_ENTRY __field(__le16, short_addr) ), TP_fast_assign( LOCAL_ASSIGN; __entry->short_addr = short_addr; ), TP_printk(LOCAL_PR_FMT ", short addr: 0x%04x", LOCAL_PR_ARG, le16_to_cpu(__entry->short_addr)) ); TRACE_EVENT(802154_drv_set_pan_id, TP_PROTO(struct ieee802154_local *local, __le16 pan_id), TP_ARGS(local, pan_id), TP_STRUCT__entry( LOCAL_ENTRY __field(__le16, pan_id) ), TP_fast_assign( LOCAL_ASSIGN; __entry->pan_id = pan_id; ), TP_printk(LOCAL_PR_FMT ", pan id: 0x%04x", LOCAL_PR_ARG, le16_to_cpu(__entry->pan_id)) ); TRACE_EVENT(802154_drv_set_extended_addr, TP_PROTO(struct ieee802154_local *local, __le64 extended_addr), TP_ARGS(local, extended_addr), TP_STRUCT__entry( LOCAL_ENTRY __field(__le64, extended_addr) ), TP_fast_assign( LOCAL_ASSIGN; __entry->extended_addr = extended_addr; ), TP_printk(LOCAL_PR_FMT ", extended addr: 0x%llx", LOCAL_PR_ARG, le64_to_cpu(__entry->extended_addr)) ); TRACE_EVENT(802154_drv_set_pan_coord, TP_PROTO(struct ieee802154_local *local, bool is_coord), TP_ARGS(local, is_coord), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, is_coord) ), TP_fast_assign( LOCAL_ASSIGN; __entry->is_coord = is_coord; ), TP_printk(LOCAL_PR_FMT ", is_coord: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->is_coord)) ); TRACE_EVENT(802154_drv_set_csma_params, TP_PROTO(struct ieee802154_local *local, u8 min_be, u8 max_be, u8 max_csma_backoffs), TP_ARGS(local, min_be, max_be, max_csma_backoffs), TP_STRUCT__entry( LOCAL_ENTRY __field(u8, min_be) __field(u8, max_be) __field(u8, max_csma_backoffs) ), TP_fast_assign( LOCAL_ASSIGN, __entry->min_be = min_be; __entry->max_be = max_be; __entry->max_csma_backoffs = max_csma_backoffs; ), TP_printk(LOCAL_PR_FMT ", min be: %d, max be: %d, max csma backoffs: %d", LOCAL_PR_ARG, __entry->min_be, __entry->max_be, __entry->max_csma_backoffs) ); TRACE_EVENT(802154_drv_set_max_frame_retries, TP_PROTO(struct ieee802154_local *local, s8 max_frame_retries), TP_ARGS(local, max_frame_retries), TP_STRUCT__entry( LOCAL_ENTRY __field(s8, max_frame_retries) ), TP_fast_assign( LOCAL_ASSIGN; __entry->max_frame_retries = max_frame_retries; ), TP_printk(LOCAL_PR_FMT ", max frame retries: %d", LOCAL_PR_ARG, __entry->max_frame_retries) ); TRACE_EVENT(802154_drv_set_promiscuous_mode, TP_PROTO(struct ieee802154_local *local, bool on), TP_ARGS(local, on), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, on) ), TP_fast_assign( LOCAL_ASSIGN; __entry->on = on; ), TP_printk(LOCAL_PR_FMT ", promiscuous mode: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->on)) ); TRACE_EVENT(802154_new_scan_event, TP_PROTO(struct ieee802154_coord_desc *desc), TP_ARGS(desc), TP_STRUCT__entry( __field(__le16, pan_id) __field(__le64, addr) __field(u8, channel) __field(u8, page) ), TP_fast_assign( __entry->page = desc->page; __entry->channel = desc->channel; __entry->pan_id = desc->addr.pan_id; __entry->addr = desc->addr.extended_addr; ), TP_printk("panid: %u, coord_addr: 0x%llx, page: %u, channel: %u", __le16_to_cpu(__entry->pan_id), __le64_to_cpu(__entry->addr), __entry->page, __entry->channel) ); DEFINE_EVENT(802154_new_scan_event, 802154_scan_event, TP_PROTO(struct ieee802154_coord_desc *desc), TP_ARGS(desc) ); #endif /* !__MAC802154_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 6 5 4 7 7 7 1 1 6 2 2 3 4 8 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/eventfd.h> #include <linux/eventpoll.h> #include <linux/io_uring.h> #include <linux/io_uring_types.h> #include "io-wq.h" #include "eventfd.h" struct io_ev_fd { struct eventfd_ctx *cq_ev_fd; unsigned int eventfd_async; /* protected by ->completion_lock */ unsigned last_cq_tail; refcount_t refs; atomic_t ops; struct rcu_head rcu; }; enum { IO_EVENTFD_OP_SIGNAL_BIT, }; static void io_eventfd_free(struct rcu_head *rcu) { struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); eventfd_ctx_put(ev_fd->cq_ev_fd); kfree(ev_fd); } static void io_eventfd_put(struct io_ev_fd *ev_fd) { if (refcount_dec_and_test(&ev_fd->refs)) call_rcu(&ev_fd->rcu, io_eventfd_free); } static void io_eventfd_do_signal(struct rcu_head *rcu) { struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); io_eventfd_put(ev_fd); } static void io_eventfd_release(struct io_ev_fd *ev_fd, bool put_ref) { if (put_ref) io_eventfd_put(ev_fd); rcu_read_unlock(); } /* * Returns true if the caller should put the ev_fd reference, false if not. */ static bool __io_eventfd_signal(struct io_ev_fd *ev_fd) { if (eventfd_signal_allowed()) { eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); return true; } if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops)) { call_rcu_hurry(&ev_fd->rcu, io_eventfd_do_signal); return false; } return true; } /* * Trigger if eventfd_async isn't set, or if it's set and the caller is * an async worker. If ev_fd isn't valid, obviously return false. */ static bool io_eventfd_trigger(struct io_ev_fd *ev_fd) { if (ev_fd) return !ev_fd->eventfd_async || io_wq_current_is_worker(); return false; } /* * On success, returns with an ev_fd reference grabbed and the RCU read * lock held. */ static struct io_ev_fd *io_eventfd_grab(struct io_ring_ctx *ctx) { struct io_ev_fd *ev_fd; if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) return NULL; rcu_read_lock(); /* * rcu_dereference ctx->io_ev_fd once and use it for both for checking * and eventfd_signal */ ev_fd = rcu_dereference(ctx->io_ev_fd); /* * Check again if ev_fd exists in case an io_eventfd_unregister call * completed between the NULL check of ctx->io_ev_fd at the start of * the function and rcu_read_lock. */ if (io_eventfd_trigger(ev_fd) && refcount_inc_not_zero(&ev_fd->refs)) return ev_fd; rcu_read_unlock(); return NULL; } void io_eventfd_signal(struct io_ring_ctx *ctx) { struct io_ev_fd *ev_fd; ev_fd = io_eventfd_grab(ctx); if (ev_fd) io_eventfd_release(ev_fd, __io_eventfd_signal(ev_fd)); } void io_eventfd_flush_signal(struct io_ring_ctx *ctx) { struct io_ev_fd *ev_fd; ev_fd = io_eventfd_grab(ctx); if (ev_fd) { bool skip, put_ref = true; /* * Eventfd should only get triggered when at least one event * has been posted. Some applications rely on the eventfd * notification count only changing IFF a new CQE has been * added to the CQ ring. There's no dependency on 1:1 * relationship between how many times this function is called * (and hence the eventfd count) and number of CQEs posted to * the CQ ring. */ spin_lock(&ctx->completion_lock); skip = ctx->cached_cq_tail == ev_fd->last_cq_tail; ev_fd->last_cq_tail = ctx->cached_cq_tail; spin_unlock(&ctx->completion_lock); if (!skip) put_ref = __io_eventfd_signal(ev_fd); io_eventfd_release(ev_fd, put_ref); } } int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg, unsigned int eventfd_async) { struct io_ev_fd *ev_fd; __s32 __user *fds = arg; int fd; ev_fd = rcu_dereference_protected(ctx->io_ev_fd, lockdep_is_held(&ctx->uring_lock)); if (ev_fd) return -EBUSY; if (copy_from_user(&fd, fds, sizeof(*fds))) return -EFAULT; ev_fd = kmalloc(sizeof(*ev_fd), GFP_KERNEL); if (!ev_fd) return -ENOMEM; ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd); if (IS_ERR(ev_fd->cq_ev_fd)) { int ret = PTR_ERR(ev_fd->cq_ev_fd); kfree(ev_fd); return ret; } spin_lock(&ctx->completion_lock); ev_fd->last_cq_tail = ctx->cached_cq_tail; spin_unlock(&ctx->completion_lock); ev_fd->eventfd_async = eventfd_async; ctx->has_evfd = true; refcount_set(&ev_fd->refs, 1); atomic_set(&ev_fd->ops, 0); rcu_assign_pointer(ctx->io_ev_fd, ev_fd); return 0; } int io_eventfd_unregister(struct io_ring_ctx *ctx) { struct io_ev_fd *ev_fd; ev_fd = rcu_dereference_protected(ctx->io_ev_fd, lockdep_is_held(&ctx->uring_lock)); if (ev_fd) { ctx->has_evfd = false; rcu_assign_pointer(ctx->io_ev_fd, NULL); io_eventfd_put(ev_fd); return 0; } return -ENXIO; } |
| 245 303 2 1 1 3 1 1 296 10 3 212 209 3 6 1 5 208 9 65 192 2 1 183 11 190 187 184 186 180 176 9 1 3 9 2 180 3 3 1 176 2 175 175 3 171 171 172 169 171 168 167 165 163 161 160 156 155 155 154 1 2 153 151 151 189 38 2 514 568 568 1 568 27 1 3 3 1 1 1 2 566 15 563 1 2 1 566 568 567 1 1 4 2 1 3 1 1 2 2 2 4 4 552 2 52 52 4 3 3 15 11 5 1 14 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/bond/bond_netlink.c - Netlink interface for bonding * Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com> */ #include <linux/module.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_link.h> #include <linux/if_ether.h> #include <net/netlink.h> #include <net/rtnetlink.h> #include <net/bonding.h> #include <net/ipv6.h> static size_t bond_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_STATE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_MII_STATUS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_SLAVE_LINK_FAILURE_COUNT */ nla_total_size(MAX_ADDR_LEN) + /* IFLA_BOND_SLAVE_PERM_HWADDR */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_QUEUE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */ nla_total_size(sizeof(s32)) + /* IFLA_BOND_SLAVE_PRIO */ 0; } static int bond_fill_slave_info(struct sk_buff *skb, const struct net_device *bond_dev, const struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev); if (nla_put_u8(skb, IFLA_BOND_SLAVE_STATE, bond_slave_state(slave))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_SLAVE_MII_STATUS, slave->link)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, slave->link_failure_count)) goto nla_put_failure; if (nla_put(skb, IFLA_BOND_SLAVE_PERM_HWADDR, slave_dev->addr_len, slave->perm_hwaddr)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, READ_ONCE(slave->queue_id))) goto nla_put_failure; if (nla_put_s32(skb, IFLA_BOND_SLAVE_PRIO, slave->prio)) goto nla_put_failure; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { const struct aggregator *agg; const struct port *ad_port; ad_port = &SLAVE_AD_INFO(slave)->port; agg = SLAVE_AD_INFO(slave)->port.aggregator; if (agg) { if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, agg->aggregator_identifier)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, ad_port->actor_oper_port_state)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) goto nla_put_failure; } } return 0; nla_put_failure: return -EMSGSIZE; } /* Limit the max delay range to 300s */ static const struct netlink_range_validation delay_range = { .max = 300000, }; static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MODE] = { .type = NLA_U8 }, [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, [IFLA_BOND_MIIMON] = { .type = NLA_U32 }, [IFLA_BOND_UPDELAY] = { .type = NLA_U32 }, [IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 }, [IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 }, [IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 }, [IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED }, [IFLA_BOND_ARP_VALIDATE] = { .type = NLA_U32 }, [IFLA_BOND_ARP_ALL_TARGETS] = { .type = NLA_U32 }, [IFLA_BOND_PRIMARY] = { .type = NLA_U32 }, [IFLA_BOND_PRIMARY_RESELECT] = { .type = NLA_U8 }, [IFLA_BOND_FAIL_OVER_MAC] = { .type = NLA_U8 }, [IFLA_BOND_XMIT_HASH_POLICY] = { .type = NLA_U8 }, [IFLA_BOND_RESEND_IGMP] = { .type = NLA_U32 }, [IFLA_BOND_NUM_PEER_NOTIF] = { .type = NLA_U8 }, [IFLA_BOND_ALL_SLAVES_ACTIVE] = { .type = NLA_U8 }, [IFLA_BOND_MIN_LINKS] = { .type = NLA_U32 }, [IFLA_BOND_LP_INTERVAL] = { .type = NLA_U32 }, [IFLA_BOND_PACKETS_PER_SLAVE] = { .type = NLA_U32 }, [IFLA_BOND_AD_LACP_ACTIVE] = { .type = NLA_U8 }, [IFLA_BOND_AD_LACP_RATE] = { .type = NLA_U8 }, [IFLA_BOND_AD_SELECT] = { .type = NLA_U8 }, [IFLA_BOND_AD_INFO] = { .type = NLA_NESTED }, [IFLA_BOND_AD_ACTOR_SYS_PRIO] = { .type = NLA_U16 }, [IFLA_BOND_AD_USER_PORT_KEY] = { .type = NLA_U16 }, [IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range), [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, [IFLA_BOND_COUPLED_CONTROL] = { .type = NLA_U8 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { [IFLA_BOND_SLAVE_QUEUE_ID] = { .type = NLA_U16 }, [IFLA_BOND_SLAVE_PRIO] = { .type = NLA_S32 }, }; static int bond_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static int bond_slave_changelink(struct net_device *bond_dev, struct net_device *slave_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct bond_opt_value newval; int err; if (!data) return 0; if (data[IFLA_BOND_SLAVE_QUEUE_ID]) { u16 queue_id = nla_get_u16(data[IFLA_BOND_SLAVE_QUEUE_ID]); char queue_id_str[IFNAMSIZ + 7]; /* queue_id option setting expects slave_name:queue_id */ snprintf(queue_id_str, sizeof(queue_id_str), "%s:%u\n", slave_dev->name, queue_id); bond_opt_initstr(&newval, queue_id_str); err = __bond_opt_set(bond, BOND_OPT_QUEUE_ID, &newval, data[IFLA_BOND_SLAVE_QUEUE_ID], extack); if (err) return err; } if (data[IFLA_BOND_SLAVE_PRIO]) { int prio = nla_get_s32(data[IFLA_BOND_SLAVE_PRIO]); bond_opt_slave_initval(&newval, &slave_dev, prio); err = __bond_opt_set(bond, BOND_OPT_PRIO, &newval, data[IFLA_BOND_SLAVE_PRIO], extack); if (err) return err; } return 0; } static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct bond_opt_value newval; int miimon = 0; int err; if (!data) return 0; if (data[IFLA_BOND_MODE]) { int mode = nla_get_u8(data[IFLA_BOND_MODE]); bond_opt_initval(&newval, mode); err = __bond_opt_set(bond, BOND_OPT_MODE, &newval, data[IFLA_BOND_MODE], extack); if (err) return err; } if (data[IFLA_BOND_ACTIVE_SLAVE]) { int ifindex = nla_get_u32(data[IFLA_BOND_ACTIVE_SLAVE]); struct net_device *slave_dev; char *active_slave = ""; if (ifindex != 0) { slave_dev = __dev_get_by_index(dev_net(bond_dev), ifindex); if (!slave_dev) return -ENODEV; active_slave = slave_dev->name; } bond_opt_initstr(&newval, active_slave); err = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval, data[IFLA_BOND_ACTIVE_SLAVE], extack); if (err) return err; } if (data[IFLA_BOND_MIIMON]) { miimon = nla_get_u32(data[IFLA_BOND_MIIMON]); bond_opt_initval(&newval, miimon); err = __bond_opt_set(bond, BOND_OPT_MIIMON, &newval, data[IFLA_BOND_MIIMON], extack); if (err) return err; } if (data[IFLA_BOND_UPDELAY]) { int updelay = nla_get_u32(data[IFLA_BOND_UPDELAY]); bond_opt_initval(&newval, updelay); err = __bond_opt_set(bond, BOND_OPT_UPDELAY, &newval, data[IFLA_BOND_UPDELAY], extack); if (err) return err; } if (data[IFLA_BOND_DOWNDELAY]) { int downdelay = nla_get_u32(data[IFLA_BOND_DOWNDELAY]); bond_opt_initval(&newval, downdelay); err = __bond_opt_set(bond, BOND_OPT_DOWNDELAY, &newval, data[IFLA_BOND_DOWNDELAY], extack); if (err) return err; } if (data[IFLA_BOND_PEER_NOTIF_DELAY]) { int delay = nla_get_u32(data[IFLA_BOND_PEER_NOTIF_DELAY]); bond_opt_initval(&newval, delay); err = __bond_opt_set(bond, BOND_OPT_PEER_NOTIF_DELAY, &newval, data[IFLA_BOND_PEER_NOTIF_DELAY], extack); if (err) return err; } if (data[IFLA_BOND_USE_CARRIER]) { int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]); bond_opt_initval(&newval, use_carrier); err = __bond_opt_set(bond, BOND_OPT_USE_CARRIER, &newval, data[IFLA_BOND_USE_CARRIER], extack); if (err) return err; } if (data[IFLA_BOND_ARP_INTERVAL]) { int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]); if (arp_interval && miimon) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_ARP_INTERVAL], "ARP monitoring cannot be used with MII monitoring"); return -EINVAL; } bond_opt_initval(&newval, arp_interval); err = __bond_opt_set(bond, BOND_OPT_ARP_INTERVAL, &newval, data[IFLA_BOND_ARP_INTERVAL], extack); if (err) return err; } if (data[IFLA_BOND_ARP_IP_TARGET]) { struct nlattr *attr; int i = 0, rem; bond_option_arp_ip_targets_clear(bond); nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) { __be32 target; if (nla_len(attr) < sizeof(target)) return -EINVAL; target = nla_get_be32(attr); bond_opt_initval(&newval, (__force u64)target); err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS, &newval, data[IFLA_BOND_ARP_IP_TARGET], extack); if (err) break; i++; } if (i == 0 && bond->params.arp_interval) netdev_warn(bond->dev, "Removing last arp target with arp_interval on\n"); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BOND_NS_IP6_TARGET]) { struct nlattr *attr; int i = 0, rem; bond_option_ns_ip6_targets_clear(bond); nla_for_each_nested(attr, data[IFLA_BOND_NS_IP6_TARGET], rem) { struct in6_addr addr6; if (nla_len(attr) < sizeof(addr6)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address"); return -EINVAL; } addr6 = nla_get_in6_addr(attr); bond_opt_initextra(&newval, &addr6, sizeof(addr6)); err = __bond_opt_set(bond, BOND_OPT_NS_TARGETS, &newval, data[IFLA_BOND_NS_IP6_TARGET], extack); if (err) break; i++; } if (i == 0 && bond->params.arp_interval) netdev_warn(bond->dev, "Removing last ns target with arp_interval on\n"); if (err) return err; } #endif if (data[IFLA_BOND_ARP_VALIDATE]) { int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]); if (arp_validate && miimon) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_ARP_INTERVAL], "ARP validating cannot be used with MII monitoring"); return -EINVAL; } bond_opt_initval(&newval, arp_validate); err = __bond_opt_set(bond, BOND_OPT_ARP_VALIDATE, &newval, data[IFLA_BOND_ARP_VALIDATE], extack); if (err) return err; } if (data[IFLA_BOND_ARP_ALL_TARGETS]) { int arp_all_targets = nla_get_u32(data[IFLA_BOND_ARP_ALL_TARGETS]); bond_opt_initval(&newval, arp_all_targets); err = __bond_opt_set(bond, BOND_OPT_ARP_ALL_TARGETS, &newval, data[IFLA_BOND_ARP_ALL_TARGETS], extack); if (err) return err; } if (data[IFLA_BOND_PRIMARY]) { int ifindex = nla_get_u32(data[IFLA_BOND_PRIMARY]); struct net_device *dev; char *primary = ""; dev = __dev_get_by_index(dev_net(bond_dev), ifindex); if (dev) primary = dev->name; bond_opt_initstr(&newval, primary); err = __bond_opt_set(bond, BOND_OPT_PRIMARY, &newval, data[IFLA_BOND_PRIMARY], extack); if (err) return err; } if (data[IFLA_BOND_PRIMARY_RESELECT]) { int primary_reselect = nla_get_u8(data[IFLA_BOND_PRIMARY_RESELECT]); bond_opt_initval(&newval, primary_reselect); err = __bond_opt_set(bond, BOND_OPT_PRIMARY_RESELECT, &newval, data[IFLA_BOND_PRIMARY_RESELECT], extack); if (err) return err; } if (data[IFLA_BOND_FAIL_OVER_MAC]) { int fail_over_mac = nla_get_u8(data[IFLA_BOND_FAIL_OVER_MAC]); bond_opt_initval(&newval, fail_over_mac); err = __bond_opt_set(bond, BOND_OPT_FAIL_OVER_MAC, &newval, data[IFLA_BOND_FAIL_OVER_MAC], extack); if (err) return err; } if (data[IFLA_BOND_XMIT_HASH_POLICY]) { int xmit_hash_policy = nla_get_u8(data[IFLA_BOND_XMIT_HASH_POLICY]); bond_opt_initval(&newval, xmit_hash_policy); err = __bond_opt_set(bond, BOND_OPT_XMIT_HASH, &newval, data[IFLA_BOND_XMIT_HASH_POLICY], extack); if (err) return err; } if (data[IFLA_BOND_RESEND_IGMP]) { int resend_igmp = nla_get_u32(data[IFLA_BOND_RESEND_IGMP]); bond_opt_initval(&newval, resend_igmp); err = __bond_opt_set(bond, BOND_OPT_RESEND_IGMP, &newval, data[IFLA_BOND_RESEND_IGMP], extack); if (err) return err; } if (data[IFLA_BOND_NUM_PEER_NOTIF]) { int num_peer_notif = nla_get_u8(data[IFLA_BOND_NUM_PEER_NOTIF]); bond_opt_initval(&newval, num_peer_notif); err = __bond_opt_set(bond, BOND_OPT_NUM_PEER_NOTIF, &newval, data[IFLA_BOND_NUM_PEER_NOTIF], extack); if (err) return err; } if (data[IFLA_BOND_ALL_SLAVES_ACTIVE]) { int all_slaves_active = nla_get_u8(data[IFLA_BOND_ALL_SLAVES_ACTIVE]); bond_opt_initval(&newval, all_slaves_active); err = __bond_opt_set(bond, BOND_OPT_ALL_SLAVES_ACTIVE, &newval, data[IFLA_BOND_ALL_SLAVES_ACTIVE], extack); if (err) return err; } if (data[IFLA_BOND_MIN_LINKS]) { int min_links = nla_get_u32(data[IFLA_BOND_MIN_LINKS]); bond_opt_initval(&newval, min_links); err = __bond_opt_set(bond, BOND_OPT_MINLINKS, &newval, data[IFLA_BOND_MIN_LINKS], extack); if (err) return err; } if (data[IFLA_BOND_LP_INTERVAL]) { int lp_interval = nla_get_u32(data[IFLA_BOND_LP_INTERVAL]); bond_opt_initval(&newval, lp_interval); err = __bond_opt_set(bond, BOND_OPT_LP_INTERVAL, &newval, data[IFLA_BOND_LP_INTERVAL], extack); if (err) return err; } if (data[IFLA_BOND_PACKETS_PER_SLAVE]) { int packets_per_slave = nla_get_u32(data[IFLA_BOND_PACKETS_PER_SLAVE]); bond_opt_initval(&newval, packets_per_slave); err = __bond_opt_set(bond, BOND_OPT_PACKETS_PER_SLAVE, &newval, data[IFLA_BOND_PACKETS_PER_SLAVE], extack); if (err) return err; } if (data[IFLA_BOND_AD_LACP_ACTIVE]) { int lacp_active = nla_get_u8(data[IFLA_BOND_AD_LACP_ACTIVE]); bond_opt_initval(&newval, lacp_active); err = __bond_opt_set(bond, BOND_OPT_LACP_ACTIVE, &newval, data[IFLA_BOND_AD_LACP_ACTIVE], extack); if (err) return err; } if (data[IFLA_BOND_AD_LACP_RATE]) { int lacp_rate = nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]); bond_opt_initval(&newval, lacp_rate); err = __bond_opt_set(bond, BOND_OPT_LACP_RATE, &newval, data[IFLA_BOND_AD_LACP_RATE], extack); if (err) return err; } if (data[IFLA_BOND_AD_SELECT]) { int ad_select = nla_get_u8(data[IFLA_BOND_AD_SELECT]); bond_opt_initval(&newval, ad_select); err = __bond_opt_set(bond, BOND_OPT_AD_SELECT, &newval, data[IFLA_BOND_AD_SELECT], extack); if (err) return err; } if (data[IFLA_BOND_AD_ACTOR_SYS_PRIO]) { int actor_sys_prio = nla_get_u16(data[IFLA_BOND_AD_ACTOR_SYS_PRIO]); bond_opt_initval(&newval, actor_sys_prio); err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYS_PRIO, &newval, data[IFLA_BOND_AD_ACTOR_SYS_PRIO], extack); if (err) return err; } if (data[IFLA_BOND_AD_USER_PORT_KEY]) { int port_key = nla_get_u16(data[IFLA_BOND_AD_USER_PORT_KEY]); bond_opt_initval(&newval, port_key); err = __bond_opt_set(bond, BOND_OPT_AD_USER_PORT_KEY, &newval, data[IFLA_BOND_AD_USER_PORT_KEY], extack); if (err) return err; } if (data[IFLA_BOND_AD_ACTOR_SYSTEM]) { if (nla_len(data[IFLA_BOND_AD_ACTOR_SYSTEM]) != ETH_ALEN) return -EINVAL; bond_opt_initval(&newval, nla_get_u64(data[IFLA_BOND_AD_ACTOR_SYSTEM])); err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYSTEM, &newval, data[IFLA_BOND_AD_ACTOR_SYSTEM], extack); if (err) return err; } if (data[IFLA_BOND_TLB_DYNAMIC_LB]) { int dynamic_lb = nla_get_u8(data[IFLA_BOND_TLB_DYNAMIC_LB]); bond_opt_initval(&newval, dynamic_lb); err = __bond_opt_set(bond, BOND_OPT_TLB_DYNAMIC_LB, &newval, data[IFLA_BOND_TLB_DYNAMIC_LB], extack); if (err) return err; } if (data[IFLA_BOND_MISSED_MAX]) { int missed_max = nla_get_u8(data[IFLA_BOND_MISSED_MAX]); bond_opt_initval(&newval, missed_max); err = __bond_opt_set(bond, BOND_OPT_MISSED_MAX, &newval, data[IFLA_BOND_MISSED_MAX], extack); if (err) return err; } if (data[IFLA_BOND_COUPLED_CONTROL]) { int coupled_control = nla_get_u8(data[IFLA_BOND_COUPLED_CONTROL]); bond_opt_initval(&newval, coupled_control); err = __bond_opt_set(bond, BOND_OPT_COUPLED_CONTROL, &newval, data[IFLA_BOND_COUPLED_CONTROL], extack); if (err) return err; } return 0; } static int bond_newlink(struct net *src_net, struct net_device *bond_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { int err; err = bond_changelink(bond_dev, tb, data, extack); if (err < 0) return err; err = register_netdevice(bond_dev); if (!err) { struct bonding *bond = netdev_priv(bond_dev); netif_carrier_off(bond_dev); bond_work_init_all(bond); } return err; } static size_t bond_get_size(const struct net_device *bond_dev) { return nla_total_size(sizeof(u8)) + /* IFLA_BOND_MODE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ACTIVE_SLAVE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */ /* IFLA_BOND_ARP_IP_TARGET */ nla_total_size(sizeof(struct nlattr)) + nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS + nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_VALIDATE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_ALL_TARGETS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PRIMARY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_PRIMARY_RESELECT */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_FAIL_OVER_MAC */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_XMIT_HASH_POLICY */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_RESEND_IGMP */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_NUM_PEER_NOTIF */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_ALL_SLAVES_ACTIVE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIN_LINKS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_LP_INTERVAL */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PACKETS_PER_SLAVE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_ACTIVE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_RATE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_SELECT */ nla_total_size(sizeof(struct nlattr)) + /* IFLA_BOND_AD_INFO */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_AGGREGATOR */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_NUM_PORTS */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_ACTOR_KEY */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_PARTNER_KEY*/ nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_INFO_PARTNER_MAC*/ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_ACTOR_SYS_PRIO */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_USER_PORT_KEY */ nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_ACTOR_SYSTEM */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PEER_NOTIF_DELAY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_MISSED_MAX */ /* IFLA_BOND_NS_IP6_TARGET */ nla_total_size(sizeof(struct nlattr)) + nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS + nla_total_size(sizeof(u8)) + /* IFLA_BOND_COUPLED_CONTROL */ 0; } static int bond_option_active_slave_get_ifindex(struct bonding *bond) { const struct net_device *slave; int ifindex; rcu_read_lock(); slave = bond_option_active_slave_get_rcu(bond); ifindex = slave ? slave->ifindex : 0; rcu_read_unlock(); return ifindex; } static int bond_fill_info(struct sk_buff *skb, const struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); unsigned int packets_per_slave; int ifindex, i, targets_added; struct nlattr *targets; struct slave *primary; if (nla_put_u8(skb, IFLA_BOND_MODE, BOND_MODE(bond))) goto nla_put_failure; ifindex = bond_option_active_slave_get_ifindex(bond); if (ifindex && nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, ifindex)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_UPDELAY, bond->params.updelay * bond->params.miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, bond->params.downdelay * bond->params.miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_PEER_NOTIF_DELAY, bond->params.peer_notif_delay * bond->params.miimon)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval)) goto nla_put_failure; targets = nla_nest_start_noflag(skb, IFLA_BOND_ARP_IP_TARGET); if (!targets) goto nla_put_failure; targets_added = 0; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { if (bond->params.arp_targets[i]) { if (nla_put_be32(skb, i, bond->params.arp_targets[i])) goto nla_put_failure; targets_added = 1; } } if (targets_added) nla_nest_end(skb, targets); else nla_nest_cancel(skb, targets); if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS, bond->params.arp_all_targets)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) targets = nla_nest_start(skb, IFLA_BOND_NS_IP6_TARGET); if (!targets) goto nla_put_failure; targets_added = 0; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { if (!ipv6_addr_any(&bond->params.ns_targets[i])) { if (nla_put_in6_addr(skb, i, &bond->params.ns_targets[i])) goto nla_put_failure; targets_added = 1; } } if (targets_added) nla_nest_end(skb, targets); else nla_nest_cancel(skb, targets); #endif primary = rtnl_dereference(bond->primary_slave); if (primary && nla_put_u32(skb, IFLA_BOND_PRIMARY, primary->dev->ifindex)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_PRIMARY_RESELECT, bond->params.primary_reselect)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_FAIL_OVER_MAC, bond->params.fail_over_mac)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_XMIT_HASH_POLICY, bond->params.xmit_policy)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP, bond->params.resend_igmp)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF, bond->params.num_peer_notif)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_ALL_SLAVES_ACTIVE, bond->params.all_slaves_active)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_MIN_LINKS, bond->params.min_links)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_LP_INTERVAL, bond->params.lp_interval)) goto nla_put_failure; packets_per_slave = bond->params.packets_per_slave; if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE, packets_per_slave)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_LACP_ACTIVE, bond->params.lacp_active)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE, bond->params.lacp_fast)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_SELECT, bond->params.ad_select)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_TLB_DYNAMIC_LB, bond->params.tlb_dynamic_lb)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_MISSED_MAX, bond->params.missed_max)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_COUPLED_CONTROL, bond->params.coupled_control)) goto nla_put_failure; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info; if (capable(CAP_NET_ADMIN)) { if (nla_put_u16(skb, IFLA_BOND_AD_ACTOR_SYS_PRIO, bond->params.ad_actor_sys_prio)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_USER_PORT_KEY, bond->params.ad_user_port_key)) goto nla_put_failure; if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM, ETH_ALEN, &bond->params.ad_actor_system)) goto nla_put_failure; } if (!bond_3ad_get_active_agg_info(bond, &info)) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, IFLA_BOND_AD_INFO); if (!nest) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_AGGREGATOR, info.aggregator_id)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_NUM_PORTS, info.ports)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_ACTOR_KEY, info.actor_key)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_PARTNER_KEY, info.partner_key)) goto nla_put_failure; if (nla_put(skb, IFLA_BOND_AD_INFO_PARTNER_MAC, sizeof(info.partner_system), &info.partner_system)) goto nla_put_failure; nla_nest_end(skb, nest); } } return 0; nla_put_failure: return -EMSGSIZE; } static size_t bond_get_linkxstats_size(const struct net_device *dev, int attr) { switch (attr) { case IFLA_STATS_LINK_XSTATS: case IFLA_STATS_LINK_XSTATS_SLAVE: break; default: return 0; } return bond_3ad_stats_size() + nla_total_size(0); } static int bond_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { struct nlattr *nla __maybe_unused; struct slave *slave = NULL; struct nlattr *nest, *nest2; struct bonding *bond; switch (attr) { case IFLA_STATS_LINK_XSTATS: bond = netdev_priv(dev); break; case IFLA_STATS_LINK_XSTATS_SLAVE: slave = bond_slave_get_rtnl(dev); if (!slave) return 0; bond = slave->bond; break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BOND); if (!nest) return -EMSGSIZE; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct bond_3ad_stats *stats; if (slave) stats = &SLAVE_AD_INFO(slave)->stats; else stats = &BOND_AD_INFO(bond).stats; nest2 = nla_nest_start_noflag(skb, BOND_XSTATS_3AD); if (!nest2) { nla_nest_end(skb, nest); return -EMSGSIZE; } if (bond_3ad_stats_fill(skb, stats)) { nla_nest_cancel(skb, nest2); nla_nest_end(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest2); } nla_nest_end(skb, nest); return 0; } struct rtnl_link_ops bond_link_ops __read_mostly = { .kind = "bond", .priv_size = sizeof(struct bonding), .setup = bond_setup, .maxtype = IFLA_BOND_MAX, .policy = bond_policy, .validate = bond_validate, .newlink = bond_newlink, .changelink = bond_changelink, .get_size = bond_get_size, .fill_info = bond_fill_info, .get_num_tx_queues = bond_get_num_tx_queues, .get_num_rx_queues = bond_get_num_tx_queues, /* Use the same number as for TX queues */ .fill_linkxstats = bond_fill_linkxstats, .get_linkxstats_size = bond_get_linkxstats_size, .slave_maxtype = IFLA_BOND_SLAVE_MAX, .slave_policy = bond_slave_policy, .slave_changelink = bond_slave_changelink, .get_slave_size = bond_get_slave_size, .fill_slave_info = bond_fill_slave_info, }; int __init bond_netlink_init(void) { return rtnl_link_register(&bond_link_ops); } void bond_netlink_fini(void) { rtnl_link_unregister(&bond_link_ops); } MODULE_ALIAS_RTNL_LINK("bond"); |
| 96 96 50 50 8 1 8 8 2 1 7 4 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Intel Corporation. All rights reserved. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/nfc.h> #include <net/nfc/nfc.h> #include "nfc.h" #include "llcp.h" static const u8 llcp_tlv_length[LLCP_TLV_MAX] = { 0, 1, /* VERSION */ 2, /* MIUX */ 2, /* WKS */ 1, /* LTO */ 1, /* RW */ 0, /* SN */ 1, /* OPT */ 0, /* SDREQ */ 2, /* SDRES */ }; static u8 llcp_tlv8(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; return tlv[2]; } static u16 llcp_tlv16(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; return be16_to_cpu(*((__be16 *)(tlv + 2))); } static u8 llcp_tlv_version(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_VERSION); } static u16 llcp_tlv_miux(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff; } static u16 llcp_tlv_wks(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_WKS); } static u16 llcp_tlv_lto(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_LTO); } static u8 llcp_tlv_opt(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_OPT); } static u8 llcp_tlv_rw(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_RW) & 0xf; } u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length) { u8 *tlv, length; pr_debug("type %d\n", type); if (type >= LLCP_TLV_MAX) return NULL; length = llcp_tlv_length[type]; if (length == 0 && value_length == 0) return NULL; else if (length == 0) length = value_length; *tlv_length = 2 + length; tlv = kzalloc(2 + length, GFP_KERNEL); if (tlv == NULL) return tlv; tlv[0] = type; tlv[1] = length; memcpy(tlv + 2, value, length); return tlv; } struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap) { struct nfc_llcp_sdp_tlv *sdres; u8 value[2]; sdres = kzalloc(sizeof(struct nfc_llcp_sdp_tlv), GFP_KERNEL); if (sdres == NULL) return NULL; value[0] = tid; value[1] = sap; sdres->tlv = nfc_llcp_build_tlv(LLCP_TLV_SDRES, value, 2, &sdres->tlv_len); if (sdres->tlv == NULL) { kfree(sdres); return NULL; } sdres->tid = tid; sdres->sap = sap; INIT_HLIST_NODE(&sdres->node); return sdres; } struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len) { struct nfc_llcp_sdp_tlv *sdreq; pr_debug("uri: %s, len: %zu\n", uri, uri_len); /* sdreq->tlv_len is u8, takes uri_len, + 3 for header, + 1 for NULL */ if (WARN_ON_ONCE(uri_len > U8_MAX - 4)) return NULL; sdreq = kzalloc(sizeof(struct nfc_llcp_sdp_tlv), GFP_KERNEL); if (sdreq == NULL) return NULL; sdreq->tlv_len = uri_len + 3; if (uri[uri_len - 1] == 0) sdreq->tlv_len--; sdreq->tlv = kzalloc(sdreq->tlv_len + 1, GFP_KERNEL); if (sdreq->tlv == NULL) { kfree(sdreq); return NULL; } sdreq->tlv[0] = LLCP_TLV_SDREQ; sdreq->tlv[1] = sdreq->tlv_len - 2; sdreq->tlv[2] = tid; sdreq->tid = tid; sdreq->uri = sdreq->tlv + 3; memcpy(sdreq->uri, uri, uri_len); sdreq->time = jiffies; INIT_HLIST_NODE(&sdreq->node); return sdreq; } void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp) { kfree(sdp->tlv); kfree(sdp); } void nfc_llcp_free_sdp_tlv_list(struct hlist_head *head) { struct nfc_llcp_sdp_tlv *sdp; struct hlist_node *n; hlist_for_each_entry_safe(sdp, n, head, node) { hlist_del(&sdp->node); nfc_llcp_free_sdp_tlv(sdp); } } int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, const u8 *tlv_array, u16 tlv_array_len) { const u8 *tlv = tlv_array; u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); if (local == NULL) return -ENODEV; while (offset < tlv_array_len) { type = tlv[0]; length = tlv[1]; pr_debug("type 0x%x length %d\n", type, length); switch (type) { case LLCP_TLV_VERSION: local->remote_version = llcp_tlv_version(tlv); break; case LLCP_TLV_MIUX: local->remote_miu = llcp_tlv_miux(tlv) + 128; break; case LLCP_TLV_WKS: local->remote_wks = llcp_tlv_wks(tlv); break; case LLCP_TLV_LTO: local->remote_lto = llcp_tlv_lto(tlv) * 10; break; case LLCP_TLV_OPT: local->remote_opt = llcp_tlv_opt(tlv); break; default: pr_err("Invalid gt tlv value 0x%x\n", type); break; } offset += length + 2; tlv += length + 2; } pr_debug("version 0x%x miu %d lto %d opt 0x%x wks 0x%x\n", local->remote_version, local->remote_miu, local->remote_lto, local->remote_opt, local->remote_wks); return 0; } int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, const u8 *tlv_array, u16 tlv_array_len) { const u8 *tlv = tlv_array; u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); if (sock == NULL) return -ENOTCONN; while (offset < tlv_array_len) { type = tlv[0]; length = tlv[1]; pr_debug("type 0x%x length %d\n", type, length); switch (type) { case LLCP_TLV_MIUX: sock->remote_miu = llcp_tlv_miux(tlv) + 128; break; case LLCP_TLV_RW: sock->remote_rw = llcp_tlv_rw(tlv); break; case LLCP_TLV_SN: break; default: pr_err("Invalid gt tlv value 0x%x\n", type); break; } offset += length + 2; tlv += length + 2; } pr_debug("sock %p rw %d miu %d\n", sock, sock->remote_rw, sock->remote_miu); return 0; } static struct sk_buff *llcp_add_header(struct sk_buff *pdu, u8 dsap, u8 ssap, u8 ptype) { u8 header[2]; pr_debug("ptype 0x%x dsap 0x%x ssap 0x%x\n", ptype, dsap, ssap); header[0] = (u8)((dsap << 2) | (ptype >> 2)); header[1] = (u8)((ptype << 6) | ssap); pr_debug("header 0x%x 0x%x\n", header[0], header[1]); skb_put_data(pdu, header, LLCP_HEADER_SIZE); return pdu; } static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, const u8 *tlv, u8 tlv_length) { /* XXX Add an skb length check */ if (tlv == NULL) return NULL; skb_put_data(pdu, tlv, tlv_length); return pdu; } static struct sk_buff *llcp_allocate_pdu(struct nfc_llcp_sock *sock, u8 cmd, u16 size) { struct sk_buff *skb; int err; if (sock->ssap == 0) return NULL; skb = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, size + LLCP_HEADER_SIZE, &err); if (skb == NULL) { pr_err("Could not allocate PDU\n"); return NULL; } skb = llcp_add_header(skb, sock->dsap, sock->ssap, cmd); return skb; } int nfc_llcp_send_disconnect(struct nfc_llcp_sock *sock) { struct sk_buff *skb; struct nfc_dev *dev; struct nfc_llcp_local *local; local = sock->local; if (local == NULL) return -ENODEV; dev = sock->dev; if (dev == NULL) return -ENODEV; skb = llcp_allocate_pdu(sock, LLCP_PDU_DISC, 0); if (skb == NULL) return -ENOMEM; skb_queue_tail(&local->tx_queue, skb); return 0; } int nfc_llcp_send_symm(struct nfc_dev *dev) { struct sk_buff *skb; struct nfc_llcp_local *local; u16 size = 0; int err; local = nfc_llcp_find_local(dev); if (local == NULL) return -ENODEV; size += LLCP_HEADER_SIZE; size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); if (skb == NULL) { err = -ENOMEM; goto out; } skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); skb = llcp_add_header(skb, 0, 0, LLCP_PDU_SYMM); __net_timestamp(skb); nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); err = nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); out: nfc_llcp_local_put(local); return err; } int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; const u8 *service_name_tlv = NULL; const u8 *miux_tlv = NULL; const u8 *rw_tlv = NULL; u8 service_name_tlv_length = 0; u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; local = sock->local; if (local == NULL) return -ENODEV; if (sock->service_name != NULL) { service_name_tlv = nfc_llcp_build_tlv(LLCP_TLV_SN, sock->service_name, sock->service_name_len, &service_name_tlv_length); if (!service_name_tlv) { err = -ENOMEM; goto error_tlv; } size += service_name_tlv_length; } /* If the socket parameters are not set, use the local ones */ miux = be16_to_cpu(sock->miux) > LLCP_MAX_MIUX ? local->miux : sock->miux; rw = sock->rw > LLCP_MAX_RW ? local->rw : sock->rw; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); if (!miux_tlv) { err = -ENOMEM; goto error_tlv; } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); if (!rw_tlv) { err = -ENOMEM; goto error_tlv; } size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); skb = llcp_allocate_pdu(sock, LLCP_PDU_CONNECT, size); if (skb == NULL) { err = -ENOMEM; goto error_tlv; } llcp_add_tlv(skb, service_name_tlv, service_name_tlv_length); llcp_add_tlv(skb, miux_tlv, miux_tlv_length); llcp_add_tlv(skb, rw_tlv, rw_tlv_length); skb_queue_tail(&local->tx_queue, skb); err = 0; error_tlv: if (err) pr_err("error %d\n", err); kfree(service_name_tlv); kfree(miux_tlv); kfree(rw_tlv); return err; } int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; const u8 *miux_tlv = NULL; const u8 *rw_tlv = NULL; u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; local = sock->local; if (local == NULL) return -ENODEV; /* If the socket parameters are not set, use the local ones */ miux = be16_to_cpu(sock->miux) > LLCP_MAX_MIUX ? local->miux : sock->miux; rw = sock->rw > LLCP_MAX_RW ? local->rw : sock->rw; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); if (!miux_tlv) { err = -ENOMEM; goto error_tlv; } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); if (!rw_tlv) { err = -ENOMEM; goto error_tlv; } size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); if (skb == NULL) { err = -ENOMEM; goto error_tlv; } llcp_add_tlv(skb, miux_tlv, miux_tlv_length); llcp_add_tlv(skb, rw_tlv, rw_tlv_length); skb_queue_tail(&local->tx_queue, skb); err = 0; error_tlv: if (err) pr_err("error %d\n", err); kfree(miux_tlv); kfree(rw_tlv); return err; } static struct sk_buff *nfc_llcp_allocate_snl(struct nfc_llcp_local *local, size_t tlv_length) { struct sk_buff *skb; struct nfc_dev *dev; u16 size = 0; if (local == NULL) return ERR_PTR(-ENODEV); dev = local->dev; if (dev == NULL) return ERR_PTR(-ENODEV); size += LLCP_HEADER_SIZE; size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; size += tlv_length; skb = alloc_skb(size, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOMEM); skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); skb = llcp_add_header(skb, LLCP_SAP_SDP, LLCP_SAP_SDP, LLCP_PDU_SNL); return skb; } int nfc_llcp_send_snl_sdres(struct nfc_llcp_local *local, struct hlist_head *tlv_list, size_t tlvs_len) { struct nfc_llcp_sdp_tlv *sdp; struct hlist_node *n; struct sk_buff *skb; skb = nfc_llcp_allocate_snl(local, tlvs_len); if (IS_ERR(skb)) return PTR_ERR(skb); hlist_for_each_entry_safe(sdp, n, tlv_list, node) { skb_put_data(skb, sdp->tlv, sdp->tlv_len); hlist_del(&sdp->node); nfc_llcp_free_sdp_tlv(sdp); } skb_queue_tail(&local->tx_queue, skb); return 0; } int nfc_llcp_send_snl_sdreq(struct nfc_llcp_local *local, struct hlist_head *tlv_list, size_t tlvs_len) { struct nfc_llcp_sdp_tlv *sdreq; struct hlist_node *n; struct sk_buff *skb; skb = nfc_llcp_allocate_snl(local, tlvs_len); if (IS_ERR(skb)) return PTR_ERR(skb); mutex_lock(&local->sdreq_lock); if (hlist_empty(&local->pending_sdreqs)) mod_timer(&local->sdreq_timer, jiffies + msecs_to_jiffies(3 * local->remote_lto)); hlist_for_each_entry_safe(sdreq, n, tlv_list, node) { pr_debug("tid %d for %s\n", sdreq->tid, sdreq->uri); skb_put_data(skb, sdreq->tlv, sdreq->tlv_len); hlist_del(&sdreq->node); hlist_add_head(&sdreq->node, &local->pending_sdreqs); } mutex_unlock(&local->sdreq_lock); skb_queue_tail(&local->tx_queue, skb); return 0; } int nfc_llcp_send_dm(struct nfc_llcp_local *local, u8 ssap, u8 dsap, u8 reason) { struct sk_buff *skb; struct nfc_dev *dev; u16 size = 1; /* Reason code */ pr_debug("Sending DM reason 0x%x\n", reason); if (local == NULL) return -ENODEV; dev = local->dev; if (dev == NULL) return -ENODEV; size += LLCP_HEADER_SIZE; size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); if (skb == NULL) return -ENOMEM; skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); skb = llcp_add_header(skb, dsap, ssap, LLCP_PDU_DM); skb_put_data(skb, &reason, 1); skb_queue_head(&local->tx_queue, skb); return 0; } int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, struct msghdr *msg, size_t len) { struct sk_buff *pdu; struct sock *sk = &sock->sk; struct nfc_llcp_local *local; size_t frag_len = 0, remaining_len; u8 *msg_data, *msg_ptr; u16 remote_miu; pr_debug("Send I frame len %zd\n", len); local = sock->local; if (local == NULL) return -ENODEV; /* Remote is ready but has not acknowledged our frames */ if((sock->remote_ready && skb_queue_len(&sock->tx_pending_queue) >= sock->remote_rw && skb_queue_len(&sock->tx_queue) >= 2 * sock->remote_rw)) { pr_err("Pending queue is full %d frames\n", skb_queue_len(&sock->tx_pending_queue)); return -ENOBUFS; } /* Remote is not ready and we've been queueing enough frames */ if ((!sock->remote_ready && skb_queue_len(&sock->tx_queue) >= 2 * sock->remote_rw)) { pr_err("Tx queue is full %d frames\n", skb_queue_len(&sock->tx_queue)); return -ENOBUFS; } msg_data = kmalloc(len, GFP_USER | __GFP_NOWARN); if (msg_data == NULL) return -ENOMEM; if (memcpy_from_msg(msg_data, msg, len)) { kfree(msg_data); return -EFAULT; } remaining_len = len; msg_ptr = msg_data; do { remote_miu = sock->remote_miu > LLCP_MAX_MIU ? LLCP_DEFAULT_MIU : sock->remote_miu; frag_len = min_t(size_t, remote_miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); pdu = llcp_allocate_pdu(sock, LLCP_PDU_I, frag_len + LLCP_SEQUENCE_SIZE); if (pdu == NULL) { kfree(msg_data); return -ENOMEM; } skb_put(pdu, LLCP_SEQUENCE_SIZE); if (likely(frag_len > 0)) skb_put_data(pdu, msg_ptr, frag_len); skb_queue_tail(&sock->tx_queue, pdu); lock_sock(sk); nfc_llcp_queue_i_frames(sock); release_sock(sk); remaining_len -= frag_len; msg_ptr += frag_len; } while (remaining_len > 0); kfree(msg_data); return len; } int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, struct msghdr *msg, size_t len) { struct sk_buff *pdu; struct nfc_llcp_local *local; size_t frag_len = 0, remaining_len; u8 *msg_ptr, *msg_data; u16 remote_miu; int err; pr_debug("Send UI frame len %zd\n", len); local = sock->local; if (local == NULL) return -ENODEV; msg_data = kmalloc(len, GFP_USER | __GFP_NOWARN); if (msg_data == NULL) return -ENOMEM; if (memcpy_from_msg(msg_data, msg, len)) { kfree(msg_data); return -EFAULT; } remaining_len = len; msg_ptr = msg_data; do { remote_miu = sock->remote_miu > LLCP_MAX_MIU ? local->remote_miu : sock->remote_miu; frag_len = min_t(size_t, remote_miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { pr_err("Could not allocate PDU (error=%d)\n", err); len -= remaining_len; if (len == 0) len = err; break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); if (likely(frag_len > 0)) skb_put_data(pdu, msg_ptr, frag_len); /* No need to check for the peer RW for UI frames */ skb_queue_tail(&local->tx_queue, pdu); remaining_len -= frag_len; msg_ptr += frag_len; } while (remaining_len > 0); kfree(msg_data); return len; } int nfc_llcp_send_rr(struct nfc_llcp_sock *sock) { struct sk_buff *skb; struct nfc_llcp_local *local; pr_debug("Send rr nr %d\n", sock->recv_n); local = sock->local; if (local == NULL) return -ENODEV; skb = llcp_allocate_pdu(sock, LLCP_PDU_RR, LLCP_SEQUENCE_SIZE); if (skb == NULL) return -ENOMEM; skb_put(skb, LLCP_SEQUENCE_SIZE); skb->data[2] = sock->recv_n; skb_queue_head(&local->tx_queue, skb); return 0; } |
| 31 2 1 1 1 7 4 2 1 1 3 3 1 8 1 1 2 1 1 1 2 1 2 1 1 2 2 3 1 2 1 1 2 1 1 1 13 13 1 13 13 13 12 2 2 8 7 1 2 6 10 5 2 3 1 1 12 11 1 1 1 8 1 1 3 3 3 3 9 9 9 9 15 9 17 1 1 6 9 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Intel Corporation. All rights reserved. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/nfc.h> #include <linux/sched/signal.h> #include "nfc.h" #include "llcp.h" static int sock_wait_state(struct sock *sk, int state, unsigned long timeo) { DECLARE_WAITQUEUE(wait, current); int err = 0; pr_debug("sk %p", sk); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (sk->sk_state != state) { if (!timeo) { err = -EINPROGRESS; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } static struct proto llcp_sock_proto = { .name = "NFC_LLCP", .owner = THIS_MODULE, .obj_size = sizeof(struct nfc_llcp_sock), }; static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); struct nfc_llcp_local *local; struct nfc_dev *dev; struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; if (!addr || alen < offsetofend(struct sockaddr, sa_family) || addr->sa_family != AF_NFC) return -EINVAL; pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); memset(&llcp_addr, 0, sizeof(llcp_addr)); len = min_t(unsigned int, sizeof(llcp_addr), alen); memcpy(&llcp_addr, addr, len); /* This is going to be a listening socket, dsap must be 0 */ if (llcp_addr.dsap != 0) return -EINVAL; lock_sock(sk); if (sk->sk_state != LLCP_CLOSED) { ret = -EBADFD; goto error; } dev = nfc_get_device(llcp_addr.dev_idx); if (dev == NULL) { ret = -ENODEV; goto error; } local = nfc_llcp_find_local(dev); if (local == NULL) { ret = -ENODEV; goto put_dev; } llcp_sock->dev = dev; llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, llcp_addr.service_name_len, NFC_LLCP_MAX_SERVICE_NAME); llcp_sock->service_name = kmemdup(llcp_addr.service_name, llcp_sock->service_name_len, GFP_KERNEL); if (!llcp_sock->service_name) { ret = -ENOMEM; goto sock_llcp_put_local; } llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -EADDRINUSE; goto free_service_name; } llcp_sock->reserved_ssap = llcp_sock->ssap; nfc_llcp_sock_link(&local->sockets, sk); pr_debug("Socket bound to SAP %d\n", llcp_sock->ssap); sk->sk_state = LLCP_BOUND; nfc_put_device(dev); release_sock(sk); return 0; free_service_name: kfree(llcp_sock->service_name); llcp_sock->service_name = NULL; sock_llcp_put_local: nfc_llcp_local_put(llcp_sock->local); llcp_sock->local = NULL; llcp_sock->dev = NULL; put_dev: nfc_put_device(dev); error: release_sock(sk); return ret; } static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); struct nfc_llcp_local *local; struct nfc_dev *dev; struct sockaddr_nfc_llcp llcp_addr; int len, ret = 0; if (!addr || alen < offsetofend(struct sockaddr, sa_family) || addr->sa_family != AF_NFC) return -EINVAL; pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family); memset(&llcp_addr, 0, sizeof(llcp_addr)); len = min_t(unsigned int, sizeof(llcp_addr), alen); memcpy(&llcp_addr, addr, len); lock_sock(sk); if (sk->sk_state != LLCP_CLOSED) { ret = -EBADFD; goto error; } dev = nfc_get_device(llcp_addr.dev_idx); if (dev == NULL) { ret = -ENODEV; goto error; } local = nfc_llcp_find_local(dev); if (local == NULL) { ret = -ENODEV; goto put_dev; } llcp_sock->dev = dev; llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; nfc_llcp_sock_link(&local->raw_sockets, sk); sk->sk_state = LLCP_BOUND; put_dev: nfc_put_device(dev); error: release_sock(sk); return ret; } static int llcp_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int ret = 0; pr_debug("sk %p backlog %d\n", sk, backlog); lock_sock(sk); if ((sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM) || sk->sk_state != LLCP_BOUND) { ret = -EBADFD; goto error; } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; pr_debug("Socket listening\n"); sk->sk_state = LLCP_LISTEN; error: release_sock(sk); return ret; } static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); u32 opt; int err = 0; pr_debug("%p optname %d\n", sk, optname); if (level != SOL_NFC) return -ENOPROTOOPT; lock_sock(sk); switch (optname) { case NFC_LLCP_RW: if (sk->sk_state == LLCP_CONNECTED || sk->sk_state == LLCP_BOUND || sk->sk_state == LLCP_LISTEN) { err = -EINVAL; break; } err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt > LLCP_MAX_RW) { err = -EINVAL; break; } llcp_sock->rw = (u8) opt; break; case NFC_LLCP_MIUX: if (sk->sk_state == LLCP_CONNECTED || sk->sk_state == LLCP_BOUND || sk->sk_state == LLCP_LISTEN) { err = -EINVAL; break; } err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt > LLCP_MAX_MIUX) { err = -EINVAL; break; } llcp_sock->miux = cpu_to_be16((u16) opt); break; default: err = -ENOPROTOOPT; break; } release_sock(sk); pr_debug("%p rw %d miux %d\n", llcp_sock, llcp_sock->rw, llcp_sock->miux); return err; } static int nfc_llcp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct nfc_llcp_local *local; struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); int len, err = 0; u16 miux, remote_miu; u8 rw; pr_debug("%p optname %d\n", sk, optname); if (level != SOL_NFC) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; local = llcp_sock->local; if (!local) return -ENODEV; len = min_t(u32, len, sizeof(u32)); lock_sock(sk); switch (optname) { case NFC_LLCP_RW: rw = llcp_sock->rw > LLCP_MAX_RW ? local->rw : llcp_sock->rw; if (put_user(rw, (u32 __user *) optval)) err = -EFAULT; break; case NFC_LLCP_MIUX: miux = be16_to_cpu(llcp_sock->miux) > LLCP_MAX_MIUX ? be16_to_cpu(local->miux) : be16_to_cpu(llcp_sock->miux); if (put_user(miux, (u32 __user *) optval)) err = -EFAULT; break; case NFC_LLCP_REMOTE_MIU: remote_miu = llcp_sock->remote_miu > LLCP_MAX_MIU ? local->remote_miu : llcp_sock->remote_miu; if (put_user(remote_miu, (u32 __user *) optval)) err = -EFAULT; break; case NFC_LLCP_REMOTE_LTO: if (put_user(local->remote_lto / 10, (u32 __user *) optval)) err = -EFAULT; break; case NFC_LLCP_REMOTE_RW: if (put_user(llcp_sock->remote_rw, (u32 __user *) optval)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); if (put_user(len, optlen)) return -EFAULT; return err; } void nfc_llcp_accept_unlink(struct sock *sk) { struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); pr_debug("state %d\n", sk->sk_state); list_del_init(&llcp_sock->accept_queue); sk_acceptq_removed(llcp_sock->parent); llcp_sock->parent = NULL; sock_put(sk); } void nfc_llcp_accept_enqueue(struct sock *parent, struct sock *sk) { struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); struct nfc_llcp_sock *llcp_sock_parent = nfc_llcp_sock(parent); /* Lock will be free from unlink */ sock_hold(sk); list_add_tail(&llcp_sock->accept_queue, &llcp_sock_parent->accept_queue); llcp_sock->parent = parent; sk_acceptq_added(parent); } struct sock *nfc_llcp_accept_dequeue(struct sock *parent, struct socket *newsock) { struct nfc_llcp_sock *lsk, *n, *llcp_parent; struct sock *sk; llcp_parent = nfc_llcp_sock(parent); list_for_each_entry_safe(lsk, n, &llcp_parent->accept_queue, accept_queue) { sk = &lsk->sk; lock_sock(sk); if (sk->sk_state == LLCP_CLOSED) { release_sock(sk); nfc_llcp_accept_unlink(sk); continue; } if (sk->sk_state == LLCP_CONNECTED || !newsock) { list_del_init(&lsk->accept_queue); sock_put(sk); if (newsock) sock_graft(sk, newsock); release_sock(sk); pr_debug("Returning sk state %d\n", sk->sk_state); sk_acceptq_removed(parent); return sk; } release_sock(sk); } return NULL; } static int llcp_sock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *new_sk; long timeo; int ret = 0; pr_debug("parent %p\n", sk); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_state != LLCP_LISTEN) { ret = -EBADFD; goto error; } timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* Wait for an incoming connection. */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(new_sk = nfc_llcp_accept_dequeue(sk, newsock))) { set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { ret = -EAGAIN; break; } if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (ret) goto error; newsock->state = SS_CONNECTED; pr_debug("new socket %p\n", new_sk); error: release_sock(sk); return ret; } static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, llcp_addr, uaddr); if (llcp_sock == NULL || llcp_sock->dev == NULL) return -EBADFD; pr_debug("%p %d %d %d\n", sk, llcp_sock->target_idx, llcp_sock->dsap, llcp_sock->ssap); memset(llcp_addr, 0, sizeof(*llcp_addr)); lock_sock(sk); if (!llcp_sock->dev) { release_sock(sk); return -EBADFD; } llcp_addr->sa_family = AF_NFC; llcp_addr->dev_idx = llcp_sock->dev->idx; llcp_addr->target_idx = llcp_sock->target_idx; llcp_addr->nfc_protocol = llcp_sock->nfc_protocol; llcp_addr->dsap = llcp_sock->dsap; llcp_addr->ssap = llcp_sock->ssap; llcp_addr->service_name_len = llcp_sock->service_name_len; memcpy(llcp_addr->service_name, llcp_sock->service_name, llcp_addr->service_name_len); release_sock(sk); return sizeof(struct sockaddr_nfc_llcp); } static inline __poll_t llcp_accept_poll(struct sock *parent) { struct nfc_llcp_sock *llcp_sock, *parent_sock; struct sock *sk; parent_sock = nfc_llcp_sock(parent); list_for_each_entry(llcp_sock, &parent_sock->accept_queue, accept_queue) { sk = &llcp_sock->sk; if (sk->sk_state == LLCP_CONNECTED) return EPOLLIN | EPOLLRDNORM; } return 0; } static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask = 0; pr_debug("%p\n", sk); sock_poll_wait(file, sock, wait); if (sk->sk_state == LLCP_LISTEN) return llcp_accept_poll(sk); if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == LLCP_CLOSED) mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); pr_debug("mask 0x%x\n", mask); return mask; } static int llcp_sock_release(struct socket *sock) { struct sock *sk = sock->sk; struct nfc_llcp_local *local; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); int err = 0; if (!sk) return 0; pr_debug("%p\n", sk); local = llcp_sock->local; if (local == NULL) { err = -ENODEV; goto out; } lock_sock(sk); /* Send a DISC */ if (sk->sk_state == LLCP_CONNECTED) nfc_llcp_send_disconnect(llcp_sock); if (sk->sk_state == LLCP_LISTEN) { struct nfc_llcp_sock *lsk, *n; struct sock *accept_sk; list_for_each_entry_safe(lsk, n, &llcp_sock->accept_queue, accept_queue) { accept_sk = &lsk->sk; lock_sock(accept_sk); nfc_llcp_send_disconnect(lsk); nfc_llcp_accept_unlink(accept_sk); release_sock(accept_sk); } } if (sock->type == SOCK_RAW) nfc_llcp_sock_unlink(&local->raw_sockets, sk); else nfc_llcp_sock_unlink(&local->sockets, sk); if (llcp_sock->reserved_ssap < LLCP_SAP_MAX) nfc_llcp_put_ssap(llcp_sock->local, llcp_sock->ssap); release_sock(sk); out: sock_orphan(sk); sock_put(sk); return err; } static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, int len, int flags) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); struct sockaddr_nfc_llcp *addr = (struct sockaddr_nfc_llcp *)_addr; struct nfc_dev *dev; struct nfc_llcp_local *local; int ret = 0; pr_debug("sock %p sk %p flags 0x%x\n", sock, sk, flags); if (!addr || len < sizeof(*addr) || addr->sa_family != AF_NFC) return -EINVAL; if (addr->service_name_len == 0 && addr->dsap == 0) return -EINVAL; pr_debug("addr dev_idx=%u target_idx=%u protocol=%u\n", addr->dev_idx, addr->target_idx, addr->nfc_protocol); lock_sock(sk); if (sk->sk_state == LLCP_CONNECTED) { ret = -EISCONN; goto error; } if (sk->sk_state == LLCP_CONNECTING) { ret = -EINPROGRESS; goto error; } dev = nfc_get_device(addr->dev_idx); if (dev == NULL) { ret = -ENODEV; goto error; } local = nfc_llcp_find_local(dev); if (local == NULL) { ret = -ENODEV; goto put_dev; } device_lock(&dev->dev); if (dev->dep_link_up == false) { ret = -ENOLINK; device_unlock(&dev->dev); goto sock_llcp_put_local; } device_unlock(&dev->dev); if (local->rf_mode == NFC_RF_INITIATOR && addr->target_idx != local->target_idx) { ret = -ENOLINK; goto sock_llcp_put_local; } llcp_sock->dev = dev; llcp_sock->local = local; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -ENOMEM; goto sock_llcp_nullify; } llcp_sock->reserved_ssap = llcp_sock->ssap; if (addr->service_name_len == 0) llcp_sock->dsap = addr->dsap; else llcp_sock->dsap = LLCP_SAP_SDP; llcp_sock->nfc_protocol = addr->nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, addr->service_name_len, NFC_LLCP_MAX_SERVICE_NAME); llcp_sock->service_name = kmemdup(addr->service_name, llcp_sock->service_name_len, GFP_KERNEL); if (!llcp_sock->service_name) { ret = -ENOMEM; goto sock_llcp_release; } nfc_llcp_sock_link(&local->connecting_sockets, sk); ret = nfc_llcp_send_connect(llcp_sock); if (ret) goto sock_unlink; sk->sk_state = LLCP_CONNECTING; ret = sock_wait_state(sk, LLCP_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); if (ret && ret != -EINPROGRESS) goto sock_unlink; release_sock(sk); return ret; sock_unlink: nfc_llcp_sock_unlink(&local->connecting_sockets, sk); kfree(llcp_sock->service_name); llcp_sock->service_name = NULL; sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); sock_llcp_nullify: llcp_sock->local = NULL; llcp_sock->dev = NULL; sock_llcp_put_local: nfc_llcp_local_put(local); put_dev: nfc_put_device(dev); error: release_sock(sk); return ret; } static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); int ret; pr_debug("sock %p sk %p", sock, sk); ret = sock_error(sk); if (ret) return ret; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; lock_sock(sk); if (!llcp_sock->local) { release_sock(sk); return -ENODEV; } if (sk->sk_type == SOCK_DGRAM) { if (sk->sk_state != LLCP_BOUND) { release_sock(sk); return -ENOTCONN; } DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr, msg->msg_name); if (msg->msg_namelen < sizeof(*addr)) { release_sock(sk); return -EINVAL; } release_sock(sk); return nfc_llcp_send_ui_frame(llcp_sock, addr->dsap, addr->ssap, msg, len); } if (sk->sk_state != LLCP_CONNECTED) { release_sock(sk); return -ENOTCONN; } release_sock(sk); return nfc_llcp_send_i_frame(llcp_sock, msg, len); } static int llcp_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; unsigned int copied, rlen; struct sk_buff *skb, *cskb; int err = 0; pr_debug("%p %zu\n", sk, len); lock_sock(sk); if (sk->sk_state == LLCP_CLOSED && skb_queue_empty(&sk->sk_receive_queue)) { release_sock(sk); return 0; } release_sock(sk); if (flags & (MSG_OOB)) return -EOPNOTSUPP; skb = skb_recv_datagram(sk, flags, &err); if (!skb) { pr_err("Recv datagram failed state %d %d %d", sk->sk_state, err, sock_error(sk)); if (sk->sk_shutdown & RCV_SHUTDOWN) return 0; return err; } rlen = skb->len; /* real length of skb */ copied = min_t(unsigned int, rlen, len); cskb = skb; if (skb_copy_datagram_msg(cskb, 0, msg, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; } sock_recv_timestamp(msg, sk, skb); if (sk->sk_type == SOCK_DGRAM && msg->msg_name) { struct nfc_llcp_ui_cb *ui_cb = nfc_llcp_ui_skb_cb(skb); DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, sockaddr, msg->msg_name); msg->msg_namelen = sizeof(struct sockaddr_nfc_llcp); pr_debug("Datagram socket %d %d\n", ui_cb->dsap, ui_cb->ssap); memset(sockaddr, 0, sizeof(*sockaddr)); sockaddr->sa_family = AF_NFC; sockaddr->nfc_protocol = NFC_PROTO_NFC_DEP; sockaddr->dsap = ui_cb->dsap; sockaddr->ssap = ui_cb->ssap; } /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { /* SOCK_STREAM: re-queue skb if it contains unreceived data */ if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { skb_pull(skb, copied); if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); goto done; } } kfree_skb(skb); } /* XXX Queue backlogged skbs */ done: /* SOCK_SEQPACKET: return real length if MSG_TRUNC is set */ if (sk->sk_type == SOCK_SEQPACKET && (flags & MSG_TRUNC)) copied = rlen; return copied; } static const struct proto_ops llcp_sock_ops = { .family = PF_NFC, .owner = THIS_MODULE, .bind = llcp_sock_bind, .connect = llcp_sock_connect, .release = llcp_sock_release, .socketpair = sock_no_socketpair, .accept = llcp_sock_accept, .getname = llcp_sock_getname, .poll = llcp_sock_poll, .ioctl = sock_no_ioctl, .listen = llcp_sock_listen, .shutdown = sock_no_shutdown, .setsockopt = nfc_llcp_setsockopt, .getsockopt = nfc_llcp_getsockopt, .sendmsg = llcp_sock_sendmsg, .recvmsg = llcp_sock_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops llcp_rawsock_ops = { .family = PF_NFC, .owner = THIS_MODULE, .bind = llcp_raw_sock_bind, .connect = sock_no_connect, .release = llcp_sock_release, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = llcp_sock_getname, .poll = llcp_sock_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = sock_no_sendmsg, .recvmsg = llcp_sock_recvmsg, .mmap = sock_no_mmap, }; static void llcp_sock_destruct(struct sock *sk) { struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); pr_debug("%p\n", sk); if (sk->sk_state == LLCP_CONNECTED) nfc_put_device(llcp_sock->dev); skb_queue_purge(&sk->sk_receive_queue); nfc_llcp_sock_free(llcp_sock); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Freeing alive NFC LLCP socket %p\n", sk); return; } } struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp, int kern) { struct sock *sk; struct nfc_llcp_sock *llcp_sock; sk = sk_alloc(&init_net, PF_NFC, gfp, &llcp_sock_proto, kern); if (!sk) return NULL; llcp_sock = nfc_llcp_sock(sk); sock_init_data(sock, sk); sk->sk_state = LLCP_CLOSED; sk->sk_protocol = NFC_SOCKPROTO_LLCP; sk->sk_type = type; sk->sk_destruct = llcp_sock_destruct; llcp_sock->ssap = 0; llcp_sock->dsap = LLCP_SAP_SDP; llcp_sock->rw = LLCP_MAX_RW + 1; llcp_sock->miux = cpu_to_be16(LLCP_MAX_MIUX + 1); llcp_sock->send_n = llcp_sock->send_ack_n = 0; llcp_sock->recv_n = llcp_sock->recv_ack_n = 0; llcp_sock->remote_ready = 1; llcp_sock->reserved_ssap = LLCP_SAP_MAX; nfc_llcp_socket_remote_param_init(llcp_sock); skb_queue_head_init(&llcp_sock->tx_queue); skb_queue_head_init(&llcp_sock->tx_pending_queue); INIT_LIST_HEAD(&llcp_sock->accept_queue); if (sock != NULL) sock->state = SS_UNCONNECTED; return sk; } void nfc_llcp_sock_free(struct nfc_llcp_sock *sock) { kfree(sock->service_name); skb_queue_purge(&sock->tx_queue); skb_queue_purge(&sock->tx_pending_queue); list_del_init(&sock->accept_queue); sock->parent = NULL; nfc_llcp_local_put(sock->local); } static int llcp_sock_create(struct net *net, struct socket *sock, const struct nfc_protocol *nfc_proto, int kern) { struct sock *sk; pr_debug("%p\n", sock); if (sock->type != SOCK_STREAM && sock->type != SOCK_DGRAM && sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (sock->type == SOCK_RAW) { if (!capable(CAP_NET_RAW)) return -EPERM; sock->ops = &llcp_rawsock_ops; } else { sock->ops = &llcp_sock_ops; } sk = nfc_llcp_sock_alloc(sock, sock->type, GFP_ATOMIC, kern); if (sk == NULL) return -ENOMEM; return 0; } static const struct nfc_protocol llcp_nfc_proto = { .id = NFC_SOCKPROTO_LLCP, .proto = &llcp_sock_proto, .owner = THIS_MODULE, .create = llcp_sock_create }; int __init nfc_llcp_sock_init(void) { return nfc_proto_register(&llcp_nfc_proto); } void nfc_llcp_sock_exit(void) { nfc_proto_unregister(&llcp_nfc_proto); } |
| 2704 2705 2704 1033 995 858 858 1448 1 1448 776 31079 28018 29476 25183 1823 17965 31062 30955 17947 101 100 104 3 103 76 104 32062 31172 27562 32046 556 117 27433 8321 30993 27646 31977 11 12155 32056 1059 1898 32046 25 641 117 26 557 71 32076 766 8866 32076 2 32137 11721 32064 7 67 5 9059 2 2 1 9062 31513 31211 9066 133 5 133 31425 31491 10691 31403 3 3 9 9 31427 3 31485 8 8 8 211 212 71 5 5 4 5 5 5 5 5 4 2697 2698 18 1 176 17 21 23 132 178 20 20 18 20 17 20 20 17 17 44 44 1 29 47 6 47 48 48 1 28 37 37 37 37 307 307 307 336 94 337 327 94 326 336 326 39 248 9 55 155 243 94 38 29 9 374 37 336 375 216 216 584 4761 1543 1543 1543 1543 1543 5 409 410 410 410 410 410 410 410 410 410 6 6 6 6 6 6 6 6 6451 791 20 48 44 1540 4761 70 5 1 410 4 2698 6 1 3 140 33242 36034 830 4 1051 36096 35493 33242 28649 27752 33156 33251 626 33100 29839 31581 32055 1 1051 33517 33574 14336 31721 29836 832 1051 12791 1 758 12817 46 12794 31288 6389 6397 1 1509 8761 33501 13507 13841 12 16152 2421 2429 56 15717 8522 8525 1 69 59 9 1 5 74 1 16 1651 7258 2551 2052 2533 334 5 2009 1937 8 8 1937 178 63 1822 252 252 1822 3 1821 3 1809 1450 324 5 158 2 1443 163 1769 2549 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/sprintf.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #include <linux/notifier.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <linux/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); noinline static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); noinline static long long simple_strntoll(const char *cp, char **endp, unsigned int base, size_t max_chars) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, endp, base, max_chars - 1); return simple_strntoull(cp, endp, base, max_chars); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoll); static inline int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 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), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); enum format_state { FORMAT_STATE_NONE, /* Just a string part */ FORMAT_STATE_NUM, FORMAT_STATE_WIDTH, FORMAT_STATE_PRECISION, FORMAT_STATE_CHAR, FORMAT_STATE_STR, FORMAT_STATE_PTR, FORMAT_STATE_PERCENT_CHAR, FORMAT_STATE_INVALID, }; struct printf_spec { unsigned char flags; /* flags to number() */ unsigned char base; /* number base, 8, 10 or 16 only */ short precision; /* # of digits/chars */ int field_width; /* width of output field */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static bool filled_random_ptr_key __read_mostly; static siphash_key_t ptr_key __read_mostly; static int fill_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Pairs with smp_rmb() before reading ptr_key. */ smp_wmb(); WRITE_ONCE(filled_random_ptr_key, true); return NOTIFY_DONE; } static int __init vsprintf_init_hashval(void) { static struct notifier_block fill_ptr_key_nb = { .notifier_call = fill_ptr_key }; execute_with_initialized_rng(&fill_ptr_key_nb); return 0; } subsys_initcall(vsprintf_init_hashval) /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (!READ_ONCE(filled_random_ptr_key)) return -EBUSY; /* Pairs with smp_wmb() after writing ptr_key. */ smp_rmb(); #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_hardirq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev_is_partition(bdev)) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev_partno(bdev), spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *hex_range(char *buf, char *end, u64 start_val, u64 end_val, struct printf_spec spec) { buf = number(buf, end, start_val, spec); if (start_val == end_val) return buf; if (buf < end) *buf = '-'; ++buf; return number(buf, end, end_val, spec); } static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = hex_range(p, pend, res->start, res->end, *specp); } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *range_string(char *buf, char *end, const struct range *range, struct printf_spec spec, const char *fmt) { char sym[sizeof("[range 0x0123456789abcdef-0x0123456789abcdef]")]; char *p = sym, *pend = sym + sizeof(sym); struct printf_spec range_spec = { .field_width = 2 + 2 * sizeof(range->start), /* 0x + 2 * 8 */ .flags = SPECIAL | SMALL | ZEROPAD, .base = 16, .precision = -1, }; if (check_pointer(&buf, end, range, spec)) return buf; p = string_nocheck(p, pend, "[range ", default_str_spec); p = hex_range(p, pend, range->start, range->end, range_spec); *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); bool first = true; int rbot, rtop; if (check_pointer(&buf, end, bitmap, spec)) return buf; for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) { if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rtop == rbot + 1) continue; if (buf < end) *buf = '-'; buf = number(++buf, end, rtop - 1, default_dec_spec); } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; u32 orig, val; if (fmt[1] != 'c' || fmt[2] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); val = orig & ~BIT(31); for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> (i * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } *p++ = ' '; strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian"); p += strlen(p); *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; buf = number(buf, end, flags, default_flag_spec); if (buf < end) *buf = '('; buf++; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } if (buf < end) *buf = ')'; buf++; return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { if (*fmt == 'r' && fmt[1] == 'a') return range_string(buf, end, ptr, spec, fmt); return resource_string(buf, end, ptr, spec, fmt); } int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* Used for Rust formatting ('%pA'). */ char *rust_fmt_argument(char *buf, char *end, void *ptr); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'ra' For struct ranges, e.g., [range 0x0000000000000000 - 0x00000000000000ff] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. * * There is also a '%pA' format specifier, but it is only intended to be used * from Rust code to format core::fmt::Arguments. Do *not* use it from C. * See rust/kernel/print.rs for details. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_or_range(fmt, buf, end, ptr, spec); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'A': if (!IS_ENABLED(CONFIG_RUST)) { WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); return error_string(buf, end, "(%pA?)", spec); } return rust_fmt_argument(buf, end, ptr); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } struct fmt { const char *str; unsigned char state; // enum format_state unsigned char size; // size of numbers }; #define SPEC_CHAR(x, flag) [(x)-32] = flag static unsigned char spec_flag(unsigned char c) { static const unsigned char spec_flag_array[] = { SPEC_CHAR(' ', SPACE), SPEC_CHAR('#', SPECIAL), SPEC_CHAR('+', PLUS), SPEC_CHAR('-', LEFT), SPEC_CHAR('0', ZEROPAD), }; c -= 32; return (c < sizeof(spec_flag_array)) ? spec_flag_array[c] : 0; } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack struct fmt format_decode(struct fmt fmt, struct printf_spec *spec) { const char *start = fmt.str; char flag; /* we finished early by reading the field width */ if (unlikely(fmt.state == FORMAT_STATE_WIDTH)) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } fmt.state = FORMAT_STATE_NONE; goto precision; } /* we finished early by reading the precision */ if (unlikely(fmt.state == FORMAT_STATE_PRECISION)) { if (spec->precision < 0) spec->precision = 0; fmt.state = FORMAT_STATE_NONE; goto qualifier; } /* By default */ fmt.state = FORMAT_STATE_NONE; for (; *fmt.str ; fmt.str++) { if (*fmt.str == '%') break; } /* Return the current non-format string */ if (fmt.str != start || !*fmt.str) return fmt; /* Process flags. This also skips the first '%' */ spec->flags = 0; do { /* this also skips first '%' */ flag = spec_flag(*++fmt.str); spec->flags |= flag; } while (flag); /* get field width */ spec->field_width = -1; if (isdigit(*fmt.str)) spec->field_width = skip_atoi(&fmt.str); else if (unlikely(*fmt.str == '*')) { /* it's the next argument */ fmt.state = FORMAT_STATE_WIDTH; fmt.str++; return fmt; } precision: /* get the precision */ spec->precision = -1; if (unlikely(*fmt.str == '.')) { fmt.str++; if (isdigit(*fmt.str)) { spec->precision = skip_atoi(&fmt.str); if (spec->precision < 0) spec->precision = 0; } else if (*fmt.str == '*') { /* it's the next argument */ fmt.state = FORMAT_STATE_PRECISION; fmt.str++; return fmt; } } qualifier: /* Set up default numeric format */ spec->base = 10; fmt.state = FORMAT_STATE_NUM; fmt.size = sizeof(int); static const struct format_state { unsigned char state; unsigned char size; unsigned char flags_or_double_size; unsigned char base; } lookup_state[256] = { // Length ['l'] = { 0, sizeof(long), sizeof(long long) }, ['L'] = { 0, sizeof(long long) }, ['h'] = { 0, sizeof(short), sizeof(char) }, ['H'] = { 0, sizeof(char) }, // Questionable historical ['z'] = { 0, sizeof(size_t) }, ['t'] = { 0, sizeof(ptrdiff_t) }, // Non-numeric formats ['c'] = { FORMAT_STATE_CHAR }, ['s'] = { FORMAT_STATE_STR }, ['p'] = { FORMAT_STATE_PTR }, ['%'] = { FORMAT_STATE_PERCENT_CHAR }, // Numerics ['o'] = { FORMAT_STATE_NUM, 0, 0, 8 }, ['x'] = { FORMAT_STATE_NUM, 0, SMALL, 16 }, ['X'] = { FORMAT_STATE_NUM, 0, 0, 16 }, ['d'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, ['i'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, ['u'] = { FORMAT_STATE_NUM, 0, 0, 10, }, /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ }; const struct format_state *p = lookup_state + (u8)*fmt.str; if (p->size) { fmt.size = p->size; if (p->flags_or_double_size && fmt.str[0] == fmt.str[1]) { fmt.size = p->flags_or_double_size; fmt.str++; } fmt.str++; p = lookup_state + *fmt.str; } if (p->state) { if (p->base) spec->base = p->base; spec->flags |= p->flags_or_double_size; fmt.state = p->state; fmt.str++; return fmt; } WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt.str); fmt.state = FORMAT_STATE_INVALID; return fmt; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /* * Turn a 1/2/4-byte value into a 64-bit one for printing: truncate * as necessary and deal with signedness. * * 'size' is the size of the value in bytes. */ static unsigned long long convert_num_spec(unsigned int val, int size, struct printf_spec spec) { unsigned int shift = 32 - size*8; val <<= shift; if (!(spec.flags & SIGN)) return val >> shift; return (int)val >> shift; } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt_str: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt_str, va_list args) { char *str, *end; struct printf_spec spec = {0}; struct fmt fmt = { .str = fmt_str, .state = FORMAT_STATE_NONE, }; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt.str) { const char *old_fmt = fmt.str; fmt = format_decode(fmt, &spec); switch (fmt.state) { case FORMAT_STATE_NONE: { int read = fmt.str - old_fmt; if (str < end) { int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; continue; } case FORMAT_STATE_NUM: { unsigned long long num; if (fmt.size <= sizeof(int)) num = convert_num_spec(va_arg(args, int), fmt.size, spec); else num = va_arg(args, long long); str = number(str, end, num, spec); continue; } case FORMAT_STATE_WIDTH: set_field_width(&spec, va_arg(args, int)); continue; case FORMAT_STATE_PRECISION: set_precision(&spec, va_arg(args, int)); continue; case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } continue; } case FORMAT_STATE_STR: str = string(str, end, va_arg(args, char *), spec); continue; case FORMAT_STATE_PTR: str = pointer(fmt.str, str, end, va_arg(args, void *), spec); while (isalnum(*fmt.str)) fmt.str++; continue; case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; continue; default: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; if (unlikely(!size)) return 0; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; return size - 1; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt_str: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt_str, va_list args) { struct fmt fmt = { .str = fmt_str, .state = FORMAT_STATE_NONE, }; struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt.str) { fmt = format_decode(fmt, &spec); switch (fmt.state) { case FORMAT_STATE_NONE: case FORMAT_STATE_PERCENT_CHAR: break; case FORMAT_STATE_INVALID: goto out; case FORMAT_STATE_WIDTH: case FORMAT_STATE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt.str == 'p') set_field_width(&spec, width); break; case FORMAT_STATE_CHAR: save_arg(char); break; case FORMAT_STATE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_STATE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt.str) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt.str)) { save_arg(void *); break; } str = pointer(fmt.str, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt.str)) fmt.str++; break; case FORMAT_STATE_NUM: if (fmt.size > sizeof(int)) { save_arg(long long); } else { save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt_str: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt_str, const u32 *bin_buf) { struct fmt fmt = { .str = fmt_str, .state = FORMAT_STATE_NONE, }; struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt.str) { const char *old_fmt = fmt.str; unsigned long long num; fmt = format_decode(fmt, &spec); switch (fmt.state) { case FORMAT_STATE_NONE: { int read = fmt.str - old_fmt; if (str < end) { int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; continue; } case FORMAT_STATE_WIDTH: set_field_width(&spec, get_arg(int)); continue; case FORMAT_STATE_PRECISION: set_precision(&spec, get_arg(int)); continue; case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } continue; } case FORMAT_STATE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); continue; } case FORMAT_STATE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt.str) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt.str)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt.str, str, end, get_arg(void *), spec); while (isalnum(*fmt.str)) fmt.str++; continue; } case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; continue; case FORMAT_STATE_INVALID: goto out; case FORMAT_STATE_NUM: if (fmt.size > sizeof(int)) { num = get_arg(long long); } else { num = convert_num_spec(get_arg(int), fmt.size, spec); } str = number(str, end, num, spec); continue; } } /* while(*fmt.str) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) __set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ __clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && !isodigit(digit)) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, &next, base, field_width >= 0 ? field_width : INT_MAX); else val.u = simple_strntoull(str, &next, base, field_width >= 0 ? field_width : INT_MAX); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 3 3 3 615 613 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DESC_H #define _ASM_X86_DESC_H #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> #include <asm/fixmap.h> #include <asm/irq_vectors.h> #include <asm/cpu_entry_area.h> #include <linux/debug_locks.h> #include <linux/smp.h> #include <linux/percpu.h> static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info) { desc->limit0 = info->limit & 0x0ffff; desc->base0 = (info->base_addr & 0x0000ffff); desc->base1 = (info->base_addr & 0x00ff0000) >> 16; desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; /* Set the ACCESS bit so it can be mapped RO */ desc->type |= 1; desc->s = 1; desc->dpl = 0x3; desc->p = info->seg_not_present ^ 1; desc->limit1 = (info->limit & 0xf0000) >> 16; desc->avl = info->useable; desc->d = info->seg_32bit; desc->g = info->limit_in_pages; desc->base2 = (info->base_addr & 0xff000000) >> 24; /* * Don't allow setting of the lm bit. It would confuse * user_64bit_mode and would get overridden by sysret anyway. */ desc->l = 0; } struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); DECLARE_INIT_PER_CPU(gdt_page); /* Provide the original GDT */ static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) { return per_cpu(gdt_page, cpu).gdt; } /* Provide the current original GDT */ static inline struct desc_struct *get_current_gdt_rw(void) { return this_cpu_ptr(&gdt_page)->gdt; } /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ static inline struct desc_struct *get_current_gdt_ro(void) { return get_cpu_gdt_ro(smp_processor_id()); } /* Provide the physical address of the GDT page. */ static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) { return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); } static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, unsigned dpl, unsigned ist, unsigned seg) { gate->offset_low = (u16) func; gate->bits.p = 1; gate->bits.dpl = dpl; gate->bits.zero = 0; gate->bits.type = type; gate->offset_middle = (u16) (func >> 16); #ifdef CONFIG_X86_64 gate->segment = __KERNEL_CS; gate->bits.ist = ist; gate->reserved = 0; gate->offset_high = (u32) (func >> 32); #else gate->segment = seg; gate->bits.ist = 0; #endif } static inline int desc_empty(const void *ptr) { const u32 *desc = ptr; return !(desc[0] | desc[1]); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define load_TR_desc() native_load_tr_desc() #define load_gdt(dtr) native_load_gdt(dtr) #define load_idt(dtr) native_load_idt(dtr) #define load_tr(tr) asm volatile("ltr %0"::"m" (tr)) #define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) #define store_gdt(dtr) native_store_gdt(dtr) #define store_tr(tr) (tr = native_store_tr()) #define load_TLS(t, cpu) native_load_tls(t, cpu) #define set_ldt native_set_ldt #define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc) #define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type) #define write_idt_entry(dt, entry, g) native_write_idt_entry(dt, entry, g) static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { } static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { } #endif /* CONFIG_PARAVIRT_XXL */ #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) { memcpy(&idt[entry], gate, sizeof(*gate)); } static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc) { memcpy(&ldt[entry], desc, 8); } static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type) { unsigned int size; switch (type) { case DESC_TSS: size = sizeof(tss_desc); break; case DESC_LDT: size = sizeof(ldt_desc); break; default: size = sizeof(*gdt); break; } memcpy(&gdt[entry], desc, size); } static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size) { struct ldttss_desc *desc = d; memset(desc, 0, sizeof(*desc)); desc->limit0 = (u16) size; desc->base0 = (u16) addr; desc->base1 = (addr >> 16) & 0xFF; desc->type = type; desc->p = 1; desc->limit1 = (size >> 16) & 0xF; desc->base2 = (addr >> 24) & 0xFF; #ifdef CONFIG_X86_64 desc->base3 = (u32) (addr >> 32); #endif } static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } #define set_tss_desc(cpu, addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr) static inline void native_set_ldt(const void *addr, unsigned int entries) { if (likely(entries == 0)) asm volatile("lldt %w0"::"q" (0)); else { unsigned cpu = smp_processor_id(); ldt_desc ldt; set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, entries * LDT_ENTRY_SIZE - 1); write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, &ldt, DESC_LDT); asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); } } static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); } static __always_inline void native_load_idt(const struct desc_ptr *dtr) { asm volatile("lidt %0"::"m" (*dtr)); } static inline void native_store_gdt(struct desc_ptr *dtr) { asm volatile("sgdt %0":"=m" (*dtr)); } static inline void store_idt(struct desc_ptr *dtr) { asm volatile("sidt %0":"=m" (*dtr)); } static inline void native_gdt_invalidate(void) { const struct desc_ptr invalid_gdt = { .address = 0, .size = 0 }; native_load_gdt(&invalid_gdt); } static inline void native_idt_invalidate(void) { const struct desc_ptr invalid_idt = { .address = 0, .size = 0 }; native_load_idt(&invalid_idt); } /* * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is * a read-only remapping. To prevent a page fault, the GDT is switched to the * original writeable version when needed. */ #ifdef CONFIG_X86_64 static inline void native_load_tr_desc(void) { struct desc_ptr gdt; int cpu = raw_smp_processor_id(); bool restore = 0; struct desc_struct *fixmap_gdt; native_store_gdt(&gdt); fixmap_gdt = get_cpu_gdt_ro(cpu); /* * If the current GDT is the read-only fixmap, swap to the original * writeable version. Swap back at the end. */ if (gdt.address == (unsigned long)fixmap_gdt) { load_direct_gdt(cpu); restore = 1; } asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); if (restore) load_fixmap_gdt(cpu); } #else static inline void native_load_tr_desc(void) { asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } #endif static inline unsigned long native_store_tr(void) { unsigned long tr; asm volatile("str %0":"=r" (tr)); return tr; } static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) { struct desc_struct *gdt = get_cpu_gdt_rw(cpu); unsigned int i; for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } DECLARE_PER_CPU(bool, __tss_limit_invalid); static inline void force_reload_TR(void) { struct desc_struct *d = get_current_gdt_rw(); tss_desc tss; memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); /* * LTR requires an available TSS, and the TSS is currently * busy. Make it be available so that LTR will work. */ tss.type = DESC_TSS; write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); load_TR_desc(); this_cpu_write(__tss_limit_invalid, false); } /* * Call this if you need the TSS limit to be correct, which should be the case * if and only if you have TIF_IO_BITMAP set or you're switching to a task * with TIF_IO_BITMAP set. */ static inline void refresh_tss_limit(void) { DEBUG_LOCKS_WARN_ON(preemptible()); if (unlikely(this_cpu_read(__tss_limit_invalid))) force_reload_TR(); } /* * If you do something evil that corrupts the cached TSS limit (I'm looking * at you, VMX exits), call this function. * * The optimization here is that the TSS limit only matters for Linux if the * IO bitmap is in use. If the TSS limit gets forced to its minimum value, * everything works except that IO bitmap will be ignored and all CPL 3 IO * instructions will #GP, which is exactly what we want for normal tasks. */ static inline void invalidate_tss_limit(void) { DEBUG_LOCKS_WARN_ON(preemptible()); if (unlikely(test_thread_flag(TIF_IO_BITMAP))) force_reload_TR(); else this_cpu_write(__tss_limit_invalid, true); } /* This intentionally ignores lm, since 32-bit apps don't have that field. */ #define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ (info)->read_exec_only == 1 && \ (info)->seg_32bit == 0 && \ (info)->limit_in_pages == 0 && \ (info)->seg_not_present == 1 && \ (info)->useable == 0) /* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ static inline bool LDT_zero(const struct user_desc *info) { return (info->base_addr == 0 && info->limit == 0 && info->contents == 0 && info->read_exec_only == 0 && info->seg_32bit == 0 && info->limit_in_pages == 0 && info->seg_not_present == 0 && info->useable == 0); } static inline void clear_LDT(void) { set_ldt(NULL, 0); } static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); } static inline void set_desc_base(struct desc_struct *desc, unsigned long base) { desc->base0 = base & 0xffff; desc->base1 = (base >> 16) & 0xff; desc->base2 = (base >> 24) & 0xff; } static inline unsigned long get_desc_limit(const struct desc_struct *desc) { return desc->limit0 | (desc->limit1 << 16); } static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) { desc->limit0 = limit & 0xffff; desc->limit1 = (limit >> 16) & 0xf; } static inline void init_idt_data(struct idt_data *data, unsigned int n, const void *addr) { BUG_ON(n > 0xFF); memset(data, 0, sizeof(*data)); data->vector = n; data->addr = addr; data->segment = __KERNEL_CS; data->bits.type = GATE_INTERRUPT; data->bits.p = 1; } static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) { unsigned long addr = (unsigned long) d->addr; gate->offset_low = (u16) addr; gate->segment = (u16) d->segment; gate->bits = d->bits; gate->offset_middle = (u16) (addr >> 16); #ifdef CONFIG_X86_64 gate->offset_high = (u32) (addr >> 32); gate->reserved = 0; #endif } extern unsigned long system_vectors[]; extern void load_current_idt(void); extern void idt_setup_early_handler(void); extern void idt_setup_early_traps(void); extern void idt_setup_traps(void); extern void idt_setup_apic_and_irq_gates(void); extern bool idt_is_f00f_address(unsigned long address); #ifdef CONFIG_X86_64 extern void idt_setup_early_pf(void); #else static inline void idt_setup_early_pf(void) { } #endif extern void idt_invalidate(void); #endif /* _ASM_X86_DESC_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 | // SPDX-License-Identifier: GPL-2.0 struct io_timeout_data { struct io_kiocb *req; struct hrtimer timer; struct timespec64 ts; enum hrtimer_mode mode; u32 flags; }; struct io_kiocb *__io_disarm_linked_timeout(struct io_kiocb *req, struct io_kiocb *link); static inline struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req) { struct io_kiocb *link = req->link; if (link && link->opcode == IORING_OP_LINK_TIMEOUT) return __io_disarm_linked_timeout(req, link); return NULL; } __cold void io_flush_timeouts(struct io_ring_ctx *ctx); struct io_cancel_data; int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd); __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all); void io_queue_linked_timeout(struct io_kiocb *req); void io_disarm_next(struct io_kiocb *req); int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_link_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_timeout(struct io_kiocb *req, unsigned int issue_flags); int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags); |
| 70 12 70 70 34 27 27 27 7 7 102 102 53 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * HMAC: Keyed-Hashing for Message Authentication (RFC2104). * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> * * The HMAC implementation is derived from USAGI. * Copyright (c) 2002 Kazunori Miyazawa <miyazawa@linux-ipv6.org> / USAGI */ #include <crypto/hmac.h> #include <crypto/internal/hash.h> #include <crypto/scatterwalk.h> #include <linux/err.h> #include <linux/fips.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/string.h> struct hmac_ctx { struct crypto_shash *hash; /* Contains 'u8 ipad[statesize];', then 'u8 opad[statesize];' */ u8 pads[]; }; static int hmac_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { int bs = crypto_shash_blocksize(parent); int ds = crypto_shash_digestsize(parent); int ss = crypto_shash_statesize(parent); struct hmac_ctx *tctx = crypto_shash_ctx(parent); struct crypto_shash *hash = tctx->hash; u8 *ipad = &tctx->pads[0]; u8 *opad = &tctx->pads[ss]; SHASH_DESC_ON_STACK(shash, hash); unsigned int i; if (fips_enabled && (keylen < 112 / 8)) return -EINVAL; shash->tfm = hash; if (keylen > bs) { int err; err = crypto_shash_digest(shash, inkey, keylen, ipad); if (err) return err; keylen = ds; } else memcpy(ipad, inkey, keylen); memset(ipad + keylen, 0, bs - keylen); memcpy(opad, ipad, bs); for (i = 0; i < bs; i++) { ipad[i] ^= HMAC_IPAD_VALUE; opad[i] ^= HMAC_OPAD_VALUE; } return crypto_shash_init(shash) ?: crypto_shash_update(shash, ipad, bs) ?: crypto_shash_export(shash, ipad) ?: crypto_shash_init(shash) ?: crypto_shash_update(shash, opad, bs) ?: crypto_shash_export(shash, opad); } static int hmac_export(struct shash_desc *pdesc, void *out) { struct shash_desc *desc = shash_desc_ctx(pdesc); return crypto_shash_export(desc, out); } static int hmac_import(struct shash_desc *pdesc, const void *in) { struct shash_desc *desc = shash_desc_ctx(pdesc); const struct hmac_ctx *tctx = crypto_shash_ctx(pdesc->tfm); desc->tfm = tctx->hash; return crypto_shash_import(desc, in); } static int hmac_init(struct shash_desc *pdesc) { const struct hmac_ctx *tctx = crypto_shash_ctx(pdesc->tfm); return hmac_import(pdesc, &tctx->pads[0]); } static int hmac_update(struct shash_desc *pdesc, const u8 *data, unsigned int nbytes) { struct shash_desc *desc = shash_desc_ctx(pdesc); return crypto_shash_update(desc, data, nbytes); } static int hmac_final(struct shash_desc *pdesc, u8 *out) { struct crypto_shash *parent = pdesc->tfm; int ds = crypto_shash_digestsize(parent); int ss = crypto_shash_statesize(parent); const struct hmac_ctx *tctx = crypto_shash_ctx(parent); const u8 *opad = &tctx->pads[ss]; struct shash_desc *desc = shash_desc_ctx(pdesc); return crypto_shash_final(desc, out) ?: crypto_shash_import(desc, opad) ?: crypto_shash_finup(desc, out, ds, out); } static int hmac_finup(struct shash_desc *pdesc, const u8 *data, unsigned int nbytes, u8 *out) { struct crypto_shash *parent = pdesc->tfm; int ds = crypto_shash_digestsize(parent); int ss = crypto_shash_statesize(parent); const struct hmac_ctx *tctx = crypto_shash_ctx(parent); const u8 *opad = &tctx->pads[ss]; struct shash_desc *desc = shash_desc_ctx(pdesc); return crypto_shash_finup(desc, data, nbytes, out) ?: crypto_shash_import(desc, opad) ?: crypto_shash_finup(desc, out, ds, out); } static int hmac_init_tfm(struct crypto_shash *parent) { struct crypto_shash *hash; struct shash_instance *inst = shash_alg_instance(parent); struct crypto_shash_spawn *spawn = shash_instance_ctx(inst); struct hmac_ctx *tctx = crypto_shash_ctx(parent); hash = crypto_spawn_shash(spawn); if (IS_ERR(hash)) return PTR_ERR(hash); parent->descsize = sizeof(struct shash_desc) + crypto_shash_descsize(hash); tctx->hash = hash; return 0; } static int hmac_clone_tfm(struct crypto_shash *dst, struct crypto_shash *src) { struct hmac_ctx *sctx = crypto_shash_ctx(src); struct hmac_ctx *dctx = crypto_shash_ctx(dst); struct crypto_shash *hash; hash = crypto_clone_shash(sctx->hash); if (IS_ERR(hash)) return PTR_ERR(hash); dctx->hash = hash; return 0; } static void hmac_exit_tfm(struct crypto_shash *parent) { struct hmac_ctx *tctx = crypto_shash_ctx(parent); crypto_free_shash(tctx->hash); } static int hmac_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_shash_spawn *spawn; struct crypto_alg *alg; struct shash_alg *salg; u32 mask; int err; int ds; int ss; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_shash(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; salg = crypto_spawn_shash_alg(spawn); alg = &salg->base; /* The underlying hash algorithm must not require a key */ err = -EINVAL; if (crypto_shash_alg_needs_key(salg)) goto err_free_inst; ds = salg->digestsize; ss = salg->statesize; if (ds > alg->cra_blocksize || ss < alg->cra_blocksize) goto err_free_inst; err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct hmac_ctx) + (ss * 2); inst->alg.digestsize = ds; inst->alg.statesize = ss; inst->alg.init = hmac_init; inst->alg.update = hmac_update; inst->alg.final = hmac_final; inst->alg.finup = hmac_finup; inst->alg.export = hmac_export; inst->alg.import = hmac_import; inst->alg.setkey = hmac_setkey; inst->alg.init_tfm = hmac_init_tfm; inst->alg.clone_tfm = hmac_clone_tfm; inst->alg.exit_tfm = hmac_exit_tfm; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template hmac_tmpl = { .name = "hmac", .create = hmac_create, .module = THIS_MODULE, }; static int __init hmac_module_init(void) { return crypto_register_template(&hmac_tmpl); } static void __exit hmac_module_exit(void) { crypto_unregister_template(&hmac_tmpl); } subsys_initcall(hmac_module_init); module_exit(hmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("HMAC hash algorithm"); MODULE_ALIAS_CRYPTO("hmac"); |
| 2 21 21 7 1 13 14 2 14 14 14 14 13 3 12 1 11 11 4 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "rsrc.h" #include "filetable.h" static int io_file_bitmap_get(struct io_ring_ctx *ctx) { struct io_file_table *table = &ctx->file_table; unsigned long nr = ctx->file_alloc_end; int ret; if (!table->bitmap) return -ENFILE; do { ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint); if (ret != nr) return ret; if (table->alloc_hint == ctx->file_alloc_start) break; nr = table->alloc_hint; table->alloc_hint = ctx->file_alloc_start; } while (1); return -ENFILE; } bool io_alloc_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table, unsigned nr_files) { if (io_rsrc_data_alloc(&table->data, nr_files)) return false; table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); if (table->bitmap) return true; io_rsrc_data_free(ctx, &table->data); return false; } void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table) { io_rsrc_data_free(ctx, &table->data); bitmap_free(table->bitmap); table->bitmap = NULL; } static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, u32 slot_index) __must_hold(&req->ctx->uring_lock) { struct io_rsrc_node *node; if (io_is_uring_fops(file)) return -EBADF; if (!ctx->file_table.data.nr) return -ENXIO; if (slot_index >= ctx->file_table.data.nr) return -EINVAL; node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) return -ENOMEM; if (!io_reset_rsrc_node(ctx, &ctx->file_table.data, slot_index)) io_file_bitmap_set(&ctx->file_table, slot_index); ctx->file_table.data.nodes[slot_index] = node; io_fixed_file_set(node, file); return 0; } int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file, unsigned int file_slot) { bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC; int ret; if (alloc_slot) { ret = io_file_bitmap_get(ctx); if (unlikely(ret < 0)) return ret; file_slot = ret; } else { file_slot--; } ret = io_install_fixed_file(ctx, file, file_slot); if (!ret && alloc_slot) ret = file_slot; return ret; } /* * Note when io_fixed_fd_install() returns error value, it will ensure * fput() is called correspondingly. */ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, struct file *file, unsigned int file_slot) { struct io_ring_ctx *ctx = req->ctx; int ret; io_ring_submit_lock(ctx, issue_flags); ret = __io_fixed_fd_install(ctx, file, file_slot); io_ring_submit_unlock(ctx, issue_flags); if (unlikely(ret < 0)) fput(file); return ret; } int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) { struct io_rsrc_node *node; if (unlikely(!ctx->file_table.data.nr)) return -ENXIO; if (offset >= ctx->file_table.data.nr) return -EINVAL; node = io_rsrc_node_lookup(&ctx->file_table.data, offset); if (!node) return -EBADF; io_reset_rsrc_node(ctx, &ctx->file_table.data, offset); io_file_bitmap_clear(&ctx->file_table, offset); return 0; } int io_register_file_alloc_range(struct io_ring_ctx *ctx, struct io_uring_file_index_range __user *arg) { struct io_uring_file_index_range range; u32 end; if (copy_from_user(&range, arg, sizeof(range))) return -EFAULT; if (check_add_overflow(range.off, range.len, &end)) return -EOVERFLOW; if (range.resv || end > ctx->file_table.data.nr) return -EINVAL; io_file_table_set_alloc_range(ctx, range.off, range.len); return 0; } |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* A network driver using virtio. * * Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation */ //#define DEBUG #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/module.h> #include <linux/virtio.h> #include <linux/virtio_net.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/scatterlist.h> #include <linux/if_vlan.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/average.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/dim.h> #include <net/route.h> #include <net/xdp.h> #include <net/net_failover.h> #include <net/netdev_rx_queue.h> #include <net/netdev_queues.h> #include <net/xdp_sock_drv.h> static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); static bool csum = true, gso = true, napi_tx = true; module_param(csum, bool, 0444); module_param(gso, bool, 0444); module_param(napi_tx, bool, 0644); /* FIXME: MTU in config. */ #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) #define GOOD_COPY_LEN 128 #define VIRTNET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* Separating two types of XDP xmit */ #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- * term, transient changes in packet size. */ DECLARE_EWMA(pkt_len, 0, 64) #define VIRTNET_DRIVER_VERSION "1.0.0" static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GUEST_USO4, VIRTIO_NET_F_GUEST_USO6, VIRTIO_NET_F_GUEST_HDRLEN }; #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ (1ULL << VIRTIO_NET_F_GUEST_UFO) | \ (1ULL << VIRTIO_NET_F_GUEST_USO4) | \ (1ULL << VIRTIO_NET_F_GUEST_USO6)) struct virtnet_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; size_t qstat_offset; }; struct virtnet_sq_free_stats { u64 packets; u64 bytes; u64 napi_packets; u64 napi_bytes; u64 xsk; }; struct virtnet_sq_stats { struct u64_stats_sync syncp; u64_stats_t packets; u64_stats_t bytes; u64_stats_t xdp_tx; u64_stats_t xdp_tx_drops; u64_stats_t kicks; u64_stats_t tx_timeouts; u64_stats_t stop; u64_stats_t wake; }; struct virtnet_rq_stats { struct u64_stats_sync syncp; u64_stats_t packets; u64_stats_t bytes; u64_stats_t drops; u64_stats_t xdp_packets; u64_stats_t xdp_tx; u64_stats_t xdp_redirects; u64_stats_t xdp_drops; u64_stats_t kicks; }; #define VIRTNET_SQ_STAT(name, m) {name, offsetof(struct virtnet_sq_stats, m), -1} #define VIRTNET_RQ_STAT(name, m) {name, offsetof(struct virtnet_rq_stats, m), -1} #define VIRTNET_SQ_STAT_QSTAT(name, m) \ { \ name, \ offsetof(struct virtnet_sq_stats, m), \ offsetof(struct netdev_queue_stats_tx, m), \ } #define VIRTNET_RQ_STAT_QSTAT(name, m) \ { \ name, \ offsetof(struct virtnet_rq_stats, m), \ offsetof(struct netdev_queue_stats_rx, m), \ } static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = { VIRTNET_SQ_STAT("xdp_tx", xdp_tx), VIRTNET_SQ_STAT("xdp_tx_drops", xdp_tx_drops), VIRTNET_SQ_STAT("kicks", kicks), VIRTNET_SQ_STAT("tx_timeouts", tx_timeouts), }; static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = { VIRTNET_RQ_STAT("drops", drops), VIRTNET_RQ_STAT("xdp_packets", xdp_packets), VIRTNET_RQ_STAT("xdp_tx", xdp_tx), VIRTNET_RQ_STAT("xdp_redirects", xdp_redirects), VIRTNET_RQ_STAT("xdp_drops", xdp_drops), VIRTNET_RQ_STAT("kicks", kicks), }; static const struct virtnet_stat_desc virtnet_sq_stats_desc_qstat[] = { VIRTNET_SQ_STAT_QSTAT("packets", packets), VIRTNET_SQ_STAT_QSTAT("bytes", bytes), VIRTNET_SQ_STAT_QSTAT("stop", stop), VIRTNET_SQ_STAT_QSTAT("wake", wake), }; static const struct virtnet_stat_desc virtnet_rq_stats_desc_qstat[] = { VIRTNET_RQ_STAT_QSTAT("packets", packets), VIRTNET_RQ_STAT_QSTAT("bytes", bytes), }; #define VIRTNET_STATS_DESC_CQ(name) \ {#name, offsetof(struct virtio_net_stats_cvq, name), -1} #define VIRTNET_STATS_DESC_RX(class, name) \ {#name, offsetof(struct virtio_net_stats_rx_ ## class, rx_ ## name), -1} #define VIRTNET_STATS_DESC_TX(class, name) \ {#name, offsetof(struct virtio_net_stats_tx_ ## class, tx_ ## name), -1} static const struct virtnet_stat_desc virtnet_stats_cvq_desc[] = { VIRTNET_STATS_DESC_CQ(command_num), VIRTNET_STATS_DESC_CQ(ok_num), }; static const struct virtnet_stat_desc virtnet_stats_rx_basic_desc[] = { VIRTNET_STATS_DESC_RX(basic, packets), VIRTNET_STATS_DESC_RX(basic, bytes), VIRTNET_STATS_DESC_RX(basic, notifications), VIRTNET_STATS_DESC_RX(basic, interrupts), }; static const struct virtnet_stat_desc virtnet_stats_tx_basic_desc[] = { VIRTNET_STATS_DESC_TX(basic, packets), VIRTNET_STATS_DESC_TX(basic, bytes), VIRTNET_STATS_DESC_TX(basic, notifications), VIRTNET_STATS_DESC_TX(basic, interrupts), }; static const struct virtnet_stat_desc virtnet_stats_rx_csum_desc[] = { VIRTNET_STATS_DESC_RX(csum, needs_csum), }; static const struct virtnet_stat_desc virtnet_stats_tx_gso_desc[] = { VIRTNET_STATS_DESC_TX(gso, gso_packets_noseg), VIRTNET_STATS_DESC_TX(gso, gso_bytes_noseg), }; static const struct virtnet_stat_desc virtnet_stats_rx_speed_desc[] = { VIRTNET_STATS_DESC_RX(speed, ratelimit_bytes), }; static const struct virtnet_stat_desc virtnet_stats_tx_speed_desc[] = { VIRTNET_STATS_DESC_TX(speed, ratelimit_bytes), }; #define VIRTNET_STATS_DESC_RX_QSTAT(class, name, qstat_field) \ { \ #name, \ offsetof(struct virtio_net_stats_rx_ ## class, rx_ ## name), \ offsetof(struct netdev_queue_stats_rx, qstat_field), \ } #define VIRTNET_STATS_DESC_TX_QSTAT(class, name, qstat_field) \ { \ #name, \ offsetof(struct virtio_net_stats_tx_ ## class, tx_ ## name), \ offsetof(struct netdev_queue_stats_tx, qstat_field), \ } static const struct virtnet_stat_desc virtnet_stats_rx_basic_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(basic, drops, hw_drops), VIRTNET_STATS_DESC_RX_QSTAT(basic, drop_overruns, hw_drop_overruns), }; static const struct virtnet_stat_desc virtnet_stats_tx_basic_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(basic, drops, hw_drops), VIRTNET_STATS_DESC_TX_QSTAT(basic, drop_malformed, hw_drop_errors), }; static const struct virtnet_stat_desc virtnet_stats_rx_csum_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(csum, csum_valid, csum_unnecessary), VIRTNET_STATS_DESC_RX_QSTAT(csum, csum_none, csum_none), VIRTNET_STATS_DESC_RX_QSTAT(csum, csum_bad, csum_bad), }; static const struct virtnet_stat_desc virtnet_stats_tx_csum_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(csum, csum_none, csum_none), VIRTNET_STATS_DESC_TX_QSTAT(csum, needs_csum, needs_csum), }; static const struct virtnet_stat_desc virtnet_stats_rx_gso_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_packets, hw_gro_packets), VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_bytes, hw_gro_bytes), VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_packets_coalesced, hw_gro_wire_packets), VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_bytes_coalesced, hw_gro_wire_bytes), }; static const struct virtnet_stat_desc virtnet_stats_tx_gso_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_packets, hw_gso_packets), VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_bytes, hw_gso_bytes), VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_segments, hw_gso_wire_packets), VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_segments_bytes, hw_gso_wire_bytes), }; static const struct virtnet_stat_desc virtnet_stats_rx_speed_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(speed, ratelimit_packets, hw_drop_ratelimits), }; static const struct virtnet_stat_desc virtnet_stats_tx_speed_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(speed, ratelimit_packets, hw_drop_ratelimits), }; #define VIRTNET_Q_TYPE_RX 0 #define VIRTNET_Q_TYPE_TX 1 #define VIRTNET_Q_TYPE_CQ 2 struct virtnet_interrupt_coalesce { u32 max_packets; u32 max_usecs; }; /* The dma information of pages allocated at a time. */ struct virtnet_rq_dma { dma_addr_t addr; u32 ref; u16 len; u16 need_sync; }; /* Internal representation of a send virtqueue */ struct send_queue { /* Virtqueue associated with this send _queue */ struct virtqueue *vq; /* TX: fragments + linear part + virtio header */ struct scatterlist sg[MAX_SKB_FRAGS + 2]; /* Name of the send queue: output.$index */ char name[16]; struct virtnet_sq_stats stats; struct virtnet_interrupt_coalesce intr_coal; struct napi_struct napi; /* Record whether sq is in reset state. */ bool reset; struct xsk_buff_pool *xsk_pool; dma_addr_t xsk_hdr_dma_addr; }; /* Internal representation of a receive virtqueue */ struct receive_queue { /* Virtqueue associated with this receive_queue */ struct virtqueue *vq; struct napi_struct napi; struct bpf_prog __rcu *xdp_prog; struct virtnet_rq_stats stats; /* The number of rx notifications */ u16 calls; /* Is dynamic interrupt moderation enabled? */ bool dim_enabled; /* Used to protect dim_enabled and inter_coal */ struct mutex dim_lock; /* Dynamic Interrupt Moderation */ struct dim dim; u32 packets_in_napi; struct virtnet_interrupt_coalesce intr_coal; /* Chain pages by the private ptr. */ struct page *pages; /* Average packet length for mergeable receive buffers. */ struct ewma_pkt_len mrg_avg_pkt_len; /* Page frag for packet buffer allocation. */ struct page_frag alloc_frag; /* RX: fragments + linear part + virtio header */ struct scatterlist sg[MAX_SKB_FRAGS + 2]; /* Min single buffer size for mergeable buffers case. */ unsigned int min_buf_len; /* Name of this receive queue: input.$index */ char name[16]; struct xdp_rxq_info xdp_rxq; /* Record the last dma info to free after new pages is allocated. */ struct virtnet_rq_dma *last_dma; struct xsk_buff_pool *xsk_pool; /* xdp rxq used by xsk */ struct xdp_rxq_info xsk_rxq_info; struct xdp_buff **xsk_buffs; }; /* This structure can contain rss message with maximum settings for indirection table and keysize * Note, that default structure that describes RSS configuration virtio_net_rss_config * contains same info but can't handle table values. * In any case, structure would be passed to virtio hw through sg_buf split by parts * because table sizes may be differ according to the device configuration. */ #define VIRTIO_NET_RSS_MAX_KEY_SIZE 40 struct virtio_net_ctrl_rss { u32 hash_types; u16 indirection_table_mask; u16 unclassified_queue; u16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */ u16 max_tx_vq; u8 hash_key_length; u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE]; u16 *indirection_table; }; /* Control VQ buffers: protected by the rtnl lock */ struct control_buf { struct virtio_net_ctrl_hdr hdr; virtio_net_ctrl_ack status; }; struct virtnet_info { struct virtio_device *vdev; struct virtqueue *cvq; struct net_device *dev; struct send_queue *sq; struct receive_queue *rq; unsigned int status; /* Max # of queue pairs supported by the device */ u16 max_queue_pairs; /* # of queue pairs currently used by the driver */ u16 curr_queue_pairs; /* # of XDP queue pairs currently used by the driver */ u16 xdp_queue_pairs; /* xdp_queue_pairs may be 0, when xdp is already loaded. So add this. */ bool xdp_enabled; /* I like... big packets and I cannot lie! */ bool big_packets; /* number of sg entries allocated for big packets */ unsigned int big_packets_num_skbfrags; /* Host will merge rx buffers for big packets (shake it! shake it!) */ bool mergeable_rx_bufs; /* Host supports rss and/or hash report */ bool has_rss; bool has_rss_hash_report; u8 rss_key_size; u16 rss_indir_table_size; u32 rss_hash_types_supported; u32 rss_hash_types_saved; struct virtio_net_ctrl_rss rss; /* Has control virtqueue */ bool has_cvq; /* Lock to protect the control VQ */ struct mutex cvq_lock; /* Host can handle any s/g split between our header and packet data */ bool any_header_sg; /* Packet virtio header size */ u8 hdr_len; /* Work struct for delayed refilling if we run low on memory. */ struct delayed_work refill; /* Is delayed refill enabled? */ bool refill_enabled; /* The lock to synchronize the access to refill_enabled */ spinlock_t refill_lock; /* Work struct for config space updates */ struct work_struct config_work; /* Work struct for setting rx mode */ struct work_struct rx_mode_work; /* OK to queue work setting RX mode? */ bool rx_mode_work_enabled; /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; /* CPU hotplug instances for online & dead */ struct hlist_node node; struct hlist_node node_dead; struct control_buf *ctrl; /* Ethtool settings */ u8 duplex; u32 speed; /* Is rx dynamic interrupt moderation enabled? */ bool rx_dim_enabled; /* Interrupt coalescing settings */ struct virtnet_interrupt_coalesce intr_coal_tx; struct virtnet_interrupt_coalesce intr_coal_rx; unsigned long guest_offloads; unsigned long guest_offloads_capable; /* failover when STANDBY feature enabled */ struct failover *failover; u64 device_stats_cap; }; struct padded_vnet_hdr { struct virtio_net_hdr_v1_hash hdr; /* * hdr is in a separate sg buffer, and data sg buffer shares same page * with this header sg. This padding makes next sg 16 byte aligned * after the header. */ char padding[12]; }; struct virtio_net_common_hdr { union { struct virtio_net_hdr hdr; struct virtio_net_hdr_mrg_rxbuf mrg_hdr; struct virtio_net_hdr_v1_hash hash_v1_hdr; }; }; static struct virtio_net_common_hdr xsk_hdr; static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq); static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp, struct net_device *dev, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats); static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq, struct sk_buff *skb, u8 flags); static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, struct sk_buff *curr_skb, struct page *page, void *buf, int len, int truesize); static void virtnet_xsk_completed(struct send_queue *sq, int num); enum virtnet_xmit_type { VIRTNET_XMIT_TYPE_SKB, VIRTNET_XMIT_TYPE_SKB_ORPHAN, VIRTNET_XMIT_TYPE_XDP, VIRTNET_XMIT_TYPE_XSK, }; static int rss_indirection_table_alloc(struct virtio_net_ctrl_rss *rss, u16 indir_table_size) { if (!indir_table_size) { rss->indirection_table = NULL; return 0; } rss->indirection_table = kmalloc_array(indir_table_size, sizeof(u16), GFP_KERNEL); if (!rss->indirection_table) return -ENOMEM; return 0; } static void rss_indirection_table_free(struct virtio_net_ctrl_rss *rss) { kfree(rss->indirection_table); } /* We use the last two bits of the pointer to distinguish the xmit type. */ #define VIRTNET_XMIT_TYPE_MASK (BIT(0) | BIT(1)) #define VIRTIO_XSK_FLAG_OFFSET 2 static enum virtnet_xmit_type virtnet_xmit_ptr_unpack(void **ptr) { unsigned long p = (unsigned long)*ptr; *ptr = (void *)(p & ~VIRTNET_XMIT_TYPE_MASK); return p & VIRTNET_XMIT_TYPE_MASK; } static void *virtnet_xmit_ptr_pack(void *ptr, enum virtnet_xmit_type type) { return (void *)((unsigned long)ptr | type); } static int virtnet_add_outbuf(struct send_queue *sq, int num, void *data, enum virtnet_xmit_type type) { return virtqueue_add_outbuf(sq->vq, sq->sg, num, virtnet_xmit_ptr_pack(data, type), GFP_ATOMIC); } static u32 virtnet_ptr_to_xsk_buff_len(void *ptr) { return ((unsigned long)ptr) >> VIRTIO_XSK_FLAG_OFFSET; } static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len) { sg_dma_address(sg) = addr; sg_dma_len(sg) = len; } static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, bool in_napi, struct virtnet_sq_free_stats *stats) { struct xdp_frame *frame; struct sk_buff *skb; unsigned int len; void *ptr; while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { switch (virtnet_xmit_ptr_unpack(&ptr)) { case VIRTNET_XMIT_TYPE_SKB: skb = ptr; pr_debug("Sent skb %p\n", skb); stats->napi_packets++; stats->napi_bytes += skb->len; napi_consume_skb(skb, in_napi); break; case VIRTNET_XMIT_TYPE_SKB_ORPHAN: skb = ptr; stats->packets++; stats->bytes += skb->len; napi_consume_skb(skb, in_napi); break; case VIRTNET_XMIT_TYPE_XDP: frame = ptr; stats->packets++; stats->bytes += xdp_get_frame_len(frame); xdp_return_frame(frame); break; case VIRTNET_XMIT_TYPE_XSK: stats->bytes += virtnet_ptr_to_xsk_buff_len(ptr); stats->xsk++; break; } } netdev_tx_completed_queue(txq, stats->napi_packets, stats->napi_bytes); } static void virtnet_free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, bool in_napi, struct virtnet_sq_free_stats *stats) { __free_old_xmit(sq, txq, in_napi, stats); if (stats->xsk) virtnet_xsk_completed(sq, stats->xsk); } /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ static int vq2txq(struct virtqueue *vq) { return (vq->index - 1) / 2; } static int txq2vq(int txq) { return txq * 2 + 1; } static int vq2rxq(struct virtqueue *vq) { return vq->index / 2; } static int rxq2vq(int rxq) { return rxq * 2; } static int vq_type(struct virtnet_info *vi, int qid) { if (qid == vi->max_queue_pairs * 2) return VIRTNET_Q_TYPE_CQ; if (qid % 2) return VIRTNET_Q_TYPE_TX; return VIRTNET_Q_TYPE_RX; } static inline struct virtio_net_common_hdr * skb_vnet_common_hdr(struct sk_buff *skb) { return (struct virtio_net_common_hdr *)skb->cb; } /* * private is used to chain pages for big packets, put the whole * most recent used list in the beginning for reuse */ static void give_pages(struct receive_queue *rq, struct page *page) { struct page *end; /* Find end of list, sew whole thing into vi->rq.pages. */ for (end = page; end->private; end = (struct page *)end->private); end->private = (unsigned long)rq->pages; rq->pages = page; } static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) { struct page *p = rq->pages; if (p) { rq->pages = (struct page *)p->private; /* clear private here, it is used to chain pages */ p->private = 0; } else p = alloc_page(gfp_mask); return p; } static void virtnet_rq_free_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf) { if (vi->mergeable_rx_bufs) put_page(virt_to_head_page(buf)); else if (vi->big_packets) give_pages(rq, buf); else put_page(virt_to_head_page(buf)); } static void enable_delayed_refill(struct virtnet_info *vi) { spin_lock_bh(&vi->refill_lock); vi->refill_enabled = true; spin_unlock_bh(&vi->refill_lock); } static void disable_delayed_refill(struct virtnet_info *vi) { spin_lock_bh(&vi->refill_lock); vi->refill_enabled = false; spin_unlock_bh(&vi->refill_lock); } static void enable_rx_mode_work(struct virtnet_info *vi) { rtnl_lock(); vi->rx_mode_work_enabled = true; rtnl_unlock(); } static void disable_rx_mode_work(struct virtnet_info *vi) { rtnl_lock(); vi->rx_mode_work_enabled = false; rtnl_unlock(); } static void virtqueue_napi_schedule(struct napi_struct *napi, struct virtqueue *vq) { if (napi_schedule_prep(napi)) { virtqueue_disable_cb(vq); __napi_schedule(napi); } } static bool virtqueue_napi_complete(struct napi_struct *napi, struct virtqueue *vq, int processed) { int opaque; opaque = virtqueue_enable_cb_prepare(vq); if (napi_complete_done(napi, processed)) { if (unlikely(virtqueue_poll(vq, opaque))) virtqueue_napi_schedule(napi, vq); else return true; } else { virtqueue_disable_cb(vq); } return false; } static void skb_xmit_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; /* Suppress further interrupts. */ virtqueue_disable_cb(vq); if (napi->weight) virtqueue_napi_schedule(napi, vq); else /* We were probably waiting for more output buffers. */ netif_wake_subqueue(vi->dev, vq2txq(vq)); } #define MRG_CTX_HEADER_SHIFT 22 static void *mergeable_len_to_ctx(unsigned int truesize, unsigned int headroom) { return (void *)(unsigned long)((headroom << MRG_CTX_HEADER_SHIFT) | truesize); } static unsigned int mergeable_ctx_to_headroom(void *mrg_ctx) { return (unsigned long)mrg_ctx >> MRG_CTX_HEADER_SHIFT; } static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) { return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1); } static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen, unsigned int headroom, unsigned int len) { struct sk_buff *skb; skb = build_skb(buf, buflen); if (unlikely(!skb)) return NULL; skb_reserve(skb, headroom); skb_put(skb, len); return skb; } /* Called from bottom half context */ static struct sk_buff *page_to_skb(struct virtnet_info *vi, struct receive_queue *rq, struct page *page, unsigned int offset, unsigned int len, unsigned int truesize, unsigned int headroom) { struct sk_buff *skb; struct virtio_net_common_hdr *hdr; unsigned int copy, hdr_len, hdr_padded_len; struct page *page_to_free = NULL; int tailroom, shinfo_size; char *p, *hdr_p, *buf; p = page_address(page) + offset; hdr_p = p; hdr_len = vi->hdr_len; if (vi->mergeable_rx_bufs) hdr_padded_len = hdr_len; else hdr_padded_len = sizeof(struct padded_vnet_hdr); buf = p - headroom; len -= hdr_len; offset += hdr_padded_len; p += hdr_padded_len; tailroom = truesize - headroom - hdr_padded_len - len; shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (!NET_IP_ALIGN && len > GOOD_COPY_LEN && tailroom >= shinfo_size) { skb = virtnet_build_skb(buf, truesize, p - buf, len); if (unlikely(!skb)) return NULL; page = (struct page *)page->private; if (page) give_pages(rq, page); goto ok; } /* copy small packet so we can reuse these pages for small data */ skb = napi_alloc_skb(&rq->napi, GOOD_COPY_LEN); if (unlikely(!skb)) return NULL; /* Copy all frame if it fits skb->head, otherwise * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. */ if (len <= skb_tailroom(skb)) copy = len; else copy = ETH_HLEN; skb_put_data(skb, p, copy); len -= copy; offset += copy; if (vi->mergeable_rx_bufs) { if (len) skb_add_rx_frag(skb, 0, page, offset, len, truesize); else page_to_free = page; goto ok; } /* * Verify that we can indeed put this data into a skb. * This is here to handle cases when the device erroneously * tries to receive more than is possible. This is usually * the case of a broken device. */ if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) { net_dbg_ratelimited("%s: too much data\n", skb->dev->name); dev_kfree_skb(skb); return NULL; } BUG_ON(offset >= PAGE_SIZE); while (len) { unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, frag_size, truesize); len -= frag_size; page = (struct page *)page->private; offset = 0; } if (page) give_pages(rq, page); ok: hdr = skb_vnet_common_hdr(skb); memcpy(hdr, hdr_p, hdr_len); if (page_to_free) put_page(page_to_free); return skb; } static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len) { struct virtnet_info *vi = rq->vq->vdev->priv; struct page *page = virt_to_head_page(buf); struct virtnet_rq_dma *dma; void *head; int offset; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(page); dma = head; --dma->ref; if (dma->need_sync && len) { offset = buf - (head + sizeof(*dma)); virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, offset, len, DMA_FROM_DEVICE); } if (dma->ref) return; virtqueue_dma_unmap_single_attrs(rq->vq, dma->addr, dma->len, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); put_page(page); } static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) { struct virtnet_info *vi = rq->vq->vdev->priv; void *buf; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); buf = virtqueue_get_buf_ctx(rq->vq, len, ctx); if (buf) virtnet_rq_unmap(rq, buf, *len); return buf; } static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) { struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_dma *dma; dma_addr_t addr; u32 offset; void *head; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(rq->alloc_frag.page); offset = buf - head; dma = head; addr = dma->addr - sizeof(*dma) + offset; sg_init_table(rq->sg, 1); sg_fill_dma(rq->sg, addr, len); } static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp) { struct page_frag *alloc_frag = &rq->alloc_frag; struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_dma *dma; void *buf, *head; dma_addr_t addr; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(alloc_frag->page); dma = head; /* new pages */ if (!alloc_frag->offset) { if (rq->last_dma) { /* Now, the new page is allocated, the last dma * will not be used. So the dma can be unmapped * if the ref is 0. */ virtnet_rq_unmap(rq, rq->last_dma, 0); rq->last_dma = NULL; } dma->len = alloc_frag->size - sizeof(*dma); addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1, dma->len, DMA_FROM_DEVICE, 0); if (virtqueue_dma_mapping_error(rq->vq, addr)) return NULL; dma->addr = addr; dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr); /* Add a reference to dma to prevent the entire dma from * being released during error handling. This reference * will be freed after the pages are no longer used. */ get_page(alloc_frag->page); dma->ref = 1; alloc_frag->offset = sizeof(*dma); rq->last_dma = dma; } ++dma->ref; buf = head + alloc_frag->offset; get_page(alloc_frag->page); alloc_frag->offset += size; return buf; } static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) { struct virtnet_info *vi = vq->vdev->priv; struct receive_queue *rq; int i = vq2rxq(vq); rq = &vi->rq[i]; if (rq->xsk_pool) { xsk_buff_free((struct xdp_buff *)buf); return; } if (!vi->big_packets || vi->mergeable_rx_bufs) virtnet_rq_unmap(rq, buf, 0); virtnet_rq_free_buf(vi, rq, buf); } static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, bool in_napi) { struct virtnet_sq_free_stats stats = {0}; virtnet_free_old_xmit(sq, txq, in_napi, &stats); /* Avoid overhead when no packets have been processed * happens when called speculatively from start_xmit. */ if (!stats.packets && !stats.napi_packets) return; u64_stats_update_begin(&sq->stats.syncp); u64_stats_add(&sq->stats.bytes, stats.bytes + stats.napi_bytes); u64_stats_add(&sq->stats.packets, stats.packets + stats.napi_packets); u64_stats_update_end(&sq->stats.syncp); } static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) { if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) return false; else if (q < vi->curr_queue_pairs) return true; else return false; } static void check_sq_full_and_disable(struct virtnet_info *vi, struct net_device *dev, struct send_queue *sq) { bool use_napi = sq->napi.weight; int qnum; qnum = sq - vi->sq; /* If running out of space, stop queue to avoid getting packets that we * are then unable to transmit. * An alternative would be to force queuing layer to requeue the skb by * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be * returned in a normal path of operation: it means that driver is not * maintaining the TX queue stop/start state properly, and causes * the stack to do a non-trivial amount of useless work. * Since most packets only take 1 or 2 ring slots, stopping the queue * early means 16 slots are typically wasted. */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); netif_tx_stop_queue(txq); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.stop); u64_stats_update_end(&sq->stats.syncp); if (use_napi) { if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) virtqueue_napi_schedule(&sq->napi, sq->vq); } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ free_old_xmit(sq, txq, false); if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { netif_start_subqueue(dev, qnum); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); u64_stats_update_end(&sq->stats.syncp); virtqueue_disable_cb(sq->vq); } } } } static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi, struct receive_queue *rq, void *buf, u32 len) { struct xdp_buff *xdp; u32 bufsize; xdp = (struct xdp_buff *)buf; bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len; if (unlikely(len > bufsize)) { pr_debug("%s: rx error: len %u exceeds truesize %u\n", vi->dev->name, len, bufsize); DEV_STATS_INC(vi->dev, rx_length_errors); xsk_buff_free(xdp); return NULL; } xsk_buff_set_size(xdp, len); xsk_buff_dma_sync_for_cpu(xdp); return xdp; } static struct sk_buff *xsk_construct_skb(struct receive_queue *rq, struct xdp_buff *xdp) { unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; unsigned int size; size = xdp->data_end - xdp->data_hard_start; skb = napi_alloc_skb(&rq->napi, size); if (unlikely(!skb)) { xsk_buff_free(xdp); return NULL; } skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); size = xdp->data_end - xdp->data_meta; memcpy(__skb_put(skb, size), xdp->data_meta, size); if (metasize) { __skb_pull(skb, metasize); skb_metadata_set(skb, metasize); } xsk_buff_free(xdp); return skb; } static struct sk_buff *virtnet_receive_xsk_small(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct xdp_buff *xdp, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct bpf_prog *prog; u32 ret; ret = XDP_PASS; rcu_read_lock(); prog = rcu_dereference(rq->xdp_prog); if (prog) ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats); rcu_read_unlock(); switch (ret) { case XDP_PASS: return xsk_construct_skb(rq, xdp); case XDP_TX: case XDP_REDIRECT: return NULL; default: /* drop packet */ xsk_buff_free(xdp); u64_stats_inc(&stats->drops); return NULL; } } static void xsk_drop_follow_bufs(struct net_device *dev, struct receive_queue *rq, u32 num_buf, struct virtnet_rq_stats *stats) { struct xdp_buff *xdp; u32 len; while (num_buf-- > 1) { xdp = virtqueue_get_buf(rq->vq, &len); if (unlikely(!xdp)) { pr_debug("%s: rx error: %d buffers missing\n", dev->name, num_buf); DEV_STATS_INC(dev, rx_length_errors); break; } u64_stats_add(&stats->bytes, len); xsk_buff_free(xdp); } } static int xsk_append_merge_buffer(struct virtnet_info *vi, struct receive_queue *rq, struct sk_buff *head_skb, u32 num_buf, struct virtio_net_hdr_mrg_rxbuf *hdr, struct virtnet_rq_stats *stats) { struct sk_buff *curr_skb; struct xdp_buff *xdp; u32 len, truesize; struct page *page; void *buf; curr_skb = head_skb; while (--num_buf) { buf = virtqueue_get_buf(rq->vq, &len); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", vi->dev->name, num_buf, virtio16_to_cpu(vi->vdev, hdr->num_buffers)); DEV_STATS_INC(vi->dev, rx_length_errors); return -EINVAL; } u64_stats_add(&stats->bytes, len); xdp = buf_to_xdp(vi, rq, buf, len); if (!xdp) goto err; buf = napi_alloc_frag(len); if (!buf) { xsk_buff_free(xdp); goto err; } memcpy(buf, xdp->data - vi->hdr_len, len); xsk_buff_free(xdp); page = virt_to_page(buf); truesize = len; curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) { put_page(page); goto err; } } return 0; err: xsk_drop_follow_bufs(vi->dev, rq, num_buf, stats); return -EINVAL; } static struct sk_buff *virtnet_receive_xsk_merge(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct xdp_buff *xdp, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr; struct bpf_prog *prog; struct sk_buff *skb; u32 ret, num_buf; hdr = xdp->data - vi->hdr_len; num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); ret = XDP_PASS; rcu_read_lock(); prog = rcu_dereference(rq->xdp_prog); /* TODO: support multi buffer. */ if (prog && num_buf == 1) ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats); rcu_read_unlock(); switch (ret) { case XDP_PASS: skb = xsk_construct_skb(rq, xdp); if (!skb) goto drop_bufs; if (xsk_append_merge_buffer(vi, rq, skb, num_buf, hdr, stats)) { dev_kfree_skb(skb); goto drop; } return skb; case XDP_TX: case XDP_REDIRECT: return NULL; default: /* drop packet */ xsk_buff_free(xdp); } drop_bufs: xsk_drop_follow_bufs(dev, rq, num_buf, stats); drop: u64_stats_inc(&stats->drops); return NULL; } static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf, u32 len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct net_device *dev = vi->dev; struct sk_buff *skb = NULL; struct xdp_buff *xdp; u8 flags; len -= vi->hdr_len; u64_stats_add(&stats->bytes, len); xdp = buf_to_xdp(vi, rq, buf, len); if (!xdp) return; if (unlikely(len < ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); DEV_STATS_INC(dev, rx_length_errors); xsk_buff_free(xdp); return; } flags = ((struct virtio_net_common_hdr *)(xdp->data - vi->hdr_len))->hdr.flags; if (!vi->mergeable_rx_bufs) skb = virtnet_receive_xsk_small(dev, vi, rq, xdp, xdp_xmit, stats); else skb = virtnet_receive_xsk_merge(dev, vi, rq, xdp, xdp_xmit, stats); if (skb) virtnet_receive_done(vi, rq, skb, flags); } static int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct receive_queue *rq, struct xsk_buff_pool *pool, gfp_t gfp) { struct xdp_buff **xsk_buffs; dma_addr_t addr; int err = 0; u32 len, i; int num; xsk_buffs = rq->xsk_buffs; num = xsk_buff_alloc_batch(pool, xsk_buffs, rq->vq->num_free); if (!num) return -ENOMEM; len = xsk_pool_get_rx_frame_size(pool) + vi->hdr_len; for (i = 0; i < num; ++i) { /* Use the part of XDP_PACKET_HEADROOM as the virtnet hdr space. * We assume XDP_PACKET_HEADROOM is larger than hdr->len. * (see function virtnet_xsk_pool_enable) */ addr = xsk_buff_xdp_get_dma(xsk_buffs[i]) - vi->hdr_len; sg_init_table(rq->sg, 1); sg_fill_dma(rq->sg, addr, len); err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, xsk_buffs[i], NULL, gfp); if (err) goto err; } return num; err: for (; i < num; ++i) xsk_buff_free(xsk_buffs[i]); return err; } static void *virtnet_xsk_to_ptr(u32 len) { unsigned long p; p = len << VIRTIO_XSK_FLAG_OFFSET; return virtnet_xmit_ptr_pack((void *)p, VIRTNET_XMIT_TYPE_XSK); } static int virtnet_xsk_xmit_one(struct send_queue *sq, struct xsk_buff_pool *pool, struct xdp_desc *desc) { struct virtnet_info *vi; dma_addr_t addr; vi = sq->vq->vdev->priv; addr = xsk_buff_raw_get_dma(pool, desc->addr); xsk_buff_raw_dma_sync_for_device(pool, addr, desc->len); sg_init_table(sq->sg, 2); sg_fill_dma(sq->sg, sq->xsk_hdr_dma_addr, vi->hdr_len); sg_fill_dma(sq->sg + 1, addr, desc->len); return virtqueue_add_outbuf_premapped(sq->vq, sq->sg, 2, virtnet_xsk_to_ptr(desc->len), GFP_ATOMIC); } static int virtnet_xsk_xmit_batch(struct send_queue *sq, struct xsk_buff_pool *pool, unsigned int budget, u64 *kicks) { struct xdp_desc *descs = pool->tx_descs; bool kick = false; u32 nb_pkts, i; int err; budget = min_t(u32, budget, sq->vq->num_free); nb_pkts = xsk_tx_peek_release_desc_batch(pool, budget); if (!nb_pkts) return 0; for (i = 0; i < nb_pkts; i++) { err = virtnet_xsk_xmit_one(sq, pool, &descs[i]); if (unlikely(err)) { xsk_tx_completed(sq->xsk_pool, nb_pkts - i); break; } kick = true; } if (kick && virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) (*kicks)++; return i; } static bool virtnet_xsk_xmit(struct send_queue *sq, struct xsk_buff_pool *pool, int budget) { struct virtnet_info *vi = sq->vq->vdev->priv; struct virtnet_sq_free_stats stats = {}; struct net_device *dev = vi->dev; u64 kicks = 0; int sent; /* Avoid to wakeup napi meanless, so call __free_old_xmit instead of * free_old_xmit(). */ __free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq), true, &stats); if (stats.xsk) xsk_tx_completed(sq->xsk_pool, stats.xsk); sent = virtnet_xsk_xmit_batch(sq, pool, budget, &kicks); if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq)) check_sq_full_and_disable(vi, vi->dev, sq); if (sent) { struct netdev_queue *txq; txq = netdev_get_tx_queue(vi->dev, sq - vi->sq); txq_trans_cond_update(txq); } u64_stats_update_begin(&sq->stats.syncp); u64_stats_add(&sq->stats.packets, stats.packets); u64_stats_add(&sq->stats.bytes, stats.bytes); u64_stats_add(&sq->stats.kicks, kicks); u64_stats_add(&sq->stats.xdp_tx, sent); u64_stats_update_end(&sq->stats.syncp); if (xsk_uses_need_wakeup(pool)) xsk_set_tx_need_wakeup(pool); return sent; } static void xsk_wakeup(struct send_queue *sq) { if (napi_if_scheduled_mark_missed(&sq->napi)) return; local_bh_disable(); virtqueue_napi_schedule(&sq->napi, sq->vq); local_bh_enable(); } static int virtnet_xsk_wakeup(struct net_device *dev, u32 qid, u32 flag) { struct virtnet_info *vi = netdev_priv(dev); struct send_queue *sq; if (!netif_running(dev)) return -ENETDOWN; if (qid >= vi->curr_queue_pairs) return -EINVAL; sq = &vi->sq[qid]; xsk_wakeup(sq); return 0; } static void virtnet_xsk_completed(struct send_queue *sq, int num) { xsk_tx_completed(sq->xsk_pool, num); /* If this is called by rx poll, start_xmit and xdp xmit we should * wakeup the tx napi to consume the xsk tx queue, because the tx * interrupt may not be triggered. */ xsk_wakeup(sq); } static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, struct send_queue *sq, struct xdp_frame *xdpf) { struct virtio_net_hdr_mrg_rxbuf *hdr; struct skb_shared_info *shinfo; u8 nr_frags = 0; int err, i; if (unlikely(xdpf->headroom < vi->hdr_len)) return -EOVERFLOW; if (unlikely(xdp_frame_has_frags(xdpf))) { shinfo = xdp_get_shared_info_from_frame(xdpf); nr_frags = shinfo->nr_frags; } /* In wrapping function virtnet_xdp_xmit(), we need to free * up the pending old buffers, where we need to calculate the * position of skb_shared_info in xdp_get_frame_len() and * xdp_return_frame(), which will involve to xdpf->data and * xdpf->headroom. Therefore, we need to update the value of * headroom synchronously here. */ xdpf->headroom -= vi->hdr_len; xdpf->data -= vi->hdr_len; /* Zero header and leave csum up to XDP layers */ hdr = xdpf->data; memset(hdr, 0, vi->hdr_len); xdpf->len += vi->hdr_len; sg_init_table(sq->sg, nr_frags + 1); sg_set_buf(sq->sg, xdpf->data, xdpf->len); for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = &shinfo->frags[i]; sg_set_page(&sq->sg[i + 1], skb_frag_page(frag), skb_frag_size(frag), skb_frag_off(frag)); } err = virtnet_add_outbuf(sq, nr_frags + 1, xdpf, VIRTNET_XMIT_TYPE_XDP); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ return 0; } /* when vi->curr_queue_pairs > nr_cpu_ids, the txq/sq is only used for xdp tx on * the current cpu, so it does not need to be locked. * * Here we use marco instead of inline functions because we have to deal with * three issues at the same time: 1. the choice of sq. 2. judge and execute the * lock/unlock of txq 3. make sparse happy. It is difficult for two inline * functions to perfectly solve these three problems at the same time. */ #define virtnet_xdp_get_sq(vi) ({ \ int cpu = smp_processor_id(); \ struct netdev_queue *txq; \ typeof(vi) v = (vi); \ unsigned int qp; \ \ if (v->curr_queue_pairs > nr_cpu_ids) { \ qp = v->curr_queue_pairs - v->xdp_queue_pairs; \ qp += cpu; \ txq = netdev_get_tx_queue(v->dev, qp); \ __netif_tx_acquire(txq); \ } else { \ qp = cpu % v->curr_queue_pairs; \ txq = netdev_get_tx_queue(v->dev, qp); \ __netif_tx_lock(txq, cpu); \ } \ v->sq + qp; \ }) #define virtnet_xdp_put_sq(vi, q) { \ struct netdev_queue *txq; \ typeof(vi) v = (vi); \ \ txq = netdev_get_tx_queue(v->dev, (q) - v->sq); \ if (v->curr_queue_pairs > nr_cpu_ids) \ __netif_tx_release(txq); \ else \ __netif_tx_unlock(txq); \ } static int virtnet_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct virtnet_info *vi = netdev_priv(dev); struct virtnet_sq_free_stats stats = {0}; struct receive_queue *rq = vi->rq; struct bpf_prog *xdp_prog; struct send_queue *sq; int nxmit = 0; int kicks = 0; int ret; int i; /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_access_pointer(rq->xdp_prog); if (!xdp_prog) return -ENXIO; sq = virtnet_xdp_get_sq(vi); if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { ret = -EINVAL; goto out; } /* Free up any pending old buffers before queueing new ones. */ virtnet_free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq), false, &stats); for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; if (__virtnet_xdp_xmit_one(vi, sq, xdpf)) break; nxmit++; } ret = nxmit; if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq)) check_sq_full_and_disable(vi, dev, sq); if (flags & XDP_XMIT_FLUSH) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) kicks = 1; } out: u64_stats_update_begin(&sq->stats.syncp); u64_stats_add(&sq->stats.bytes, stats.bytes); u64_stats_add(&sq->stats.packets, stats.packets); u64_stats_add(&sq->stats.xdp_tx, n); u64_stats_add(&sq->stats.xdp_tx_drops, n - nxmit); u64_stats_add(&sq->stats.kicks, kicks); u64_stats_update_end(&sq->stats.syncp); virtnet_xdp_put_sq(vi, sq); return ret; } static void put_xdp_frags(struct xdp_buff *xdp) { struct skb_shared_info *shinfo; struct page *xdp_page; int i; if (xdp_buff_has_frags(xdp)) { shinfo = xdp_get_shared_info_from_buff(xdp); for (i = 0; i < shinfo->nr_frags; i++) { xdp_page = skb_frag_page(&shinfo->frags[i]); put_page(xdp_page); } } } static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp, struct net_device *dev, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct xdp_frame *xdpf; int err; u32 act; act = bpf_prog_run_xdp(xdp_prog, xdp); u64_stats_inc(&stats->xdp_packets); switch (act) { case XDP_PASS: return act; case XDP_TX: u64_stats_inc(&stats->xdp_tx); xdpf = xdp_convert_buff_to_frame(xdp); if (unlikely(!xdpf)) { netdev_dbg(dev, "convert buff to frame failed for xdp\n"); return XDP_DROP; } err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); if (unlikely(!err)) { xdp_return_frame_rx_napi(xdpf); } else if (unlikely(err < 0)) { trace_xdp_exception(dev, xdp_prog, act); return XDP_DROP; } *xdp_xmit |= VIRTIO_XDP_TX; return act; case XDP_REDIRECT: u64_stats_inc(&stats->xdp_redirects); err = xdp_do_redirect(dev, xdp, xdp_prog); if (err) return XDP_DROP; *xdp_xmit |= VIRTIO_XDP_REDIR; return act; default: bpf_warn_invalid_xdp_action(dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); fallthrough; case XDP_DROP: return XDP_DROP; } } static unsigned int virtnet_get_headroom(struct virtnet_info *vi) { return vi->xdp_enabled ? XDP_PACKET_HEADROOM : 0; } /* We copy the packet for XDP in the following cases: * * 1) Packet is scattered across multiple rx buffers. * 2) Headroom space is insufficient. * * This is inefficient but it's a temporary condition that * we hit right after XDP is enabled and until queue is refilled * with large buffers with sufficient headroom - so it should affect * at most queue size packets. * Afterwards, the conditions to enable * XDP should preclude the underlying device from sending packets * across multiple buffers (num_buf > 1), and we make sure buffers * have enough headroom. */ static struct page *xdp_linearize_page(struct receive_queue *rq, int *num_buf, struct page *p, int offset, int page_off, unsigned int *len) { int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); struct page *page; if (page_off + *len + tailroom > PAGE_SIZE) return NULL; page = alloc_page(GFP_ATOMIC); if (!page) return NULL; memcpy(page_address(page) + page_off, page_address(p) + offset, *len); page_off += *len; while (--*num_buf) { unsigned int buflen; void *buf; int off; buf = virtnet_rq_get_buf(rq, &buflen, NULL); if (unlikely(!buf)) goto err_buf; p = virt_to_head_page(buf); off = buf - page_address(p); /* guard against a misconfigured or uncooperative backend that * is sending packet larger than the MTU. */ if ((page_off + buflen + tailroom) > PAGE_SIZE) { put_page(p); goto err_buf; } memcpy(page_address(page) + page_off, page_address(p) + off, buflen); page_off += buflen; put_page(p); } /* Headroom does not contribute to packet length */ *len = page_off - XDP_PACKET_HEADROOM; return page; err_buf: __free_pages(page, 0); return NULL; } static struct sk_buff *receive_small_build_skb(struct virtnet_info *vi, unsigned int xdp_headroom, void *buf, unsigned int len) { unsigned int header_offset; unsigned int headroom; unsigned int buflen; struct sk_buff *skb; header_offset = VIRTNET_RX_PAD + xdp_headroom; headroom = vi->hdr_len + header_offset; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); skb = virtnet_build_skb(buf, buflen, headroom, len); if (unlikely(!skb)) return NULL; buf += header_offset; memcpy(skb_vnet_common_hdr(skb), buf, vi->hdr_len); return skb; } static struct sk_buff *receive_small_xdp(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct bpf_prog *xdp_prog, void *buf, unsigned int xdp_headroom, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int header_offset = VIRTNET_RX_PAD + xdp_headroom; unsigned int headroom = vi->hdr_len + header_offset; struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset; struct page *page = virt_to_head_page(buf); struct page *xdp_page; unsigned int buflen; struct xdp_buff xdp; struct sk_buff *skb; unsigned int metasize = 0; u32 act; if (unlikely(hdr->hdr.gso_type)) goto err_xdp; /* Partially checksummed packets must be dropped. */ if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) goto err_xdp; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) { int offset = buf - page_address(page) + header_offset; unsigned int tlen = len + vi->hdr_len; int num_buf = 1; xdp_headroom = virtnet_get_headroom(vi); header_offset = VIRTNET_RX_PAD + xdp_headroom; headroom = vi->hdr_len + header_offset; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); xdp_page = xdp_linearize_page(rq, &num_buf, page, offset, header_offset, &tlen); if (!xdp_page) goto err_xdp; buf = page_address(xdp_page); put_page(page); page = xdp_page; } xdp_init_buff(&xdp, buflen, &rq->xdp_rxq); xdp_prepare_buff(&xdp, buf + VIRTNET_RX_PAD + vi->hdr_len, xdp_headroom, len, true); act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats); switch (act) { case XDP_PASS: /* Recalculate length in case bpf program changed it */ len = xdp.data_end - xdp.data; metasize = xdp.data - xdp.data_meta; break; case XDP_TX: case XDP_REDIRECT: goto xdp_xmit; default: goto err_xdp; } skb = virtnet_build_skb(buf, buflen, xdp.data - buf, len); if (unlikely(!skb)) goto err; if (metasize) skb_metadata_set(skb, metasize); return skb; err_xdp: u64_stats_inc(&stats->xdp_drops); err: u64_stats_inc(&stats->drops); put_page(page); xdp_xmit: return NULL; } static struct sk_buff *receive_small(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int xdp_headroom = (unsigned long)ctx; struct page *page = virt_to_head_page(buf); struct sk_buff *skb; /* We passed the address of virtnet header to virtio-core, * so truncate the padding. */ buf -= VIRTNET_RX_PAD + xdp_headroom; len -= vi->hdr_len; u64_stats_add(&stats->bytes, len); if (unlikely(len > GOOD_PACKET_LEN)) { pr_debug("%s: rx error: len %u exceeds max size %d\n", dev->name, len, GOOD_PACKET_LEN); DEV_STATS_INC(dev, rx_length_errors); goto err; } if (unlikely(vi->xdp_enabled)) { struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { skb = receive_small_xdp(dev, vi, rq, xdp_prog, buf, xdp_headroom, len, xdp_xmit, stats); rcu_read_unlock(); return skb; } rcu_read_unlock(); } skb = receive_small_build_skb(vi, xdp_headroom, buf, len); if (likely(skb)) return skb; err: u64_stats_inc(&stats->drops); put_page(page); return NULL; } static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, unsigned int len, struct virtnet_rq_stats *stats) { struct page *page = buf; struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0); u64_stats_add(&stats->bytes, len - vi->hdr_len); if (unlikely(!skb)) goto err; return skb; err: u64_stats_inc(&stats->drops); give_pages(rq, page); return NULL; } static void mergeable_buf_free(struct receive_queue *rq, int num_buf, struct net_device *dev, struct virtnet_rq_stats *stats) { struct page *page; void *buf; int len; while (num_buf-- > 1) { buf = virtnet_rq_get_buf(rq, &len, NULL); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers missing\n", dev->name, num_buf); DEV_STATS_INC(dev, rx_length_errors); break; } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); put_page(page); } } /* Why not use xdp_build_skb_from_frame() ? * XDP core assumes that xdp frags are PAGE_SIZE in length, while in * virtio-net there are 2 points that do not match its requirements: * 1. The size of the prefilled buffer is not fixed before xdp is set. * 2. xdp_build_skb_from_frame() does more checks that we don't need, * like eth_type_trans() (which virtio-net does in receive_buf()). */ static struct sk_buff *build_skb_from_xdp_buff(struct net_device *dev, struct virtnet_info *vi, struct xdp_buff *xdp, unsigned int xdp_frags_truesz) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); unsigned int headroom, data_len; struct sk_buff *skb; int metasize; u8 nr_frags; if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { pr_debug("Error building skb as missing reserved tailroom for xdp"); return NULL; } if (unlikely(xdp_buff_has_frags(xdp))) nr_frags = sinfo->nr_frags; skb = build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; headroom = xdp->data - xdp->data_hard_start; data_len = xdp->data_end - xdp->data; skb_reserve(skb, headroom); __skb_put(skb, data_len); metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (metasize) skb_metadata_set(skb, metasize); if (unlikely(xdp_buff_has_frags(xdp))) xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, xdp_frags_truesz, xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } /* TODO: build xdp in big mode */ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct xdp_buff *xdp, void *buf, unsigned int len, unsigned int frame_sz, int *num_buf, unsigned int *xdp_frags_truesize, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; unsigned int headroom, tailroom, room; unsigned int truesize, cur_frag_size; struct skb_shared_info *shinfo; unsigned int xdp_frags_truesz = 0; struct page *page; skb_frag_t *frag; int offset; void *ctx; xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq); xdp_prepare_buff(xdp, buf - XDP_PACKET_HEADROOM, XDP_PACKET_HEADROOM + vi->hdr_len, len - vi->hdr_len, true); if (!*num_buf) return 0; if (*num_buf > 1) { /* If we want to build multi-buffer xdp, we need * to specify that the flags of xdp_buff have the * XDP_FLAGS_HAS_FRAG bit. */ if (!xdp_buff_has_frags(xdp)) xdp_buff_set_frags_flag(xdp); shinfo = xdp_get_shared_info_from_buff(xdp); shinfo->nr_frags = 0; shinfo->xdp_frags_size = 0; } if (*num_buf > MAX_SKB_FRAGS + 1) return -EINVAL; while (--*num_buf > 0) { buf = virtnet_rq_get_buf(rq, &len, &ctx); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", dev->name, *num_buf, virtio16_to_cpu(vi->vdev, hdr->num_buffers)); DEV_STATS_INC(dev, rx_length_errors); goto err; } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); offset = buf - page_address(page); truesize = mergeable_ctx_to_truesize(ctx); headroom = mergeable_ctx_to_headroom(ctx); tailroom = headroom ? sizeof(struct skb_shared_info) : 0; room = SKB_DATA_ALIGN(headroom + tailroom); cur_frag_size = truesize; xdp_frags_truesz += cur_frag_size; if (unlikely(len > truesize - room || cur_frag_size > PAGE_SIZE)) { put_page(page); pr_debug("%s: rx error: len %u exceeds truesize %lu\n", dev->name, len, (unsigned long)(truesize - room)); DEV_STATS_INC(dev, rx_length_errors); goto err; } frag = &shinfo->frags[shinfo->nr_frags++]; skb_frag_fill_page_desc(frag, page, offset, len); if (page_is_pfmemalloc(page)) xdp_buff_set_frag_pfmemalloc(xdp); shinfo->xdp_frags_size += len; } *xdp_frags_truesize = xdp_frags_truesz; return 0; err: put_xdp_frags(xdp); return -EINVAL; } static void *mergeable_xdp_get_buf(struct virtnet_info *vi, struct receive_queue *rq, struct bpf_prog *xdp_prog, void *ctx, unsigned int *frame_sz, int *num_buf, struct page **page, int offset, unsigned int *len, struct virtio_net_hdr_mrg_rxbuf *hdr) { unsigned int truesize = mergeable_ctx_to_truesize(ctx); unsigned int headroom = mergeable_ctx_to_headroom(ctx); struct page *xdp_page; unsigned int xdp_room; /* Transient failure which in theory could occur if * in-flight packets from before XDP was enabled reach * the receive path after XDP is loaded. */ if (unlikely(hdr->hdr.gso_type)) return NULL; /* Partially checksummed packets must be dropped. */ if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return NULL; /* Now XDP core assumes frag size is PAGE_SIZE, but buffers * with headroom may add hole in truesize, which * make their length exceed PAGE_SIZE. So we disabled the * hole mechanism for xdp. See add_recvbuf_mergeable(). */ *frame_sz = truesize; if (likely(headroom >= virtnet_get_headroom(vi) && (*num_buf == 1 || xdp_prog->aux->xdp_has_frags))) { return page_address(*page) + offset; } /* This happens when headroom is not enough because * of the buffer was prefilled before XDP is set. * This should only happen for the first several packets. * In fact, vq reset can be used here to help us clean up * the prefilled buffers, but many existing devices do not * support it, and we don't want to bother users who are * using xdp normally. */ if (!xdp_prog->aux->xdp_has_frags) { /* linearize data for XDP */ xdp_page = xdp_linearize_page(rq, num_buf, *page, offset, XDP_PACKET_HEADROOM, len); if (!xdp_page) return NULL; } else { xdp_room = SKB_DATA_ALIGN(XDP_PACKET_HEADROOM + sizeof(struct skb_shared_info)); if (*len + xdp_room > PAGE_SIZE) return NULL; xdp_page = alloc_page(GFP_ATOMIC); if (!xdp_page) return NULL; memcpy(page_address(xdp_page) + XDP_PACKET_HEADROOM, page_address(*page) + offset, *len); } *frame_sz = PAGE_SIZE; put_page(*page); *page = xdp_page; return page_address(*page) + XDP_PACKET_HEADROOM; } static struct sk_buff *receive_mergeable_xdp(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct bpf_prog *xdp_prog, void *buf, void *ctx, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); struct page *page = virt_to_head_page(buf); int offset = buf - page_address(page); unsigned int xdp_frags_truesz = 0; struct sk_buff *head_skb; unsigned int frame_sz; struct xdp_buff xdp; void *data; u32 act; int err; data = mergeable_xdp_get_buf(vi, rq, xdp_prog, ctx, &frame_sz, &num_buf, &page, offset, &len, hdr); if (unlikely(!data)) goto err_xdp; err = virtnet_build_xdp_buff_mrg(dev, vi, rq, &xdp, data, len, frame_sz, &num_buf, &xdp_frags_truesz, stats); if (unlikely(err)) goto err_xdp; act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats); switch (act) { case XDP_PASS: head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz); if (unlikely(!head_skb)) break; return head_skb; case XDP_TX: case XDP_REDIRECT: return NULL; default: break; } put_xdp_frags(&xdp); err_xdp: put_page(page); mergeable_buf_free(rq, num_buf, dev, stats); u64_stats_inc(&stats->xdp_drops); u64_stats_inc(&stats->drops); return NULL; } static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, struct sk_buff *curr_skb, struct page *page, void *buf, int len, int truesize) { int num_skb_frags; int offset; num_skb_frags = skb_shinfo(curr_skb)->nr_frags; if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) { struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC); if (unlikely(!nskb)) return NULL; if (curr_skb == head_skb) skb_shinfo(curr_skb)->frag_list = nskb; else curr_skb->next = nskb; curr_skb = nskb; head_skb->truesize += nskb->truesize; num_skb_frags = 0; } if (curr_skb != head_skb) { head_skb->data_len += len; head_skb->len += len; head_skb->truesize += truesize; } offset = buf - page_address(page); if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) { put_page(page); skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1, len, truesize); } else { skb_add_rx_frag(curr_skb, num_skb_frags, page, offset, len, truesize); } return curr_skb; } static struct sk_buff *receive_mergeable(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); struct page *page = virt_to_head_page(buf); int offset = buf - page_address(page); struct sk_buff *head_skb, *curr_skb; unsigned int truesize = mergeable_ctx_to_truesize(ctx); unsigned int headroom = mergeable_ctx_to_headroom(ctx); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); head_skb = NULL; u64_stats_add(&stats->bytes, len - vi->hdr_len); if (unlikely(len > truesize - room)) { pr_debug("%s: rx error: len %u exceeds truesize %lu\n", dev->name, len, (unsigned long)(truesize - room)); DEV_STATS_INC(dev, rx_length_errors); goto err_skb; } if (unlikely(vi->xdp_enabled)) { struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { head_skb = receive_mergeable_xdp(dev, vi, rq, xdp_prog, buf, ctx, len, xdp_xmit, stats); rcu_read_unlock(); return head_skb; } rcu_read_unlock(); } head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom); curr_skb = head_skb; if (unlikely(!curr_skb)) goto err_skb; while (--num_buf) { buf = virtnet_rq_get_buf(rq, &len, &ctx); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", dev->name, num_buf, virtio16_to_cpu(vi->vdev, hdr->num_buffers)); DEV_STATS_INC(dev, rx_length_errors); goto err_buf; } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); truesize = mergeable_ctx_to_truesize(ctx); headroom = mergeable_ctx_to_headroom(ctx); tailroom = headroom ? sizeof(struct skb_shared_info) : 0; room = SKB_DATA_ALIGN(headroom + tailroom); if (unlikely(len > truesize - room)) { pr_debug("%s: rx error: len %u exceeds truesize %lu\n", dev->name, len, (unsigned long)(truesize - room)); DEV_STATS_INC(dev, rx_length_errors); goto err_skb; } curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) goto err_skb; } ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len); return head_skb; err_skb: put_page(page); mergeable_buf_free(rq, num_buf, dev, stats); err_buf: u64_stats_inc(&stats->drops); dev_kfree_skb(head_skb); return NULL; } static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash, struct sk_buff *skb) { enum pkt_hash_types rss_hash_type; if (!hdr_hash || !skb) return; switch (__le16_to_cpu(hdr_hash->hash_report)) { case VIRTIO_NET_HASH_REPORT_TCPv4: case VIRTIO_NET_HASH_REPORT_UDPv4: case VIRTIO_NET_HASH_REPORT_TCPv6: case VIRTIO_NET_HASH_REPORT_UDPv6: case VIRTIO_NET_HASH_REPORT_TCPv6_EX: case VIRTIO_NET_HASH_REPORT_UDPv6_EX: rss_hash_type = PKT_HASH_TYPE_L4; break; case VIRTIO_NET_HASH_REPORT_IPv4: case VIRTIO_NET_HASH_REPORT_IPv6: case VIRTIO_NET_HASH_REPORT_IPv6_EX: rss_hash_type = PKT_HASH_TYPE_L3; break; case VIRTIO_NET_HASH_REPORT_NONE: default: rss_hash_type = PKT_HASH_TYPE_NONE; } skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type); } static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq, struct sk_buff *skb, u8 flags) { struct virtio_net_common_hdr *hdr; struct net_device *dev = vi->dev; hdr = skb_vnet_common_hdr(skb); if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) virtio_skb_set_hash(&hdr->hash_v1_hdr, skb); if (flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; if (virtio_net_hdr_to_skb(skb, &hdr->hdr, virtio_is_little_endian(vi->vdev))) { net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n", dev->name, hdr->hdr.gso_type, hdr->hdr.gso_size); goto frame_err; } skb_record_rx_queue(skb, vq2rxq(rq->vq)); skb->protocol = eth_type_trans(skb, dev); pr_debug("Receiving skb proto 0x%04x len %i type %i\n", ntohs(skb->protocol), skb->len, skb->pkt_type); napi_gro_receive(&rq->napi, skb); return; frame_err: DEV_STATS_INC(dev, rx_frame_errors); dev_kfree_skb(skb); } static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf, unsigned int len, void **ctx, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct net_device *dev = vi->dev; struct sk_buff *skb; u8 flags; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); DEV_STATS_INC(dev, rx_length_errors); virtnet_rq_free_buf(vi, rq, buf); return; } /* 1. Save the flags early, as the XDP program might overwrite them. * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID * stay valid after XDP processing. * 2. XDP doesn't work with partially checksummed packets (refer to * virtnet_xdp_set()), so packets marked as * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. */ flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; if (vi->mergeable_rx_bufs) skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); else if (vi->big_packets) skb = receive_big(dev, vi, rq, buf, len, stats); else skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); if (unlikely(!skb)) return; virtnet_receive_done(vi, rq, skb, flags); } /* Unlike mergeable buffers, all buffers are allocated to the * same size, except for the headroom. For this reason we do * not need to use mergeable_len_to_ctx here - it is enough * to store the headroom as the context ignoring the truesize. */ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { char *buf; unsigned int xdp_headroom = virtnet_get_headroom(vi); void *ctx = (void *)(unsigned long)xdp_headroom; int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN + xdp_headroom; int err; len = SKB_DATA_ALIGN(len) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (unlikely(!skb_page_frag_refill(len, &rq->alloc_frag, gfp))) return -ENOMEM; buf = virtnet_rq_alloc(rq, len, gfp); if (unlikely(!buf)) return -ENOMEM; buf += VIRTNET_RX_PAD + xdp_headroom; virtnet_rq_init_one_sg(rq, buf, vi->hdr_len + GOOD_PACKET_LEN); err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) { virtnet_rq_unmap(rq, buf, 0); put_page(virt_to_head_page(buf)); } return err; } static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { struct page *first, *list = NULL; char *p; int i, err, offset; sg_init_table(rq->sg, vi->big_packets_num_skbfrags + 2); /* page in rq->sg[vi->big_packets_num_skbfrags + 1] is list tail */ for (i = vi->big_packets_num_skbfrags + 1; i > 1; --i) { first = get_a_page(rq, gfp); if (!first) { if (list) give_pages(rq, list); return -ENOMEM; } sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE); /* chain new page in list head to match sg */ first->private = (unsigned long)list; list = first; } first = get_a_page(rq, gfp); if (!first) { give_pages(rq, list); return -ENOMEM; } p = page_address(first); /* rq->sg[0], rq->sg[1] share the same page */ /* a separated rq->sg[0] for header - required in case !any_header_sg */ sg_set_buf(&rq->sg[0], p, vi->hdr_len); /* rq->sg[1] for data packet, from offset */ offset = sizeof(struct padded_vnet_hdr); sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset); /* chain first in list head */ first->private = (unsigned long)list; err = virtqueue_add_inbuf(rq->vq, rq->sg, vi->big_packets_num_skbfrags + 2, first, gfp); if (err < 0) give_pages(rq, first); return err; } static unsigned int get_mergeable_buf_len(struct receive_queue *rq, struct ewma_pkt_len *avg_pkt_len, unsigned int room) { struct virtnet_info *vi = rq->vq->vdev->priv; const size_t hdr_len = vi->hdr_len; unsigned int len; if (room) return PAGE_SIZE - room; len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), rq->min_buf_len, PAGE_SIZE - hdr_len); return ALIGN(len, L1_CACHE_BYTES); } static int add_recvbuf_mergeable(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { struct page_frag *alloc_frag = &rq->alloc_frag; unsigned int headroom = virtnet_get_headroom(vi); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); unsigned int len, hole; void *ctx; char *buf; int err; /* Extra tailroom is needed to satisfy XDP's assumption. This * means rx frags coalescing won't work, but consider we've * disabled GSO for XDP, it won't be a big issue. */ len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) return -ENOMEM; if (!alloc_frag->offset && len + room + sizeof(struct virtnet_rq_dma) > alloc_frag->size) len -= sizeof(struct virtnet_rq_dma); buf = virtnet_rq_alloc(rq, len + room, gfp); if (unlikely(!buf)) return -ENOMEM; buf += headroom; /* advance address leaving hole at front of pkt */ hole = alloc_frag->size - alloc_frag->offset; if (hole < len + room) { /* To avoid internal fragmentation, if there is very likely not * enough space for another buffer, add the remaining space to * the current buffer. * XDP core assumes that frame_size of xdp_buff and the length * of the frag are PAGE_SIZE, so we disable the hole mechanism. */ if (!headroom) len += hole; alloc_frag->offset += hole; } virtnet_rq_init_one_sg(rq, buf, len); ctx = mergeable_len_to_ctx(len + room, headroom); err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) { virtnet_rq_unmap(rq, buf, 0); put_page(virt_to_head_page(buf)); } return err; } /* * Returns false if we couldn't fill entirely (OOM). * * Normally run in the receive path, but can also be run from ndo_open * before we're receiving packets, or from refill_work which is * careful to disable receiving (using napi_disable). */ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { int err; if (rq->xsk_pool) { err = virtnet_add_recvbuf_xsk(vi, rq, rq->xsk_pool, gfp); goto kick; } do { if (vi->mergeable_rx_bufs) err = add_recvbuf_mergeable(vi, rq, gfp); else if (vi->big_packets) err = add_recvbuf_big(vi, rq, gfp); else err = add_recvbuf_small(vi, rq, gfp); if (err) break; } while (rq->vq->num_free); kick: if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { unsigned long flags; flags = u64_stats_update_begin_irqsave(&rq->stats.syncp); u64_stats_inc(&rq->stats.kicks); u64_stats_update_end_irqrestore(&rq->stats.syncp, flags); } return err != -ENOMEM; } static void skb_recv_done(struct virtqueue *rvq) { struct virtnet_info *vi = rvq->vdev->priv; struct receive_queue *rq = &vi->rq[vq2rxq(rvq)]; rq->calls++; virtqueue_napi_schedule(&rq->napi, rvq); } static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi) { napi_enable(napi); /* If all buffers were filled by other side before we napi_enabled, we * won't get another interrupt, so process any outstanding packets now. * Call local_bh_enable after to trigger softIRQ processing. */ local_bh_disable(); virtqueue_napi_schedule(napi, vq); local_bh_enable(); } static void virtnet_napi_tx_enable(struct virtnet_info *vi, struct virtqueue *vq, struct napi_struct *napi) { if (!napi->weight) return; /* Tx napi touches cachelines on the cpu handling tx interrupts. Only * enable the feature if this is likely affine with the transmit path. */ if (!vi->affinity_hint_set) { napi->weight = 0; return; } return virtnet_napi_enable(vq, napi); } static void virtnet_napi_tx_disable(struct napi_struct *napi) { if (napi->weight) napi_disable(napi); } static void refill_work(struct work_struct *work) { struct virtnet_info *vi = container_of(work, struct virtnet_info, refill.work); bool still_empty; int i; for (i = 0; i < vi->curr_queue_pairs; i++) { struct receive_queue *rq = &vi->rq[i]; napi_disable(&rq->napi); still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); virtnet_napi_enable(rq->vq, &rq->napi); /* In theory, this can happen: if we don't get any buffers in * we will *never* try to fill again. */ if (still_empty) schedule_delayed_work(&vi->refill, HZ/2); } } static int virtnet_receive_xsk_bufs(struct virtnet_info *vi, struct receive_queue *rq, int budget, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int len; int packets = 0; void *buf; while (packets < budget) { buf = virtqueue_get_buf(rq->vq, &len); if (!buf) break; virtnet_receive_xsk_buf(vi, rq, buf, len, xdp_xmit, stats); packets++; } return packets; } static int virtnet_receive_packets(struct virtnet_info *vi, struct receive_queue *rq, int budget, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int len; int packets = 0; void *buf; if (!vi->big_packets || vi->mergeable_rx_bufs) { void *ctx; while (packets < budget && (buf = virtnet_rq_get_buf(rq, &len, &ctx))) { receive_buf(vi, rq, buf, len, ctx, xdp_xmit, stats); packets++; } } else { while (packets < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { receive_buf(vi, rq, buf, len, NULL, xdp_xmit, stats); packets++; } } return packets; } static int virtnet_receive(struct receive_queue *rq, int budget, unsigned int *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_stats stats = {}; int i, packets; if (rq->xsk_pool) packets = virtnet_receive_xsk_bufs(vi, rq, budget, xdp_xmit, &stats); else packets = virtnet_receive_packets(vi, rq, budget, xdp_xmit, &stats); if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { if (!try_fill_recv(vi, rq, GFP_ATOMIC)) { spin_lock(&vi->refill_lock); if (vi->refill_enabled) schedule_delayed_work(&vi->refill, 0); spin_unlock(&vi->refill_lock); } } u64_stats_set(&stats.packets, packets); u64_stats_update_begin(&rq->stats.syncp); for (i = 0; i < ARRAY_SIZE(virtnet_rq_stats_desc); i++) { size_t offset = virtnet_rq_stats_desc[i].offset; u64_stats_t *item, *src; item = (u64_stats_t *)((u8 *)&rq->stats + offset); src = (u64_stats_t *)((u8 *)&stats + offset); u64_stats_add(item, u64_stats_read(src)); } u64_stats_add(&rq->stats.packets, u64_stats_read(&stats.packets)); u64_stats_add(&rq->stats.bytes, u64_stats_read(&stats.bytes)); u64_stats_update_end(&rq->stats.syncp); return packets; } static void virtnet_poll_cleantx(struct receive_queue *rq, int budget) { struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int index = vq2rxq(rq->vq); struct send_queue *sq = &vi->sq[index]; struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) return; if (__netif_tx_trylock(txq)) { if (sq->reset) { __netif_tx_unlock(txq); return; } do { virtqueue_disable_cb(sq->vq); free_old_xmit(sq, txq, !!budget); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { if (netif_tx_queue_stopped(txq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); u64_stats_update_end(&sq->stats.syncp); } netif_tx_wake_queue(txq); } __netif_tx_unlock(txq); } } static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq) { struct dim_sample cur_sample = {}; if (!rq->packets_in_napi) return; /* Don't need protection when fetching stats, since fetcher and * updater of the stats are in same context */ dim_update_sample(rq->calls, u64_stats_read(&rq->stats.packets), u64_stats_read(&rq->stats.bytes), &cur_sample); net_dim(&rq->dim, &cur_sample); rq->packets_in_napi = 0; } static int virtnet_poll(struct napi_struct *napi, int budget) { struct receive_queue *rq = container_of(napi, struct receive_queue, napi); struct virtnet_info *vi = rq->vq->vdev->priv; struct send_queue *sq; unsigned int received; unsigned int xdp_xmit = 0; bool napi_complete; virtnet_poll_cleantx(rq, budget); received = virtnet_receive(rq, budget, &xdp_xmit); rq->packets_in_napi += received; if (xdp_xmit & VIRTIO_XDP_REDIR) xdp_do_flush(); /* Out of packets? */ if (received < budget) { napi_complete = virtqueue_napi_complete(napi, rq->vq, received); /* Intentionally not taking dim_lock here. This may result in a * spurious net_dim call. But if that happens virtnet_rx_dim_work * will not act on the scheduled work. */ if (napi_complete && rq->dim_enabled) virtnet_rx_dim_update(vi, rq); } if (xdp_xmit & VIRTIO_XDP_TX) { sq = virtnet_xdp_get_sq(vi); if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.kicks); u64_stats_update_end(&sq->stats.syncp); } virtnet_xdp_put_sq(vi, sq); } return received; } static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) { virtnet_napi_tx_disable(&vi->sq[qp_index].napi); napi_disable(&vi->rq[qp_index].napi); xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); } static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) { struct net_device *dev = vi->dev; int err; err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, vi->rq[qp_index].napi.napi_id); if (err < 0) return err; err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) goto err_xdp_reg_mem_model; virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); return 0; err_xdp_reg_mem_model: xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); return err; } static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim) { if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return; net_dim_work_cancel(dim); } static void virtnet_update_settings(struct virtnet_info *vi) { u32 speed; u8 duplex; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) return; virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); if (ethtool_validate_speed(speed)) vi->speed = speed; virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); if (ethtool_validate_duplex(duplex)) vi->duplex = duplex; } static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); int i, err; enable_delayed_refill(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) /* Make sure we have some buffers: if oom use wq. */ if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); err = virtnet_enable_queue_pair(vi, i); if (err < 0) goto err_enable_qp; } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { if (vi->status & VIRTIO_NET_S_LINK_UP) netif_carrier_on(vi->dev); virtio_config_driver_enable(vi->vdev); } else { vi->status = VIRTIO_NET_S_LINK_UP; netif_carrier_on(dev); } return 0; err_enable_qp: disable_delayed_refill(vi); cancel_delayed_work_sync(&vi->refill); for (i--; i >= 0; i--) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); } return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) { struct send_queue *sq = container_of(napi, struct send_queue, napi); struct virtnet_info *vi = sq->vq->vdev->priv; unsigned int index = vq2txq(sq->vq); struct netdev_queue *txq; int opaque, xsk_done = 0; bool done; if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { /* We don't need to enable cb for XDP */ napi_complete_done(napi, 0); return 0; } txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); virtqueue_disable_cb(sq->vq); if (sq->xsk_pool) xsk_done = virtnet_xsk_xmit(sq, sq->xsk_pool, budget); else free_old_xmit(sq, txq, !!budget); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { if (netif_tx_queue_stopped(txq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); u64_stats_update_end(&sq->stats.syncp); } netif_tx_wake_queue(txq); } if (xsk_done >= budget) { __netif_tx_unlock(txq); return budget; } opaque = virtqueue_enable_cb_prepare(sq->vq); done = napi_complete_done(napi, 0); if (!done) virtqueue_disable_cb(sq->vq); __netif_tx_unlock(txq); if (done) { if (unlikely(virtqueue_poll(sq->vq, opaque))) { if (napi_schedule_prep(napi)) { __netif_tx_lock(txq, raw_smp_processor_id()); virtqueue_disable_cb(sq->vq); __netif_tx_unlock(txq); __napi_schedule(napi); } } } return 0; } static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) { struct virtio_net_hdr_mrg_rxbuf *hdr; const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; struct virtnet_info *vi = sq->vq->vdev->priv; int num_sg; unsigned hdr_len = vi->hdr_len; bool can_push; pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); can_push = vi->any_header_sg && !((unsigned long)skb->data & (__alignof__(*hdr) - 1)) && !skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len; /* Even if we can, don't push here yet as this would skew * csum_start offset below. */ if (can_push) hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len); else hdr = &skb_vnet_common_hdr(skb)->mrg_hdr; if (virtio_net_hdr_from_skb(skb, &hdr->hdr, virtio_is_little_endian(vi->vdev), false, 0)) return -EPROTO; if (vi->mergeable_rx_bufs) hdr->num_buffers = 0; sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2)); if (can_push) { __skb_push(skb, hdr_len); num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len); if (unlikely(num_sg < 0)) return num_sg; /* Pull header back to avoid skew in tx bytes calculations. */ __skb_pull(skb, hdr_len); } else { sg_set_buf(sq->sg, hdr, hdr_len); num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len); if (unlikely(num_sg < 0)) return num_sg; num_sg++; } return virtnet_add_outbuf(sq, num_sg, skb, orphan ? VIRTNET_XMIT_TYPE_SKB_ORPHAN : VIRTNET_XMIT_TYPE_SKB); } static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); int qnum = skb_get_queue_mapping(skb); struct send_queue *sq = &vi->sq[qnum]; int err; struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); bool xmit_more = netdev_xmit_more(); bool use_napi = sq->napi.weight; bool kick; /* Free up any pending old buffers before queueing new ones. */ do { if (use_napi) virtqueue_disable_cb(sq->vq); free_old_xmit(sq, txq, false); } while (use_napi && !xmit_more && unlikely(!virtqueue_enable_cb_delayed(sq->vq))); /* timestamp packet in software */ skb_tx_timestamp(skb); /* Try to transmit */ err = xmit_skb(sq, skb, !use_napi); /* This should not happen! */ if (unlikely(err)) { DEV_STATS_INC(dev, tx_fifo_errors); if (net_ratelimit()) dev_warn(&dev->dev, "Unexpected TXQ (%d) queue failure: %d\n", qnum, err); DEV_STATS_INC(dev, tx_dropped); dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Don't wait up for transmitted skbs to be freed. */ if (!use_napi) { skb_orphan(skb); nf_reset_ct(skb); } check_sq_full_and_disable(vi, dev, sq); kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) : !xmit_more || netif_xmit_stopped(txq); if (kick) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.kicks); u64_stats_update_end(&sq->stats.syncp); } } return NETDEV_TX_OK; } static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) { bool running = netif_running(vi->dev); if (running) { napi_disable(&rq->napi); virtnet_cancel_dim(vi, &rq->dim); } } static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) { bool running = netif_running(vi->dev); if (!try_fill_recv(vi, rq, GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); if (running) virtnet_napi_enable(rq->vq, &rq->napi); } static int virtnet_rx_resize(struct virtnet_info *vi, struct receive_queue *rq, u32 ring_num) { int err, qindex; qindex = rq - vi->rq; virtnet_rx_pause(vi, rq); err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf, NULL); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); virtnet_rx_resume(vi, rq); return err; } static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq) { bool running = netif_running(vi->dev); struct netdev_queue *txq; int qindex; qindex = sq - vi->sq; if (running) virtnet_napi_tx_disable(&sq->napi); txq = netdev_get_tx_queue(vi->dev, qindex); /* 1. wait all ximt complete * 2. fix the race of netif_stop_subqueue() vs netif_start_subqueue() */ __netif_tx_lock_bh(txq); /* Prevent rx poll from accessing sq. */ sq->reset = true; /* Prevent the upper layer from trying to send packets. */ netif_stop_subqueue(vi->dev, qindex); __netif_tx_unlock_bh(txq); } static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq) { bool running = netif_running(vi->dev); struct netdev_queue *txq; int qindex; qindex = sq - vi->sq; txq = netdev_get_tx_queue(vi->dev, qindex); __netif_tx_lock_bh(txq); sq->reset = false; netif_tx_wake_queue(txq); __netif_tx_unlock_bh(txq); if (running) virtnet_napi_tx_enable(vi, sq->vq, &sq->napi); } static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, u32 ring_num) { int qindex, err; qindex = sq - vi->sq; virtnet_tx_pause(vi, sq); err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf, virtnet_sq_free_unused_buf_done); if (err) netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err); virtnet_tx_resume(vi, sq); return err; } /* * Send command via the control virtqueue and check status. Commands * supported by the hypervisor, as indicated by feature bits, should * never fail unless improperly formatted. */ static bool virtnet_send_command_reply(struct virtnet_info *vi, u8 class, u8 cmd, struct scatterlist *out, struct scatterlist *in) { struct scatterlist *sgs[5], hdr, stat; u32 out_num = 0, tmp, in_num = 0; bool ok; int ret; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); mutex_lock(&vi->cvq_lock); vi->ctrl->status = ~0; vi->ctrl->hdr.class = class; vi->ctrl->hdr.cmd = cmd; /* Add header */ sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr)); sgs[out_num++] = &hdr; if (out) sgs[out_num++] = out; /* Add return status. */ sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status)); sgs[out_num + in_num++] = &stat; if (in) sgs[out_num + in_num++] = in; BUG_ON(out_num + in_num > ARRAY_SIZE(sgs)); ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, in_num, vi, GFP_ATOMIC); if (ret < 0) { dev_warn(&vi->vdev->dev, "Failed to add sgs for command vq: %d\n.", ret); mutex_unlock(&vi->cvq_lock); return false; } if (unlikely(!virtqueue_kick(vi->cvq))) goto unlock; /* Spin for a response, the kick causes an ioport write, trapping * into the hypervisor, so the request should be handled immediately. */ while (!virtqueue_get_buf(vi->cvq, &tmp) && !virtqueue_is_broken(vi->cvq)) { cond_resched(); cpu_relax(); } unlock: ok = vi->ctrl->status == VIRTIO_NET_OK; mutex_unlock(&vi->cvq_lock); return ok; } static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, struct scatterlist *out) { return virtnet_send_command_reply(vi, class, cmd, out, NULL); } static int virtnet_set_mac_address(struct net_device *dev, void *p) { struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; int ret; struct sockaddr *addr; struct scatterlist sg; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY)) return -EOPNOTSUPP; addr = kmemdup(p, sizeof(*addr), GFP_KERNEL); if (!addr) return -ENOMEM; ret = eth_prepare_mac_addr_change(dev, addr); if (ret) goto out; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { sg_init_one(&sg, addr->sa_data, dev->addr_len); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { dev_warn(&vdev->dev, "Failed to set mac address by vq command.\n"); ret = -EINVAL; goto out; } } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) { unsigned int i; /* Naturally, this has an atomicity problem. */ for (i = 0; i < dev->addr_len; i++) virtio_cwrite8(vdev, offsetof(struct virtio_net_config, mac) + i, addr->sa_data[i]); } eth_commit_mac_addr_change(dev, p); ret = 0; out: kfree(addr); return ret; } static void virtnet_stats(struct net_device *dev, struct rtnl_link_stats64 *tot) { struct virtnet_info *vi = netdev_priv(dev); unsigned int start; int i; for (i = 0; i < vi->max_queue_pairs; i++) { u64 tpackets, tbytes, terrors, rpackets, rbytes, rdrops; struct receive_queue *rq = &vi->rq[i]; struct send_queue *sq = &vi->sq[i]; do { start = u64_stats_fetch_begin(&sq->stats.syncp); tpackets = u64_stats_read(&sq->stats.packets); tbytes = u64_stats_read(&sq->stats.bytes); terrors = u64_stats_read(&sq->stats.tx_timeouts); } while (u64_stats_fetch_retry(&sq->stats.syncp, start)); do { start = u64_stats_fetch_begin(&rq->stats.syncp); rpackets = u64_stats_read(&rq->stats.packets); rbytes = u64_stats_read(&rq->stats.bytes); rdrops = u64_stats_read(&rq->stats.drops); } while (u64_stats_fetch_retry(&rq->stats.syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; tot->rx_bytes += rbytes; tot->tx_bytes += tbytes; tot->rx_dropped += rdrops; tot->tx_errors += terrors; } tot->tx_dropped = DEV_STATS_READ(dev, tx_dropped); tot->tx_fifo_errors = DEV_STATS_READ(dev, tx_fifo_errors); tot->rx_length_errors = DEV_STATS_READ(dev, rx_length_errors); tot->rx_frame_errors = DEV_STATS_READ(dev, rx_frame_errors); } static void virtnet_ack_link_announce(struct virtnet_info *vi) { if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE, VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL)) dev_warn(&vi->dev->dev, "Failed to ack link announce.\n"); } static bool virtnet_commit_rss_command(struct virtnet_info *vi); static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pairs) { u32 indir_val = 0; int i = 0; for (; i < vi->rss_indir_table_size; ++i) { indir_val = ethtool_rxfh_indir_default(i, queue_pairs); vi->rss.indirection_table[i] = indir_val; } vi->rss.max_tx_vq = queue_pairs; } static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) { struct virtio_net_ctrl_mq *mq __free(kfree) = NULL; struct virtio_net_ctrl_rss old_rss; struct net_device *dev = vi->dev; struct scatterlist sg; if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; /* Firstly check if we need update rss. Do updating if both (1) rss enabled and * (2) no user configuration. * * During rss command processing, device updates queue_pairs using rss.max_tx_vq. That is, * the device updates queue_pairs together with rss, so we can skip the sperate queue_pairs * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly. */ if (vi->has_rss && !netif_is_rxfh_configured(dev)) { memcpy(&old_rss, &vi->rss, sizeof(old_rss)); if (rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size)) { vi->rss.indirection_table = old_rss.indirection_table; return -ENOMEM; } virtnet_rss_update_by_qpairs(vi, queue_pairs); if (!virtnet_commit_rss_command(vi)) { /* restore ctrl_rss if commit_rss_command failed */ rss_indirection_table_free(&vi->rss); memcpy(&vi->rss, &old_rss, sizeof(old_rss)); dev_warn(&dev->dev, "Fail to set num of queue pairs to %d, because committing RSS failed\n", queue_pairs); return -EINVAL; } rss_indirection_table_free(&old_rss); goto succ; } mq = kzalloc(sizeof(*mq), GFP_KERNEL); if (!mq) return -ENOMEM; mq->virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); sg_init_one(&sg, mq, sizeof(*mq)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) { dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n", queue_pairs); return -EINVAL; } succ: vi->curr_queue_pairs = queue_pairs; /* virtnet_open() will refill when device is going to up. */ if (dev->flags & IFF_UP) schedule_delayed_work(&vi->refill, 0); return 0; } static int virtnet_close(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); int i; /* Make sure NAPI doesn't schedule refill work */ disable_delayed_refill(vi); /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); /* Prevent the config change callback from changing carrier * after close */ virtio_config_driver_disable(vi->vdev); /* Stop getting status/speed updates: we don't care until next * open */ cancel_work_sync(&vi->config_work); for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); } netif_carrier_off(dev); return 0; } static void virtnet_rx_mode_work(struct work_struct *work) { struct virtnet_info *vi = container_of(work, struct virtnet_info, rx_mode_work); u8 *promisc_allmulti __free(kfree) = NULL; struct net_device *dev = vi->dev; struct scatterlist sg[2]; struct virtio_net_ctrl_mac *mac_data; struct netdev_hw_addr *ha; int uc_count; int mc_count; void *buf; int i; /* We can't dynamically set ndo_set_rx_mode, so return gracefully */ if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; promisc_allmulti = kzalloc(sizeof(*promisc_allmulti), GFP_KERNEL); if (!promisc_allmulti) { dev_warn(&dev->dev, "Failed to set RX mode, no memory.\n"); return; } rtnl_lock(); *promisc_allmulti = !!(dev->flags & IFF_PROMISC); sg_init_one(sg, promisc_allmulti, sizeof(*promisc_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_PROMISC, sg)) dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", *promisc_allmulti ? "en" : "dis"); *promisc_allmulti = !!(dev->flags & IFF_ALLMULTI); sg_init_one(sg, promisc_allmulti, sizeof(*promisc_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_ALLMULTI, sg)) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", *promisc_allmulti ? "en" : "dis"); netif_addr_lock_bh(dev); uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); /* MAC filter - use one buffer for both lists */ buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) + (2 * sizeof(mac_data->entries)), GFP_ATOMIC); mac_data = buf; if (!buf) { netif_addr_unlock_bh(dev); rtnl_unlock(); return; } sg_init_table(sg, 2); /* Store the unicast list and count in the front of the buffer */ mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count); i = 0; netdev_for_each_uc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); sg_set_buf(&sg[0], mac_data, sizeof(mac_data->entries) + (uc_count * ETH_ALEN)); /* multicast list and count fill the end */ mac_data = (void *)&mac_data->macs[uc_count][0]; mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count); i = 0; netdev_for_each_mc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); netif_addr_unlock_bh(dev); sg_set_buf(&sg[1], mac_data, sizeof(mac_data->entries) + (mc_count * ETH_ALEN)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, VIRTIO_NET_CTRL_MAC_TABLE_SET, sg)) dev_warn(&dev->dev, "Failed to set MAC filter table.\n"); rtnl_unlock(); kfree(buf); } static void virtnet_set_rx_mode(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); if (vi->rx_mode_work_enabled) schedule_work(&vi->rx_mode_work); } static int virtnet_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct virtnet_info *vi = netdev_priv(dev); __virtio16 *_vid __free(kfree) = NULL; struct scatterlist sg; _vid = kzalloc(sizeof(*_vid), GFP_KERNEL); if (!_vid) return -ENOMEM; *_vid = cpu_to_virtio16(vi->vdev, vid); sg_init_one(&sg, _vid, sizeof(*_vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_ADD, &sg)) dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid); return 0; } static int virtnet_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct virtnet_info *vi = netdev_priv(dev); __virtio16 *_vid __free(kfree) = NULL; struct scatterlist sg; _vid = kzalloc(sizeof(*_vid), GFP_KERNEL); if (!_vid) return -ENOMEM; *_vid = cpu_to_virtio16(vi->vdev, vid); sg_init_one(&sg, _vid, sizeof(*_vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_DEL, &sg)) dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid); return 0; } static void virtnet_clean_affinity(struct virtnet_info *vi) { int i; if (vi->affinity_hint_set) { for (i = 0; i < vi->max_queue_pairs; i++) { virtqueue_set_affinity(vi->rq[i].vq, NULL); virtqueue_set_affinity(vi->sq[i].vq, NULL); } vi->affinity_hint_set = false; } } static void virtnet_set_affinity(struct virtnet_info *vi) { cpumask_var_t mask; int stragglers; int group_size; int i, j, cpu; int num_cpu; int stride; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { virtnet_clean_affinity(vi); return; } num_cpu = num_online_cpus(); stride = max_t(int, num_cpu / vi->curr_queue_pairs, 1); stragglers = num_cpu >= vi->curr_queue_pairs ? num_cpu % vi->curr_queue_pairs : 0; cpu = cpumask_first(cpu_online_mask); for (i = 0; i < vi->curr_queue_pairs; i++) { group_size = stride + (i < stragglers ? 1 : 0); for (j = 0; j < group_size; j++) { cpumask_set_cpu(cpu, mask); cpu = cpumask_next_wrap(cpu, cpu_online_mask, nr_cpu_ids, false); } virtqueue_set_affinity(vi->rq[i].vq, mask); virtqueue_set_affinity(vi->sq[i].vq, mask); __netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, XPS_CPUS); cpumask_clear(mask); } vi->affinity_hint_set = true; free_cpumask_var(mask); } static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node) { struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, node); virtnet_set_affinity(vi); return 0; } static int virtnet_cpu_dead(unsigned int cpu, struct hlist_node *node) { struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, node_dead); virtnet_set_affinity(vi); return 0; } static int virtnet_cpu_down_prep(unsigned int cpu, struct hlist_node *node) { struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, node); virtnet_clean_affinity(vi); return 0; } static enum cpuhp_state virtionet_online; static int virtnet_cpu_notif_add(struct virtnet_info *vi) { int ret; ret = cpuhp_state_add_instance_nocalls(virtionet_online, &vi->node); if (ret) return ret; ret = cpuhp_state_add_instance_nocalls(CPUHP_VIRT_NET_DEAD, &vi->node_dead); if (!ret) return ret; cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node); return ret; } static void virtnet_cpu_notif_remove(struct virtnet_info *vi) { cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node); cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_NET_DEAD, &vi->node_dead); } static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi, u16 vqn, u32 max_usecs, u32 max_packets) { struct virtio_net_ctrl_coal_vq *coal_vq __free(kfree) = NULL; struct scatterlist sgs; coal_vq = kzalloc(sizeof(*coal_vq), GFP_KERNEL); if (!coal_vq) return -ENOMEM; coal_vq->vqn = cpu_to_le16(vqn); coal_vq->coal.max_usecs = cpu_to_le32(max_usecs); coal_vq->coal.max_packets = cpu_to_le32(max_packets); sg_init_one(&sgs, coal_vq, sizeof(*coal_vq)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET, &sgs)) return -EINVAL; return 0; } static int virtnet_send_rx_ctrl_coal_vq_cmd(struct virtnet_info *vi, u16 queue, u32 max_usecs, u32 max_packets) { int err; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return -EOPNOTSUPP; err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue), max_usecs, max_packets); if (err) return err; vi->rq[queue].intr_coal.max_usecs = max_usecs; vi->rq[queue].intr_coal.max_packets = max_packets; return 0; } static int virtnet_send_tx_ctrl_coal_vq_cmd(struct virtnet_info *vi, u16 queue, u32 max_usecs, u32 max_packets) { int err; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return -EOPNOTSUPP; err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue), max_usecs, max_packets); if (err) return err; vi->sq[queue].intr_coal.max_usecs = max_usecs; vi->sq[queue].intr_coal.max_packets = max_packets; return 0; } static void virtnet_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); ring->rx_max_pending = vi->rq[0].vq->num_max; ring->tx_max_pending = vi->sq[0].vq->num_max; ring->rx_pending = virtqueue_get_vring_size(vi->rq[0].vq); ring->tx_pending = virtqueue_get_vring_size(vi->sq[0].vq); } static int virtnet_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); u32 rx_pending, tx_pending; struct receive_queue *rq; struct send_queue *sq; int i, err; if (ring->rx_mini_pending || ring->rx_jumbo_pending) return -EINVAL; rx_pending = virtqueue_get_vring_size(vi->rq[0].vq); tx_pending = virtqueue_get_vring_size(vi->sq[0].vq); if (ring->rx_pending == rx_pending && ring->tx_pending == tx_pending) return 0; if (ring->rx_pending > vi->rq[0].vq->num_max) return -EINVAL; if (ring->tx_pending > vi->sq[0].vq->num_max) return -EINVAL; for (i = 0; i < vi->max_queue_pairs; i++) { rq = vi->rq + i; sq = vi->sq + i; if (ring->tx_pending != tx_pending) { err = virtnet_tx_resize(vi, sq, ring->tx_pending); if (err) return err; /* Upon disabling and re-enabling a transmit virtqueue, the device must * set the coalescing parameters of the virtqueue to those configured * through the VIRTIO_NET_CTRL_NOTF_COAL_TX_SET command, or, if the driver * did not set any TX coalescing parameters, to 0. */ err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, i, vi->intr_coal_tx.max_usecs, vi->intr_coal_tx.max_packets); /* Don't break the tx resize action if the vq coalescing is not * supported. The same is true for rx resize below. */ if (err && err != -EOPNOTSUPP) return err; } if (ring->rx_pending != rx_pending) { err = virtnet_rx_resize(vi, rq, ring->rx_pending); if (err) return err; /* The reason is same as the transmit virtqueue reset */ mutex_lock(&vi->rq[i].dim_lock); err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, i, vi->intr_coal_rx.max_usecs, vi->intr_coal_rx.max_packets); mutex_unlock(&vi->rq[i].dim_lock); if (err && err != -EOPNOTSUPP) return err; } } return 0; } static bool virtnet_commit_rss_command(struct virtnet_info *vi) { struct net_device *dev = vi->dev; struct scatterlist sgs[4]; unsigned int sg_buf_size; /* prepare sgs */ sg_init_table(sgs, 4); sg_buf_size = offsetof(struct virtio_net_ctrl_rss, hash_cfg_reserved); sg_set_buf(&sgs[0], &vi->rss, sg_buf_size); if (vi->has_rss) { sg_buf_size = sizeof(uint16_t) * vi->rss_indir_table_size; sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size); } else { sg_set_buf(&sgs[1], &vi->rss.hash_cfg_reserved, sizeof(uint16_t)); } sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key) - offsetof(struct virtio_net_ctrl_rss, max_tx_vq); sg_set_buf(&sgs[2], &vi->rss.max_tx_vq, sg_buf_size); sg_buf_size = vi->rss_key_size; sg_set_buf(&sgs[3], vi->rss.key, sg_buf_size); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG : VIRTIO_NET_CTRL_MQ_HASH_CONFIG, sgs)) goto err; return true; err: dev_warn(&dev->dev, "VIRTIONET issue with committing RSS sgs\n"); return false; } static void virtnet_init_default_rss(struct virtnet_info *vi) { vi->rss.hash_types = vi->rss_hash_types_supported; vi->rss_hash_types_saved = vi->rss_hash_types_supported; vi->rss.indirection_table_mask = vi->rss_indir_table_size ? vi->rss_indir_table_size - 1 : 0; vi->rss.unclassified_queue = 0; virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs); vi->rss.hash_key_length = vi->rss_key_size; netdev_rss_key_fill(vi->rss.key, vi->rss_key_size); } static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info) { info->data = 0; switch (info->flow_type) { case TCP_V4_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv4) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case TCP_V6_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv6) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case UDP_V4_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv4) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case UDP_V6_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv6) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case IPV4_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) info->data = RXH_IP_SRC | RXH_IP_DST; break; case IPV6_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) info->data = RXH_IP_SRC | RXH_IP_DST; break; default: info->data = 0; break; } } static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *info) { u32 new_hashtypes = vi->rss_hash_types_saved; bool is_disable = info->data & RXH_DISCARD; bool is_l4 = info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3); /* supports only 'sd', 'sdfn' and 'r' */ if (!((info->data == (RXH_IP_SRC | RXH_IP_DST)) | is_l4 | is_disable)) return false; switch (info->flow_type) { case TCP_V4_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv4 : 0); break; case UDP_V4_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_UDPv4); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv4 : 0); break; case IPV4_FLOW: new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv4; if (!is_disable) new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv4; break; case TCP_V6_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_TCPv6); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv6 : 0); break; case UDP_V6_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_UDPv6); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv6 : 0); break; case IPV6_FLOW: new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv6; if (!is_disable) new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv6; break; default: /* unsupported flow */ return false; } /* if unsupported hashtype was set */ if (new_hashtypes != (new_hashtypes & vi->rss_hash_types_supported)) return false; if (new_hashtypes != vi->rss_hash_types_saved) { vi->rss_hash_types_saved = new_hashtypes; vi->rss.hash_types = vi->rss_hash_types_saved; if (vi->dev->features & NETIF_F_RXHASH) return virtnet_commit_rss_command(vi); } return true; } static void virtnet_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); strscpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version)); strscpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info)); } /* TODO: Eliminate OOO packets during switching */ static int virtnet_set_channels(struct net_device *dev, struct ethtool_channels *channels) { struct virtnet_info *vi = netdev_priv(dev); u16 queue_pairs = channels->combined_count; int err; /* We don't support separate rx/tx channels. * We don't allow setting 'other' channels. */ if (channels->rx_count || channels->tx_count || channels->other_count) return -EINVAL; if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0) return -EINVAL; /* For now we don't support modifying channels while XDP is loaded * also when XDP is loaded all RX queues have XDP programs so we only * need to check a single RX queue. */ if (vi->rq[0].xdp_prog) return -EINVAL; cpus_read_lock(); err = virtnet_set_queues(vi, queue_pairs); if (err) { cpus_read_unlock(); goto err; } virtnet_set_affinity(vi); cpus_read_unlock(); netif_set_real_num_tx_queues(dev, queue_pairs); netif_set_real_num_rx_queues(dev, queue_pairs); err: return err; } static void virtnet_stats_sprintf(u8 **p, const char *fmt, const char *noq_fmt, int num, int qid, const struct virtnet_stat_desc *desc) { int i; if (qid < 0) { for (i = 0; i < num; ++i) ethtool_sprintf(p, noq_fmt, desc[i].desc); } else { for (i = 0; i < num; ++i) ethtool_sprintf(p, fmt, qid, desc[i].desc); } } /* qid == -1: for rx/tx queue total field */ static void virtnet_get_stats_string(struct virtnet_info *vi, int type, int qid, u8 **data) { const struct virtnet_stat_desc *desc; const char *fmt, *noq_fmt; u8 *p = *data; u32 num; if (type == VIRTNET_Q_TYPE_CQ && qid >= 0) { noq_fmt = "cq_hw_%s"; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_CVQ) { desc = &virtnet_stats_cvq_desc[0]; num = ARRAY_SIZE(virtnet_stats_cvq_desc); virtnet_stats_sprintf(&p, NULL, noq_fmt, num, -1, desc); } } if (type == VIRTNET_Q_TYPE_RX) { fmt = "rx%u_%s"; noq_fmt = "rx_%s"; desc = &virtnet_rq_stats_desc[0]; num = ARRAY_SIZE(virtnet_rq_stats_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); fmt = "rx%u_hw_%s"; noq_fmt = "rx_hw_%s"; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { desc = &virtnet_stats_rx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_basic_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { desc = &virtnet_stats_rx_csum_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_csum_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { desc = &virtnet_stats_rx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_speed_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } } if (type == VIRTNET_Q_TYPE_TX) { fmt = "tx%u_%s"; noq_fmt = "tx_%s"; desc = &virtnet_sq_stats_desc[0]; num = ARRAY_SIZE(virtnet_sq_stats_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); fmt = "tx%u_hw_%s"; noq_fmt = "tx_hw_%s"; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { desc = &virtnet_stats_tx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_basic_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { desc = &virtnet_stats_tx_gso_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_gso_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { desc = &virtnet_stats_tx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_speed_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } } *data = p; } struct virtnet_stats_ctx { /* The stats are write to qstats or ethtool -S */ bool to_qstat; /* Used to calculate the offset inside the output buffer. */ u32 desc_num[3]; /* The actual supported stat types. */ u64 bitmap[3]; /* Used to calculate the reply buffer size. */ u32 size[3]; /* Record the output buffer. */ u64 *data; }; static void virtnet_stats_ctx_init(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, u64 *data, bool to_qstat) { u32 queue_type; ctx->data = data; ctx->to_qstat = to_qstat; if (to_qstat) { ctx->desc_num[VIRTNET_Q_TYPE_RX] = ARRAY_SIZE(virtnet_rq_stats_desc_qstat); ctx->desc_num[VIRTNET_Q_TYPE_TX] = ARRAY_SIZE(virtnet_sq_stats_desc_qstat); queue_type = VIRTNET_Q_TYPE_RX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_basic_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_CSUM; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_csum_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_csum); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_GSO) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_GSO; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_gso_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_gso); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_speed_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_speed); } queue_type = VIRTNET_Q_TYPE_TX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_basic_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_CSUM) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_CSUM; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_csum_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_csum); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_GSO; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_gso_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_gso); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_speed_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_speed); } return; } ctx->desc_num[VIRTNET_Q_TYPE_RX] = ARRAY_SIZE(virtnet_rq_stats_desc); ctx->desc_num[VIRTNET_Q_TYPE_TX] = ARRAY_SIZE(virtnet_sq_stats_desc); if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_CVQ) { queue_type = VIRTNET_Q_TYPE_CQ; ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_CVQ; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_cvq_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_cvq); } queue_type = VIRTNET_Q_TYPE_RX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_basic_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_CSUM; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_csum_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_csum); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_speed_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_speed); } queue_type = VIRTNET_Q_TYPE_TX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_basic_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_GSO; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_gso_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_gso); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_speed_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_speed); } } /* stats_sum_queue - Calculate the sum of the same fields in sq or rq. * @sum: the position to store the sum values * @num: field num * @q_value: the first queue fields * @q_num: number of the queues */ static void stats_sum_queue(u64 *sum, u32 num, u64 *q_value, u32 q_num) { u32 step = num; int i, j; u64 *p; for (i = 0; i < num; ++i) { p = sum + i; *p = 0; for (j = 0; j < q_num; ++j) *p += *(q_value + i + j * step); } } static void virtnet_fill_total_fields(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx) { u64 *data, *first_rx_q, *first_tx_q; u32 num_cq, num_rx, num_tx; num_cq = ctx->desc_num[VIRTNET_Q_TYPE_CQ]; num_rx = ctx->desc_num[VIRTNET_Q_TYPE_RX]; num_tx = ctx->desc_num[VIRTNET_Q_TYPE_TX]; first_rx_q = ctx->data + num_rx + num_tx + num_cq; first_tx_q = first_rx_q + vi->curr_queue_pairs * num_rx; data = ctx->data; stats_sum_queue(data, num_rx, first_rx_q, vi->curr_queue_pairs); data = ctx->data + num_rx; stats_sum_queue(data, num_tx, first_tx_q, vi->curr_queue_pairs); } static void virtnet_fill_stats_qstat(struct virtnet_info *vi, u32 qid, struct virtnet_stats_ctx *ctx, const u8 *base, bool drv_stats, u8 reply_type) { const struct virtnet_stat_desc *desc; const u64_stats_t *v_stat; u64 offset, bitmap; const __le64 *v; u32 queue_type; int i, num; queue_type = vq_type(vi, qid); bitmap = ctx->bitmap[queue_type]; if (drv_stats) { if (queue_type == VIRTNET_Q_TYPE_RX) { desc = &virtnet_rq_stats_desc_qstat[0]; num = ARRAY_SIZE(virtnet_rq_stats_desc_qstat); } else { desc = &virtnet_sq_stats_desc_qstat[0]; num = ARRAY_SIZE(virtnet_sq_stats_desc_qstat); } for (i = 0; i < num; ++i) { offset = desc[i].qstat_offset / sizeof(*ctx->data); v_stat = (const u64_stats_t *)(base + desc[i].offset); ctx->data[offset] = u64_stats_read(v_stat); } return; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { desc = &virtnet_stats_rx_basic_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_basic_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { desc = &virtnet_stats_rx_csum_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_csum_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_GSO) { desc = &virtnet_stats_rx_gso_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_gso_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_GSO) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { desc = &virtnet_stats_rx_speed_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_speed_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { desc = &virtnet_stats_tx_basic_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_basic_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_CSUM) { desc = &virtnet_stats_tx_csum_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_csum_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_CSUM) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_GSO) { desc = &virtnet_stats_tx_gso_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_gso_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { desc = &virtnet_stats_tx_speed_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_speed_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED) goto found; } return; found: for (i = 0; i < num; ++i) { offset = desc[i].qstat_offset / sizeof(*ctx->data); v = (const __le64 *)(base + desc[i].offset); ctx->data[offset] = le64_to_cpu(*v); } } /* virtnet_fill_stats - copy the stats to qstats or ethtool -S * The stats source is the device or the driver. * * @vi: virtio net info * @qid: the vq id * @ctx: stats ctx (initiated by virtnet_stats_ctx_init()) * @base: pointer to the device reply or the driver stats structure. * @drv_stats: designate the base type (device reply, driver stats) * @type: the type of the device reply (if drv_stats is true, this must be zero) */ static void virtnet_fill_stats(struct virtnet_info *vi, u32 qid, struct virtnet_stats_ctx *ctx, const u8 *base, bool drv_stats, u8 reply_type) { u32 queue_type, num_rx, num_tx, num_cq; const struct virtnet_stat_desc *desc; const u64_stats_t *v_stat; u64 offset, bitmap; const __le64 *v; int i, num; if (ctx->to_qstat) return virtnet_fill_stats_qstat(vi, qid, ctx, base, drv_stats, reply_type); num_cq = ctx->desc_num[VIRTNET_Q_TYPE_CQ]; num_rx = ctx->desc_num[VIRTNET_Q_TYPE_RX]; num_tx = ctx->desc_num[VIRTNET_Q_TYPE_TX]; queue_type = vq_type(vi, qid); bitmap = ctx->bitmap[queue_type]; /* skip the total fields of pairs */ offset = num_rx + num_tx; if (queue_type == VIRTNET_Q_TYPE_TX) { offset += num_cq + num_rx * vi->curr_queue_pairs + num_tx * (qid / 2); num = ARRAY_SIZE(virtnet_sq_stats_desc); if (drv_stats) { desc = &virtnet_sq_stats_desc[0]; goto drv_stats; } offset += num; } else if (queue_type == VIRTNET_Q_TYPE_RX) { offset += num_cq + num_rx * (qid / 2); num = ARRAY_SIZE(virtnet_rq_stats_desc); if (drv_stats) { desc = &virtnet_rq_stats_desc[0]; goto drv_stats; } offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_CVQ) { desc = &virtnet_stats_cvq_desc[0]; num = ARRAY_SIZE(virtnet_stats_cvq_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_CVQ) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { desc = &virtnet_stats_rx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_basic_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { desc = &virtnet_stats_rx_csum_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_csum_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { desc = &virtnet_stats_rx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_speed_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { desc = &virtnet_stats_tx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_basic_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_GSO) { desc = &virtnet_stats_tx_gso_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_gso_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { desc = &virtnet_stats_tx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_speed_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED) goto found; offset += num; } return; found: for (i = 0; i < num; ++i) { v = (const __le64 *)(base + desc[i].offset); ctx->data[offset + i] = le64_to_cpu(*v); } return; drv_stats: for (i = 0; i < num; ++i) { v_stat = (const u64_stats_t *)(base + desc[i].offset); ctx->data[offset + i] = u64_stats_read(v_stat); } } static int __virtnet_get_hw_stats(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, struct virtio_net_ctrl_queue_stats *req, int req_size, void *reply, int res_size) { struct virtio_net_stats_reply_hdr *hdr; struct scatterlist sgs_in, sgs_out; void *p; u32 qid; int ok; sg_init_one(&sgs_out, req, req_size); sg_init_one(&sgs_in, reply, res_size); ok = virtnet_send_command_reply(vi, VIRTIO_NET_CTRL_STATS, VIRTIO_NET_CTRL_STATS_GET, &sgs_out, &sgs_in); if (!ok) return ok; for (p = reply; p - reply < res_size; p += le16_to_cpu(hdr->size)) { hdr = p; qid = le16_to_cpu(hdr->vq_index); virtnet_fill_stats(vi, qid, ctx, p, false, hdr->type); } return 0; } static void virtnet_make_stat_req(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, struct virtio_net_ctrl_queue_stats *req, int qid, int *idx) { int qtype = vq_type(vi, qid); u64 bitmap = ctx->bitmap[qtype]; if (!bitmap) return; req->stats[*idx].vq_index = cpu_to_le16(qid); req->stats[*idx].types_bitmap[0] = cpu_to_le64(bitmap); *idx += 1; } /* qid: -1: get stats of all vq. * > 0: get the stats for the special vq. This must not be cvq. */ static int virtnet_get_hw_stats(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, int qid) { int qnum, i, j, res_size, qtype, last_vq, first_vq; struct virtio_net_ctrl_queue_stats *req; bool enable_cvq; void *reply; int ok; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_DEVICE_STATS)) return 0; if (qid == -1) { last_vq = vi->curr_queue_pairs * 2 - 1; first_vq = 0; enable_cvq = true; } else { last_vq = qid; first_vq = qid; enable_cvq = false; } qnum = 0; res_size = 0; for (i = first_vq; i <= last_vq ; ++i) { qtype = vq_type(vi, i); if (ctx->bitmap[qtype]) { ++qnum; res_size += ctx->size[qtype]; } } if (enable_cvq && ctx->bitmap[VIRTNET_Q_TYPE_CQ]) { res_size += ctx->size[VIRTNET_Q_TYPE_CQ]; qnum += 1; } req = kcalloc(qnum, sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; reply = kmalloc(res_size, GFP_KERNEL); if (!reply) { kfree(req); return -ENOMEM; } j = 0; for (i = first_vq; i <= last_vq ; ++i) virtnet_make_stat_req(vi, ctx, req, i, &j); if (enable_cvq) virtnet_make_stat_req(vi, ctx, req, vi->max_queue_pairs * 2, &j); ok = __virtnet_get_hw_stats(vi, ctx, req, sizeof(*req) * j, reply, res_size); kfree(req); kfree(reply); return ok; } static void virtnet_get_strings(struct net_device *dev, u32 stringset, u8 *data) { struct virtnet_info *vi = netdev_priv(dev); unsigned int i; u8 *p = data; switch (stringset) { case ETH_SS_STATS: /* Generate the total field names. */ virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_RX, -1, &p); virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_TX, -1, &p); virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_CQ, 0, &p); for (i = 0; i < vi->curr_queue_pairs; ++i) virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_RX, i, &p); for (i = 0; i < vi->curr_queue_pairs; ++i) virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_TX, i, &p); break; } } static int virtnet_get_sset_count(struct net_device *dev, int sset) { struct virtnet_info *vi = netdev_priv(dev); struct virtnet_stats_ctx ctx = {0}; u32 pair_count; switch (sset) { case ETH_SS_STATS: virtnet_stats_ctx_init(vi, &ctx, NULL, false); pair_count = ctx.desc_num[VIRTNET_Q_TYPE_RX] + ctx.desc_num[VIRTNET_Q_TYPE_TX]; return pair_count + ctx.desc_num[VIRTNET_Q_TYPE_CQ] + vi->curr_queue_pairs * pair_count; default: return -EOPNOTSUPP; } } static void virtnet_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct virtnet_info *vi = netdev_priv(dev); struct virtnet_stats_ctx ctx = {0}; unsigned int start, i; const u8 *stats_base; virtnet_stats_ctx_init(vi, &ctx, data, false); if (virtnet_get_hw_stats(vi, &ctx, -1)) dev_warn(&vi->dev->dev, "Failed to get hw stats.\n"); for (i = 0; i < vi->curr_queue_pairs; i++) { struct receive_queue *rq = &vi->rq[i]; struct send_queue *sq = &vi->sq[i]; stats_base = (const u8 *)&rq->stats; do { start = u64_stats_fetch_begin(&rq->stats.syncp); virtnet_fill_stats(vi, i * 2, &ctx, stats_base, true, 0); } while (u64_stats_fetch_retry(&rq->stats.syncp, start)); stats_base = (const u8 *)&sq->stats; do { start = u64_stats_fetch_begin(&sq->stats.syncp); virtnet_fill_stats(vi, i * 2 + 1, &ctx, stats_base, true, 0); } while (u64_stats_fetch_retry(&sq->stats.syncp, start)); } virtnet_fill_total_fields(vi, &ctx); } static void virtnet_get_channels(struct net_device *dev, struct ethtool_channels *channels) { struct virtnet_info *vi = netdev_priv(dev); channels->combined_count = vi->curr_queue_pairs; channels->max_combined = vi->max_queue_pairs; channels->max_other = 0; channels->rx_count = 0; channels->tx_count = 0; channels->other_count = 0; } static int virtnet_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct virtnet_info *vi = netdev_priv(dev); return ethtool_virtdev_set_link_ksettings(dev, cmd, &vi->speed, &vi->duplex); } static int virtnet_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct virtnet_info *vi = netdev_priv(dev); cmd->base.speed = vi->speed; cmd->base.duplex = vi->duplex; cmd->base.port = PORT_OTHER; return 0; } static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct virtio_net_ctrl_coal_tx *coal_tx __free(kfree) = NULL; struct scatterlist sgs_tx; int i; coal_tx = kzalloc(sizeof(*coal_tx), GFP_KERNEL); if (!coal_tx) return -ENOMEM; coal_tx->tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); coal_tx->tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); sg_init_one(&sgs_tx, coal_tx, sizeof(*coal_tx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, &sgs_tx)) return -EINVAL; vi->intr_coal_tx.max_usecs = ec->tx_coalesce_usecs; vi->intr_coal_tx.max_packets = ec->tx_max_coalesced_frames; for (i = 0; i < vi->max_queue_pairs; i++) { vi->sq[i].intr_coal.max_usecs = ec->tx_coalesce_usecs; vi->sq[i].intr_coal.max_packets = ec->tx_max_coalesced_frames; } return 0; } static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct virtio_net_ctrl_coal_rx *coal_rx __free(kfree) = NULL; bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce; struct scatterlist sgs_rx; int i; if (rx_ctrl_dim_on && !virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return -EOPNOTSUPP; if (rx_ctrl_dim_on && (ec->rx_coalesce_usecs != vi->intr_coal_rx.max_usecs || ec->rx_max_coalesced_frames != vi->intr_coal_rx.max_packets)) return -EINVAL; if (rx_ctrl_dim_on && !vi->rx_dim_enabled) { vi->rx_dim_enabled = true; for (i = 0; i < vi->max_queue_pairs; i++) { mutex_lock(&vi->rq[i].dim_lock); vi->rq[i].dim_enabled = true; mutex_unlock(&vi->rq[i].dim_lock); } return 0; } coal_rx = kzalloc(sizeof(*coal_rx), GFP_KERNEL); if (!coal_rx) return -ENOMEM; if (!rx_ctrl_dim_on && vi->rx_dim_enabled) { vi->rx_dim_enabled = false; for (i = 0; i < vi->max_queue_pairs; i++) { mutex_lock(&vi->rq[i].dim_lock); vi->rq[i].dim_enabled = false; mutex_unlock(&vi->rq[i].dim_lock); } } /* Since the per-queue coalescing params can be set, * we need apply the global new params even if they * are not updated. */ coal_rx->rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); coal_rx->rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); sg_init_one(&sgs_rx, coal_rx, sizeof(*coal_rx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, &sgs_rx)) return -EINVAL; vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs; vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames; for (i = 0; i < vi->max_queue_pairs; i++) { mutex_lock(&vi->rq[i].dim_lock); vi->rq[i].intr_coal.max_usecs = ec->rx_coalesce_usecs; vi->rq[i].intr_coal.max_packets = ec->rx_max_coalesced_frames; mutex_unlock(&vi->rq[i].dim_lock); } return 0; } static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { int err; err = virtnet_send_tx_notf_coal_cmds(vi, ec); if (err) return err; err = virtnet_send_rx_notf_coal_cmds(vi, ec); if (err) return err; return 0; } static int virtnet_send_rx_notf_coal_vq_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec, u16 queue) { bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce; u32 max_usecs, max_packets; bool cur_rx_dim; int err; mutex_lock(&vi->rq[queue].dim_lock); cur_rx_dim = vi->rq[queue].dim_enabled; max_usecs = vi->rq[queue].intr_coal.max_usecs; max_packets = vi->rq[queue].intr_coal.max_packets; if (rx_ctrl_dim_on && (ec->rx_coalesce_usecs != max_usecs || ec->rx_max_coalesced_frames != max_packets)) { mutex_unlock(&vi->rq[queue].dim_lock); return -EINVAL; } if (rx_ctrl_dim_on && !cur_rx_dim) { vi->rq[queue].dim_enabled = true; mutex_unlock(&vi->rq[queue].dim_lock); return 0; } if (!rx_ctrl_dim_on && cur_rx_dim) vi->rq[queue].dim_enabled = false; /* If no params are updated, userspace ethtool will * reject the modification. */ err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, queue, ec->rx_coalesce_usecs, ec->rx_max_coalesced_frames); mutex_unlock(&vi->rq[queue].dim_lock); return err; } static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec, u16 queue) { int err; err = virtnet_send_rx_notf_coal_vq_cmds(vi, ec, queue); if (err) return err; err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, queue, ec->tx_coalesce_usecs, ec->tx_max_coalesced_frames); if (err) return err; return 0; } static void virtnet_rx_dim_work(struct work_struct *work) { struct dim *dim = container_of(work, struct dim, work); struct receive_queue *rq = container_of(dim, struct receive_queue, dim); struct virtnet_info *vi = rq->vq->vdev->priv; struct net_device *dev = vi->dev; struct dim_cq_moder update_moder; int qnum, err; qnum = rq - vi->rq; mutex_lock(&rq->dim_lock); if (!rq->dim_enabled) goto out; update_moder = net_dim_get_rx_irq_moder(dev, dim); if (update_moder.usec != rq->intr_coal.max_usecs || update_moder.pkts != rq->intr_coal.max_packets) { err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum, update_moder.usec, update_moder.pkts); if (err) pr_debug("%s: Failed to send dim parameters on rxq%d\n", dev->name, qnum); } out: dim->state = DIM_START_MEASURE; mutex_unlock(&rq->dim_lock); } static int virtnet_coal_params_supported(struct ethtool_coalesce *ec) { /* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL * or VIRTIO_NET_F_VQ_NOTF_COAL feature is negotiated. */ if (ec->rx_coalesce_usecs || ec->tx_coalesce_usecs) return -EOPNOTSUPP; if (ec->tx_max_coalesced_frames > 1 || ec->rx_max_coalesced_frames != 1) return -EINVAL; return 0; } static int virtnet_should_update_vq_weight(int dev_flags, int weight, int vq_weight, bool *should_update) { if (weight ^ vq_weight) { if (dev_flags & IFF_UP) return -EBUSY; *should_update = true; } return 0; } static int virtnet_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); int ret, queue_number, napi_weight, i; bool update_napi = false; /* Can't change NAPI weight if the link is up */ napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; for (queue_number = 0; queue_number < vi->max_queue_pairs; queue_number++) { ret = virtnet_should_update_vq_weight(dev->flags, napi_weight, vi->sq[queue_number].napi.weight, &update_napi); if (ret) return ret; if (update_napi) { /* All queues that belong to [queue_number, vi->max_queue_pairs] will be * updated for the sake of simplicity, which might not be necessary */ break; } } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) ret = virtnet_send_notf_coal_cmds(vi, ec); else ret = virtnet_coal_params_supported(ec); if (ret) return ret; if (update_napi) { /* xsk xmit depends on the tx napi. So if xsk is active, * prevent modifications to tx napi. */ for (i = queue_number; i < vi->max_queue_pairs; i++) { if (vi->sq[i].xsk_pool) return -EBUSY; } for (; queue_number < vi->max_queue_pairs; queue_number++) vi->sq[queue_number].napi.weight = napi_weight; } return ret; } static int virtnet_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { ec->rx_coalesce_usecs = vi->intr_coal_rx.max_usecs; ec->tx_coalesce_usecs = vi->intr_coal_tx.max_usecs; ec->tx_max_coalesced_frames = vi->intr_coal_tx.max_packets; ec->rx_max_coalesced_frames = vi->intr_coal_rx.max_packets; ec->use_adaptive_rx_coalesce = vi->rx_dim_enabled; } else { ec->rx_max_coalesced_frames = 1; if (vi->sq[0].napi.weight) ec->tx_max_coalesced_frames = 1; } return 0; } static int virtnet_set_per_queue_coalesce(struct net_device *dev, u32 queue, struct ethtool_coalesce *ec) { struct virtnet_info *vi = netdev_priv(dev); int ret, napi_weight; bool update_napi = false; if (queue >= vi->max_queue_pairs) return -EINVAL; /* Can't change NAPI weight if the link is up */ napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; ret = virtnet_should_update_vq_weight(dev->flags, napi_weight, vi->sq[queue].napi.weight, &update_napi); if (ret) return ret; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) ret = virtnet_send_notf_coal_vq_cmds(vi, ec, queue); else ret = virtnet_coal_params_supported(ec); if (ret) return ret; if (update_napi) vi->sq[queue].napi.weight = napi_weight; return 0; } static int virtnet_get_per_queue_coalesce(struct net_device *dev, u32 queue, struct ethtool_coalesce *ec) { struct virtnet_info *vi = netdev_priv(dev); if (queue >= vi->max_queue_pairs) return -EINVAL; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) { mutex_lock(&vi->rq[queue].dim_lock); ec->rx_coalesce_usecs = vi->rq[queue].intr_coal.max_usecs; ec->tx_coalesce_usecs = vi->sq[queue].intr_coal.max_usecs; ec->tx_max_coalesced_frames = vi->sq[queue].intr_coal.max_packets; ec->rx_max_coalesced_frames = vi->rq[queue].intr_coal.max_packets; ec->use_adaptive_rx_coalesce = vi->rq[queue].dim_enabled; mutex_unlock(&vi->rq[queue].dim_lock); } else { ec->rx_max_coalesced_frames = 1; if (vi->sq[queue].napi.weight) ec->tx_max_coalesced_frames = 1; } return 0; } static void virtnet_init_settings(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); vi->speed = SPEED_UNKNOWN; vi->duplex = DUPLEX_UNKNOWN; } static u32 virtnet_get_rxfh_key_size(struct net_device *dev) { return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size; } static u32 virtnet_get_rxfh_indir_size(struct net_device *dev) { return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size; } static int virtnet_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh) { struct virtnet_info *vi = netdev_priv(dev); int i; if (rxfh->indir) { for (i = 0; i < vi->rss_indir_table_size; ++i) rxfh->indir[i] = vi->rss.indirection_table[i]; } if (rxfh->key) memcpy(rxfh->key, vi->rss.key, vi->rss_key_size); rxfh->hfunc = ETH_RSS_HASH_TOP; return 0; } static int virtnet_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); bool update = false; int i; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && rxfh->hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; if (rxfh->indir) { if (!vi->has_rss) return -EOPNOTSUPP; for (i = 0; i < vi->rss_indir_table_size; ++i) vi->rss.indirection_table[i] = rxfh->indir[i]; update = true; } if (rxfh->key) { /* If either _F_HASH_REPORT or _F_RSS are negotiated, the * device provides hash calculation capabilities, that is, * hash_key is configured. */ if (!vi->has_rss && !vi->has_rss_hash_report) return -EOPNOTSUPP; memcpy(vi->rss.key, rxfh->key, vi->rss_key_size); update = true; } if (update) virtnet_commit_rss_command(vi); return 0; } static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct virtnet_info *vi = netdev_priv(dev); int rc = 0; switch (info->cmd) { case ETHTOOL_GRXRINGS: info->data = vi->curr_queue_pairs; break; case ETHTOOL_GRXFH: virtnet_get_hashflow(vi, info); break; default: rc = -EOPNOTSUPP; } return rc; } static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) { struct virtnet_info *vi = netdev_priv(dev); int rc = 0; switch (info->cmd) { case ETHTOOL_SRXFH: if (!virtnet_set_hashflow(vi, info)) rc = -EINVAL; break; default: rc = -EOPNOTSUPP; } return rc; } static const struct ethtool_ops virtnet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, .get_drvinfo = virtnet_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = virtnet_get_ringparam, .set_ringparam = virtnet_set_ringparam, .get_strings = virtnet_get_strings, .get_sset_count = virtnet_get_sset_count, .get_ethtool_stats = virtnet_get_ethtool_stats, .set_channels = virtnet_set_channels, .get_channels = virtnet_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_link_ksettings = virtnet_get_link_ksettings, .set_link_ksettings = virtnet_set_link_ksettings, .set_coalesce = virtnet_set_coalesce, .get_coalesce = virtnet_get_coalesce, .set_per_queue_coalesce = virtnet_set_per_queue_coalesce, .get_per_queue_coalesce = virtnet_get_per_queue_coalesce, .get_rxfh_key_size = virtnet_get_rxfh_key_size, .get_rxfh_indir_size = virtnet_get_rxfh_indir_size, .get_rxfh = virtnet_get_rxfh, .set_rxfh = virtnet_set_rxfh, .get_rxnfc = virtnet_get_rxnfc, .set_rxnfc = virtnet_set_rxnfc, }; static void virtnet_get_queue_stats_rx(struct net_device *dev, int i, struct netdev_queue_stats_rx *stats) { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = &vi->rq[i]; struct virtnet_stats_ctx ctx = {0}; virtnet_stats_ctx_init(vi, &ctx, (void *)stats, true); virtnet_get_hw_stats(vi, &ctx, i * 2); virtnet_fill_stats(vi, i * 2, &ctx, (void *)&rq->stats, true, 0); } static void virtnet_get_queue_stats_tx(struct net_device *dev, int i, struct netdev_queue_stats_tx *stats) { struct virtnet_info *vi = netdev_priv(dev); struct send_queue *sq = &vi->sq[i]; struct virtnet_stats_ctx ctx = {0}; virtnet_stats_ctx_init(vi, &ctx, (void *)stats, true); virtnet_get_hw_stats(vi, &ctx, i * 2 + 1); virtnet_fill_stats(vi, i * 2 + 1, &ctx, (void *)&sq->stats, true, 0); } static void virtnet_get_base_stats(struct net_device *dev, struct netdev_queue_stats_rx *rx, struct netdev_queue_stats_tx *tx) { struct virtnet_info *vi = netdev_priv(dev); /* The queue stats of the virtio-net will not be reset. So here we * return 0. */ rx->bytes = 0; rx->packets = 0; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { rx->hw_drops = 0; rx->hw_drop_overruns = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { rx->csum_unnecessary = 0; rx->csum_none = 0; rx->csum_bad = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_GSO) { rx->hw_gro_packets = 0; rx->hw_gro_bytes = 0; rx->hw_gro_wire_packets = 0; rx->hw_gro_wire_bytes = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) rx->hw_drop_ratelimits = 0; tx->bytes = 0; tx->packets = 0; tx->stop = 0; tx->wake = 0; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { tx->hw_drops = 0; tx->hw_drop_errors = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_CSUM) { tx->csum_none = 0; tx->needs_csum = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { tx->hw_gso_packets = 0; tx->hw_gso_bytes = 0; tx->hw_gso_wire_packets = 0; tx->hw_gso_wire_bytes = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) tx->hw_drop_ratelimits = 0; } static const struct netdev_stat_ops virtnet_stat_ops = { .get_queue_stats_rx = virtnet_get_queue_stats_rx, .get_queue_stats_tx = virtnet_get_queue_stats_tx, .get_base_stats = virtnet_get_base_stats, }; static void virtnet_freeze_down(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; /* Make sure no work handler is accessing the device */ flush_work(&vi->config_work); disable_rx_mode_work(vi); flush_work(&vi->rx_mode_work); netif_tx_lock_bh(vi->dev); netif_device_detach(vi->dev); netif_tx_unlock_bh(vi->dev); if (netif_running(vi->dev)) virtnet_close(vi->dev); } static int init_vqs(struct virtnet_info *vi); static int virtnet_restore_up(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; int err; err = init_vqs(vi); if (err) return err; virtio_device_ready(vdev); enable_delayed_refill(vi); enable_rx_mode_work(vi); if (netif_running(vi->dev)) { err = virtnet_open(vi->dev); if (err) return err; } netif_tx_lock_bh(vi->dev); netif_device_attach(vi->dev); netif_tx_unlock_bh(vi->dev); return err; } static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads) { __virtio64 *_offloads __free(kfree) = NULL; struct scatterlist sg; _offloads = kzalloc(sizeof(*_offloads), GFP_KERNEL); if (!_offloads) return -ENOMEM; *_offloads = cpu_to_virtio64(vi->vdev, offloads); sg_init_one(&sg, _offloads, sizeof(*_offloads)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS, VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) { dev_warn(&vi->dev->dev, "Fail to set guest offload.\n"); return -EINVAL; } return 0; } static int virtnet_clear_guest_offloads(struct virtnet_info *vi) { u64 offloads = 0; if (!vi->guest_offloads) return 0; return virtnet_set_guest_offloads(vi, offloads); } static int virtnet_restore_guest_offloads(struct virtnet_info *vi) { u64 offloads = vi->guest_offloads; if (!vi->guest_offloads) return 0; return virtnet_set_guest_offloads(vi, offloads); } static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queue *rq, struct xsk_buff_pool *pool) { int err, qindex; qindex = rq - vi->rq; if (pool) { err = xdp_rxq_info_reg(&rq->xsk_rxq_info, vi->dev, qindex, rq->napi.napi_id); if (err < 0) return err; err = xdp_rxq_info_reg_mem_model(&rq->xsk_rxq_info, MEM_TYPE_XSK_BUFF_POOL, NULL); if (err < 0) goto unreg; xsk_pool_set_rxq_info(pool, &rq->xsk_rxq_info); } virtnet_rx_pause(vi, rq); err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf, NULL); if (err) { netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err); pool = NULL; } rq->xsk_pool = pool; virtnet_rx_resume(vi, rq); if (pool) return 0; unreg: xdp_rxq_info_unreg(&rq->xsk_rxq_info); return err; } static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi, struct send_queue *sq, struct xsk_buff_pool *pool) { int err, qindex; qindex = sq - vi->sq; virtnet_tx_pause(vi, sq); err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf, virtnet_sq_free_unused_buf_done); if (err) { netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err); pool = NULL; } sq->xsk_pool = pool; virtnet_tx_resume(vi, sq); return err; } static int virtnet_xsk_pool_enable(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid) { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq; struct device *dma_dev; struct send_queue *sq; dma_addr_t hdr_dma; int err, size; if (vi->hdr_len > xsk_pool_get_headroom(pool)) return -EINVAL; /* In big_packets mode, xdp cannot work, so there is no need to * initialize xsk of rq. */ if (vi->big_packets && !vi->mergeable_rx_bufs) return -ENOENT; if (qid >= vi->curr_queue_pairs) return -EINVAL; sq = &vi->sq[qid]; rq = &vi->rq[qid]; /* xsk assumes that tx and rx must have the same dma device. The af-xdp * may use one buffer to receive from the rx and reuse this buffer to * send by the tx. So the dma dev of sq and rq must be the same one. * * But vq->dma_dev allows every vq has the respective dma dev. So I * check the dma dev of vq and sq is the same dev. */ if (virtqueue_dma_dev(rq->vq) != virtqueue_dma_dev(sq->vq)) return -EINVAL; dma_dev = virtqueue_dma_dev(rq->vq); if (!dma_dev) return -EINVAL; size = virtqueue_get_vring_size(rq->vq); rq->xsk_buffs = kvcalloc(size, sizeof(*rq->xsk_buffs), GFP_KERNEL); if (!rq->xsk_buffs) return -ENOMEM; hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len, DMA_TO_DEVICE, 0); if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) return -ENOMEM; err = xsk_pool_dma_map(pool, dma_dev, 0); if (err) goto err_xsk_map; err = virtnet_rq_bind_xsk_pool(vi, rq, pool); if (err) goto err_rq; err = virtnet_sq_bind_xsk_pool(vi, sq, pool); if (err) goto err_sq; /* Now, we do not support tx offload(such as tx csum), so all the tx * virtnet hdr is zero. So all the tx packets can share a single hdr. */ sq->xsk_hdr_dma_addr = hdr_dma; return 0; err_sq: virtnet_rq_bind_xsk_pool(vi, rq, NULL); err_rq: xsk_pool_dma_unmap(pool, 0); err_xsk_map: virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len, DMA_TO_DEVICE, 0); return err; } static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid) { struct virtnet_info *vi = netdev_priv(dev); struct xsk_buff_pool *pool; struct receive_queue *rq; struct send_queue *sq; int err; if (qid >= vi->curr_queue_pairs) return -EINVAL; sq = &vi->sq[qid]; rq = &vi->rq[qid]; pool = rq->xsk_pool; err = virtnet_rq_bind_xsk_pool(vi, rq, NULL); err |= virtnet_sq_bind_xsk_pool(vi, sq, NULL); xsk_pool_dma_unmap(pool, 0); virtqueue_dma_unmap_single_attrs(sq->vq, sq->xsk_hdr_dma_addr, vi->hdr_len, DMA_TO_DEVICE, 0); kvfree(rq->xsk_buffs); return err; } static int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp) { if (xdp->xsk.pool) return virtnet_xsk_pool_enable(dev, xdp->xsk.pool, xdp->xsk.queue_id); else return virtnet_xsk_pool_disable(dev, xdp->xsk.queue_id); } static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { unsigned int room = SKB_DATA_ALIGN(XDP_PACKET_HEADROOM + sizeof(struct skb_shared_info)); unsigned int max_sz = PAGE_SIZE - room - ETH_HLEN; struct virtnet_info *vi = netdev_priv(dev); struct bpf_prog *old_prog; u16 xdp_qp = 0, curr_qp; int i, err; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) && (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO6))) { NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing GRO_HW/CSUM, disable GRO_HW/CSUM first"); return -EOPNOTSUPP; } if (vi->mergeable_rx_bufs && !vi->any_header_sg) { NL_SET_ERR_MSG_MOD(extack, "XDP expects header/data in single page, any_header_sg required"); return -EINVAL; } if (prog && !prog->aux->xdp_has_frags && dev->mtu > max_sz) { NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP without frags"); netdev_warn(dev, "single-buffer XDP requires MTU less than %u\n", max_sz); return -EINVAL; } curr_qp = vi->curr_queue_pairs - vi->xdp_queue_pairs; if (prog) xdp_qp = nr_cpu_ids; /* XDP requires extra queues for XDP_TX */ if (curr_qp + xdp_qp > vi->max_queue_pairs) { netdev_warn_once(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n", curr_qp + xdp_qp, vi->max_queue_pairs); xdp_qp = 0; } old_prog = rtnl_dereference(vi->rq[0].xdp_prog); if (!prog && !old_prog) return 0; if (prog) bpf_prog_add(prog, vi->max_queue_pairs - 1); /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) { napi_disable(&vi->rq[i].napi); virtnet_napi_tx_disable(&vi->sq[i].napi); } } if (!prog) { for (i = 0; i < vi->max_queue_pairs; i++) { rcu_assign_pointer(vi->rq[i].xdp_prog, prog); if (i == 0) virtnet_restore_guest_offloads(vi); } synchronize_net(); } err = virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; if (prog) { vi->xdp_enabled = true; for (i = 0; i < vi->max_queue_pairs; i++) { rcu_assign_pointer(vi->rq[i].xdp_prog, prog); if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); } if (!old_prog) xdp_features_set_redirect_target(dev, true); } else { xdp_features_clear_redirect_target(dev); vi->xdp_enabled = false; } for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); if (netif_running(dev)) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); } } return 0; err: if (!prog) { virtnet_clear_guest_offloads(vi); for (i = 0; i < vi->max_queue_pairs; i++) rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); } if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); } } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); return err; } static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return virtnet_xdp_set(dev, xdp->prog, xdp->extack); case XDP_SETUP_XSK_POOL: return virtnet_xsk_pool_setup(dev, xdp); default: return -EINVAL; } } static int virtnet_get_phys_port_name(struct net_device *dev, char *buf, size_t len) { struct virtnet_info *vi = netdev_priv(dev); int ret; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY)) return -EOPNOTSUPP; ret = snprintf(buf, len, "sby"); if (ret >= len) return -EOPNOTSUPP; return 0; } static int virtnet_set_features(struct net_device *dev, netdev_features_t features) { struct virtnet_info *vi = netdev_priv(dev); u64 offloads; int err; if ((dev->features ^ features) & NETIF_F_GRO_HW) { if (vi->xdp_enabled) return -EBUSY; if (features & NETIF_F_GRO_HW) offloads = vi->guest_offloads_capable; else offloads = vi->guest_offloads_capable & ~GUEST_OFFLOAD_GRO_HW_MASK; err = virtnet_set_guest_offloads(vi, offloads); if (err) return err; vi->guest_offloads = offloads; } if ((dev->features ^ features) & NETIF_F_RXHASH) { if (features & NETIF_F_RXHASH) vi->rss.hash_types = vi->rss_hash_types_saved; else vi->rss.hash_types = VIRTIO_NET_HASH_REPORT_NONE; if (!virtnet_commit_rss_command(vi)) return -EINVAL; } return 0; } static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct virtnet_info *priv = netdev_priv(dev); struct send_queue *sq = &priv->sq[txqueue]; struct netdev_queue *txq = netdev_get_tx_queue(dev, txqueue); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.tx_timeouts); u64_stats_update_end(&sq->stats.syncp); netdev_err(dev, "TX timeout on queue: %u, sq: %s, vq: 0x%x, name: %s, %u usecs ago\n", txqueue, sq->name, sq->vq->index, sq->vq->name, jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start))); } static int virtnet_init_irq_moder(struct virtnet_info *vi) { u8 profile_flags = 0, coal_flags = 0; int ret, i; profile_flags |= DIM_PROFILE_RX; coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS; ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags, DIM_CQ_PERIOD_MODE_START_FROM_EQE, 0, virtnet_rx_dim_work, NULL); if (ret) return ret; for (i = 0; i < vi->max_queue_pairs; i++) net_dim_setting(vi->dev, &vi->rq[i].dim, false); return 0; } static void virtnet_free_irq_moder(struct virtnet_info *vi) { if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return; rtnl_lock(); net_dim_free_irq_moder(vi->dev); rtnl_unlock(); } static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, .ndo_start_xmit = start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = virtnet_set_mac_address, .ndo_set_rx_mode = virtnet_set_rx_mode, .ndo_get_stats64 = virtnet_stats, .ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid, .ndo_bpf = virtnet_xdp, .ndo_xdp_xmit = virtnet_xdp_xmit, .ndo_xsk_wakeup = virtnet_xsk_wakeup, .ndo_features_check = passthru_features_check, .ndo_get_phys_port_name = virtnet_get_phys_port_name, .ndo_set_features = virtnet_set_features, .ndo_tx_timeout = virtnet_tx_timeout, }; static void virtnet_config_changed_work(struct work_struct *work) { struct virtnet_info *vi = container_of(work, struct virtnet_info, config_work); u16 v; if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS, struct virtio_net_config, status, &v) < 0) return; if (v & VIRTIO_NET_S_ANNOUNCE) { netdev_notify_peers(vi->dev); virtnet_ack_link_announce(vi); } /* Ignore unknown (future) status bits */ v &= VIRTIO_NET_S_LINK_UP; if (vi->status == v) return; vi->status = v; if (vi->status & VIRTIO_NET_S_LINK_UP) { virtnet_update_settings(vi); netif_carrier_on(vi->dev); netif_tx_wake_all_queues(vi->dev); } else { netif_carrier_off(vi->dev); netif_tx_stop_all_queues(vi->dev); } } static void virtnet_config_changed(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; schedule_work(&vi->config_work); } static void virtnet_free_queues(struct virtnet_info *vi) { int i; for (i = 0; i < vi->max_queue_pairs; i++) { __netif_napi_del(&vi->rq[i].napi); __netif_napi_del(&vi->sq[i].napi); } /* We called __netif_napi_del(), * we need to respect an RCU grace period before freeing vi->rq */ synchronize_net(); kfree(vi->rq); kfree(vi->sq); kfree(vi->ctrl); } static void _free_receive_bufs(struct virtnet_info *vi) { struct bpf_prog *old_prog; int i; for (i = 0; i < vi->max_queue_pairs; i++) { while (vi->rq[i].pages) __free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0); old_prog = rtnl_dereference(vi->rq[i].xdp_prog); RCU_INIT_POINTER(vi->rq[i].xdp_prog, NULL); if (old_prog) bpf_prog_put(old_prog); } } static void free_receive_bufs(struct virtnet_info *vi) { rtnl_lock(); _free_receive_bufs(vi); rtnl_unlock(); } static void free_receive_page_frags(struct virtnet_info *vi) { int i; for (i = 0; i < vi->max_queue_pairs; i++) if (vi->rq[i].alloc_frag.page) { if (vi->rq[i].last_dma) virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0); put_page(vi->rq[i].alloc_frag.page); } } static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) { struct virtnet_info *vi = vq->vdev->priv; struct send_queue *sq; int i = vq2txq(vq); sq = &vi->sq[i]; switch (virtnet_xmit_ptr_unpack(&buf)) { case VIRTNET_XMIT_TYPE_SKB: case VIRTNET_XMIT_TYPE_SKB_ORPHAN: dev_kfree_skb(buf); break; case VIRTNET_XMIT_TYPE_XDP: xdp_return_frame(buf); break; case VIRTNET_XMIT_TYPE_XSK: xsk_tx_completed(sq->xsk_pool, 1); break; } } static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; int i = vq2txq(vq); netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); } static void free_unused_bufs(struct virtnet_info *vi) { void *buf; int i; for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_sq_free_unused_buf(vq, buf); cond_resched(); } for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_rq_unmap_free_buf(vq, buf); cond_resched(); } } static void virtnet_del_vqs(struct virtnet_info *vi) { struct virtio_device *vdev = vi->vdev; virtnet_clean_affinity(vi); vdev->config->del_vqs(vdev); virtnet_free_queues(vi); } /* How large should a single buffer be so a queue full of these can fit at * least one full packet? * Logic below assumes the mergeable buffer header is used. */ static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq) { const unsigned int hdr_len = vi->hdr_len; unsigned int rq_size = virtqueue_get_vring_size(vq); unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu; unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len; unsigned int min_buf_len = DIV_ROUND_UP(buf_len, rq_size); return max(max(min_buf_len, hdr_len) - hdr_len, (unsigned int)GOOD_PACKET_LEN); } static int virtnet_find_vqs(struct virtnet_info *vi) { struct virtqueue_info *vqs_info; struct virtqueue **vqs; int ret = -ENOMEM; int total_vqs; bool *ctx; u16 i; /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by * possible control vq. */ total_vqs = vi->max_queue_pairs * 2 + virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ); /* Allocate space for find_vqs parameters */ vqs = kcalloc(total_vqs, sizeof(*vqs), GFP_KERNEL); if (!vqs) goto err_vq; vqs_info = kcalloc(total_vqs, sizeof(*vqs_info), GFP_KERNEL); if (!vqs_info) goto err_vqs_info; if (!vi->big_packets || vi->mergeable_rx_bufs) { ctx = kcalloc(total_vqs, sizeof(*ctx), GFP_KERNEL); if (!ctx) goto err_ctx; } else { ctx = NULL; } /* Parameters for control virtqueue, if any */ if (vi->has_cvq) { vqs_info[total_vqs - 1].name = "control"; } /* Allocate/initialize parameters for send/receive virtqueues */ for (i = 0; i < vi->max_queue_pairs; i++) { vqs_info[rxq2vq(i)].callback = skb_recv_done; vqs_info[txq2vq(i)].callback = skb_xmit_done; sprintf(vi->rq[i].name, "input.%u", i); sprintf(vi->sq[i].name, "output.%u", i); vqs_info[rxq2vq(i)].name = vi->rq[i].name; vqs_info[txq2vq(i)].name = vi->sq[i].name; if (ctx) vqs_info[rxq2vq(i)].ctx = true; } ret = virtio_find_vqs(vi->vdev, total_vqs, vqs, vqs_info, NULL); if (ret) goto err_find; if (vi->has_cvq) { vi->cvq = vqs[total_vqs - 1]; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN)) vi->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } for (i = 0; i < vi->max_queue_pairs; i++) { vi->rq[i].vq = vqs[rxq2vq(i)]; vi->rq[i].min_buf_len = mergeable_min_buf_len(vi, vi->rq[i].vq); vi->sq[i].vq = vqs[txq2vq(i)]; } /* run here: ret == 0. */ err_find: kfree(ctx); err_ctx: kfree(vqs_info); err_vqs_info: kfree(vqs); err_vq: return ret; } static int virtnet_alloc_queues(struct virtnet_info *vi) { int i; if (vi->has_cvq) { vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL); if (!vi->ctrl) goto err_ctrl; } else { vi->ctrl = NULL; } vi->sq = kcalloc(vi->max_queue_pairs, sizeof(*vi->sq), GFP_KERNEL); if (!vi->sq) goto err_sq; vi->rq = kcalloc(vi->max_queue_pairs, sizeof(*vi->rq), GFP_KERNEL); if (!vi->rq) goto err_rq; INIT_DELAYED_WORK(&vi->refill, refill_work); for (i = 0; i < vi->max_queue_pairs; i++) { vi->rq[i].pages = NULL; netif_napi_add_weight(vi->dev, &vi->rq[i].napi, virtnet_poll, napi_weight); netif_napi_add_tx_weight(vi->dev, &vi->sq[i].napi, virtnet_poll_tx, napi_tx ? napi_weight : 0); sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg)); ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len); sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg)); u64_stats_init(&vi->rq[i].stats.syncp); u64_stats_init(&vi->sq[i].stats.syncp); mutex_init(&vi->rq[i].dim_lock); } return 0; err_rq: kfree(vi->sq); err_sq: kfree(vi->ctrl); err_ctrl: return -ENOMEM; } static int init_vqs(struct virtnet_info *vi) { int ret; /* Allocate send & receive queues */ ret = virtnet_alloc_queues(vi); if (ret) goto err; ret = virtnet_find_vqs(vi); if (ret) goto err_free; cpus_read_lock(); virtnet_set_affinity(vi); cpus_read_unlock(); return 0; err_free: virtnet_free_queues(vi); err: return ret; } #ifdef CONFIG_SYSFS static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue, char *buf) { struct virtnet_info *vi = netdev_priv(queue->dev); unsigned int queue_index = get_netdev_rx_queue_index(queue); unsigned int headroom = virtnet_get_headroom(vi); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; struct ewma_pkt_len *avg; BUG_ON(queue_index >= vi->max_queue_pairs); avg = &vi->rq[queue_index].mrg_avg_pkt_len; return sprintf(buf, "%u\n", get_mergeable_buf_len(&vi->rq[queue_index], avg, SKB_DATA_ALIGN(headroom + tailroom))); } static struct rx_queue_attribute mergeable_rx_buffer_size_attribute = __ATTR_RO(mergeable_rx_buffer_size); static struct attribute *virtio_net_mrg_rx_attrs[] = { &mergeable_rx_buffer_size_attribute.attr, NULL }; static const struct attribute_group virtio_net_mrg_rx_group = { .name = "virtio_net", .attrs = virtio_net_mrg_rx_attrs }; #endif static bool virtnet_fail_on_feature(struct virtio_device *vdev, unsigned int fbit, const char *fname, const char *dname) { if (!virtio_has_feature(vdev, fbit)) return false; dev_err(&vdev->dev, "device advertises feature %s but not %s", fname, dname); return true; } #define VIRTNET_FAIL_ON(vdev, fbit, dbit) \ virtnet_fail_on_feature(vdev, fbit, #fbit, dbit) static bool virtnet_validate_features(struct virtio_device *vdev) { if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ) && (VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_RX, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_VLAN, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_MQ, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_RSS, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_VQ_NOTF_COAL, "VIRTIO_NET_F_CTRL_VQ"))) { return false; } return true; } #define MIN_MTU ETH_MIN_MTU #define MAX_MTU ETH_MAX_MTU static int virtnet_validate(struct virtio_device *vdev) { if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", __func__); return -EINVAL; } if (!virtnet_validate_features(vdev)) return -EINVAL; if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) { int mtu = virtio_cread16(vdev, offsetof(struct virtio_net_config, mtu)); if (mtu < MIN_MTU) __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU); } if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY) && !virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { dev_warn(&vdev->dev, "device advertises feature VIRTIO_NET_F_STANDBY but not VIRTIO_NET_F_MAC, disabling standby"); __virtio_clear_bit(vdev, VIRTIO_NET_F_STANDBY); } return 0; } static bool virtnet_check_guest_gso(const struct virtnet_info *vi) { return virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) || (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO4) && virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO6)); } static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu) { bool guest_gso = virtnet_check_guest_gso(vi); /* If device can receive ANY guest GSO packets, regardless of mtu, * allocate packets of maximum size, otherwise limit it to only * mtu size worth only. */ if (mtu > ETH_DATA_LEN || guest_gso) { vi->big_packets = true; vi->big_packets_num_skbfrags = guest_gso ? MAX_SKB_FRAGS : DIV_ROUND_UP(mtu, PAGE_SIZE); } } #define VIRTIO_NET_HASH_REPORT_MAX_TABLE 10 static enum xdp_rss_hash_type virtnet_xdp_rss_type[VIRTIO_NET_HASH_REPORT_MAX_TABLE] = { [VIRTIO_NET_HASH_REPORT_NONE] = XDP_RSS_TYPE_NONE, [VIRTIO_NET_HASH_REPORT_IPv4] = XDP_RSS_TYPE_L3_IPV4, [VIRTIO_NET_HASH_REPORT_TCPv4] = XDP_RSS_TYPE_L4_IPV4_TCP, [VIRTIO_NET_HASH_REPORT_UDPv4] = XDP_RSS_TYPE_L4_IPV4_UDP, [VIRTIO_NET_HASH_REPORT_IPv6] = XDP_RSS_TYPE_L3_IPV6, [VIRTIO_NET_HASH_REPORT_TCPv6] = XDP_RSS_TYPE_L4_IPV6_TCP, [VIRTIO_NET_HASH_REPORT_UDPv6] = XDP_RSS_TYPE_L4_IPV6_UDP, [VIRTIO_NET_HASH_REPORT_IPv6_EX] = XDP_RSS_TYPE_L3_IPV6_EX, [VIRTIO_NET_HASH_REPORT_TCPv6_EX] = XDP_RSS_TYPE_L4_IPV6_TCP_EX, [VIRTIO_NET_HASH_REPORT_UDPv6_EX] = XDP_RSS_TYPE_L4_IPV6_UDP_EX }; static int virtnet_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { const struct xdp_buff *xdp = (void *)_ctx; struct virtio_net_hdr_v1_hash *hdr_hash; struct virtnet_info *vi; u16 hash_report; if (!(xdp->rxq->dev->features & NETIF_F_RXHASH)) return -ENODATA; vi = netdev_priv(xdp->rxq->dev); hdr_hash = (struct virtio_net_hdr_v1_hash *)(xdp->data - vi->hdr_len); hash_report = __le16_to_cpu(hdr_hash->hash_report); if (hash_report >= VIRTIO_NET_HASH_REPORT_MAX_TABLE) hash_report = VIRTIO_NET_HASH_REPORT_NONE; *rss_type = virtnet_xdp_rss_type[hash_report]; *hash = __le32_to_cpu(hdr_hash->hash_value); return 0; } static const struct xdp_metadata_ops virtnet_xdp_metadata_ops = { .xmo_rx_hash = virtnet_xdp_rx_hash, }; static int virtnet_probe(struct virtio_device *vdev) { int i, err = -ENOMEM; struct net_device *dev; struct virtnet_info *vi; u16 max_queue_pairs; int mtu = 0; /* Find if host supports multiqueue/rss virtio_net device */ max_queue_pairs = 1; if (virtio_has_feature(vdev, VIRTIO_NET_F_MQ) || virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) max_queue_pairs = virtio_cread16(vdev, offsetof(struct virtio_net_config, max_virtqueue_pairs)); /* We need at least 2 queue's */ if (max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) max_queue_pairs = 1; /* Allocate ourselves a network device with room for our info */ dev = alloc_etherdev_mq(sizeof(struct virtnet_info), max_queue_pairs); if (!dev) return -ENOMEM; /* Set up network device as normal. */ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE | IFF_TX_SKB_NO_LINEAR; dev->netdev_ops = &virtnet_netdev; dev->stat_ops = &virtnet_stat_ops; dev->features = NETIF_F_HIGHDMA; dev->ethtool_ops = &virtnet_ethtool_ops; SET_NETDEV_DEV(dev, &vdev->dev); /* Do we support "hardware" checksums? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) { /* This opens up the world of extra features. */ dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (csum) dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6; } /* Individual feature bits: what can host handle? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO4)) dev->hw_features |= NETIF_F_TSO; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO6)) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_USO)) dev->hw_features |= NETIF_F_GSO_UDP_L4; dev->features |= NETIF_F_GSO_ROBUST; if (gso) dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } /* 1. With VIRTIO_NET_F_GUEST_CSUM negotiation, the driver doesn't * need to calculate checksums for partially checksummed packets, * as they're considered valid by the upper layer. * 2. Without VIRTIO_NET_F_GUEST_CSUM negotiation, the driver only * receives fully checksummed packets. The device may assist in * validating these packets' checksums, so the driver won't have to. */ dev->features |= NETIF_F_RXCSUM; if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)) dev->features |= NETIF_F_GRO_HW; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) dev->hw_features |= NETIF_F_GRO_HW; dev->vlan_features = dev->features; dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY; /* MTU range: 68 - 65535 */ dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU; /* Configuration may specify what MAC to use. Otherwise random. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { u8 addr[ETH_ALEN]; virtio_cread_bytes(vdev, offsetof(struct virtio_net_config, mac), addr, ETH_ALEN); eth_hw_addr_set(dev, addr); } else { eth_hw_addr_random(dev); dev_info(&vdev->dev, "Assigned random MAC address %pM\n", dev->dev_addr); } /* Set up our device-specific information */ vi = netdev_priv(dev); vi->dev = dev; vi->vdev = vdev; vdev->priv = vi; INIT_WORK(&vi->config_work, virtnet_config_changed_work); INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work); spin_lock_init(&vi->refill_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { vi->mergeable_rx_bufs = true; dev->xdp_features |= NETDEV_XDP_ACT_RX_SG; } if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) vi->has_rss_hash_report = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) { vi->has_rss = true; vi->rss_indir_table_size = virtio_cread16(vdev, offsetof(struct virtio_net_config, rss_max_indirection_table_length)); } err = rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size); if (err) goto free; if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_key_size = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) { dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n", vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE); err = -EINVAL; goto free; } vi->rss_hash_types_supported = virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types)); vi->rss_hash_types_supported &= ~(VIRTIO_NET_RSS_HASH_TYPE_IP_EX | VIRTIO_NET_RSS_HASH_TYPE_TCP_EX | VIRTIO_NET_RSS_HASH_TYPE_UDP_EX); dev->hw_features |= NETIF_F_RXHASH; dev->xdp_metadata_ops = &virtnet_xdp_metadata_ops; } if (vi->has_rss_hash_report) vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash); else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) || virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); else vi->hdr_len = sizeof(struct virtio_net_hdr); if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) || virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) vi->any_header_sg = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) vi->has_cvq = true; mutex_init(&vi->cvq_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) { mtu = virtio_cread16(vdev, offsetof(struct virtio_net_config, mtu)); if (mtu < dev->min_mtu) { /* Should never trigger: MTU was previously validated * in virtnet_validate. */ dev_err(&vdev->dev, "device MTU appears to have changed it is now %d < %d", mtu, dev->min_mtu); err = -EINVAL; goto free; } dev->mtu = mtu; dev->max_mtu = mtu; } virtnet_set_big_packets(vi, mtu); if (vi->any_header_sg) dev->needed_headroom = vi->hdr_len; /* Enable multiqueue by default */ if (num_online_cpus() >= max_queue_pairs) vi->curr_queue_pairs = max_queue_pairs; else vi->curr_queue_pairs = num_online_cpus(); vi->max_queue_pairs = max_queue_pairs; /* Allocate/initialize the rx/tx queues, and invoke find_vqs */ err = init_vqs(vi); if (err) goto free; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { vi->intr_coal_rx.max_usecs = 0; vi->intr_coal_tx.max_usecs = 0; vi->intr_coal_rx.max_packets = 0; /* Keep the default values of the coalescing parameters * aligned with the default napi_tx state. */ if (vi->sq[0].napi.weight) vi->intr_coal_tx.max_packets = 1; else vi->intr_coal_tx.max_packets = 0; } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) { /* The reason is the same as VIRTIO_NET_F_NOTF_COAL. */ for (i = 0; i < vi->max_queue_pairs; i++) if (vi->sq[i].napi.weight) vi->sq[i].intr_coal.max_packets = 1; err = virtnet_init_irq_moder(vi); if (err) goto free; } #ifdef CONFIG_SYSFS if (vi->mergeable_rx_bufs) dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group; #endif netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs); netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs); virtnet_init_settings(dev); if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) { vi->failover = net_failover_create(vi->dev); if (IS_ERR(vi->failover)) { err = PTR_ERR(vi->failover); goto free_vqs; } } if (vi->has_rss || vi->has_rss_hash_report) virtnet_init_default_rss(vi); enable_rx_mode_work(vi); /* serialize netdev register + virtio_device_ready() with ndo_open() */ rtnl_lock(); err = register_netdevice(dev); if (err) { pr_debug("virtio_net: registering device failed\n"); rtnl_unlock(); goto free_failover; } /* Disable config change notification until ndo_open. */ virtio_config_driver_disable(vi->vdev); virtio_device_ready(vdev); if (vi->has_rss || vi->has_rss_hash_report) { if (!virtnet_commit_rss_command(vi)) { dev_warn(&vdev->dev, "RSS disabled because committing failed.\n"); dev->hw_features &= ~NETIF_F_RXHASH; vi->has_rss_hash_report = false; vi->has_rss = false; } } virtnet_set_queues(vi, vi->curr_queue_pairs); /* a random MAC address has been assigned, notify the device. * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there * because many devices work fine without getting MAC explicitly */ if (!virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { struct scatterlist sg; sg_init_one(&sg, dev->dev_addr, dev->addr_len); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { pr_debug("virtio_net: setting MAC address failed\n"); rtnl_unlock(); err = -EINVAL; goto free_unregister_netdev; } } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_DEVICE_STATS)) { struct virtio_net_stats_capabilities *stats_cap __free(kfree) = NULL; struct scatterlist sg; __le64 v; stats_cap = kzalloc(sizeof(*stats_cap), GFP_KERNEL); if (!stats_cap) { rtnl_unlock(); err = -ENOMEM; goto free_unregister_netdev; } sg_init_one(&sg, stats_cap, sizeof(*stats_cap)); if (!virtnet_send_command_reply(vi, VIRTIO_NET_CTRL_STATS, VIRTIO_NET_CTRL_STATS_QUERY, NULL, &sg)) { pr_debug("virtio_net: fail to get stats capability\n"); rtnl_unlock(); err = -EINVAL; goto free_unregister_netdev; } v = stats_cap->supported_stats_types[0]; vi->device_stats_cap = le64_to_cpu(v); } /* Assume link up if device can't report link status, otherwise get link status from config. */ netif_carrier_off(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { virtnet_config_changed_work(&vi->config_work); } else { vi->status = VIRTIO_NET_S_LINK_UP; virtnet_update_settings(vi); netif_carrier_on(dev); } for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) if (virtio_has_feature(vi->vdev, guest_offloads[i])) set_bit(guest_offloads[i], &vi->guest_offloads); vi->guest_offloads_capable = vi->guest_offloads; rtnl_unlock(); err = virtnet_cpu_notif_add(vi); if (err) { pr_debug("virtio_net: registering cpu notifier failed\n"); goto free_unregister_netdev; } pr_debug("virtnet: registered device %s with %d RX and TX vq's\n", dev->name, max_queue_pairs); return 0; free_unregister_netdev: unregister_netdev(dev); free_failover: net_failover_destroy(vi->failover); free_vqs: virtio_reset_device(vdev); cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); free: free_netdev(dev); return err; } static void remove_vq_common(struct virtnet_info *vi) { int i; virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); /* * Rule of thumb is netdev_tx_reset_queue() should follow any * skb freeing not followed by netdev_tx_completed_queue() */ for (i = 0; i < vi->max_queue_pairs; i++) netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); free_receive_bufs(vi); free_receive_page_frags(vi); virtnet_del_vqs(vi); } static void virtnet_remove(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; virtnet_cpu_notif_remove(vi); /* Make sure no work handler is accessing the device. */ flush_work(&vi->config_work); disable_rx_mode_work(vi); flush_work(&vi->rx_mode_work); virtnet_free_irq_moder(vi); unregister_netdev(vi->dev); net_failover_destroy(vi->failover); remove_vq_common(vi); rss_indirection_table_free(&vi->rss); free_netdev(vi->dev); } static __maybe_unused int virtnet_freeze(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; virtnet_cpu_notif_remove(vi); virtnet_freeze_down(vdev); remove_vq_common(vi); return 0; } static __maybe_unused int virtnet_restore(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; int err; err = virtnet_restore_up(vdev); if (err) return err; virtnet_set_queues(vi, vi->curr_queue_pairs); err = virtnet_cpu_notif_add(vi); if (err) { virtnet_freeze_down(vdev); remove_vq_common(vi); return err; } return 0; } static struct virtio_device_id id_table[] = { { VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID }, { 0 }, }; #define VIRTNET_FEATURES \ VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, \ VIRTIO_NET_F_MAC, \ VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, \ VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, \ VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, \ VIRTIO_NET_F_HOST_USO, VIRTIO_NET_F_GUEST_USO4, VIRTIO_NET_F_GUEST_USO6, \ VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, \ VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \ VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \ VIRTIO_NET_F_CTRL_MAC_ADDR, \ VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \ VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \ VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL, \ VIRTIO_NET_F_VQ_NOTF_COAL, \ VIRTIO_NET_F_GUEST_HDRLEN, VIRTIO_NET_F_DEVICE_STATS static unsigned int features[] = { VIRTNET_FEATURES, }; static unsigned int features_legacy[] = { VIRTNET_FEATURES, VIRTIO_NET_F_GSO, VIRTIO_F_ANY_LAYOUT, }; static struct virtio_driver virtio_net_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), .feature_table_legacy = features_legacy, .feature_table_size_legacy = ARRAY_SIZE(features_legacy), .driver.name = KBUILD_MODNAME, .id_table = id_table, .validate = virtnet_validate, .probe = virtnet_probe, .remove = virtnet_remove, .config_changed = virtnet_config_changed, #ifdef CONFIG_PM_SLEEP .freeze = virtnet_freeze, .restore = virtnet_restore, #endif }; static __init int virtio_net_driver_init(void) { int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online", virtnet_cpu_online, virtnet_cpu_down_prep); if (ret < 0) goto out; virtionet_online = ret; ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead", NULL, virtnet_cpu_dead); if (ret) goto err_dead; ret = register_virtio_driver(&virtio_net_driver); if (ret) goto err_virtio; return 0; err_virtio: cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD); err_dead: cpuhp_remove_multi_state(virtionet_online); out: return ret; } module_init(virtio_net_driver_init); static __exit void virtio_net_driver_exit(void) { unregister_virtio_driver(&virtio_net_driver); cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD); cpuhp_remove_multi_state(virtionet_online); } module_exit(virtio_net_driver_exit); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio network driver"); MODULE_LICENSE("GPL"); |
| 3 78 78 1 6580 662 311 626 27 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash func */ int (*cmp)(const void *key1, const void *key2); /* comparison func */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; u64 chain2_len_sum; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig, int (*copy)(struct hashtab_node *new, const struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); #ifdef CONFIG_SECURITY_SELINUX_DEBUG /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #else static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info) { return; } #endif #endif /* _SS_HASHTAB_H */ |
| 14 14 18 14 11 14 18 11 16 11 2 11 11 11 11 1364 288 856 517 1 1 24 2 2 1 18 17 1 19 3 2 28 26 3 1550 4 1546 4 1 1 2 1564 1565 761 4 1541 13 2 1550 4 1 11 1533 4 4 1527 12 12 1554 1554 5 1 1544 | 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 | /* * memfd_create system call and file sealing support * * Code was originally included in shmem.c, and broken out to facilitate * use by hugetlbfs as well as tmpfs. * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/khugepaged.h> #include <linux/syscalls.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/memfd.h> #include <linux/pid_namespace.h> #include <uapi/linux/memfd.h> /* * We need a tag: a new tag would expand every xa_node by 8 bytes, * so reuse a tag which we firmly believe is never set or cleared on tmpfs * or hugetlbfs because they are memory only filesystems. */ #define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE #define LAST_SCAN 4 /* about 150ms max */ static bool memfd_folio_has_extra_refs(struct folio *folio) { return folio_ref_count(folio) - folio_mapcount(folio) != folio_nr_pages(folio); } static void memfd_tag_pins(struct xa_state *xas) { struct folio *folio; int latency = 0; lru_add_drain(); xas_lock_irq(xas); xas_for_each(xas, folio, ULONG_MAX) { if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio)) xas_set_mark(xas, MEMFD_TAG_PINNED); if (++latency < XA_CHECK_SCHED) continue; latency = 0; xas_pause(xas); xas_unlock_irq(xas); cond_resched(); xas_lock_irq(xas); } xas_unlock_irq(xas); } /* * This is a helper function used by memfd_pin_user_pages() in GUP (gup.c). * It is mainly called to allocate a folio in a memfd when the caller * (memfd_pin_folios()) cannot find a folio in the page cache at a given * index in the mapping. */ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { #ifdef CONFIG_HUGETLB_PAGE struct folio *folio; gfp_t gfp_mask; int err; if (is_file_hugepages(memfd)) { /* * The folio would most likely be accessed by a DMA driver, * therefore, we have zone memory constraints where we can * alloc from. Also, the folio will be pinned for an indefinite * amount of time, so it is not expected to be migrated away. */ struct hstate *h = hstate_file(memfd); gfp_mask = htlb_alloc_mask(h); gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE); idx >>= huge_page_order(h); folio = alloc_hugetlb_folio_reserve(h, numa_node_id(), NULL, gfp_mask); if (folio) { err = hugetlb_add_to_page_cache(folio, memfd->f_mapping, idx); if (err) { folio_put(folio); return ERR_PTR(err); } folio_unlock(folio); return folio; } return ERR_PTR(-ENOMEM); } #endif return shmem_read_folio(memfd->f_mapping, idx); } /* * Setting SEAL_WRITE requires us to verify there's no pending writer. However, * via get_user_pages(), drivers might have some pending I/O without any active * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all folios * and see whether it has an elevated ref-count. If so, we tag them and wait for * them to be dropped. * The caller must guarantee that no new user will acquire writable references * to those folios to avoid races. */ static int memfd_wait_for_pins(struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; int error, scan; memfd_tag_pins(&xas); error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { int latency = 0; if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; if (!scan) lru_add_drain_all(); else if (schedule_timeout_killable((HZ << scan) / 200)) scan = LAST_SCAN; xas_set(&xas, 0); xas_lock_irq(&xas); xas_for_each_marked(&xas, folio, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true; if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still * found folios pinned. */ if (scan == LAST_SCAN) error = -EBUSY; else clear = false; } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED); if (++latency < XA_CHECK_SCHED) continue; latency = 0; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } return error; } static unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; #ifdef CONFIG_HUGETLBFS if (is_file_hugepages(file)) return &HUGETLBFS_I(file_inode(file))->seals; #endif return NULL; } #define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_EXEC | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ F_SEAL_WRITE | \ F_SEAL_FUTURE_WRITE) static int memfd_add_seals(struct file *file, unsigned int seals) { struct inode *inode = file_inode(file); unsigned int *file_seals; int error; /* * SEALING * Sealing allows multiple parties to share a tmpfs or hugetlbfs file * but restrict access to a specific subset of file operations. Seals * can only be added, but never removed. This way, mutually untrusted * parties can share common memory regions with a well-defined policy. * A malicious peer can thus never perform unwanted operations on a * shared object. * * Seals are only supported on special tmpfs or hugetlbfs files and * always affect the whole underlying inode. Once a seal is set, it * may prevent some kinds of access to the file. Currently, the * following seals are defined: * SEAL_SEAL: Prevent further seals from being set on this file * SEAL_SHRINK: Prevent the file from shrinking * SEAL_GROW: Prevent the file from growing * SEAL_WRITE: Prevent write access to the file * SEAL_EXEC: Prevent modification of the exec bits in the file mode * * As we don't require any trust relationship between two parties, we * must prevent seals from being removed. Therefore, sealing a file * only adds a given set of seals to the file, it never touches * existing seals. Furthermore, the "setting seals"-operation can be * sealed itself, which basically prevents any further seal from being * added. * * Semantics of sealing are only defined on volatile files. Only * anonymous tmpfs and hugetlbfs files support sealing. More * importantly, seals are never written to disk. Therefore, there's * no plan to support it on other file types. */ if (!(file->f_mode & FMODE_WRITE)) return -EPERM; if (seals & ~(unsigned int)F_ALL_SEALS) return -EINVAL; inode_lock(inode); file_seals = memfd_file_seals_ptr(file); if (!file_seals) { error = -EINVAL; goto unlock; } if (*file_seals & F_SEAL_SEAL) { error = -EPERM; goto unlock; } if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) { error = mapping_deny_writable(file->f_mapping); if (error) goto unlock; error = memfd_wait_for_pins(file->f_mapping); if (error) { mapping_allow_writable(file->f_mapping); goto unlock; } } /* * SEAL_EXEC implys SEAL_WRITE, making W^X from the start. */ if (seals & F_SEAL_EXEC && inode->i_mode & 0111) seals |= F_SEAL_SHRINK|F_SEAL_GROW|F_SEAL_WRITE|F_SEAL_FUTURE_WRITE; *file_seals |= seals; error = 0; unlock: inode_unlock(inode); return error; } static int memfd_get_seals(struct file *file) { unsigned int *seals = memfd_file_seals_ptr(file); return seals ? *seals : -EINVAL; } long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { long error; switch (cmd) { case F_ADD_SEALS: error = memfd_add_seals(file, arg); break; case F_GET_SEALS: error = memfd_get_seals(file); break; default: error = -EINVAL; break; } return error; } #define MFD_NAME_PREFIX "memfd:" #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) #define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC) static int check_sysctl_memfd_noexec(unsigned int *flags) { #ifdef CONFIG_SYSCTL struct pid_namespace *ns = task_active_pid_ns(current); int sysctl = pidns_memfd_noexec_scope(ns); if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { if (sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL) *flags |= MFD_NOEXEC_SEAL; else *flags |= MFD_EXEC; } if (!(*flags & MFD_NOEXEC_SEAL) && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) { pr_err_ratelimited( "%s[%d]: memfd_create() requires MFD_NOEXEC_SEAL with vm.memfd_noexec=%d\n", current->comm, task_pid_nr(current), sysctl); return -EACCES; } #endif return 0; } static inline bool is_write_sealed(unsigned int seals) { return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); } static int check_write_seal(unsigned long *vm_flags_ptr) { unsigned long vm_flags = *vm_flags_ptr; unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE); /* If a private matting then writability is irrelevant. */ if (!(mask & VM_SHARED)) return 0; /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * write seals are active. */ if (mask & VM_WRITE) return -EPERM; /* * This is a read-only mapping, disallow mprotect() from making a * write-sealed mapping writable in future. */ *vm_flags_ptr &= ~VM_MAYWRITE; return 0; } int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr) { int err = 0; unsigned int *seals_ptr = memfd_file_seals_ptr(file); unsigned int seals = seals_ptr ? *seals_ptr : 0; if (is_write_sealed(seals)) err = check_write_seal(vm_flags_ptr); return err; } static int sanitize_flags(unsigned int *flags_ptr) { unsigned int flags = *flags_ptr; if (!(flags & MFD_HUGETLB)) { if (flags & ~(unsigned int)MFD_ALL_FLAGS) return -EINVAL; } else { /* Allow huge page size encoding in flags. */ if (flags & ~(unsigned int)(MFD_ALL_FLAGS | (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) return -EINVAL; } /* Invalid if both EXEC and NOEXEC_SEAL are set.*/ if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) return -EINVAL; return check_sysctl_memfd_noexec(flags_ptr); } static char *alloc_name(const char __user *uname) { int error; char *name; long len; name = kmalloc(NAME_MAX + 1, GFP_KERNEL); if (!name) return ERR_PTR(-ENOMEM); strcpy(name, MFD_NAME_PREFIX); /* returned length does not include terminating zero */ len = strncpy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, MFD_NAME_MAX_LEN + 1); if (len < 0) { error = -EFAULT; goto err_name; } else if (len > MFD_NAME_MAX_LEN) { error = -EINVAL; goto err_name; } return name; err_name: kfree(name); return ERR_PTR(error); } static struct file *alloc_file(const char *name, unsigned int flags) { unsigned int *file_seals; struct file *file; if (flags & MFD_HUGETLB) { file = hugetlb_file_setup(name, 0, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); } else { file = shmem_file_setup(name, 0, VM_NORESERVE); } if (IS_ERR(file)) return file; file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; if (flags & MFD_NOEXEC_SEAL) { struct inode *inode = file_inode(file); inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); if (file_seals) { *file_seals &= ~F_SEAL_SEAL; *file_seals |= F_SEAL_EXEC; } } else if (flags & MFD_ALLOW_SEALING) { /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); if (file_seals) *file_seals &= ~F_SEAL_SEAL; } return file; } SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags) { struct file *file; int fd, error; char *name; error = sanitize_flags(&flags); if (error < 0) return error; name = alloc_name(uname); if (IS_ERR(name)) return PTR_ERR(name); fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); if (fd < 0) { error = fd; goto err_name; } file = alloc_file(name, flags); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_fd; } fd_install(fd, file); kfree(name); return fd; err_fd: put_unused_fd(fd); err_name: kfree(name); return error; } |
| 64 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * File: pep.h * * Phonet Pipe End Point sockets definitions * * Copyright (C) 2008 Nokia Corporation. */ #ifndef NET_PHONET_PEP_H #define NET_PHONET_PEP_H #include <linux/skbuff.h> #include <net/phonet/phonet.h> struct pep_sock { struct pn_sock pn_sk; /* XXX: union-ify listening vs connected stuff ? */ /* Listening socket stuff: */ struct hlist_head hlist; /* Connected socket stuff: */ struct sock *listener; struct sk_buff_head ctrlreq_queue; #define PNPIPE_CTRLREQ_MAX 10 atomic_t tx_credits; int ifindex; u16 peer_type; /* peer type/subtype */ u8 pipe_handle; u8 rx_credits; u8 rx_fc; /* RX flow control */ u8 tx_fc; /* TX flow control */ u8 init_enable; /* auto-enable at creation */ u8 aligned; }; static inline struct pep_sock *pep_sk(struct sock *sk) { return (struct pep_sock *)sk; } extern const struct proto_ops phonet_stream_ops; /* Pipe protocol definitions */ struct pnpipehdr { u8 utid; /* transaction ID */ u8 message_id; u8 pipe_handle; union { u8 state_after_connect; /* connect request */ u8 state_after_reset; /* reset request */ u8 error_code; /* any response */ u8 pep_type; /* status indication */ u8 data0; /* anything else */ }; u8 data[]; }; #define other_pep_type data[0] static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb) { return (struct pnpipehdr *)skb_transport_header(skb); } #define MAX_PNPIPE_HEADER (MAX_PHONET_HEADER + 4) enum { PNS_PIPE_CREATE_REQ = 0x00, PNS_PIPE_CREATE_RESP, PNS_PIPE_REMOVE_REQ, PNS_PIPE_REMOVE_RESP, PNS_PIPE_DATA = 0x20, PNS_PIPE_ALIGNED_DATA, PNS_PEP_CONNECT_REQ = 0x40, PNS_PEP_CONNECT_RESP, PNS_PEP_DISCONNECT_REQ, PNS_PEP_DISCONNECT_RESP, PNS_PEP_RESET_REQ, PNS_PEP_RESET_RESP, PNS_PEP_ENABLE_REQ, PNS_PEP_ENABLE_RESP, PNS_PEP_CTRL_REQ, PNS_PEP_CTRL_RESP, PNS_PEP_DISABLE_REQ = 0x4C, PNS_PEP_DISABLE_RESP, PNS_PEP_STATUS_IND = 0x60, PNS_PIPE_CREATED_IND, PNS_PIPE_RESET_IND = 0x63, PNS_PIPE_ENABLED_IND, PNS_PIPE_REDIRECTED_IND, PNS_PIPE_DISABLED_IND = 0x66, }; #define PN_PIPE_INVALID_HANDLE 0xff #define PN_PEP_TYPE_COMMON 0x00 /* Phonet pipe status indication */ enum { PN_PEP_IND_FLOW_CONTROL, PN_PEP_IND_ID_MCFC_GRANT_CREDITS, }; /* Phonet pipe error codes */ enum { PN_PIPE_NO_ERROR, PN_PIPE_ERR_INVALID_PARAM, PN_PIPE_ERR_INVALID_HANDLE, PN_PIPE_ERR_INVALID_CTRL_ID, PN_PIPE_ERR_NOT_ALLOWED, PN_PIPE_ERR_PEP_IN_USE, PN_PIPE_ERR_OVERLOAD, PN_PIPE_ERR_DEV_DISCONNECTED, PN_PIPE_ERR_TIMEOUT, PN_PIPE_ERR_ALL_PIPES_IN_USE, PN_PIPE_ERR_GENERAL, PN_PIPE_ERR_NOT_SUPPORTED, }; /* Phonet pipe states */ enum { PN_PIPE_DISABLE, PN_PIPE_ENABLE, }; /* Phonet pipe sub-block types */ enum { PN_PIPE_SB_CREATE_REQ_PEP_SUB_TYPE, PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE, PN_PIPE_SB_REDIRECT_REQ_PEP_SUB_TYPE, PN_PIPE_SB_NEGOTIATED_FC, PN_PIPE_SB_REQUIRED_FC_TX, PN_PIPE_SB_PREFERRED_FC_RX, PN_PIPE_SB_ALIGNED_DATA, }; /* Phonet pipe flow control models */ enum { PN_NO_FLOW_CONTROL, PN_LEGACY_FLOW_CONTROL, PN_ONE_CREDIT_FLOW_CONTROL, PN_MULTI_CREDIT_FLOW_CONTROL, PN_MAX_FLOW_CONTROL, }; #define pn_flow_safe(fc) ((fc) >> 1) /* Phonet pipe flow control states */ enum { PEP_IND_EMPTY, PEP_IND_BUSY, PEP_IND_READY, }; #endif |
| 104 74 74 59 59 59 9 1 50 47 41 6 6 80 80 80 72 16 80 80 59 50 9 9 9 9 59 61 52 4 9 9 35 22 21 6 1 1 1 12 89 89 89 47 34 34 47 47 88 89 89 81 10 71 71 71 2 2 2 53 53 53 79 79 79 79 79 74 74 61 60 51 35 59 59 61 1 5 5 1 1 1 1 1 5 5 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich */ #include "bridge_loop_avoidance.h" #include "main.h" #include <linux/atomic.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/crc16.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/sprintf.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/string_choices.h> #include <linux/workqueue.h> #include <net/arp.h> #include <net/genetlink.h> #include <net/netlink.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" #include "originator.h" #include "translation-table.h" static const u8 batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; static void batadv_bla_periodic_work(struct work_struct *work); static void batadv_bla_send_announce(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw); /** * batadv_choose_claim() - choose the right bucket for a claim. * @data: data to hash * @size: size of the hash table * * Return: the hash index of the claim */ static inline u32 batadv_choose_claim(const void *data, u32 size) { const struct batadv_bla_claim *claim = data; u32 hash = 0; hash = jhash(&claim->addr, sizeof(claim->addr), hash); hash = jhash(&claim->vid, sizeof(claim->vid), hash); return hash % size; } /** * batadv_choose_backbone_gw() - choose the right bucket for a backbone gateway. * @data: data to hash * @size: size of the hash table * * Return: the hash index of the backbone gateway */ static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { const struct batadv_bla_backbone_gw *gw; u32 hash = 0; gw = data; hash = jhash(&gw->orig, sizeof(gw->orig), hash); hash = jhash(&gw->vid, sizeof(gw->vid), hash); return hash % size; } /** * batadv_compare_backbone_gw() - compare address and vid of two backbone gws * @node: list node of the first entry to compare * @data2: pointer to the second backbone gateway * * Return: true if the backbones have the same data, false otherwise */ static bool batadv_compare_backbone_gw(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_bla_backbone_gw, hash_entry); const struct batadv_bla_backbone_gw *gw1 = data1; const struct batadv_bla_backbone_gw *gw2 = data2; if (!batadv_compare_eth(gw1->orig, gw2->orig)) return false; if (gw1->vid != gw2->vid) return false; return true; } /** * batadv_compare_claim() - compare address and vid of two claims * @node: list node of the first entry to compare * @data2: pointer to the second claims * * Return: true if the claim have the same data, 0 otherwise */ static bool batadv_compare_claim(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_bla_claim, hash_entry); const struct batadv_bla_claim *cl1 = data1; const struct batadv_bla_claim *cl2 = data2; if (!batadv_compare_eth(cl1->addr, cl2->addr)) return false; if (cl1->vid != cl2->vid) return false; return true; } /** * batadv_backbone_gw_release() - release backbone gw from lists and queue for * free after rcu grace period * @ref: kref pointer of the backbone gw */ static void batadv_backbone_gw_release(struct kref *ref) { struct batadv_bla_backbone_gw *backbone_gw; backbone_gw = container_of(ref, struct batadv_bla_backbone_gw, refcount); kfree_rcu(backbone_gw, rcu); } /** * batadv_backbone_gw_put() - decrement the backbone gw refcounter and possibly * release it * @backbone_gw: backbone gateway to be free'd */ static void batadv_backbone_gw_put(struct batadv_bla_backbone_gw *backbone_gw) { if (!backbone_gw) return; kref_put(&backbone_gw->refcount, batadv_backbone_gw_release); } /** * batadv_claim_release() - release claim from lists and queue for free after * rcu grace period * @ref: kref pointer of the claim */ static void batadv_claim_release(struct kref *ref) { struct batadv_bla_claim *claim; struct batadv_bla_backbone_gw *old_backbone_gw; claim = container_of(ref, struct batadv_bla_claim, refcount); spin_lock_bh(&claim->backbone_lock); old_backbone_gw = claim->backbone_gw; claim->backbone_gw = NULL; spin_unlock_bh(&claim->backbone_lock); spin_lock_bh(&old_backbone_gw->crc_lock); old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&old_backbone_gw->crc_lock); batadv_backbone_gw_put(old_backbone_gw); kfree_rcu(claim, rcu); } /** * batadv_claim_put() - decrement the claim refcounter and possibly release it * @claim: claim to be free'd */ static void batadv_claim_put(struct batadv_bla_claim *claim) { if (!claim) return; kref_put(&claim->refcount, batadv_claim_release); } /** * batadv_claim_hash_find() - looks for a claim in the claim hash * @bat_priv: the bat priv with all the soft interface information * @data: search data (may be local/static data) * * Return: claim if found or NULL otherwise. */ static struct batadv_bla_claim * batadv_claim_hash_find(struct batadv_priv *bat_priv, struct batadv_bla_claim *data) { struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct hlist_head *head; struct batadv_bla_claim *claim; struct batadv_bla_claim *claim_tmp = NULL; int index; if (!hash) return NULL; index = batadv_choose_claim(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { if (!batadv_compare_claim(&claim->hash_entry, data)) continue; if (!kref_get_unless_zero(&claim->refcount)) continue; claim_tmp = claim; break; } rcu_read_unlock(); return claim_tmp; } /** * batadv_backbone_hash_find() - looks for a backbone gateway in the hash * @bat_priv: the bat priv with all the soft interface information * @addr: the address of the originator * @vid: the VLAN ID * * Return: backbone gateway if found or NULL otherwise */ static struct batadv_bla_backbone_gw * batadv_backbone_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct batadv_bla_backbone_gw search_entry, *backbone_gw; struct batadv_bla_backbone_gw *backbone_gw_tmp = NULL; int index; if (!hash) return NULL; ether_addr_copy(search_entry.orig, addr); search_entry.vid = vid; index = batadv_choose_backbone_gw(&search_entry, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_backbone_gw(&backbone_gw->hash_entry, &search_entry)) continue; if (!kref_get_unless_zero(&backbone_gw->refcount)) continue; backbone_gw_tmp = backbone_gw; break; } rcu_read_unlock(); return backbone_gw_tmp; } /** * batadv_bla_del_backbone_claims() - delete all claims for a backbone * @backbone_gw: backbone gateway where the claims should be removed */ static void batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_hashtable *hash; struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_bla_claim *claim; int i; spinlock_t *list_lock; /* protects write access to the hash lists */ hash = backbone_gw->bat_priv->bla.claim_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(claim, node_tmp, head, hash_entry) { if (claim->backbone_gw != backbone_gw) continue; batadv_claim_put(claim); hlist_del_rcu(&claim->hash_entry); } spin_unlock_bh(list_lock); } /* all claims gone, initialize CRC */ spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc = BATADV_BLA_CRC_INIT; spin_unlock_bh(&backbone_gw->crc_lock); } /** * batadv_bla_send_claim() - sends a claim frame according to the provided info * @bat_priv: the bat priv with all the soft interface information * @mac: the mac address to be announced within the claim * @vid: the VLAN ID * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) */ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, unsigned short vid, int claimtype) { struct sk_buff *skb; struct ethhdr *ethhdr; struct batadv_hard_iface *primary_if; struct net_device *soft_iface; u8 *hw_src; struct batadv_bla_claim_dst local_claim_dest; __be32 zeroip = 0; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return; memcpy(&local_claim_dest, &bat_priv->bla.claim_dest, sizeof(local_claim_dest)); local_claim_dest.type = claimtype; soft_iface = primary_if->soft_iface; skb = arp_create(ARPOP_REPLY, ETH_P_ARP, /* IP DST: 0.0.0.0 */ zeroip, primary_if->soft_iface, /* IP SRC: 0.0.0.0 */ zeroip, /* Ethernet DST: Broadcast */ NULL, /* Ethernet SRC/HW SRC: originator mac */ primary_if->net_dev->dev_addr, /* HW DST: FF:43:05:XX:YY:YY * with XX = claim type * and YY:YY = group id */ (u8 *)&local_claim_dest); if (!skb) goto out; ethhdr = (struct ethhdr *)skb->data; hw_src = (u8 *)ethhdr + ETH_HLEN + sizeof(struct arphdr); /* now we pretend that the client would have sent this ... */ switch (claimtype) { case BATADV_CLAIM_TYPE_CLAIM: /* normal claim frame * set Ethernet SRC to the clients mac */ ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): CLAIM %pM on vid %d\n", __func__, mac, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_UNCLAIM: /* unclaim frame * set HW SRC to the clients mac */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): UNCLAIM %pM on vid %d\n", __func__, mac, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_ANNOUNCE: /* announcement frame * set HW SRC to the special mac containing the crc */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ANNOUNCE of %pM on vid %d\n", __func__, ethhdr->h_source, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_REQUEST: /* request frame * set HW SRC and header destination to the receiving backbone * gws mac */ ether_addr_copy(hw_src, mac); ether_addr_copy(ethhdr->h_dest, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): REQUEST of %pM to %pM on vid %d\n", __func__, ethhdr->h_source, ethhdr->h_dest, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_LOOPDETECT: ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): LOOPDETECT of %pM to %pM on vid %d\n", __func__, ethhdr->h_source, ethhdr->h_dest, batadv_print_vid(vid)); break; } if (vid & BATADV_VLAN_HAS_TAG) { skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); if (!skb) goto out; } skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, soft_iface); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); netif_rx(skb); out: batadv_hardif_put(primary_if); } /** * batadv_bla_loopdetect_report() - worker for reporting the loop * @work: work queue item * * Throws an uevent, as the loopdetect check function can't do that itself * since the kernel may sleep while throwing uevents. */ static void batadv_bla_loopdetect_report(struct work_struct *work) { struct batadv_bla_backbone_gw *backbone_gw; struct batadv_priv *bat_priv; char vid_str[6] = { '\0' }; backbone_gw = container_of(work, struct batadv_bla_backbone_gw, report_work); bat_priv = backbone_gw->bat_priv; batadv_info(bat_priv->soft_iface, "Possible loop on VLAN %d detected which can't be handled by BLA - please check your network setup!\n", batadv_print_vid(backbone_gw->vid)); snprintf(vid_str, sizeof(vid_str), "%d", batadv_print_vid(backbone_gw->vid)); vid_str[sizeof(vid_str) - 1] = 0; batadv_throw_uevent(bat_priv, BATADV_UEV_BLA, BATADV_UEV_LOOPDETECT, vid_str); batadv_backbone_gw_put(backbone_gw); } /** * batadv_bla_get_backbone_gw() - finds or creates a backbone gateway * @bat_priv: the bat priv with all the soft interface information * @orig: the mac address of the originator * @vid: the VLAN ID * @own_backbone: set if the requested backbone is local * * Return: the (possibly created) backbone gateway or NULL on error */ static struct batadv_bla_backbone_gw * batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, unsigned short vid, bool own_backbone) { struct batadv_bla_backbone_gw *entry; struct batadv_orig_node *orig_node; int hash_added; entry = batadv_backbone_hash_find(bat_priv, orig, vid); if (entry) return entry; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): not found (%pM, %d), creating new entry\n", __func__, orig, batadv_print_vid(vid)); entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return NULL; entry->vid = vid; entry->lasttime = jiffies; entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; spin_lock_init(&entry->crc_lock); atomic_set(&entry->request_sent, 0); atomic_set(&entry->wait_periods, 0); ether_addr_copy(entry->orig, orig); INIT_WORK(&entry->report_work, batadv_bla_loopdetect_report); kref_init(&entry->refcount); kref_get(&entry->refcount); hash_added = batadv_hash_add(bat_priv->bla.backbone_hash, batadv_compare_backbone_gw, batadv_choose_backbone_gw, entry, &entry->hash_entry); if (unlikely(hash_added != 0)) { /* hash failed, free the structure */ kfree(entry); return NULL; } /* this is a gateway now, remove any TT entry on this VLAN */ orig_node = batadv_orig_hash_find(bat_priv, orig); if (orig_node) { batadv_tt_global_del_orig(bat_priv, orig_node, vid, "became a backbone gateway"); batadv_orig_node_put(orig_node); } if (own_backbone) { batadv_bla_send_announce(bat_priv, entry); /* this will be decreased in the worker thread */ atomic_inc(&entry->request_sent); atomic_set(&entry->wait_periods, BATADV_BLA_WAIT_PERIODS); atomic_inc(&bat_priv->bla.num_requests); } return entry; } /** * batadv_bla_update_own_backbone_gw() - updates the own backbone gw for a VLAN * @bat_priv: the bat priv with all the soft interface information * @primary_if: the selected primary interface * @vid: VLAN identifier * * update or add the own backbone gw to make sure we announce * where we receive other backbone gws */ static void batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, vid, true); if (unlikely(!backbone_gw)) return; backbone_gw->lasttime = jiffies; batadv_backbone_gw_put(backbone_gw); } /** * batadv_bla_answer_request() - answer a bla request by sending own claims * @bat_priv: the bat priv with all the soft interface information * @primary_if: interface where the request came on * @vid: the vid where the request came on * * Repeat all of our own claims, and finally send an ANNOUNCE frame * to allow the requester another check if the CRC is correct now. */ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, unsigned short vid) { struct hlist_head *head; struct batadv_hashtable *hash; struct batadv_bla_claim *claim; struct batadv_bla_backbone_gw *backbone_gw; int i; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): received a claim request, send all of our own claims again\n", __func__); backbone_gw = batadv_backbone_hash_find(bat_priv, primary_if->net_dev->dev_addr, vid); if (!backbone_gw) return; hash = bat_priv->bla.claim_hash; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { /* only own claims are interesting */ if (claim->backbone_gw != backbone_gw) continue; batadv_bla_send_claim(bat_priv, claim->addr, claim->vid, BATADV_CLAIM_TYPE_CLAIM); } rcu_read_unlock(); } /* finally, send an announcement frame */ batadv_bla_send_announce(bat_priv, backbone_gw); batadv_backbone_gw_put(backbone_gw); } /** * batadv_bla_send_request() - send a request to repeat claims * @backbone_gw: the backbone gateway from whom we are out of sync * * When the crc is wrong, ask the backbone gateway for a full table update. * After the request, it will repeat all of his own claims and finally * send an announcement claim with which we can check again. */ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) { /* first, remove all old entries */ batadv_bla_del_backbone_claims(backbone_gw); batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "Sending REQUEST to %pM\n", backbone_gw->orig); /* send request */ batadv_bla_send_claim(backbone_gw->bat_priv, backbone_gw->orig, backbone_gw->vid, BATADV_CLAIM_TYPE_REQUEST); /* no local broadcasts should be sent or received, for now. */ if (!atomic_read(&backbone_gw->request_sent)) { atomic_inc(&backbone_gw->bat_priv->bla.num_requests); atomic_set(&backbone_gw->request_sent, 1); } } /** * batadv_bla_send_announce() - Send an announcement frame * @bat_priv: the bat priv with all the soft interface information * @backbone_gw: our backbone gateway which should be announced */ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw) { u8 mac[ETH_ALEN]; __be16 crc; memcpy(mac, batadv_announce_mac, 4); spin_lock_bh(&backbone_gw->crc_lock); crc = htons(backbone_gw->crc); spin_unlock_bh(&backbone_gw->crc_lock); memcpy(&mac[4], &crc, 2); batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, BATADV_CLAIM_TYPE_ANNOUNCE); } /** * batadv_bla_add_claim() - Adds a claim in the claim hash * @bat_priv: the bat priv with all the soft interface information * @mac: the mac address of the claim * @vid: the VLAN ID of the frame * @backbone_gw: the backbone gateway which claims it */ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_bla_backbone_gw *old_backbone_gw; struct batadv_bla_claim *claim; struct batadv_bla_claim search_claim; bool remove_crc = false; int hash_added; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); /* create a new claim entry if it does not exist yet. */ if (!claim) { claim = kzalloc(sizeof(*claim), GFP_ATOMIC); if (!claim) return; ether_addr_copy(claim->addr, mac); spin_lock_init(&claim->backbone_lock); claim->vid = vid; claim->lasttime = jiffies; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; kref_init(&claim->refcount); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): adding new entry %pM, vid %d to hash ...\n", __func__, mac, batadv_print_vid(vid)); kref_get(&claim->refcount); hash_added = batadv_hash_add(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim, &claim->hash_entry); if (unlikely(hash_added != 0)) { /* only local changes happened. */ kfree(claim); return; } } else { claim->lasttime = jiffies; if (claim->backbone_gw == backbone_gw) /* no need to register a new backbone */ goto claim_free_ref; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): changing ownership for %pM, vid %d to gw %pM\n", __func__, mac, batadv_print_vid(vid), backbone_gw->orig); remove_crc = true; } /* replace backbone_gw atomically and adjust reference counters */ spin_lock_bh(&claim->backbone_lock); old_backbone_gw = claim->backbone_gw; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; spin_unlock_bh(&claim->backbone_lock); if (remove_crc) { /* remove claim address from old backbone_gw */ spin_lock_bh(&old_backbone_gw->crc_lock); old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&old_backbone_gw->crc_lock); } batadv_backbone_gw_put(old_backbone_gw); /* add claim address to new backbone_gw */ spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&backbone_gw->crc_lock); backbone_gw->lasttime = jiffies; claim_free_ref: batadv_claim_put(claim); } /** * batadv_bla_claim_get_backbone_gw() - Get valid reference for backbone_gw of * claim * @claim: claim whose backbone_gw should be returned * * Return: valid reference to claim::backbone_gw */ static struct batadv_bla_backbone_gw * batadv_bla_claim_get_backbone_gw(struct batadv_bla_claim *claim) { struct batadv_bla_backbone_gw *backbone_gw; spin_lock_bh(&claim->backbone_lock); backbone_gw = claim->backbone_gw; kref_get(&backbone_gw->refcount); spin_unlock_bh(&claim->backbone_lock); return backbone_gw; } /** * batadv_bla_del_claim() - delete a claim from the claim hash * @bat_priv: the bat priv with all the soft interface information * @mac: mac address of the claim to be removed * @vid: VLAN id for the claim to be removed */ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; struct batadv_bla_claim *claim_removed_entry; struct hlist_node *claim_removed_node; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) return; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, mac, batadv_print_vid(vid)); claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim); if (!claim_removed_node) goto free_claim; /* reference from the hash is gone */ claim_removed_entry = hlist_entry(claim_removed_node, struct batadv_bla_claim, hash_entry); batadv_claim_put(claim_removed_entry); free_claim: /* don't need the reference from hash_find() anymore */ batadv_claim_put(claim); } /** * batadv_handle_announce() - check for ANNOUNCE frame * @bat_priv: the bat priv with all the soft interface information * @an_addr: announcement mac address (ARP Sender HW address) * @backbone_addr: originator address of the sender (Ethernet source MAC) * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, u8 *backbone_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; u16 backbone_crc, crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return false; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid, false); if (unlikely(!backbone_gw)) return true; /* handle as ANNOUNCE frame */ backbone_gw->lasttime = jiffies; crc = ntohs(*((__force __be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", __func__, batadv_print_vid(vid), backbone_gw->orig, crc); spin_lock_bh(&backbone_gw->crc_lock); backbone_crc = backbone_gw->crc; spin_unlock_bh(&backbone_gw->crc_lock); if (backbone_crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "%s(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", __func__, backbone_gw->orig, batadv_print_vid(backbone_gw->vid), backbone_crc, crc); batadv_bla_send_request(backbone_gw); } else { /* if we have sent a request and the crc was OK, * we can allow traffic again. */ if (atomic_read(&backbone_gw->request_sent)) { atomic_dec(&backbone_gw->bat_priv->bla.num_requests); atomic_set(&backbone_gw->request_sent, 0); } } batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_handle_request() - check for REQUEST frame * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @backbone_addr: backbone address to be requested (ARP sender HW MAC) * @ethhdr: ethernet header of a packet * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, u8 *backbone_addr, struct ethhdr *ethhdr, unsigned short vid) { /* check for REQUEST frame */ if (!batadv_compare_eth(backbone_addr, ethhdr->h_dest)) return false; /* sanity check, this should not happen on a normal switch, * we ignore it in this case. */ if (!batadv_compare_eth(ethhdr->h_dest, primary_if->net_dev->dev_addr)) return true; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): REQUEST vid %d (sent by %pM)...\n", __func__, batadv_print_vid(vid), ethhdr->h_source); batadv_bla_answer_request(bat_priv, primary_if, vid); return true; } /** * batadv_handle_unclaim() - check for UNCLAIM frame * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @backbone_addr: originator address of the backbone (Ethernet source) * @claim_addr: Client to be unclaimed (ARP sender HW MAC) * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, const u8 *backbone_addr, const u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; /* unclaim in any case if it is our own */ if (primary_if && batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) batadv_bla_send_claim(bat_priv, claim_addr, vid, BATADV_CLAIM_TYPE_UNCLAIM); backbone_gw = batadv_backbone_hash_find(bat_priv, backbone_addr, vid); if (!backbone_gw) return true; /* this must be an UNCLAIM frame */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): UNCLAIM %pM on vid %d (sent by %pM)...\n", __func__, claim_addr, batadv_print_vid(vid), backbone_gw->orig); batadv_bla_del_claim(bat_priv, claim_addr, vid); batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_handle_claim() - check for CLAIM frame * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @backbone_addr: originator address of the backbone (Ethernet Source) * @claim_addr: client mac address to be claimed (ARP sender HW MAC) * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, const u8 *backbone_addr, const u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; /* register the gateway if not yet available, and add the claim. */ backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid, false); if (unlikely(!backbone_gw)) return true; /* this must be a CLAIM frame */ batadv_bla_add_claim(bat_priv, claim_addr, vid, backbone_gw); if (batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) batadv_bla_send_claim(bat_priv, claim_addr, vid, BATADV_CLAIM_TYPE_CLAIM); /* TODO: we could call something like tt_local_del() here. */ batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_check_claim_group() - check for claim group membership * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary interface of this batman interface * @hw_src: the Hardware source in the ARP Header * @hw_dst: the Hardware destination in the ARP Header * @ethhdr: pointer to the Ethernet header of the claim frame * * checks if it is a claim packet and if it's on the same group. * This function also applies the group ID of the sender * if it is in the same mesh. * * Return: * 2 - if it is a claim packet and on the same group * 1 - if is a claim packet from another group * 0 - if it is not a claim packet */ static int batadv_check_claim_group(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, u8 *hw_src, u8 *hw_dst, struct ethhdr *ethhdr) { u8 *backbone_addr; struct batadv_orig_node *orig_node; struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->bla.claim_dest; /* if announcement packet, use the source, * otherwise assume it is in the hw_src */ switch (bla_dst->type) { case BATADV_CLAIM_TYPE_CLAIM: backbone_addr = hw_src; break; case BATADV_CLAIM_TYPE_REQUEST: case BATADV_CLAIM_TYPE_ANNOUNCE: case BATADV_CLAIM_TYPE_UNCLAIM: backbone_addr = ethhdr->h_source; break; default: return 0; } /* don't accept claim frames from ourselves */ if (batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) return 0; /* if its already the same group, it is fine. */ if (bla_dst->group == bla_dst_own->group) return 2; /* lets see if this originator is in our mesh */ orig_node = batadv_orig_hash_find(bat_priv, backbone_addr); /* don't accept claims from gateways which are not in * the same mesh or group. */ if (!orig_node) return 1; /* if our mesh friends mac is bigger, use it for ourselves. */ if (ntohs(bla_dst->group) > ntohs(bla_dst_own->group)) { batadv_dbg(BATADV_DBG_BLA, bat_priv, "taking other backbones claim group: %#.4x\n", ntohs(bla_dst->group)); bla_dst_own->group = bla_dst->group; } batadv_orig_node_put(orig_node); return 2; } /** * batadv_bla_process_claim() - Check if this is a claim frame, and process it * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @skb: the frame to be checked * * Return: true if it was a claim frame, otherwise return false to * tell the callee that it can use the frame on its own. */ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct sk_buff *skb) { struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; u8 *hw_src, *hw_dst; struct vlan_hdr *vhdr, vhdr_buf; struct ethhdr *ethhdr; struct arphdr *arphdr; unsigned short vid; int vlan_depth = 0; __be16 proto; int headlen; int ret; vid = batadv_get_vid(skb, 0); ethhdr = eth_hdr(skb); proto = ethhdr->h_proto; headlen = ETH_HLEN; if (vid & BATADV_VLAN_HAS_TAG) { /* Traverse the VLAN/Ethertypes. * * At this point it is known that the first protocol is a VLAN * header, so start checking at the encapsulated protocol. * * The depth of the VLAN headers is recorded to drop BLA claim * frames encapsulated into multiple VLAN headers (QinQ). */ do { vhdr = skb_header_pointer(skb, headlen, VLAN_HLEN, &vhdr_buf); if (!vhdr) return false; proto = vhdr->h_vlan_encapsulated_proto; headlen += VLAN_HLEN; vlan_depth++; } while (proto == htons(ETH_P_8021Q)); } if (proto != htons(ETH_P_ARP)) return false; /* not a claim frame */ /* this must be a ARP frame. check if it is a claim. */ if (unlikely(!pskb_may_pull(skb, headlen + arp_hdr_len(skb->dev)))) return false; /* pskb_may_pull() may have modified the pointers, get ethhdr again */ ethhdr = eth_hdr(skb); arphdr = (struct arphdr *)((u8 *)ethhdr + headlen); /* Check whether the ARP frame carries a valid * IP information */ if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) return false; if (arphdr->ar_pro != htons(ETH_P_IP)) return false; if (arphdr->ar_hln != ETH_ALEN) return false; if (arphdr->ar_pln != 4) return false; hw_src = (u8 *)arphdr + sizeof(struct arphdr); hw_dst = hw_src + ETH_ALEN + 4; bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->bla.claim_dest; /* check if it is a claim frame in general */ if (memcmp(bla_dst->magic, bla_dst_own->magic, sizeof(bla_dst->magic)) != 0) return false; /* check if there is a claim frame encapsulated deeper in (QinQ) and * drop that, as this is not supported by BLA but should also not be * sent via the mesh. */ if (vlan_depth > 1) return true; /* Let the loopdetect frames on the mesh in any case. */ if (bla_dst->type == BATADV_CLAIM_TYPE_LOOPDETECT) return false; /* check if it is a claim frame. */ ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst, ethhdr); if (ret == 1) batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", __func__, ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst); if (ret < 2) return !!ret; /* become a backbone gw ourselves on this vlan if not happened yet */ batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); /* check for the different types of claim frames ... */ switch (bla_dst->type) { case BATADV_CLAIM_TYPE_CLAIM: if (batadv_handle_claim(bat_priv, primary_if, hw_src, ethhdr->h_source, vid)) return true; break; case BATADV_CLAIM_TYPE_UNCLAIM: if (batadv_handle_unclaim(bat_priv, primary_if, ethhdr->h_source, hw_src, vid)) return true; break; case BATADV_CLAIM_TYPE_ANNOUNCE: if (batadv_handle_announce(bat_priv, hw_src, ethhdr->h_source, vid)) return true; break; case BATADV_CLAIM_TYPE_REQUEST: if (batadv_handle_request(bat_priv, primary_if, hw_src, ethhdr, vid)) return true; break; } batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", __func__, ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst); return true; } /** * batadv_bla_purge_backbone_gw() - Remove backbone gateways after a timeout or * immediately * @bat_priv: the bat priv with all the soft interface information * @now: whether the whole hash shall be wiped now * * Check when we last heard from other nodes, and remove them in case of * a time out, or clean all backbone gws if now is set. */ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { struct batadv_bla_backbone_gw *backbone_gw; struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ int i; hash = bat_priv->bla.backbone_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(backbone_gw, node_tmp, head, hash_entry) { if (now) goto purge_now; if (!batadv_has_timed_out(backbone_gw->lasttime, BATADV_BLA_BACKBONE_TIMEOUT)) continue; batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "%s(): backbone gw %pM timed out\n", __func__, backbone_gw->orig); purge_now: /* don't wait for the pending request anymore */ if (atomic_read(&backbone_gw->request_sent)) atomic_dec(&bat_priv->bla.num_requests); batadv_bla_del_backbone_claims(backbone_gw); hlist_del_rcu(&backbone_gw->hash_entry); batadv_backbone_gw_put(backbone_gw); } spin_unlock_bh(list_lock); } } /** * batadv_bla_purge_claims() - Remove claims after a timeout or immediately * @bat_priv: the bat priv with all the soft interface information * @primary_if: the selected primary interface, may be NULL if now is set * @now: whether the whole hash shall be wiped now * * Check when we heard last time from our own claims, and remove them in case of * a time out, or clean all claims if now is set */ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct hlist_head *head; struct batadv_hashtable *hash; int i; hash = bat_priv->bla.claim_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) goto skip; if (!batadv_has_timed_out(claim->lasttime, BATADV_BLA_CLAIM_TIMEOUT)) goto skip; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): timed out.\n", __func__); purge_now: batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, claim->addr, claim->vid); batadv_handle_unclaim(bat_priv, primary_if, backbone_gw->orig, claim->addr, claim->vid); skip: batadv_backbone_gw_put(backbone_gw); } rcu_read_unlock(); } } /** * batadv_bla_update_orig_address() - Update the backbone gateways when the own * originator address changes * @bat_priv: the bat priv with all the soft interface information * @primary_if: the new selected primary_if * @oldif: the old primary interface, may be NULL */ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct batadv_hard_iface *oldif) { struct batadv_bla_backbone_gw *backbone_gw; struct hlist_head *head; struct batadv_hashtable *hash; __be16 group; int i; /* reset bridge loop avoidance group id */ group = htons(crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN)); bat_priv->bla.claim_dest.group = group; /* purge everything when bridge loop avoidance is turned off */ if (!atomic_read(&bat_priv->bridge_loop_avoidance)) oldif = NULL; if (!oldif) { batadv_bla_purge_claims(bat_priv, NULL, 1); batadv_bla_purge_backbone_gw(bat_priv, 1); return; } hash = bat_priv->bla.backbone_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { /* own orig still holds the old value. */ if (!batadv_compare_eth(backbone_gw->orig, oldif->net_dev->dev_addr)) continue; ether_addr_copy(backbone_gw->orig, primary_if->net_dev->dev_addr); /* send an announce frame so others will ask for our * claims and update their tables. */ batadv_bla_send_announce(bat_priv, backbone_gw); } rcu_read_unlock(); } } /** * batadv_bla_send_loopdetect() - send a loopdetect frame * @bat_priv: the bat priv with all the soft interface information * @backbone_gw: the backbone gateway for which a loop should be detected * * To detect loops that the bridge loop avoidance can't handle, send a loop * detection packet on the backbone. Unlike other BLA frames, this frame will * be allowed on the mesh by other nodes. If it is received on the mesh, this * indicates that there is a loop. */ static void batadv_bla_send_loopdetect(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw) { batadv_dbg(BATADV_DBG_BLA, bat_priv, "Send loopdetect frame for vid %d\n", backbone_gw->vid); batadv_bla_send_claim(bat_priv, bat_priv->bla.loopdetect_addr, backbone_gw->vid, BATADV_CLAIM_TYPE_LOOPDETECT); } /** * batadv_bla_status_update() - purge bla interfaces if necessary * @net_dev: the soft interface net device */ void batadv_bla_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hard_iface *primary_if; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return; /* this function already purges everything when bla is disabled, * so just call that one. */ batadv_bla_update_orig_address(bat_priv, primary_if, primary_if); batadv_hardif_put(primary_if); } /** * batadv_bla_periodic_work() - performs periodic bla work * @work: kernel work struct * * periodic work to do: * * purge structures when they are too old * * send announcements */ static void batadv_bla_periodic_work(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct batadv_priv_bla *priv_bla; struct hlist_head *head; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hashtable *hash; struct batadv_hard_iface *primary_if; bool send_loopdetect = false; int i; delayed_work = to_delayed_work(work); priv_bla = container_of(delayed_work, struct batadv_priv_bla, work); bat_priv = container_of(priv_bla, struct batadv_priv, bla); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; batadv_bla_purge_claims(bat_priv, primary_if, 0); batadv_bla_purge_backbone_gw(bat_priv, 0); if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto out; if (atomic_dec_and_test(&bat_priv->bla.loopdetect_next)) { /* set a new random mac address for the next bridge loop * detection frames. Set the locally administered bit to avoid * collisions with users mac addresses. */ eth_random_addr(bat_priv->bla.loopdetect_addr); bat_priv->bla.loopdetect_addr[0] = 0xba; bat_priv->bla.loopdetect_addr[1] = 0xbe; bat_priv->bla.loopdetect_lasttime = jiffies; atomic_set(&bat_priv->bla.loopdetect_next, BATADV_BLA_LOOPDETECT_PERIODS); /* mark for sending loop detect on all VLANs */ send_loopdetect = true; } hash = bat_priv->bla.backbone_hash; if (!hash) goto out; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) continue; backbone_gw->lasttime = jiffies; batadv_bla_send_announce(bat_priv, backbone_gw); if (send_loopdetect) batadv_bla_send_loopdetect(bat_priv, backbone_gw); /* request_sent is only set after creation to avoid * problems when we are not yet known as backbone gw * in the backbone. * * We can reset this now after we waited some periods * to give bridge forward delays and bla group forming * some grace time. */ if (atomic_read(&backbone_gw->request_sent) == 0) continue; if (!atomic_dec_and_test(&backbone_gw->wait_periods)) continue; atomic_dec(&backbone_gw->bat_priv->bla.num_requests); atomic_set(&backbone_gw->request_sent, 0); } rcu_read_unlock(); } out: batadv_hardif_put(primary_if); queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); } /* The hash for claim and backbone hash receive the same key because they * are getting initialized by hash_new with the same key. Reinitializing * them with to different keys to allow nested locking without generating * lockdep warnings */ static struct lock_class_key batadv_claim_hash_lock_class_key; static struct lock_class_key batadv_backbone_hash_lock_class_key; /** * batadv_bla_init() - initialize all bla structures * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success, < 0 on error. */ int batadv_bla_init(struct batadv_priv *bat_priv) { int i; u8 claim_dest[ETH_ALEN] = {0xff, 0x43, 0x05, 0x00, 0x00, 0x00}; struct batadv_hard_iface *primary_if; u16 crc; unsigned long entrytime; spin_lock_init(&bat_priv->bla.bcast_duplist_lock); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hash registering\n"); /* setting claim destination address */ memcpy(&bat_priv->bla.claim_dest.magic, claim_dest, 3); bat_priv->bla.claim_dest.type = 0; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if) { crc = crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN); bat_priv->bla.claim_dest.group = htons(crc); batadv_hardif_put(primary_if); } else { bat_priv->bla.claim_dest.group = 0; /* will be set later */ } /* initialize the duplicate list */ entrytime = jiffies - msecs_to_jiffies(BATADV_DUPLIST_TIMEOUT); for (i = 0; i < BATADV_DUPLIST_SIZE; i++) bat_priv->bla.bcast_duplist[i].entrytime = entrytime; bat_priv->bla.bcast_duplist_curr = 0; atomic_set(&bat_priv->bla.loopdetect_next, BATADV_BLA_LOOPDETECT_PERIODS); if (bat_priv->bla.claim_hash) return 0; bat_priv->bla.claim_hash = batadv_hash_new(128); if (!bat_priv->bla.claim_hash) return -ENOMEM; bat_priv->bla.backbone_hash = batadv_hash_new(32); if (!bat_priv->bla.backbone_hash) { batadv_hash_destroy(bat_priv->bla.claim_hash); return -ENOMEM; } batadv_hash_set_lock_class(bat_priv->bla.claim_hash, &batadv_claim_hash_lock_class_key); batadv_hash_set_lock_class(bat_priv->bla.backbone_hash, &batadv_backbone_hash_lock_class_key); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hashes initialized\n"); INIT_DELAYED_WORK(&bat_priv->bla.work, batadv_bla_periodic_work); queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); return 0; } /** * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information * @skb: contains the multicast packet to be checked * @payload_ptr: pointer to position inside the head buffer of the skb * marking the start of the data to be CRC'ed * @orig: originator mac address, NULL if unknown * * Check if it is on our broadcast list. Another gateway might have sent the * same packet because it is connected to the same backbone, so we have to * remove this duplicate. * * This is performed by checking the CRC, which will tell us * with a good chance that it is the same packet. If it is furthermore * sent by another host, drop it. We allow equal packets from * the same host however as this might be intended. * * Return: true if a packet is in the duplicate list, false otherwise. */ static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb, u8 *payload_ptr, const u8 *orig) { struct batadv_bcast_duplist_entry *entry; bool ret = false; int i, curr; __be32 crc; /* calculate the crc ... */ crc = batadv_skb_crc32(skb, payload_ptr); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); for (i = 0; i < BATADV_DUPLIST_SIZE; i++) { curr = (bat_priv->bla.bcast_duplist_curr + i); curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bla.bcast_duplist[curr]; /* we can stop searching if the entry is too old ; * later entries will be even older */ if (batadv_has_timed_out(entry->entrytime, BATADV_DUPLIST_TIMEOUT)) break; if (entry->crc != crc) continue; /* are the originators both known and not anonymous? */ if (orig && !is_zero_ether_addr(orig) && !is_zero_ether_addr(entry->orig)) { /* If known, check if the new frame came from * the same originator: * We are safe to take identical frames from the * same orig, if known, as multiplications in * the mesh are detected via the (orig, seqno) pair. * So we can be a bit more liberal here and allow * identical frames from the same orig which the source * host might have sent multiple times on purpose. */ if (batadv_compare_eth(entry->orig, orig)) continue; } /* this entry seems to match: same crc, not too old, * and from another gw. therefore return true to forbid it. */ ret = true; goto out; } /* not found, add a new entry (overwrite the oldest entry) * and allow it, its the first occurrence. */ curr = (bat_priv->bla.bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1); curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; /* known originator */ if (orig) ether_addr_copy(entry->orig, orig); /* anonymous originator */ else eth_zero_addr(entry->orig); bat_priv->bla.bcast_duplist_curr = curr; out: spin_unlock_bh(&bat_priv->bla.bcast_duplist_lock); return ret; } /** * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information * @skb: contains the multicast packet to be checked, decapsulated from a * unicast_packet * * Check if it is on our broadcast list. Another gateway might have sent the * same packet because it is connected to the same backbone, so we have to * remove this duplicate. * * Return: true if a packet is in the duplicate list, false otherwise. */ static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb) { return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); } /** * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information * @skb: contains the bcast_packet to be checked * * Check if it is on our broadcast list. Another gateway might have sent the * same packet because it is connected to the same backbone, so we have to * remove this duplicate. * * Return: true if a packet is in the duplicate list, false otherwise. */ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_bcast_packet *bcast_packet; u8 *payload_ptr; bcast_packet = (struct batadv_bcast_packet *)skb->data; payload_ptr = (u8 *)(bcast_packet + 1); return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, bcast_packet->orig); } /** * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for * the VLAN identified by vid. * @bat_priv: the bat priv with all the soft interface information * @orig: originator mac address * @vid: VLAN identifier * * Return: true if orig is a backbone for this vid, false otherwise. */ bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct batadv_bla_backbone_gw *backbone_gw; int i; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) return false; if (!hash) return false; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (batadv_compare_eth(backbone_gw->orig, orig) && backbone_gw->vid == vid) { rcu_read_unlock(); return true; } } rcu_read_unlock(); } return false; } /** * batadv_bla_is_backbone_gw() - check if originator is a backbone gw for a VLAN * @skb: the frame to be checked * @orig_node: the orig_node of the frame * @hdr_size: maximum length of the frame * * Return: true if the orig_node is also a gateway on the soft interface, * otherwise it returns false. */ bool batadv_bla_is_backbone_gw(struct sk_buff *skb, struct batadv_orig_node *orig_node, int hdr_size) { struct batadv_bla_backbone_gw *backbone_gw; unsigned short vid; if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) return false; /* first, find out the vid. */ if (!pskb_may_pull(skb, hdr_size + ETH_HLEN)) return false; vid = batadv_get_vid(skb, hdr_size); /* see if this originator is a backbone gw for this VLAN */ backbone_gw = batadv_backbone_hash_find(orig_node->bat_priv, orig_node->orig, vid); if (!backbone_gw) return false; batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_bla_free() - free all bla structures * @bat_priv: the bat priv with all the soft interface information * * for softinterface free or module unload */ void batadv_bla_free(struct batadv_priv *bat_priv) { struct batadv_hard_iface *primary_if; cancel_delayed_work_sync(&bat_priv->bla.work); primary_if = batadv_primary_if_get_selected(bat_priv); if (bat_priv->bla.claim_hash) { batadv_bla_purge_claims(bat_priv, primary_if, 1); batadv_hash_destroy(bat_priv->bla.claim_hash); bat_priv->bla.claim_hash = NULL; } if (bat_priv->bla.backbone_hash) { batadv_bla_purge_backbone_gw(bat_priv, 1); batadv_hash_destroy(bat_priv->bla.backbone_hash); bat_priv->bla.backbone_hash = NULL; } batadv_hardif_put(primary_if); } /** * batadv_bla_loopdetect_check() - check and handle a detected loop * @bat_priv: the bat priv with all the soft interface information * @skb: the packet to check * @primary_if: interface where the request came on * @vid: the VLAN ID of the frame * * Checks if this packet is a loop detect frame which has been sent by us, * throws an uevent and logs the event if that is the case. * * Return: true if it is a loop detect frame which is to be dropped, false * otherwise. */ static bool batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_hard_iface *primary_if, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; bool ret; ethhdr = eth_hdr(skb); /* Only check for the MAC address and skip more checks here for * performance reasons - this function is on the hotpath, after all. */ if (!batadv_compare_eth(ethhdr->h_source, bat_priv->bla.loopdetect_addr)) return false; /* If the packet came too late, don't forward it on the mesh * but don't consider that as loop. It might be a coincidence. */ if (batadv_has_timed_out(bat_priv->bla.loopdetect_lasttime, BATADV_BLA_LOOPDETECT_TIMEOUT)) return true; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, vid, true); if (unlikely(!backbone_gw)) return true; ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); /* backbone_gw is unreferenced in the report work function * if queue_work() call was successful */ if (!ret) batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_bla_rx() - check packets coming from the mesh. * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame * @packet_type: the batman packet type this frame came in * * batadv_bla_rx avoidance checks if: * * we have to race for a claim * * if the frame is allowed on the LAN * * In these cases, the skb is further handled by this function * * Return: true if handled, otherwise it returns false and the caller shall * further process the skb. */ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int packet_type) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; bool own_claim; bool ret; ethhdr = eth_hdr(skb); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto handled; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto allow; if (batadv_bla_loopdetect_check(bat_priv, skb, primary_if, vid)) goto handled; if (unlikely(atomic_read(&bat_priv->bla.num_requests))) /* don't allow multicast packets while requests are in flight */ if (is_multicast_ether_addr(ethhdr->h_dest)) /* Both broadcast flooding or multicast-via-unicasts * delivery might send to multiple backbone gateways * sharing the same LAN and therefore need to coordinate * which backbone gateway forwards into the LAN, * by claiming the payload source address. * * Broadcast flooding and multicast-via-unicasts * delivery use the following two batman packet types. * Note: explicitly exclude BATADV_UNICAST_4ADDR, * as the DHCP gateway feature will send explicitly * to only one BLA gateway, so the claiming process * should be avoided there. */ if (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST) goto handled; /* potential duplicates from foreign BLA backbone gateways via * multicast-in-unicast packets */ if (is_multicast_ether_addr(ethhdr->h_dest) && packet_type == BATADV_UNICAST && batadv_bla_check_ucast_duplist(bat_priv, skb)) goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) { bool local = batadv_is_my_client(bat_priv, ethhdr->h_source, vid); /* possible optimization: race for a claim */ /* No claim exists yet, claim it for us! */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Unclaimed MAC %pM found. Claim it. Local: %s\n", __func__, ethhdr->h_source, str_yes_no(local)); batadv_handle_claim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } /* if it is our own claim ... */ backbone_gw = batadv_bla_claim_get_backbone_gw(claim); own_claim = batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr); batadv_backbone_gw_put(backbone_gw); if (own_claim) { /* ... allow it in any case */ claim->lasttime = jiffies; goto allow; } /* if it is a multicast ... */ if (is_multicast_ether_addr(ethhdr->h_dest) && (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) { /* ... drop it. the responsible gateway is in charge. * * We need to check packet type because with the gateway * feature, broadcasts (like DHCP requests) may be sent * using a unicast 4 address packet type. See comment above. */ goto handled; } else { /* seems the client considers us as its best gateway. * send a claim and update the claim table * immediately. */ batadv_handle_claim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } allow: batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); ret = false; goto out; handled: kfree_skb(skb); ret = true; out: batadv_hardif_put(primary_if); batadv_claim_put(claim); return ret; } /** * batadv_bla_tx() - check packets going into the mesh * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame * * batadv_bla_tx checks if: * * a claim was received which has to be processed * * the frame is allowed on the mesh * * in these cases, the skb is further handled by this function. * * This call might reallocate skb data. * * Return: true if handled, otherwise it returns false and the caller shall * further process the skb. */ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; bool client_roamed; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto allow; if (batadv_bla_process_claim(bat_priv, primary_if, skb)) goto handled; ethhdr = eth_hdr(skb); if (unlikely(atomic_read(&bat_priv->bla.num_requests))) /* don't allow broadcasts while requests are in flight */ if (is_multicast_ether_addr(ethhdr->h_dest)) goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); /* if no claim exists, allow it. */ if (!claim) goto allow; /* check if we are responsible. */ backbone_gw = batadv_bla_claim_get_backbone_gw(claim); client_roamed = batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr); batadv_backbone_gw_put(backbone_gw); if (client_roamed) { /* if yes, the client has roamed and we have * to unclaim it. */ if (batadv_has_timed_out(claim->lasttime, 100)) { /* only unclaim if the last claim entry is * older than 100 ms to make sure we really * have a roaming client here. */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Roaming client %pM detected. Unclaim it.\n", __func__, ethhdr->h_source); batadv_handle_unclaim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } else { batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Race for claim %pM detected. Drop packet.\n", __func__, ethhdr->h_source); goto handled; } } /* check if it is a multicast/broadcast frame */ if (is_multicast_ether_addr(ethhdr->h_dest)) { /* drop it. the responsible gateway has forwarded it into * the backbone network. */ goto handled; } else { /* we must allow it. at least if we are * responsible for the DESTINATION. */ goto allow; } allow: batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); ret = false; goto out; handled: ret = true; out: batadv_hardif_put(primary_if); batadv_claim_put(claim); return ret; } /** * batadv_bla_claim_dump_entry() - dump one entry of the claim table * to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @claim: entry to dump * * Return: 0 or error code. */ static int batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_bla_claim *claim) { const u8 *primary_addr = primary_if->net_dev->dev_addr; u16 backbone_crc; bool is_own; void *hdr; int ret = -EINVAL; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_BLA_CLAIM); if (!hdr) { ret = -ENOBUFS; goto out; } genl_dump_check_consistent(cb, hdr); is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); spin_lock_bh(&claim->backbone_gw->crc_lock); backbone_crc = claim->backbone_gw->crc; spin_unlock_bh(&claim->backbone_gw->crc_lock); if (is_own) if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { genlmsg_cancel(msg, hdr); goto out; } if (nla_put(msg, BATADV_ATTR_BLA_ADDRESS, ETH_ALEN, claim->addr) || nla_put_u16(msg, BATADV_ATTR_BLA_VID, claim->vid) || nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, claim->backbone_gw->orig) || nla_put_u16(msg, BATADV_ATTR_BLA_CRC, backbone_crc)) { genlmsg_cancel(msg, hdr); goto out; } genlmsg_end(msg, hdr); ret = 0; out: return ret; } /** * batadv_bla_claim_dump_bucket() - dump one bucket of the claim table * to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: always 0. */ static int batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_hashtable *hash, unsigned int bucket, int *idx_skip) { struct batadv_bla_claim *claim; int idx = 0; int ret = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(claim, &hash->table[bucket], hash_entry) { if (idx++ < *idx_skip) continue; ret = batadv_bla_claim_dump_entry(msg, portid, cb, primary_if, claim); if (ret) { *idx_skip = idx - 1; goto unlock; } } *idx_skip = 0; unlock: spin_unlock_bh(&hash->list_locks[bucket]); return ret; } /** * batadv_bla_claim_dump() - dump claim table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; int ret = 0; soft_iface = batadv_netlink_get_softif(cb); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); hash = bat_priv->bla.claim_hash; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } while (bucket < hash->size) { if (batadv_bla_claim_dump_bucket(msg, portid, cb, primary_if, hash, bucket, &idx)) break; bucket++; } cb->args[0] = bucket; cb->args[1] = idx; ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); return ret; } /** * batadv_bla_backbone_dump_entry() - dump one entry of the backbone table to a * netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @backbone_gw: entry to dump * * Return: 0 or error code. */ static int batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_bla_backbone_gw *backbone_gw) { const u8 *primary_addr = primary_if->net_dev->dev_addr; u16 backbone_crc; bool is_own; int msecs; void *hdr; int ret = -EINVAL; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_BLA_BACKBONE); if (!hdr) { ret = -ENOBUFS; goto out; } genl_dump_check_consistent(cb, hdr); is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); spin_lock_bh(&backbone_gw->crc_lock); backbone_crc = backbone_gw->crc; spin_unlock_bh(&backbone_gw->crc_lock); msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); if (is_own) if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { genlmsg_cancel(msg, hdr); goto out; } if (nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, backbone_gw->orig) || nla_put_u16(msg, BATADV_ATTR_BLA_VID, backbone_gw->vid) || nla_put_u16(msg, BATADV_ATTR_BLA_CRC, backbone_crc) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, msecs)) { genlmsg_cancel(msg, hdr); goto out; } genlmsg_end(msg, hdr); ret = 0; out: return ret; } /** * batadv_bla_backbone_dump_bucket() - dump one bucket of the backbone table to * a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: always 0. */ static int batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_hashtable *hash, unsigned int bucket, int *idx_skip) { struct batadv_bla_backbone_gw *backbone_gw; int idx = 0; int ret = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(backbone_gw, &hash->table[bucket], hash_entry) { if (idx++ < *idx_skip) continue; ret = batadv_bla_backbone_dump_entry(msg, portid, cb, primary_if, backbone_gw); if (ret) { *idx_skip = idx - 1; goto unlock; } } *idx_skip = 0; unlock: spin_unlock_bh(&hash->list_locks[bucket]); return ret; } /** * batadv_bla_backbone_dump() - dump backbone table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; int ret = 0; soft_iface = batadv_netlink_get_softif(cb); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); hash = bat_priv->bla.backbone_hash; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } while (bucket < hash->size) { if (batadv_bla_backbone_dump_bucket(msg, portid, cb, primary_if, hash, bucket, &idx)) break; bucket++; } cb->args[0] = bucket; cb->args[1] = idx; ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); return ret; } #ifdef CONFIG_BATMAN_ADV_DAT /** * batadv_bla_check_claim() - check if address is claimed * * @bat_priv: the bat priv with all the soft interface information * @addr: mac address of which the claim status is checked * @vid: the VLAN ID * * addr is checked if this address is claimed by the local device itself. * * Return: true if bla is disabled or the mac is claimed by the device, * false if the device addr is already claimed by another gateway */ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid) { struct batadv_bla_claim search_claim; struct batadv_bla_claim *claim = NULL; struct batadv_hard_iface *primary_if = NULL; bool ret = true; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) return ret; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return ret; /* First look if the mac address is claimed */ ether_addr_copy(search_claim.addr, addr); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); /* If there is a claim and we are not owner of the claim, * return false. */ if (claim) { if (!batadv_compare_eth(claim->backbone_gw->orig, primary_if->net_dev->dev_addr)) ret = false; batadv_claim_put(claim); } batadv_hardif_put(primary_if); return ret; } #endif |
| 119 6 1 11 11 12 28 28 12 1 11 12 4 20 12 63 10 72 213 2 170 41 60 27 2 1 23 23 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #ifndef _LINUX_SKMSG_H #define _LINUX_SKMSG_H #include <linux/bpf.h> #include <linux/filter.h> #include <linux/scatterlist.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/tcp.h> #include <net/strparser.h> #define MAX_MSG_FRAGS MAX_SKB_FRAGS #define NR_MSG_FRAG_IDS (MAX_MSG_FRAGS + 1) enum __sk_action { __SK_DROP = 0, __SK_PASS, __SK_REDIRECT, __SK_NONE, }; struct sk_msg_sg { u32 start; u32 curr; u32 end; u32 size; u32 copybreak; DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the * chaining; * 2) to chain tailer SG entries after the message. */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { struct sk_msg_sg sg; void *data; void *data_end; u32 apply_bytes; u32 cork_bytes; u32 flags; struct sk_buff *skb; struct sock *sk_redir; struct sock *sk; struct list_head list; }; struct sk_psock_progs { struct bpf_prog *msg_parser; struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; struct bpf_link *msg_parser_link; struct bpf_link *stream_parser_link; struct bpf_link *stream_verdict_link; struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { struct list_head list; struct bpf_map *map; void *link_raw; }; struct sk_psock_work_state { u32 len; u32 off; }; struct sk_psock { struct sock *sk; struct sock *sk_redir; u32 apply_bytes; u32 cork_bytes; u32 eval; bool redir_ingress; /* undefined if sk_redir is null */ struct sk_msg *cork; struct sk_psock_progs progs; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) struct strparser strp; u32 copied_seq; u32 ingress_bytes; #endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; spinlock_t ingress_lock; unsigned long state; struct list_head link; spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); /* psock_update_sk_prot may be called with restore=false many times * so the handler must be safe for this case. It will be called * exactly once with restore=true when the psock is being destroyed * and psock refcnt is zero, but before an RCU grace period. */ int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; struct sock *sk_pair; struct rcu_work rwork; }; int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce); int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, u32 off, u32 len); void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); int sk_msg_free(struct sock *sk, struct sk_msg *msg); int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); bool sk_msg_is_readable(struct sock *sk); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) { WARN_ON(i == msg->sg.end && bytes); } static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) { if (psock->apply_bytes) { if (psock->apply_bytes < bytes) psock->apply_bytes = 0; else psock->apply_bytes -= bytes; } } static inline u32 sk_msg_iter_dist(u32 start, u32 end) { return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start); } #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ var = NR_MSG_FRAG_IDS - 1; \ else \ var--; \ } while (0) #define sk_msg_iter_var_next(var) \ do { \ var++; \ if (var == NR_MSG_FRAG_IDS) \ var = 0; \ } while (0) #define sk_msg_iter_prev(msg, which) \ sk_msg_iter_var_prev(msg->sg.which) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); memset(msg, 0, sizeof(*msg)); sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, int which, u32 size) { dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) { memcpy(dst, src, sizeof(*src)); sk_msg_init(src); } static inline bool sk_msg_full(const struct sk_msg *msg) { return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS; } static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) { return &msg->sg.data[which]; } static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) { return msg->sg.data[which]; } static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); } static inline bool sk_msg_to_ingress(const struct sk_msg *msg) { return msg->flags & BPF_F_INGRESS; } static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { msg->data = sg_virt(sge); msg->data_end = msg->data + sge->length; } } static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, u32 len, u32 offset) { struct scatterlist *sge; get_page(page); sge = sk_msg_elem(msg, msg->sg.end); sg_set_page(sge, page, len, offset); sg_unmark_end(sge); __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) __set_bit(i, msg->sg.copy); else __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; } while (1); } static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, true); } static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, false); } static inline struct sk_psock *sk_psock(const struct sock *sk) { return __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_PSOCK); } static inline void sk_psock_set_state(struct sk_psock *psock, enum sk_psock_state_bits bit) { set_bit(bit, &psock->state); } static inline void sk_psock_clear_state(struct sk_psock *psock, enum sk_psock_state_bits bit) { clear_bit(bit, &psock->state); } static inline bool sk_psock_test_state(const struct sk_psock *psock, enum sk_psock_state_bits bit) { return test_bit(bit, &psock->state); } static inline void sock_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); kfree_skb(skb); } static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { bool ret; spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); ret = true; } else { sk_msg_free(psock->sk, msg); kfree(msg); ret = false; } spin_unlock_bh(&psock->ingress_lock); return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); if (msg) list_del(&msg->list); spin_unlock_bh(&psock->ingress_lock); return msg; } static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); spin_unlock_bh(&psock->ingress_lock); return msg; } static inline struct sk_msg *sk_psock_next_msg(struct sk_psock *psock, struct sk_msg *msg) { struct sk_msg *ret; spin_lock_bh(&psock->ingress_lock); if (list_is_last(&msg->list, &psock->ingress_msg)) ret = NULL; else ret = list_next_entry(msg, list); spin_unlock_bh(&psock->ingress_lock); return ret; } static inline bool sk_psock_queue_empty(const struct sk_psock *psock) { return psock ? list_empty(&psock->ingress_msg) : true; } static inline void kfree_sk_msg(struct sk_msg *msg) { if (msg->skb) consume_skb(msg->skb); kfree(msg); } static inline void sk_psock_report_error(struct sk_psock *psock, int err) { struct sock *sk = psock->sk; sk->sk_err = err; sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); #else static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { return -EOPNOTSUPP; } static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { } static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { } #endif void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define sk_psock_init_link() \ ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ GFP_ATOMIC | __GFP_NOWARN)) static inline void sk_psock_free_link(struct sk_psock_link *link) { kfree(link); } struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); static inline void sk_psock_cork_free(struct sk_psock *psock) { if (psock->cork) { sk_msg_free(psock->sk, psock->cork); kfree(psock->cork); psock->cork = NULL; } } static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { if (psock->psock_update_sk_prot) psock->psock_update_sk_prot(sk, psock, true); } static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (psock && !refcount_inc_not_zero(&psock->refcnt)) psock = NULL; rcu_read_unlock(); return psock; } void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) { if (refcount_dec_and_test(&psock->refcnt)) sk_psock_drop(sk, psock); } static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, struct bpf_prog *prog) { prog = xchg(pprog, prog); if (prog) bpf_prog_put(prog); } static inline int psock_replace_prog(struct bpf_prog **pprog, struct bpf_prog *prog, struct bpf_prog *old) { if (cmpxchg(pprog, old, prog) != old) return -ENOENT; if (old) bpf_prog_put(old); return 0; } static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); psock_set_prog(&progs->stream_parser, NULL); psock_set_prog(&progs->stream_verdict, NULL); psock_set_prog(&progs->skb_verdict, NULL); } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); static inline bool sk_psock_strp_enabled(struct sk_psock *psock) { if (!psock) return false; return !!psock->saved_data_ready; } #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) /* We only have two bits so far. */ #define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) static inline bool skb_bpf_strparser(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return sk_redir & BPF_F_STRPARSER; } static inline void skb_bpf_set_strparser(struct sk_buff *skb) { skb->_sk_redir |= BPF_F_STRPARSER; } static inline bool skb_bpf_ingress(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return sk_redir & BPF_F_INGRESS; } static inline void skb_bpf_set_ingress(struct sk_buff *skb) { skb->_sk_redir |= BPF_F_INGRESS; } static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir, bool ingress) { skb->_sk_redir = (unsigned long)sk_redir; if (ingress) skb->_sk_redir |= BPF_F_INGRESS; } static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return (struct sock *)(sk_redir & BPF_F_PTR_MASK); } static inline void skb_bpf_redirect_clear(struct sk_buff *skb) { skb->_sk_redir = 0; } #endif /* CONFIG_NET_SOCK_MSG */ #endif /* _LINUX_SKMSG_H */ |
| 65 3 65 2 1 1 1 67 67 168 34 34 34 168 166 34 34 168 34 34 1 34 1 34 34 34 69 63 69 34 67 67 66 66 168 168 166 166 166 166 168 167 168 168 168 168 168 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IEEE 802.1D Generic Attribute Registration Protocol (GARP) * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/module.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/garp.h> #include <linux/unaligned.h> static unsigned int garp_join_time __read_mostly = 200; module_param(garp_join_time, uint, 0644); MODULE_PARM_DESC(garp_join_time, "Join time in ms (default 200ms)"); MODULE_DESCRIPTION("IEEE 802.1D Generic Attribute Registration Protocol (GARP)"); MODULE_LICENSE("GPL"); static const struct garp_state_trans { u8 state; u8 action; } garp_applicant_state_table[GARP_APPLICANT_MAX + 1][GARP_EVENT_MAX + 1] = { [GARP_APPLICANT_VA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_AA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_QA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_LA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_VO, .action = GARP_ACTION_S_LEAVE_EMPTY }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_VP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_VO }, }, [GARP_APPLICANT_AP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_AO }, }, [GARP_APPLICANT_QP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_QO }, }, [GARP_APPLICANT_VO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_AO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_QO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, }; static int garp_attr_cmp(const struct garp_attr *attr, const void *data, u8 len, u8 type) { if (attr->type != type) return attr->type - type; if (attr->dlen != len) return attr->dlen - len; return memcmp(attr->data, data, len); } static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = app->gid.rb_node; struct garp_attr *attr; int d; while (parent) { attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) parent = parent->rb_left; else if (d < 0) parent = parent->rb_right; else return attr; } return NULL; } static struct garp_attr *garp_attr_create(struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = NULL, **p = &app->gid.rb_node; struct garp_attr *attr; int d; while (*p) { parent = *p; attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) p = &parent->rb_left; else if (d < 0) p = &parent->rb_right; else { /* The attribute already exists; re-use it. */ return attr; } } attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); if (!attr) return attr; attr->state = GARP_APPLICANT_VO; attr->type = type; attr->dlen = len; memcpy(attr->data, data, len); rb_link_node(&attr->node, parent, p); rb_insert_color(&attr->node, &app->gid); return attr; } static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr) { rb_erase(&attr->node, &app->gid); kfree(attr); } static void garp_attr_destroy_all(struct garp_applicant *app) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_destroy(app, attr); } } static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; struct garp_pdu_hdr *gp; #define LLC_RESERVE sizeof(struct llc_pdu_un) skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), GFP_ATOMIC); if (!skb) return -ENOMEM; skb->dev = app->dev; skb->protocol = htons(ETH_P_802_2); skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE); gp = __skb_put(skb, sizeof(*gp)); put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol); app->pdu = skb; return 0; } static int garp_pdu_append_end_mark(struct garp_applicant *app) { if (skb_tailroom(app->pdu) < sizeof(u8)) return -1; __skb_put_u8(app->pdu, GARP_END_MARK); return 0; } static void garp_pdu_queue(struct garp_applicant *app) { if (!app->pdu) return; garp_pdu_append_end_mark(app); garp_pdu_append_end_mark(app); llc_pdu_header_init(app->pdu, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(app->pdu); llc_mac_hdr_init(app->pdu, app->dev->dev_addr, app->app->proto.group_address); skb_queue_tail(&app->queue, app->pdu); app->pdu = NULL; } static void garp_queue_xmit(struct garp_applicant *app) { struct sk_buff *skb; while ((skb = skb_dequeue(&app->queue))) dev_queue_xmit(skb); } static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype) { struct garp_msg_hdr *gm; if (skb_tailroom(app->pdu) < sizeof(*gm)) return -1; gm = __skb_put(app->pdu, sizeof(*gm)); gm->attrtype = attrtype; garp_cb(app->pdu)->cur_type = attrtype; return 0; } static int garp_pdu_append_attr(struct garp_applicant *app, const struct garp_attr *attr, enum garp_attr_event event) { struct garp_attr_hdr *ga; unsigned int len; int err; again: if (!app->pdu) { err = garp_pdu_init(app); if (err < 0) return err; } if (garp_cb(app->pdu)->cur_type != attr->type) { if (garp_cb(app->pdu)->cur_type && garp_pdu_append_end_mark(app) < 0) goto queue; if (garp_pdu_append_msg(app, attr->type) < 0) goto queue; } len = sizeof(*ga) + attr->dlen; if (skb_tailroom(app->pdu) < len) goto queue; ga = __skb_put(app->pdu, len); ga->len = len; ga->event = event; memcpy(ga->data, attr->data, attr->dlen); return 0; queue: garp_pdu_queue(app); goto again; } static void garp_attr_event(struct garp_applicant *app, struct garp_attr *attr, enum garp_event event) { enum garp_applicant_state state; state = garp_applicant_state_table[attr->state][event].state; if (state == GARP_APPLICANT_INVALID) return; switch (garp_applicant_state_table[attr->state][event].action) { case GARP_ACTION_NONE: break; case GARP_ACTION_S_JOIN_IN: /* When appending the attribute fails, don't update state in * order to retry on next TRANSMIT_PDU event. */ if (garp_pdu_append_attr(app, attr, GARP_JOIN_IN) < 0) return; break; case GARP_ACTION_S_LEAVE_EMPTY: garp_pdu_append_attr(app, attr, GARP_LEAVE_EMPTY); /* As a pure applicant, sending a leave message implies that * the attribute was unregistered and can be destroyed. */ garp_attr_destroy(app, attr); return; default: WARN_ON(1); } attr->state = state; } int garp_request_join(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_create(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return -ENOMEM; } garp_attr_event(app, attr, GARP_EVENT_REQ_JOIN); spin_unlock_bh(&app->lock); return 0; } EXPORT_SYMBOL_GPL(garp_request_join); void garp_request_leave(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_lookup(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return; } garp_attr_event(app, attr, GARP_EVENT_REQ_LEAVE); spin_unlock_bh(&app->lock); } EXPORT_SYMBOL_GPL(garp_request_leave); static void garp_gid_event(struct garp_applicant *app, enum garp_event event) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_event(app, attr, event); } } static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; delay = get_random_u32_below(msecs_to_jiffies(garp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } static void garp_join_timer(struct timer_list *t) { struct garp_applicant *app = from_timer(app, t, join_timer); spin_lock(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_pdu_queue(app); spin_unlock(&app->lock); garp_queue_xmit(app); garp_join_timer_arm(app); } static int garp_pdu_parse_end_mark(struct sk_buff *skb) { if (!pskb_may_pull(skb, sizeof(u8))) return -1; if (*skb->data == GARP_END_MARK) { skb_pull(skb, sizeof(u8)); return -1; } return 0; } static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb, u8 attrtype) { const struct garp_attr_hdr *ga; struct garp_attr *attr; enum garp_event event; unsigned int dlen; if (!pskb_may_pull(skb, sizeof(*ga))) return -1; ga = (struct garp_attr_hdr *)skb->data; if (ga->len < sizeof(*ga)) return -1; if (!pskb_may_pull(skb, ga->len)) return -1; skb_pull(skb, ga->len); dlen = sizeof(*ga) - ga->len; if (attrtype > app->app->maxattr) return 0; switch (ga->event) { case GARP_LEAVE_ALL: if (dlen != 0) return -1; garp_gid_event(app, GARP_EVENT_R_LEAVE_EMPTY); return 0; case GARP_JOIN_EMPTY: event = GARP_EVENT_R_JOIN_EMPTY; break; case GARP_JOIN_IN: event = GARP_EVENT_R_JOIN_IN; break; case GARP_LEAVE_EMPTY: event = GARP_EVENT_R_LEAVE_EMPTY; break; case GARP_EMPTY: event = GARP_EVENT_R_EMPTY; break; default: return 0; } if (dlen == 0) return -1; attr = garp_attr_lookup(app, ga->data, dlen, attrtype); if (attr == NULL) return 0; garp_attr_event(app, attr, event); return 0; } static int garp_pdu_parse_msg(struct garp_applicant *app, struct sk_buff *skb) { const struct garp_msg_hdr *gm; if (!pskb_may_pull(skb, sizeof(*gm))) return -1; gm = (struct garp_msg_hdr *)skb->data; if (gm->attrtype == 0) return -1; skb_pull(skb, sizeof(*gm)); while (skb->len > 0) { if (garp_pdu_parse_attr(app, skb, gm->attrtype) < 0) return -1; if (garp_pdu_parse_end_mark(skb) < 0) break; } return 0; } static void garp_pdu_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct garp_application *appl = proto->data; struct garp_port *port; struct garp_applicant *app; const struct garp_pdu_hdr *gp; port = rcu_dereference(dev->garp_port); if (!port) goto err; app = rcu_dereference(port->applicants[appl->type]); if (!app) goto err; if (!pskb_may_pull(skb, sizeof(*gp))) goto err; gp = (struct garp_pdu_hdr *)skb->data; if (get_unaligned(&gp->protocol) != htons(GARP_PROTOCOL_ID)) goto err; skb_pull(skb, sizeof(*gp)); spin_lock(&app->lock); while (skb->len > 0) { if (garp_pdu_parse_msg(app, skb) < 0) break; if (garp_pdu_parse_end_mark(skb) < 0) break; } spin_unlock(&app->lock); err: kfree_skb(skb); } static int garp_init_port(struct net_device *dev) { struct garp_port *port; port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; rcu_assign_pointer(dev->garp_port, port); return 0; } static void garp_release_port(struct net_device *dev) { struct garp_port *port = rtnl_dereference(dev->garp_port); unsigned int i; for (i = 0; i <= GARP_APPLICATION_MAX; i++) { if (rtnl_dereference(port->applicants[i])) return; } RCU_INIT_POINTER(dev->garp_port, NULL); kfree_rcu(port, rcu); } int garp_init_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_applicant *app; int err; ASSERT_RTNL(); if (!rtnl_dereference(dev->garp_port)) { err = garp_init_port(dev); if (err < 0) goto err1; } err = -ENOMEM; app = kzalloc(sizeof(*app), GFP_KERNEL); if (!app) goto err2; err = dev_mc_add(dev, appl->proto.group_address); if (err < 0) goto err3; app->dev = dev; app->app = appl; app->gid = RB_ROOT; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->garp_port->applicants[appl->type], app); timer_setup(&app->join_timer, garp_join_timer, 0); garp_join_timer_arm(app); return 0; err3: kfree(app); err2: garp_release_port(dev); err1: return err; } EXPORT_SYMBOL_GPL(garp_init_applicant); void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); ASSERT_RTNL(); RCU_INIT_POINTER(port->applicants[appl->type], NULL); /* Delete timer and generate a final TRANSMIT_PDU event to flush out * all pending messages before the applicant is gone. */ timer_shutdown_sync(&app->join_timer); spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); garp_queue_xmit(app); dev_mc_del(dev, appl->proto.group_address); kfree_rcu(app, rcu); garp_release_port(dev); } EXPORT_SYMBOL_GPL(garp_uninit_applicant); int garp_register_application(struct garp_application *appl) { appl->proto.rcv = garp_pdu_rcv; appl->proto.data = appl; return stp_proto_register(&appl->proto); } EXPORT_SYMBOL_GPL(garp_register_application); void garp_unregister_application(struct garp_application *appl) { stp_proto_unregister(&appl->proto); } EXPORT_SYMBOL_GPL(garp_unregister_application); |
| 26 5 12 35 35 35 35 38 35 40 1 1 38 36 1 35 35 639 9 639 773 770 645 10 530 609 12 57 202 771 531 104 11 63 10 61 374 1 6 183 122 4 113 179 9 5 563 1 44 48 2 2 360 303 161 103 139 14 94 23 38 92 38 56 3 111 110 194 13 6 4 128 50 65 15 25 16 7 125 10 124 124 115 19 121 9 124 13 119 94 8 49 46 91 106 21 112 27 112 29 124 124 123 124 124 100 115 19 121 9 100 94 100 3 2 159 7 1 133 134 30 160 160 144 14 148 10 144 14 150 8 150 8 83 81 4 70 4 70 4 18 3 19 41 3 71 3 71 93 18 109 106 2 2 37 72 16 3 13 7 5 8 2 2 9 11 9 2 7 4 2 3 3 4 1 1 2 1 1 4 63 67 62 22 62 62 171 171 86 72 34 38 41 34 72 7 1 2 4 4 12 1 2 9 6 18 18 18 18 18 18 27 1 1 25 18 106 106 36 53 53 44 39 3 19 35 35 26 55 55 60 1 59 37 2 2 7 1 1 5 1 1 6 6 2 31 30 6 8 8 6 16 34 1 21 2 32 178 178 178 178 178 178 178 178 64 127 163 7 77 80 60 7 7 163 133 2 2 130 59 2 1 1 55 21 34 55 17 38 12 43 19 36 54 1 55 14 44 27 2 1 25 19 6 25 19 6 2 23 25 12 2 10 9 6 1 1 1 7 2 1 1 2 4 3 1 4 1 3 1 3 1 5 3 1 1 48 8 46 15 33 27 50 51 50 50 43 54 46 40 612 2 26 3 2 4 17 19 17 17 17 19 19 7 7 7 17 17 17 19 19 6 6 6 4 226 126 84 84 36 178 179 135 133 1 43 60 55 7 54 22 17 19 54 54 54 54 22 17 19 54 95 29 8 42 16 2 2 2 2 63 10 1 2 15 15 2 13 13 16 14 2 16 16 16 15 15 5 15 2 6 624 1 1 622 35 612 374 1 275 8 1 2 1 7 7 1 7 7 7 6 2 6 6 6 6 502 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/key/af_key.c An implementation of PF_KEYv2 sockets. * * Authors: Maxim Giryaev <gem@asplinux.ru> * David S. Miller <davem@redhat.com> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * Kazunori MIYAZAWA / USAGI Project <miyazawa@linux-ipv6.org> * Derek Atkins <derek@ihtfp.com> */ #include <linux/capability.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/socket.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/xfrm.h> #include <net/sock.h> #define _X2KEY(x) ((x) == XFRM_INF ? 0 : (x)) #define _KEY2X(x) ((x) == 0 ? XFRM_INF : (x)) static unsigned int pfkey_net_id __read_mostly; struct netns_pfkey { /* List of all pfkey sockets. */ struct hlist_head table; atomic_t socks_nr; }; static DEFINE_MUTEX(pfkey_mutex); #define DUMMY_MARK 0 static const struct xfrm_mark dummy_mark = {0, 0}; struct pfkey_sock { /* struct sock must be the first member of struct pfkey_sock */ struct sock sk; int registered; int promisc; struct { uint8_t msg_version; uint32_t msg_portid; int (*dump)(struct pfkey_sock *sk); void (*done)(struct pfkey_sock *sk); union { struct xfrm_policy_walk policy; struct xfrm_state_walk state; } u; struct sk_buff *skb; } dump; struct mutex dump_lock; }; static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, xfrm_address_t *saddr, xfrm_address_t *daddr, u16 *family); static inline struct pfkey_sock *pfkey_sk(struct sock *sk) { return (struct pfkey_sock *)sk; } static int pfkey_can_dump(const struct sock *sk) { if (3 * atomic_read(&sk->sk_rmem_alloc) <= 2 * sk->sk_rcvbuf) return 1; return 0; } static void pfkey_terminate_dump(struct pfkey_sock *pfk) { if (pfk->dump.dump) { if (pfk->dump.skb) { kfree_skb(pfk->dump.skb); pfk->dump.skb = NULL; } pfk->dump.done(pfk); pfk->dump.dump = NULL; pfk->dump.done = NULL; } } static void pfkey_sock_destruct(struct sock *sk) { struct net *net = sock_net(sk); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_terminate_dump(pfkey_sk(sk)); skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive pfkey socket: %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); atomic_dec(&net_pfkey->socks_nr); } static const struct proto_ops pfkey_ops; static void pfkey_insert(struct sock *sk) { struct net *net = sock_net(sk); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); mutex_lock(&pfkey_mutex); sk_add_node_rcu(sk, &net_pfkey->table); mutex_unlock(&pfkey_mutex); } static void pfkey_remove(struct sock *sk) { mutex_lock(&pfkey_mutex); sk_del_node_init_rcu(sk); mutex_unlock(&pfkey_mutex); } static struct proto key_proto = { .name = "KEY", .owner = THIS_MODULE, .obj_size = sizeof(struct pfkey_sock), }; static int pfkey_create(struct net *net, struct socket *sock, int protocol, int kern) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; struct pfkey_sock *pfk; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (protocol != PF_KEY_V2) return -EPROTONOSUPPORT; sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern); if (sk == NULL) return -ENOMEM; pfk = pfkey_sk(sk); mutex_init(&pfk->dump_lock); sock->ops = &pfkey_ops; sock_init_data(sock, sk); sk->sk_family = PF_KEY; sk->sk_destruct = pfkey_sock_destruct; atomic_inc(&net_pfkey->socks_nr); pfkey_insert(sk); return 0; } static int pfkey_release(struct socket *sock) { struct sock *sk = sock->sk; if (!sk) return 0; pfkey_remove(sk); sock_orphan(sk); sock->sk = NULL; skb_queue_purge(&sk->sk_write_queue); synchronize_rcu(); sock_put(sk); return 0; } static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, struct sock *sk) { int err = -ENOBUFS; if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) return err; skb = skb_clone(skb, allocation); if (skb) { skb_set_owner_r(skb, sk); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); err = 0; } return err; } /* Send SKB to all pfkey sockets matching selected criteria. */ #define BROADCAST_ALL 0 #define BROADCAST_ONE 1 #define BROADCAST_REGISTERED 2 #define BROADCAST_PROMISC_ONLY 4 static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, int broadcast_flags, struct sock *one_sk, struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think * XXX PF_KEY socket apps will not mind current behavior. */ if (!skb) return -ENOMEM; rcu_read_lock(); sk_for_each_rcu(sk, &net_pfkey->table) { struct pfkey_sock *pfk = pfkey_sk(sk); int err2; /* Yes, it means that if you are meant to receive this * pfkey message you receive it twice as promiscuous * socket. */ if (pfk->promisc) pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) continue; if (broadcast_flags != BROADCAST_ALL) { if (broadcast_flags & BROADCAST_PROMISC_ONLY) continue; if ((broadcast_flags & BROADCAST_REGISTERED) && !pfk->registered) continue; if (broadcast_flags & BROADCAST_ONE) continue; } err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ if ((broadcast_flags & BROADCAST_REGISTERED) && err) err = err2; } rcu_read_unlock(); if (one_sk != NULL) err = pfkey_broadcast_one(skb, allocation, one_sk); kfree_skb(skb); return err; } static int pfkey_do_dump(struct pfkey_sock *pfk) { struct sadb_msg *hdr; int rc; mutex_lock(&pfk->dump_lock); if (!pfk->dump.dump) { rc = 0; goto out; } rc = pfk->dump.dump(pfk); if (rc == -ENOBUFS) { rc = 0; goto out; } if (pfk->dump.skb) { if (!pfkey_can_dump(&pfk->sk)) { rc = 0; goto out; } hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; hdr->sadb_msg_errno = rc; pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = NULL; } pfkey_terminate_dump(pfk); out: mutex_unlock(&pfk->dump_lock); return rc; } static inline void pfkey_hdr_dup(struct sadb_msg *new, const struct sadb_msg *orig) { *new = *orig; } static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) { struct sk_buff *skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); struct sadb_msg *hdr; if (!skb) return -ENOBUFS; /* Woe be to the platform trying to support PFKEY yet * having normal errnos outside the 1-255 range, inclusive. */ err = -err; if (err == ERESTARTSYS || err == ERESTARTNOHAND || err == ERESTARTNOINTR) err = EINTR; if (err >= 512) err = EINVAL; BUG_ON(err <= 0 || err >= 256); hdr = skb_put(skb, sizeof(struct sadb_msg)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = (uint8_t) err; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk)); return 0; } static const u8 sadb_ext_min_len[] = { [SADB_EXT_RESERVED] = (u8) 0, [SADB_EXT_SA] = (u8) sizeof(struct sadb_sa), [SADB_EXT_LIFETIME_CURRENT] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_LIFETIME_HARD] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_LIFETIME_SOFT] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_ADDRESS_SRC] = (u8) sizeof(struct sadb_address), [SADB_EXT_ADDRESS_DST] = (u8) sizeof(struct sadb_address), [SADB_EXT_ADDRESS_PROXY] = (u8) sizeof(struct sadb_address), [SADB_EXT_KEY_AUTH] = (u8) sizeof(struct sadb_key), [SADB_EXT_KEY_ENCRYPT] = (u8) sizeof(struct sadb_key), [SADB_EXT_IDENTITY_SRC] = (u8) sizeof(struct sadb_ident), [SADB_EXT_IDENTITY_DST] = (u8) sizeof(struct sadb_ident), [SADB_EXT_SENSITIVITY] = (u8) sizeof(struct sadb_sens), [SADB_EXT_PROPOSAL] = (u8) sizeof(struct sadb_prop), [SADB_EXT_SUPPORTED_AUTH] = (u8) sizeof(struct sadb_supported), [SADB_EXT_SUPPORTED_ENCRYPT] = (u8) sizeof(struct sadb_supported), [SADB_EXT_SPIRANGE] = (u8) sizeof(struct sadb_spirange), [SADB_X_EXT_KMPRIVATE] = (u8) sizeof(struct sadb_x_kmprivate), [SADB_X_EXT_POLICY] = (u8) sizeof(struct sadb_x_policy), [SADB_X_EXT_SA2] = (u8) sizeof(struct sadb_x_sa2), [SADB_X_EXT_NAT_T_TYPE] = (u8) sizeof(struct sadb_x_nat_t_type), [SADB_X_EXT_NAT_T_SPORT] = (u8) sizeof(struct sadb_x_nat_t_port), [SADB_X_EXT_NAT_T_DPORT] = (u8) sizeof(struct sadb_x_nat_t_port), [SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address), [SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx), [SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress), [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter), }; /* Verify sadb_address_{len,prefixlen} against sa_family. */ static int verify_address_len(const void *p) { const struct sadb_address *sp = p; const struct sockaddr *addr = (const struct sockaddr *)(sp + 1); const struct sockaddr_in *sin; #if IS_ENABLED(CONFIG_IPV6) const struct sockaddr_in6 *sin6; #endif int len; if (sp->sadb_address_len < DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family), sizeof(uint64_t))) return -EINVAL; switch (addr->sa_family) { case AF_INET: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t)); if (sp->sadb_address_len != len || sp->sadb_address_prefixlen > 32) return -EINVAL; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin6), sizeof(uint64_t)); if (sp->sadb_address_len != len || sp->sadb_address_prefixlen > 128) return -EINVAL; break; #endif default: /* It is user using kernel to keep track of security * associations for another protocol, such as * OSPF/RSVP/RIPV2/MIP. It is user's job to verify * lengths. * * XXX Actually, association/policy database is not yet * XXX able to cope with arbitrary sockaddr families. * XXX When it can, remove this -EINVAL. -DaveM */ return -EINVAL; } return 0; } static inline int sadb_key_len(const struct sadb_key *key) { int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8); return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes, sizeof(uint64_t)); } static int verify_key_len(const void *p) { const struct sadb_key *key = p; if (sadb_key_len(key) > key->sadb_key_len) return -EINVAL; return 0; } static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx) { return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) + sec_ctx->sadb_x_ctx_len, sizeof(uint64_t)); } static inline int verify_sec_ctx_len(const void *p) { const struct sadb_x_sec_ctx *sec_ctx = p; int len = sec_ctx->sadb_x_ctx_len; if (len > PAGE_SIZE) return -EINVAL; len = pfkey_sec_ctx_len(sec_ctx); if (sec_ctx->sadb_x_sec_len != len) return -EINVAL; return 0; } static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx, gfp_t gfp) { struct xfrm_user_sec_ctx *uctx = NULL; int ctx_size = sec_ctx->sadb_x_ctx_len; uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp); if (!uctx) return NULL; uctx->len = pfkey_sec_ctx_len(sec_ctx); uctx->exttype = sec_ctx->sadb_x_sec_exttype; uctx->ctx_doi = sec_ctx->sadb_x_ctx_doi; uctx->ctx_alg = sec_ctx->sadb_x_ctx_alg; uctx->ctx_len = sec_ctx->sadb_x_ctx_len; memcpy(uctx + 1, sec_ctx + 1, uctx->ctx_len); return uctx; } static int present_and_same_family(const struct sadb_address *src, const struct sadb_address *dst) { const struct sockaddr *s_addr, *d_addr; if (!src || !dst) return 0; s_addr = (const struct sockaddr *)(src + 1); d_addr = (const struct sockaddr *)(dst + 1); if (s_addr->sa_family != d_addr->sa_family) return 0; if (s_addr->sa_family != AF_INET #if IS_ENABLED(CONFIG_IPV6) && s_addr->sa_family != AF_INET6 #endif ) return 0; return 1; } static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void **ext_hdrs) { const char *p = (char *) hdr; int len = skb->len; len -= sizeof(*hdr); p += sizeof(*hdr); while (len > 0) { const struct sadb_ext *ehdr = (const struct sadb_ext *) p; uint16_t ext_type; int ext_len; if (len < sizeof(*ehdr)) return -EINVAL; ext_len = ehdr->sadb_ext_len; ext_len *= sizeof(uint64_t); ext_type = ehdr->sadb_ext_type; if (ext_len < sizeof(uint64_t) || ext_len > len || ext_type == SADB_EXT_RESERVED) return -EINVAL; if (ext_type <= SADB_EXT_MAX) { int min = (int) sadb_ext_min_len[ext_type]; if (ext_len < min) return -EINVAL; if (ext_hdrs[ext_type-1] != NULL) return -EINVAL; switch (ext_type) { case SADB_EXT_ADDRESS_SRC: case SADB_EXT_ADDRESS_DST: case SADB_EXT_ADDRESS_PROXY: case SADB_X_EXT_NAT_T_OA: if (verify_address_len(p)) return -EINVAL; break; case SADB_X_EXT_SEC_CTX: if (verify_sec_ctx_len(p)) return -EINVAL; break; case SADB_EXT_KEY_AUTH: case SADB_EXT_KEY_ENCRYPT: if (verify_key_len(p)) return -EINVAL; break; default: break; } ext_hdrs[ext_type-1] = (void *) p; } p += ext_len; len -= ext_len; } return 0; } static uint16_t pfkey_satype2proto(uint8_t satype) { switch (satype) { case SADB_SATYPE_UNSPEC: return IPSEC_PROTO_ANY; case SADB_SATYPE_AH: return IPPROTO_AH; case SADB_SATYPE_ESP: return IPPROTO_ESP; case SADB_X_SATYPE_IPCOMP: return IPPROTO_COMP; default: return 0; } /* NOTREACHED */ } static uint8_t pfkey_proto2satype(uint16_t proto) { switch (proto) { case IPPROTO_AH: return SADB_SATYPE_AH; case IPPROTO_ESP: return SADB_SATYPE_ESP; case IPPROTO_COMP: return SADB_X_SATYPE_IPCOMP; default: return 0; } /* NOTREACHED */ } /* BTW, this scheme means that there is no way with PFKEY2 sockets to * say specifically 'just raw sockets' as we encode them as 255. */ static uint8_t pfkey_proto_to_xfrm(uint8_t proto) { return proto == IPSEC_PROTO_ANY ? 0 : proto; } static uint8_t pfkey_proto_from_xfrm(uint8_t proto) { return proto ? proto : IPSEC_PROTO_ANY; } static inline int pfkey_sockaddr_len(sa_family_t family) { switch (family) { case AF_INET: return sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return sizeof(struct sockaddr_in6); #endif } return 0; } static int pfkey_sockaddr_extract(const struct sockaddr *sa, xfrm_address_t *xaddr) { switch (sa->sa_family) { case AF_INET: xaddr->a4 = ((struct sockaddr_in *)sa)->sin_addr.s_addr; return AF_INET; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: memcpy(xaddr->a6, &((struct sockaddr_in6 *)sa)->sin6_addr, sizeof(struct in6_addr)); return AF_INET6; #endif } return 0; } static int pfkey_sadb_addr2xfrm_addr(const struct sadb_address *addr, xfrm_address_t *xaddr) { return pfkey_sockaddr_extract((struct sockaddr *)(addr + 1), xaddr); } static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs) { const struct sadb_sa *sa; const struct sadb_address *addr; uint16_t proto; unsigned short family; xfrm_address_t *xaddr; sa = ext_hdrs[SADB_EXT_SA - 1]; if (sa == NULL) return NULL; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return NULL; /* sadb_address_len should be checked by caller */ addr = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; if (addr == NULL) return NULL; family = ((const struct sockaddr *)(addr + 1))->sa_family; switch (family) { case AF_INET: xaddr = (xfrm_address_t *)&((const struct sockaddr_in *)(addr + 1))->sin_addr; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: xaddr = (xfrm_address_t *)&((const struct sockaddr_in6 *)(addr + 1))->sin6_addr; break; #endif default: xaddr = NULL; } if (!xaddr) return NULL; return xfrm_state_lookup(net, DUMMY_MARK, xaddr, sa->sadb_sa_spi, proto, family); } #define PFKEY_ALIGN8(a) (1 + (((a) - 1) | (8 - 1))) static int pfkey_sockaddr_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family)); } static inline int pfkey_mode_from_xfrm(int mode) { switch(mode) { case XFRM_MODE_TRANSPORT: return IPSEC_MODE_TRANSPORT; case XFRM_MODE_TUNNEL: return IPSEC_MODE_TUNNEL; case XFRM_MODE_BEET: return IPSEC_MODE_BEET; default: return -1; } } static inline int pfkey_mode_to_xfrm(int mode) { switch(mode) { case IPSEC_MODE_ANY: /*XXX*/ case IPSEC_MODE_TRANSPORT: return XFRM_MODE_TRANSPORT; case IPSEC_MODE_TUNNEL: return XFRM_MODE_TUNNEL; case IPSEC_MODE_BEET: return XFRM_MODE_BEET; default: return -1; } } static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port, struct sockaddr *sa, unsigned short family) { switch (family) { case AF_INET: { struct sockaddr_in *sin = (struct sockaddr_in *)sa; sin->sin_family = AF_INET; sin->sin_port = port; sin->sin_addr.s_addr = xaddr->a4; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return 32; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa; sin6->sin6_family = AF_INET6; sin6->sin6_port = port; sin6->sin6_flowinfo = 0; sin6->sin6_addr = xaddr->in6; sin6->sin6_scope_id = 0; return 128; } #endif } return 0; } static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, int add_keys, int hsc) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_sa *sa; struct sadb_lifetime *lifetime; struct sadb_address *addr; struct sadb_key *key; struct sadb_x_sa2 *sa2; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; int size; int auth_key_size = 0; int encrypt_key_size = 0; int sockaddr_size; struct xfrm_encap_tmpl *natt = NULL; int mode; /* address family check */ sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return ERR_PTR(-EINVAL); /* base, SA, (lifetime (HSC),) address(SD), (address(P),) key(AE), (identity(SD),) (sensitivity)> */ size = sizeof(struct sadb_msg) +sizeof(struct sadb_sa) + sizeof(struct sadb_lifetime) + ((hsc & 1) ? sizeof(struct sadb_lifetime) : 0) + ((hsc & 2) ? sizeof(struct sadb_lifetime) : 0) + sizeof(struct sadb_address)*2 + sockaddr_size*2 + sizeof(struct sadb_x_sa2); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } /* identity & sensitivity */ if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) size += sizeof(struct sadb_address) + sockaddr_size; if (add_keys) { if (x->aalg && x->aalg->alg_key_len) { auth_key_size = PFKEY_ALIGN8((x->aalg->alg_key_len + 7) / 8); size += sizeof(struct sadb_key) + auth_key_size; } if (x->ealg && x->ealg->alg_key_len) { encrypt_key_size = PFKEY_ALIGN8((x->ealg->alg_key_len+7) / 8); size += sizeof(struct sadb_key) + encrypt_key_size; } } if (x->encap) natt = x->encap; if (natt && natt->encap_type) { size += sizeof(struct sadb_x_nat_t_type); size += sizeof(struct sadb_x_nat_t_port); size += sizeof(struct sadb_x_nat_t_port); } skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return ERR_PTR(-ENOBUFS); /* call should fill header later */ hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ hdr->sadb_msg_len = size / sizeof(uint64_t); /* sa */ sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = x->props.replay_window; switch (x->km.state) { case XFRM_STATE_VALID: sa->sadb_sa_state = x->km.dying ? SADB_SASTATE_DYING : SADB_SASTATE_MATURE; break; case XFRM_STATE_ACQ: sa->sadb_sa_state = SADB_SASTATE_LARVAL; break; default: sa->sadb_sa_state = SADB_SASTATE_DEAD; break; } sa->sadb_sa_auth = 0; if (x->aalg) { struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0); sa->sadb_sa_auth = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } sa->sadb_sa_encrypt = 0; BUG_ON(x->ealg && x->calg); if (x->ealg) { struct xfrm_algo_desc *a = xfrm_ealg_get_byname(x->ealg->alg_name, 0); sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } /* KAME compatible: sadb_sa_encrypt is overloaded with calg id */ if (x->calg) { struct xfrm_algo_desc *a = xfrm_calg_get_byname(x->calg->alg_name, 0); sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } sa->sadb_sa_flags = 0; if (x->props.flags & XFRM_STATE_NOECN) sa->sadb_sa_flags |= SADB_SAFLAGS_NOECN; if (x->props.flags & XFRM_STATE_DECAP_DSCP) sa->sadb_sa_flags |= SADB_SAFLAGS_DECAP_DSCP; if (x->props.flags & XFRM_STATE_NOPMTUDISC) sa->sadb_sa_flags |= SADB_SAFLAGS_NOPMTUDISC; /* hard time */ if (hsc & 2) { lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.hard_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.hard_byte_limit); lifetime->sadb_lifetime_addtime = x->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = x->lft.hard_use_expires_seconds; } /* soft time */ if (hsc & 1) { lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.soft_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.soft_byte_limit); lifetime->sadb_lifetime_addtime = x->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = x->lft.soft_use_expires_seconds; } /* current time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; lifetime->sadb_lifetime_allocations = x->curlft.packets; lifetime->sadb_lifetime_bytes = x->curlft.bytes; lifetime->sadb_lifetime_addtime = x->curlft.add_time; lifetime->sadb_lifetime_usetime = x->curlft.use_time; /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; /* "if the ports are non-zero, then the sadb_address_proto field, normally zero, MUST be filled in with the transport protocol's number." - RFC2367 */ addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); BUG_ON(!addr->sadb_address_prefixlen); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); BUG_ON(!addr->sadb_address_prefixlen); if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_PROXY; addr->sadb_address_proto = pfkey_proto_from_xfrm(x->sel.proto); addr->sadb_address_prefixlen = x->sel.prefixlen_s; addr->sadb_address_reserved = 0; pfkey_sockaddr_fill(&x->sel.saddr, x->sel.sport, (struct sockaddr *) (addr + 1), x->props.family); } /* auth key */ if (add_keys && auth_key_size) { key = skb_put(skb, sizeof(struct sadb_key) + auth_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + auth_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_AUTH; key->sadb_key_bits = x->aalg->alg_key_len; key->sadb_key_reserved = 0; memcpy(key + 1, x->aalg->alg_key, (x->aalg->alg_key_len+7)/8); } /* encrypt key */ if (add_keys && encrypt_key_size) { key = skb_put(skb, sizeof(struct sadb_key) + encrypt_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + encrypt_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_ENCRYPT; key->sadb_key_bits = x->ealg->alg_key_len; key->sadb_key_reserved = 0; memcpy(key + 1, x->ealg->alg_key, (x->ealg->alg_key_len+7)/8); } /* sa */ sa2 = skb_put(skb, sizeof(struct sadb_x_sa2)); sa2->sadb_x_sa2_len = sizeof(struct sadb_x_sa2)/sizeof(uint64_t); sa2->sadb_x_sa2_exttype = SADB_X_EXT_SA2; if ((mode = pfkey_mode_from_xfrm(x->props.mode)) < 0) { kfree_skb(skb); return ERR_PTR(-EINVAL); } sa2->sadb_x_sa2_mode = mode; sa2->sadb_x_sa2_reserved1 = 0; sa2->sadb_x_sa2_reserved2 = 0; sa2->sadb_x_sa2_sequence = 0; sa2->sadb_x_sa2_reqid = x->props.reqid; if (natt && natt->encap_type) { struct sadb_x_nat_t_type *n_type; struct sadb_x_nat_t_port *n_port; /* type */ n_type = skb_put(skb, sizeof(*n_type)); n_type->sadb_x_nat_t_type_len = sizeof(*n_type)/sizeof(uint64_t); n_type->sadb_x_nat_t_type_exttype = SADB_X_EXT_NAT_T_TYPE; n_type->sadb_x_nat_t_type_type = natt->encap_type; n_type->sadb_x_nat_t_type_reserved[0] = 0; n_type->sadb_x_nat_t_type_reserved[1] = 0; n_type->sadb_x_nat_t_type_reserved[2] = 0; /* source port */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* dest port */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = natt->encap_dport; n_port->sadb_x_nat_t_port_reserved = 0; } /* security context */ if (xfrm_ctx) { sec_ctx = skb_put(skb, sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } return skb; } static inline struct sk_buff *pfkey_xfrm_state2msg(const struct xfrm_state *x) { struct sk_buff *skb; skb = __pfkey_xfrm_state2msg(x, 1, 3); return skb; } static inline struct sk_buff *pfkey_xfrm_state2msg_expire(const struct xfrm_state *x, int hsc) { return __pfkey_xfrm_state2msg(x, 0, hsc); } static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct xfrm_state *x; const struct sadb_lifetime *lifetime; const struct sadb_sa *sa; const struct sadb_key *key; const struct sadb_x_sec_ctx *sec_ctx; uint16_t proto; int err; sa = ext_hdrs[SADB_EXT_SA - 1]; if (!sa || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return ERR_PTR(-EINVAL); if (hdr->sadb_msg_satype == SADB_SATYPE_ESP && !ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]) return ERR_PTR(-EINVAL); if (hdr->sadb_msg_satype == SADB_SATYPE_AH && !ext_hdrs[SADB_EXT_KEY_AUTH-1]) return ERR_PTR(-EINVAL); if (!!ext_hdrs[SADB_EXT_LIFETIME_HARD-1] != !!ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]) return ERR_PTR(-EINVAL); proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return ERR_PTR(-EINVAL); /* default error is no buffer space */ err = -ENOBUFS; /* RFC2367: Only SADB_SASTATE_MATURE SAs may be submitted in an SADB_ADD message. SADB_SASTATE_LARVAL SAs are created by SADB_GETSPI and it is not sensible to add a new SA in the DYING or SADB_SASTATE_DEAD state. Therefore, the sadb_sa_state field of all submitted SAs MUST be SADB_SASTATE_MATURE and the kernel MUST return an error if this is not true. However, KAME setkey always uses SADB_SASTATE_LARVAL. Hence, we have to _ignore_ sadb_sa_state, which is also reasonable. */ if (sa->sadb_sa_auth > SADB_AALG_MAX || (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP && sa->sadb_sa_encrypt > SADB_X_CALG_MAX) || sa->sadb_sa_encrypt > SADB_EALG_MAX) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key != NULL && sa->sadb_sa_encrypt != SADB_EALG_NULL && key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); x = xfrm_state_alloc(net); if (x == NULL) return ERR_PTR(-ENOBUFS); x->id.proto = proto; x->id.spi = sa->sadb_sa_spi; x->props.replay_window = min_t(unsigned int, sa->sadb_sa_replay, (sizeof(x->replay.bitmap) * 8)); if (sa->sadb_sa_flags & SADB_SAFLAGS_NOECN) x->props.flags |= XFRM_STATE_NOECN; if (sa->sadb_sa_flags & SADB_SAFLAGS_DECAP_DSCP) x->props.flags |= XFRM_STATE_DECAP_DSCP; if (sa->sadb_sa_flags & SADB_SAFLAGS_NOPMTUDISC) x->props.flags |= XFRM_STATE_NOPMTUDISC; lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD - 1]; if (lifetime != NULL) { x->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT - 1]; if (lifetime != NULL) { x->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.soft_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) goto out; err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) goto out; } err = -ENOBUFS; key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (sa->sadb_sa_auth) { int keysize = 0; struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } if (key) keysize = (key->sadb_key_bits + 7) / 8; x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL); if (!x->aalg) { err = -ENOMEM; goto out; } strcpy(x->aalg->alg_name, a->name); x->aalg->alg_key_len = 0; if (key) { x->aalg->alg_key_len = key->sadb_key_bits; memcpy(x->aalg->alg_key, key+1, keysize); } x->aalg->alg_trunc_len = a->uinfo.auth.icv_truncbits; x->props.aalgo = sa->sadb_sa_auth; /* x->algo.flags = sa->sadb_sa_flags; */ } if (sa->sadb_sa_encrypt) { if (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP) { struct xfrm_algo_desc *a = xfrm_calg_get_byid(sa->sadb_sa_encrypt); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL); if (!x->calg) { err = -ENOMEM; goto out; } strcpy(x->calg->alg_name, a->name); x->props.calgo = sa->sadb_sa_encrypt; } else { int keysize = 0; struct xfrm_algo_desc *a = xfrm_ealg_get_byid(sa->sadb_sa_encrypt); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } key = (struct sadb_key*) ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key) keysize = (key->sadb_key_bits + 7) / 8; x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL); if (!x->ealg) { err = -ENOMEM; goto out; } strcpy(x->ealg->alg_name, a->name); x->ealg->alg_key_len = 0; if (key) { x->ealg->alg_key_len = key->sadb_key_bits; memcpy(x->ealg->alg_key, key+1, keysize); } x->props.ealgo = sa->sadb_sa_encrypt; x->geniv = a->uinfo.encr.geniv; } } /* x->algo.flags = sa->sadb_sa_flags; */ x->props.family = pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_SRC-1], &x->props.saddr); pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_DST-1], &x->id.daddr); if (ext_hdrs[SADB_X_EXT_SA2-1]) { const struct sadb_x_sa2 *sa2 = ext_hdrs[SADB_X_EXT_SA2-1]; int mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode); if (mode < 0) { err = -EINVAL; goto out; } x->props.mode = mode; x->props.reqid = sa2->sadb_x_sa2_reqid; } if (ext_hdrs[SADB_EXT_ADDRESS_PROXY-1]) { const struct sadb_address *addr = ext_hdrs[SADB_EXT_ADDRESS_PROXY-1]; /* Nobody uses this, but we try. */ x->sel.family = pfkey_sadb_addr2xfrm_addr(addr, &x->sel.saddr); x->sel.prefixlen_s = addr->sadb_address_prefixlen; } if (!x->sel.family) x->sel.family = x->props.family; if (ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]) { const struct sadb_x_nat_t_type* n_type; struct xfrm_encap_tmpl *natt; x->encap = kzalloc(sizeof(*x->encap), GFP_KERNEL); if (!x->encap) { err = -ENOMEM; goto out; } natt = x->encap; n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]; natt->encap_type = n_type->sadb_x_nat_t_type_type; if (ext_hdrs[SADB_X_EXT_NAT_T_SPORT-1]) { const struct sadb_x_nat_t_port *n_port = ext_hdrs[SADB_X_EXT_NAT_T_SPORT-1]; natt->encap_sport = n_port->sadb_x_nat_t_port_port; } if (ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]) { const struct sadb_x_nat_t_port *n_port = ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]; natt->encap_dport = n_port->sadb_x_nat_t_port_port; } } err = xfrm_init_state(x); if (err) goto out; x->km.seq = hdr->sadb_msg_seq; return x; out: x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); return ERR_PTR(err); } static int pfkey_reserved(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { return -EOPNOTSUPP; } static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct sk_buff *resp_skb; struct sadb_x_sa2 *sa2; struct sadb_address *saddr, *daddr; struct sadb_msg *out_hdr; struct sadb_spirange *range; struct xfrm_state *x = NULL; int mode; int err; u32 min_spi, max_spi; u32 reqid; u8 proto; unsigned short family; xfrm_address_t *xsaddr = NULL, *xdaddr = NULL; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; if ((sa2 = ext_hdrs[SADB_X_EXT_SA2-1]) != NULL) { mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode); if (mode < 0) return -EINVAL; reqid = sa2->sadb_x_sa2_reqid; } else { mode = 0; reqid = 0; } saddr = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; daddr = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; family = ((struct sockaddr *)(saddr + 1))->sa_family; switch (family) { case AF_INET: xdaddr = (xfrm_address_t *)&((struct sockaddr_in *)(daddr + 1))->sin_addr.s_addr; xsaddr = (xfrm_address_t *)&((struct sockaddr_in *)(saddr + 1))->sin_addr.s_addr; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: xdaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(daddr + 1))->sin6_addr; xsaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(saddr + 1))->sin6_addr; break; #endif } if (hdr->sadb_msg_seq) { x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq, UINT_MAX); if (x && !xfrm_addr_equal(&x->id.daddr, xdaddr, family)) { xfrm_state_put(x); x = NULL; } } if (!x) x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, UINT_MAX, proto, xdaddr, xsaddr, 1, family); if (x == NULL) return -ENOENT; min_spi = 0x100; max_spi = 0x0fffffff; range = ext_hdrs[SADB_EXT_SPIRANGE-1]; if (range) { min_spi = range->sadb_spirange_min; max_spi = range->sadb_spirange_max; } err = verify_spi_info(x->id.proto, min_spi, max_spi, NULL); if (err) { xfrm_state_put(x); return err; } err = xfrm_alloc_spi(x, min_spi, max_spi, NULL); resp_skb = err ? ERR_PTR(err) : pfkey_xfrm_state2msg(x); if (IS_ERR(resp_skb)) { xfrm_state_put(x); return PTR_ERR(resp_skb); } out_hdr = (struct sadb_msg *) resp_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = SADB_GETSPI; out_hdr->sadb_msg_satype = pfkey_proto2satype(proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; xfrm_state_put(x); pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net); return 0; } static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; if (hdr->sadb_msg_len != sizeof(struct sadb_msg)/8) return -EOPNOTSUPP; if (hdr->sadb_msg_seq == 0 || hdr->sadb_msg_errno == 0) return 0; x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq, UINT_MAX); if (x == NULL) return 0; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_ACQ) x->km.state = XFRM_STATE_ERROR; spin_unlock_bh(&x->lock); xfrm_state_put(x); return 0; } static inline int event2poltype(int event) { switch (event) { case XFRM_MSG_DELPOLICY: return SADB_X_SPDDELETE; case XFRM_MSG_NEWPOLICY: return SADB_X_SPDADD; case XFRM_MSG_UPDPOLICY: return SADB_X_SPDUPDATE; case XFRM_MSG_POLEXPIRE: // return SADB_X_SPDEXPIRE; default: pr_err("pfkey: Unknown policy event %d\n", event); break; } return 0; } static inline int event2keytype(int event) { switch (event) { case XFRM_MSG_DELSA: return SADB_DELETE; case XFRM_MSG_NEWSA: return SADB_ADD; case XFRM_MSG_UPDSA: return SADB_UPDATE; case XFRM_MSG_EXPIRE: return SADB_EXPIRE; default: pr_err("pfkey: Unknown SA event %d\n", event); break; } return 0; } /* ADD/UPD/DEL */ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; skb = pfkey_xfrm_state2msg(x); if (IS_ERR(skb)) return PTR_ERR(skb); hdr = (struct sadb_msg *) skb->data; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = event2keytype(c->event); hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); return 0; } static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; int err; struct km_event c; x = pfkey_msg2xfrm_state(net, hdr, ext_hdrs); if (IS_ERR(x)) return PTR_ERR(x); xfrm_state_hold(x); if (hdr->sadb_msg_type == SADB_ADD) err = xfrm_state_add(x); else err = xfrm_state_update(x); xfrm_audit_state_add(x, err ? 0 : 1, true); if (err < 0) { x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); goto out; } if (hdr->sadb_msg_type == SADB_ADD) c.event = XFRM_MSG_NEWSA; else c.event = XFRM_MSG_UPDSA; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; km_state_notify(x, &c); out: xfrm_state_put(x); return err; } static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; struct km_event c; int err; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; x = pfkey_xfrm_state_lookup(net, hdr, ext_hdrs); if (x == NULL) return -ESRCH; if ((err = security_xfrm_state_delete(x))) goto out; if (xfrm_state_kern(x)) { err = -EPERM; goto out; } err = xfrm_state_delete(x); if (err < 0) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_DELSA; km_state_notify(x, &c); out: xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; } static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); __u8 proto; struct sk_buff *out_skb; struct sadb_msg *out_hdr; struct xfrm_state *x; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; x = pfkey_xfrm_state_lookup(net, hdr, ext_hdrs); if (x == NULL) return -ESRCH; out_skb = pfkey_xfrm_state2msg(x); proto = x->id.proto; xfrm_state_put(x); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = SADB_GET; out_hdr->sadb_msg_satype = pfkey_proto2satype(proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); return 0; } static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, gfp_t allocation) { struct sk_buff *skb; struct sadb_msg *hdr; int len, auth_len, enc_len, i; auth_len = xfrm_count_pfkey_auth_supported(); if (auth_len) { auth_len *= sizeof(struct sadb_alg); auth_len += sizeof(struct sadb_supported); } enc_len = xfrm_count_pfkey_enc_supported(); if (enc_len) { enc_len *= sizeof(struct sadb_alg); enc_len += sizeof(struct sadb_supported); } len = enc_len + auth_len + sizeof(struct sadb_msg); skb = alloc_skb(len + 16, allocation); if (!skb) goto out_put_algs; hdr = skb_put(skb, sizeof(*hdr)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = 0; hdr->sadb_msg_len = len / sizeof(uint64_t); if (auth_len) { struct sadb_supported *sp; struct sadb_alg *ap; sp = skb_put(skb, auth_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = auth_len / sizeof(uint64_t); sp->sadb_supported_exttype = SADB_EXT_SUPPORTED_AUTH; for (i = 0; ; i++) { struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg->available) *ap++ = aalg->desc; } } if (enc_len) { struct sadb_supported *sp; struct sadb_alg *ap; sp = skb_put(skb, enc_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = enc_len / sizeof(uint64_t); sp->sadb_supported_exttype = SADB_EXT_SUPPORTED_ENCRYPT; for (i = 0; ; i++) { struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (ealg->available) *ap++ = ealg->desc; } } out_put_algs: return skb; } static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); struct sk_buff *supp_skb; if (hdr->sadb_msg_satype > SADB_SATYPE_MAX) return -EINVAL; if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) { if (pfk->registered&(1<<hdr->sadb_msg_satype)) return -EEXIST; pfk->registered |= (1<<hdr->sadb_msg_satype); } mutex_lock(&pfkey_mutex); xfrm_probe_algs(); supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); mutex_unlock(&pfkey_mutex); if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<<hdr->sadb_msg_satype); return -ENOBUFS; } pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk, sock_net(sk)); return 0; } static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) { struct sk_buff *skb; struct sadb_msg *hdr; skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; hdr = skb_put_data(skb, ihdr, sizeof(struct sadb_msg)); hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); } static int key_notify_sa_flush(const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); hdr->sadb_msg_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); unsigned int proto; struct km_event c; int err, err2; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ err = 0; return err ? err : err2; } c.data.proto = proto; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_FLUSHSA; c.net = net; km_state_notify(NULL, &c); return 0; } static int dump_sa(struct xfrm_state *x, int count, void *ptr) { struct pfkey_sock *pfk = ptr; struct sk_buff *out_skb; struct sadb_msg *out_hdr; if (!pfkey_can_dump(&pfk->sk)) return -ENOBUFS; out_skb = pfkey_xfrm_state2msg(x); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; out_hdr->sadb_msg_type = SADB_DUMP; out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = count + 1; out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; return 0; } static int pfkey_dump_sa(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); return xfrm_state_walk(net, &pfk->dump.u.state, dump_sa, (void *) pfk); } static void pfkey_dump_sa_done(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); xfrm_state_walk_done(&pfk->dump.u.state, net); } static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { u8 proto; struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); mutex_lock(&pfk->dump_lock); if (pfk->dump.dump != NULL) { mutex_unlock(&pfk->dump_lock); return -EBUSY; } proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) { mutex_unlock(&pfk->dump_lock); return -EINVAL; } if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); return -ENOMEM; } memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, sizeof(xfrm_address_t)); memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr, sizeof(xfrm_address_t)); filter->family = xfilter->sadb_x_filter_family; filter->splen = xfilter->sadb_x_filter_splen; filter->dplen = xfilter->sadb_x_filter_dplen; } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); int satype = hdr->sadb_msg_satype; bool reset_errno = false; if (hdr->sadb_msg_len == (sizeof(*hdr) / sizeof(uint64_t))) { reset_errno = true; if (satype != 0 && satype != 1) return -EINVAL; pfk->promisc = satype; } if (reset_errno && skb_cloned(skb)) skb = skb_copy(skb, GFP_KERNEL); else skb = skb_clone(skb, GFP_KERNEL); if (reset_errno && skb) { struct sadb_msg *new_hdr = (struct sadb_msg *) skb->data; new_hdr->sadb_msg_errno = 0; } pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk)); return 0; } static int check_reqid(struct xfrm_policy *xp, int dir, int count, void *ptr) { int i; u32 reqid = *(u32*)ptr; for (i=0; i<xp->xfrm_nr; i++) { if (xp->xfrm_vec[i].reqid == reqid) return -EEXIST; } return 0; } static u32 gen_reqid(struct net *net) { struct xfrm_policy_walk walk; u32 start; int rc; static u32 reqid = IPSEC_MANUAL_REQID_MAX; start = reqid; do { ++reqid; if (reqid == 0) reqid = IPSEC_MANUAL_REQID_MAX+1; xfrm_policy_walk_init(&walk, XFRM_POLICY_TYPE_MAIN); rc = xfrm_policy_walk(net, &walk, check_reqid, (void*)&reqid); xfrm_policy_walk_done(&walk, net); if (rc != -EEXIST) return reqid; } while (reqid != start); return 0; } static int parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; int mode; if (xp->xfrm_nr >= XFRM_MAX_DEPTH) return -ELOOP; if (rq->sadb_x_ipsecrequest_mode == 0) return -EINVAL; if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto)) return -EINVAL; t->id.proto = rq->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) return -EINVAL; t->optional = 1; } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; if (!t->reqid && !(t->reqid = gen_reqid(net))) return -ENOBUFS; } /* addresses present only in tunnel mode */ if (t->mode == XFRM_MODE_TUNNEL) { int err; err = parse_sockaddr_pair( (struct sockaddr *)(rq + 1), rq->sadb_x_ipsecrequest_len - sizeof(*rq), &t->saddr, &t->id.daddr, &t->encap_family); if (err) return err; } else t->encap_family = xp->family; /* No way to set this via kame pfkey */ t->allalgs = 1; xp->xfrm_nr++; return 0; } static int parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) { int err; int len = pol->sadb_x_policy_len*8 - sizeof(struct sadb_x_policy); struct sadb_x_ipsecrequest *rq = (void*)(pol+1); if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy)) return -EINVAL; while (len >= sizeof(*rq)) { if (len < rq->sadb_x_ipsecrequest_len || rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); } return 0; } static inline int pfkey_xfrm_policy2sec_ctx_size(const struct xfrm_policy *xp) { struct xfrm_sec_ctx *xfrm_ctx = xp->security; if (xfrm_ctx) { int len = sizeof(struct sadb_x_sec_ctx); len += xfrm_ctx->ctx_len; return PFKEY_ALIGN8(len); } return 0; } static int pfkey_xfrm_policy2msg_size(const struct xfrm_policy *xp) { const struct xfrm_tmpl *t; int sockaddr_size = pfkey_sockaddr_size(xp->family); int socklen = 0; int i; for (i=0; i<xp->xfrm_nr; i++) { t = xp->xfrm_vec + i; socklen += pfkey_sockaddr_len(t->encap_family); } return sizeof(struct sadb_msg) + (sizeof(struct sadb_lifetime) * 3) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + sizeof(struct sadb_x_policy) + (xp->xfrm_nr * sizeof(struct sadb_x_ipsecrequest)) + (socklen * 2) + pfkey_xfrm_policy2sec_ctx_size(xp); } static struct sk_buff * pfkey_xfrm_policy2msg_prep(const struct xfrm_policy *xp) { struct sk_buff *skb; int size; size = pfkey_xfrm_policy2msg_size(xp); skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return ERR_PTR(-ENOBUFS); return skb; } static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy *xp, int dir) { struct sadb_msg *hdr; struct sadb_address *addr; struct sadb_lifetime *lifetime; struct sadb_x_policy *pol; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int i; int size; int sockaddr_size = pfkey_sockaddr_size(xp->family); int socklen = pfkey_sockaddr_len(xp->family); size = pfkey_xfrm_policy2msg_size(xp); /* call should fill header later */ hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = pfkey_proto_from_xfrm(xp->selector.proto); addr->sadb_address_prefixlen = xp->selector.prefixlen_s; addr->sadb_address_reserved = 0; if (!pfkey_sockaddr_fill(&xp->selector.saddr, xp->selector.sport, (struct sockaddr *) (addr + 1), xp->family)) BUG(); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = pfkey_proto_from_xfrm(xp->selector.proto); addr->sadb_address_prefixlen = xp->selector.prefixlen_d; addr->sadb_address_reserved = 0; pfkey_sockaddr_fill(&xp->selector.daddr, xp->selector.dport, (struct sockaddr *) (addr + 1), xp->family); /* hard time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; lifetime->sadb_lifetime_allocations = _X2KEY(xp->lft.hard_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(xp->lft.hard_byte_limit); lifetime->sadb_lifetime_addtime = xp->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.hard_use_expires_seconds; /* soft time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; lifetime->sadb_lifetime_allocations = _X2KEY(xp->lft.soft_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(xp->lft.soft_byte_limit); lifetime->sadb_lifetime_addtime = xp->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.soft_use_expires_seconds; /* current time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; lifetime->sadb_lifetime_allocations = xp->curlft.packets; lifetime->sadb_lifetime_bytes = xp->curlft.bytes; lifetime->sadb_lifetime_addtime = xp->curlft.add_time; lifetime->sadb_lifetime_usetime = xp->curlft.use_time; pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_DISCARD; if (xp->action == XFRM_POLICY_ALLOW) { if (xp->xfrm_nr) pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; else pol->sadb_x_policy_type = IPSEC_POLICY_NONE; } pol->sadb_x_policy_dir = dir+1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; for (i=0; i<xp->xfrm_nr; i++) { const struct xfrm_tmpl *t = xp->xfrm_vec + i; struct sadb_x_ipsecrequest *rq; int req_size; int mode; req_size = sizeof(struct sadb_x_ipsecrequest); if (t->mode == XFRM_MODE_TUNNEL) { socklen = pfkey_sockaddr_len(t->encap_family); req_size += socklen * 2; } else { size -= 2*socklen; } rq = skb_put(skb, req_size); pol->sadb_x_policy_len += req_size/8; memset(rq, 0, sizeof(*rq)); rq->sadb_x_ipsecrequest_len = req_size; rq->sadb_x_ipsecrequest_proto = t->id.proto; if ((mode = pfkey_mode_from_xfrm(t->mode)) < 0) return -EINVAL; rq->sadb_x_ipsecrequest_mode = mode; rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_REQUIRE; if (t->reqid) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_UNIQUE; if (t->optional) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_USE; rq->sadb_x_ipsecrequest_reqid = t->reqid; if (t->mode == XFRM_MODE_TUNNEL) { u8 *sa = (void *)(rq + 1); pfkey_sockaddr_fill(&t->saddr, 0, (struct sockaddr *)sa, t->encap_family); pfkey_sockaddr_fill(&t->id.daddr, 0, (struct sockaddr *) (sa + socklen), t->encap_family); } } /* security context */ if ((xfrm_ctx = xp->security)) { int ctx_size = pfkey_xfrm_policy2sec_ctx_size(xp); sec_ctx = skb_put(skb, ctx_size); sec_ctx->sadb_x_sec_len = ctx_size / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_reserved = refcount_read(&xp->refcnt); return 0; } static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; int err; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); return err; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; if (c->data.byid && c->event == XFRM_MSG_DELPOLICY) out_hdr->sadb_msg_type = SADB_X_SPDDELETE2; else out_hdr->sadb_msg_type = event2poltype(c->event); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; out_hdr->sadb_msg_pid = c->portid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); return 0; } static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); int err = 0; struct sadb_lifetime *lifetime; struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct km_event c; struct sadb_x_sec_ctx *sec_ctx; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || !ext_hdrs[SADB_X_EXT_POLICY-1]) return -EINVAL; pol = ext_hdrs[SADB_X_EXT_POLICY-1]; if (pol->sadb_x_policy_type > IPSEC_POLICY_IPSEC) return -EINVAL; if (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) return -EINVAL; xp = xfrm_policy_alloc(net, GFP_KERNEL); if (xp == NULL) return -ENOBUFS; xp->action = (pol->sadb_x_policy_type == IPSEC_POLICY_DISCARD ? XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->priority = pol->sadb_x_policy_priority; sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; xp->family = pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.saddr); xp->selector.family = xp->family; xp->selector.prefixlen_s = sa->sadb_address_prefixlen; xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.sport) xp->selector.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.daddr); xp->selector.prefixlen_d = sa->sadb_address_prefixlen; /* Amusing, we set this twice. KAME apps appear to set same value * in both addresses. */ xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.dport) xp->selector.dport_mask = htons(0xffff); sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) { err = -ENOBUFS; goto out; } err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL); kfree(uctx); if (err) goto out; } xp->lft.soft_byte_limit = XFRM_INF; xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; if ((lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD-1]) != NULL) { xp->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); xp->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); xp->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; xp->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } if ((lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]) != NULL) { xp->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); xp->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); xp->lft.soft_add_expires_seconds = lifetime->sadb_lifetime_addtime; xp->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && (err = parse_ipsecrequests(xp, pol)) < 0) goto out; err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp, hdr->sadb_msg_type != SADB_X_SPDUPDATE); xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) goto out; if (hdr->sadb_msg_type == SADB_X_SPDUPDATE) c.event = XFRM_MSG_UPDPOLICY; else c.event = XFRM_MSG_NEWPOLICY; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); xfrm_pol_put(xp); return 0; out: xp->walk.dead = 1; xfrm_policy_destroy(xp); return err; } static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); int err; struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct xfrm_selector sel; struct km_event c; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *pol_ctx = NULL; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || !ext_hdrs[SADB_X_EXT_POLICY-1]) return -EINVAL; pol = ext_hdrs[SADB_X_EXT_POLICY-1]; if (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) return -EINVAL; memset(&sel, 0, sizeof(sel)); sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.sport) sel.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.dport) sel.dport_mask = htons(0xffff); sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) return -ENOMEM; err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL); kfree(uctx); if (err) return err; } xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); if (xp == NULL) return -ENOENT; xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.data.byid = 0; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); out: xfrm_pol_put(xp); return err; } static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struct sadb_msg *hdr, int dir) { int err; struct sk_buff *out_skb; struct sadb_msg *out_hdr; err = 0; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) { err = PTR_ERR(out_skb); goto out; } err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); goto out; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = hdr->sadb_msg_type; out_hdr->sadb_msg_satype = 0; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp)); err = 0; out: return err; } static int pfkey_sockaddr_pair_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2); } static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, xfrm_address_t *saddr, xfrm_address_t *daddr, u16 *family) { int af, socklen; if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) return -EINVAL; af = pfkey_sockaddr_extract(sa, saddr); if (!af) return -EINVAL; socklen = pfkey_sockaddr_len(af); if (pfkey_sockaddr_extract((struct sockaddr *) (((u8 *)sa) + socklen), daddr) != af) return -EINVAL; *family = af; return 0; } #ifdef CONFIG_NET_KEY_MIGRATE static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct xfrm_migrate *m) { int err; struct sadb_x_ipsecrequest *rq2; int mode; if (len < sizeof(*rq1) || len < rq1->sadb_x_ipsecrequest_len || rq1->sadb_x_ipsecrequest_len < sizeof(*rq1)) return -EINVAL; /* old endoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1), rq1->sadb_x_ipsecrequest_len - sizeof(*rq1), &m->old_saddr, &m->old_daddr, &m->old_family); if (err) return err; rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len); len -= rq1->sadb_x_ipsecrequest_len; if (len <= sizeof(*rq2) || len < rq2->sadb_x_ipsecrequest_len || rq2->sadb_x_ipsecrequest_len < sizeof(*rq2)) return -EINVAL; /* new endpoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1), rq2->sadb_x_ipsecrequest_len - sizeof(*rq2), &m->new_saddr, &m->new_daddr, &m->new_family); if (err) return err; if (rq1->sadb_x_ipsecrequest_proto != rq2->sadb_x_ipsecrequest_proto || rq1->sadb_x_ipsecrequest_mode != rq2->sadb_x_ipsecrequest_mode || rq1->sadb_x_ipsecrequest_reqid != rq2->sadb_x_ipsecrequest_reqid) return -EINVAL; m->proto = rq1->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq1->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; m->mode = mode; m->reqid = rq1->sadb_x_ipsecrequest_reqid; return ((int)(rq1->sadb_x_ipsecrequest_len + rq2->sadb_x_ipsecrequest_len)); } static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { int i, len, ret, err = -EINVAL; u8 dir; struct sadb_address *sa; struct sadb_x_kmaddress *kma; struct sadb_x_policy *pol; struct sadb_x_ipsecrequest *rq; struct xfrm_selector sel; struct xfrm_migrate m[XFRM_MAX_DEPTH]; struct xfrm_kmaddress k; struct net *net = sock_net(sk); if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC - 1], ext_hdrs[SADB_EXT_ADDRESS_DST - 1]) || !ext_hdrs[SADB_X_EXT_POLICY - 1]) { err = -EINVAL; goto out; } kma = ext_hdrs[SADB_X_EXT_KMADDRESS - 1]; pol = ext_hdrs[SADB_X_EXT_POLICY - 1]; if (pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) { err = -EINVAL; goto out; } if (kma) { /* convert sadb_x_kmaddress to xfrm_kmaddress */ k.reserved = kma->sadb_x_kmaddress_reserved; ret = parse_sockaddr_pair((struct sockaddr *)(kma + 1), 8*(kma->sadb_x_kmaddress_len) - sizeof(*kma), &k.local, &k.remote, &k.family); if (ret < 0) { err = ret; goto out; } } dir = pol->sadb_x_policy_dir - 1; memset(&sel, 0, sizeof(sel)); /* set source address info of selector */ sa = ext_hdrs[SADB_EXT_ADDRESS_SRC - 1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa + 1))->sin_port; if (sel.sport) sel.sport_mask = htons(0xffff); /* set destination address info of selector */ sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa + 1))->sin_port; if (sel.dport) sel.dport_mask = htons(0xffff); rq = (struct sadb_x_ipsecrequest *)(pol + 1); /* extract ipsecrequests */ i = 0; len = pol->sadb_x_policy_len * 8 - sizeof(struct sadb_x_policy); while (len > 0 && i < XFRM_MAX_DEPTH) { ret = ipsecrequests_to_migrate(rq, len, &m[i]); if (ret < 0) { err = ret; goto out; } else { rq = (struct sadb_x_ipsecrequest *)((u8 *)rq + ret); len -= ret; i++; } } if (!i || len > 0) { err = -EINVAL; goto out; } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, kma ? &k : NULL, net, NULL, 0, NULL); out: return err; } #else static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { return -ENOPROTOOPT; } #endif static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); unsigned int dir; int err = 0, delete; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct km_event c; if ((pol = ext_hdrs[SADB_X_EXT_POLICY-1]) == NULL) return -EINVAL; dir = xfrm_policy_id2dir(pol->sadb_x_policy_id); if (dir >= XFRM_POLICY_MAX) return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; if (delete) { xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.data.byid = 1; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, dir, &c); } else { err = key_pol_get_resp(sk, xp, hdr, dir); } out: xfrm_pol_put(xp); return err; } static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) { struct pfkey_sock *pfk = ptr; struct sk_buff *out_skb; struct sadb_msg *out_hdr; int err; if (!pfkey_can_dump(&pfk->sk)) return -ENOBUFS; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); return err; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; out_hdr->sadb_msg_type = SADB_X_SPDDUMP; out_hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = count + 1; out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; return 0; } static int pfkey_dump_sp(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); return xfrm_policy_walk(net, &pfk->dump.u.policy, dump_sp, (void *) pfk); } static void pfkey_dump_sp_done(struct pfkey_sock *pfk) { struct net *net = sock_net((struct sock *)pfk); xfrm_policy_walk_done(&pfk->dump.u.policy, net); } static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); mutex_lock(&pfk->dump_lock); if (pfk->dump.dump != NULL) { mutex_unlock(&pfk->dump_lock); return -EBUSY; } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } static int key_notify_policy_flush(const struct km_event *c) { struct sk_buff *skb_out; struct sadb_msg *hdr; skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb_out) return -ENOBUFS; hdr = skb_put(skb_out, sizeof(struct sadb_msg)); hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct km_event c; int err, err2; err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - old silent behavior */ return 0; return err; } c.data.type = XFRM_POLICY_TYPE_MAIN; c.event = XFRM_MSG_FLUSHPOLICY; c.portid = hdr->sadb_msg_pid; c.seq = hdr->sadb_msg_seq; c.net = net; km_policy_notify(NULL, 0, &c); return 0; } typedef int (*pfkey_handler)(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs); static const pfkey_handler pfkey_funcs[SADB_MAX + 1] = { [SADB_RESERVED] = pfkey_reserved, [SADB_GETSPI] = pfkey_getspi, [SADB_UPDATE] = pfkey_add, [SADB_ADD] = pfkey_add, [SADB_DELETE] = pfkey_delete, [SADB_GET] = pfkey_get, [SADB_ACQUIRE] = pfkey_acquire, [SADB_REGISTER] = pfkey_register, [SADB_EXPIRE] = NULL, [SADB_FLUSH] = pfkey_flush, [SADB_DUMP] = pfkey_dump, [SADB_X_PROMISC] = pfkey_promisc, [SADB_X_PCHANGE] = NULL, [SADB_X_SPDUPDATE] = pfkey_spdadd, [SADB_X_SPDADD] = pfkey_spdadd, [SADB_X_SPDDELETE] = pfkey_spddelete, [SADB_X_SPDGET] = pfkey_spdget, [SADB_X_SPDACQUIRE] = NULL, [SADB_X_SPDDUMP] = pfkey_spddump, [SADB_X_SPDFLUSH] = pfkey_spdflush, [SADB_X_SPDSETIDX] = pfkey_spdadd, [SADB_X_SPDDELETE2] = pfkey_spdget, [SADB_X_MIGRATE] = pfkey_migrate, }; static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr) { void *ext_hdrs[SADB_EXT_MAX]; int err; /* Non-zero return value of pfkey_broadcast() does not always signal * an error and even on an actual error we may still want to process * the message so rather ignore the return value. */ pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); if (!err) { err = -EOPNOTSUPP; if (pfkey_funcs[hdr->sadb_msg_type]) err = pfkey_funcs[hdr->sadb_msg_type](sk, skb, hdr, ext_hdrs); } return err; } static struct sadb_msg *pfkey_get_base_msg(struct sk_buff *skb, int *errp) { struct sadb_msg *hdr = NULL; if (skb->len < sizeof(*hdr)) { *errp = -EMSGSIZE; } else { hdr = (struct sadb_msg *) skb->data; if (hdr->sadb_msg_version != PF_KEY_V2 || hdr->sadb_msg_reserved != 0 || (hdr->sadb_msg_type <= SADB_RESERVED || hdr->sadb_msg_type > SADB_MAX)) { hdr = NULL; *errp = -EINVAL; } else if (hdr->sadb_msg_len != (skb->len / sizeof(uint64_t)) || hdr->sadb_msg_len < (sizeof(struct sadb_msg) / sizeof(uint64_t))) { hdr = NULL; *errp = -EMSGSIZE; } else { *errp = 0; } } return hdr; } static inline int aalg_tmpl_set(const struct xfrm_tmpl *t, const struct xfrm_algo_desc *d) { unsigned int id = d->desc.sadb_alg_id; if (id >= sizeof(t->aalgos) * 8) return 0; return (t->aalgos >> id) & 1; } static inline int ealg_tmpl_set(const struct xfrm_tmpl *t, const struct xfrm_algo_desc *d) { unsigned int id = d->desc.sadb_alg_id; if (id >= sizeof(t->ealgos) * 8) return 0; return (t->ealgos >> id) & 1; } static int count_ah_combs(const struct xfrm_tmpl *t) { int i, sz = 0; for (i = 0; ; i++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); } static int count_esp_combs(const struct xfrm_tmpl *t) { int i, k, sz = 0; for (i = 0; ; i++) { const struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; memset(p->sadb_prop_reserved, 0, sizeof(p->sadb_prop_reserved)); for (i = 0; ; i++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg) && aalg->available) { struct sadb_comb *c; c = skb_put_zero(skb, sizeof(struct sadb_comb)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; c->sadb_comb_auth_maxbits = aalg->desc.sadb_alg_maxbits; c->sadb_comb_hard_addtime = 24*60*60; c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; sz += sizeof(*c); } } return sz + sizeof(*p); } static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; memset(p->sadb_prop_reserved, 0, sizeof(p->sadb_prop_reserved)); for (i=0; ; i++) { const struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { struct sadb_comb *c; const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (!(aalg_tmpl_set(t, aalg) && aalg->available)) continue; c = skb_put(skb, sizeof(struct sadb_comb)); memset(c, 0, sizeof(*c)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; c->sadb_comb_auth_maxbits = aalg->desc.sadb_alg_maxbits; c->sadb_comb_encrypt = ealg->desc.sadb_alg_id; c->sadb_comb_encrypt_minbits = ealg->desc.sadb_alg_minbits; c->sadb_comb_encrypt_maxbits = ealg->desc.sadb_alg_maxbits; c->sadb_comb_hard_addtime = 24*60*60; c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; sz += sizeof(*c); } } return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) { return 0; } static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; int hard; int hsc; hard = c->data.hard; if (hard) hsc = 2; else hsc = 1; out_skb = pfkey_xfrm_state2msg_expire(x, hsc); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; out_hdr->sadb_msg_type = SADB_EXPIRE; out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = 0; out_hdr->sadb_msg_pid = 0; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); return 0; } static int pfkey_send_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = x ? xs_net(x) : c->net; struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); if (atomic_read(&net_pfkey->socks_nr) == 0) return 0; switch (c->event) { case XFRM_MSG_EXPIRE: return key_notify_sa_expire(x, c); case XFRM_MSG_DELSA: case XFRM_MSG_NEWSA: case XFRM_MSG_UPDSA: return key_notify_sa(x, c); case XFRM_MSG_FLUSHSA: return key_notify_sa_flush(c); case XFRM_MSG_NEWAE: /* not yet supported */ break; default: pr_err("pfkey: Unknown SA event %d\n", c->event); break; } return 0; } static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { if (xp && xp->type != XFRM_POLICY_TYPE_MAIN) return 0; switch (c->event) { case XFRM_MSG_POLEXPIRE: return key_notify_policy_expire(xp, c); case XFRM_MSG_DELPOLICY: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDPOLICY: return key_notify_policy(xp, dir, c); case XFRM_MSG_FLUSHPOLICY: if (c->data.type != XFRM_POLICY_TYPE_MAIN) break; return key_notify_policy_flush(c); default: pr_err("pfkey: Unknown policy event %d\n", c->event); break; } return 0; } static u32 get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } static bool pfkey_is_alive(const struct km_event *c) { struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id); struct sock *sk; bool is_alive = false; rcu_read_lock(); sk_for_each_rcu(sk, &net_pfkey->table) { if (pfkey_sk(sk)->registered) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_address *addr; struct sadb_x_policy *pol; int sockaddr_size; int size; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return -EINVAL; size = sizeof(struct sadb_msg) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_ACQUIRE; hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = x->km.seq = get_acqseq(); hdr->sadb_msg_pid = 0; /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = XFRM_POLICY_OUT + 1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ alg_size = 0; if (x->id.proto == IPPROTO_AH) alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) alg_size = dump_esp_combs(skb, t); hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { sec_ctx = skb_put(skb, sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); } static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { struct net *net = sock_net(sk); struct xfrm_policy *xp; struct sadb_x_policy *pol = (struct sadb_x_policy*)data; struct sadb_x_sec_ctx *sec_ctx; switch (sk->sk_family) { case AF_INET: if (opt != IP_IPSEC_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (opt != IPV6_IPSEC_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #endif default: *dir = -EINVAL; return NULL; } *dir = -EINVAL; if (len < sizeof(struct sadb_x_policy) || pol->sadb_x_policy_len*8 > len || pol->sadb_x_policy_type > IPSEC_POLICY_BYPASS || (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir > IPSEC_DIR_OUTBOUND)) return NULL; xp = xfrm_policy_alloc(net, GFP_ATOMIC); if (xp == NULL) { *dir = -ENOBUFS; return NULL; } xp->action = (pol->sadb_x_policy_type == IPSEC_POLICY_DISCARD ? XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->lft.soft_byte_limit = XFRM_INF; xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; xp->family = sk->sk_family; xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && (*dir = parse_ipsecrequests(xp, pol)) < 0) goto out; /* security context too */ if (len >= (pol->sadb_x_policy_len*8 + sizeof(struct sadb_x_sec_ctx))) { char *p = (char *)pol; struct xfrm_user_sec_ctx *uctx; p += pol->sadb_x_policy_len*8; sec_ctx = (struct sadb_x_sec_ctx *)p; if (len < pol->sadb_x_policy_len*8 + sec_ctx->sadb_x_sec_len*8) { *dir = -EINVAL; goto out; } if ((*dir = verify_sec_ctx_len(p))) goto out; uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC); *dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC); kfree(uctx); if (*dir) goto out; } *dir = pol->sadb_x_policy_dir-1; return xp; out: xp->walk.dead = 1; xfrm_policy_destroy(xp); return NULL; } static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_sa *sa; struct sadb_address *addr; struct sadb_x_nat_t_port *n_port; int sockaddr_size; int size; __u8 satype = (x->id.proto == IPPROTO_ESP ? SADB_SATYPE_ESP : 0); struct xfrm_encap_tmpl *natt = NULL; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return -EINVAL; if (!satype) return -EINVAL; if (!x->encap) return -EINVAL; natt = x->encap; /* Build an SADB_X_NAT_T_NEW_MAPPING message: * * HDR | SA | ADDRESS_SRC (old addr) | NAT_T_SPORT (old port) | * ADDRESS_DST (new addr) | NAT_T_DPORT (new port) */ size = sizeof(struct sadb_msg) + sizeof(struct sadb_sa) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + (sizeof(struct sadb_x_nat_t_port) * 2); skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_NAT_T_NEW_MAPPING; hdr->sadb_msg_satype = satype; hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0; /* SA */ sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = 0; sa->sadb_sa_state = 0; sa->sadb_sa_auth = 0; sa->sadb_sa_encrypt = 0; sa->sadb_sa_flags = 0; /* ADDRESS_SRC (old addr) */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* NAT_T_SPORT (old port) */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* ADDRESS_DST (new addr) */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(ipaddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* NAT_T_DPORT (new port) */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = sport; n_port->sadb_x_nat_t_port_reserved = 0; return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); } #ifdef CONFIG_NET_KEY_MIGRATE static int set_sadb_address(struct sk_buff *skb, int sasize, int type, const struct xfrm_selector *sel) { struct sadb_address *addr; addr = skb_put(skb, sizeof(struct sadb_address) + sasize); addr->sadb_address_len = (sizeof(struct sadb_address) + sasize)/8; addr->sadb_address_exttype = type; addr->sadb_address_proto = sel->proto; addr->sadb_address_reserved = 0; switch (type) { case SADB_EXT_ADDRESS_SRC: addr->sadb_address_prefixlen = sel->prefixlen_s; pfkey_sockaddr_fill(&sel->saddr, 0, (struct sockaddr *)(addr + 1), sel->family); break; case SADB_EXT_ADDRESS_DST: addr->sadb_address_prefixlen = sel->prefixlen_d; pfkey_sockaddr_fill(&sel->daddr, 0, (struct sockaddr *)(addr + 1), sel->family); break; default: return -EINVAL; } return 0; } static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress *k) { struct sadb_x_kmaddress *kma; u8 *sa; int family = k->family; int socklen = pfkey_sockaddr_len(family); int size_req; size_req = (sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(family)); kma = skb_put_zero(skb, size_req); kma->sadb_x_kmaddress_len = size_req / 8; kma->sadb_x_kmaddress_exttype = SADB_X_EXT_KMADDRESS; kma->sadb_x_kmaddress_reserved = k->reserved; sa = (u8 *)(kma + 1); if (!pfkey_sockaddr_fill(&k->local, 0, (struct sockaddr *)sa, family) || !pfkey_sockaddr_fill(&k->remote, 0, (struct sockaddr *)(sa+socklen), family)) return -EINVAL; return 0; } static int set_ipsecrequest(struct sk_buff *skb, uint8_t proto, uint8_t mode, int level, uint32_t reqid, uint8_t family, const xfrm_address_t *src, const xfrm_address_t *dst) { struct sadb_x_ipsecrequest *rq; u8 *sa; int socklen = pfkey_sockaddr_len(family); int size_req; size_req = sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(family); rq = skb_put_zero(skb, size_req); rq->sadb_x_ipsecrequest_len = size_req; rq->sadb_x_ipsecrequest_proto = proto; rq->sadb_x_ipsecrequest_mode = mode; rq->sadb_x_ipsecrequest_level = level; rq->sadb_x_ipsecrequest_reqid = reqid; sa = (u8 *) (rq + 1); if (!pfkey_sockaddr_fill(src, 0, (struct sockaddr *)sa, family) || !pfkey_sockaddr_fill(dst, 0, (struct sockaddr *)(sa + socklen), family)) return -EINVAL; return 0; } #endif #ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { int i; int sasize_sel; int size = 0; int size_pol = 0; struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_x_policy *pol; const struct xfrm_migrate *mp; if (type != XFRM_POLICY_TYPE_MAIN) return 0; if (num_bundles <= 0 || num_bundles > XFRM_MAX_DEPTH) return -EINVAL; if (k != NULL) { /* addresses for KM */ size += PFKEY_ALIGN8(sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(k->family)); } /* selector */ sasize_sel = pfkey_sockaddr_size(sel->family); if (!sasize_sel) return -EINVAL; size += (sizeof(struct sadb_address) + sasize_sel) * 2; /* policy info */ size_pol += sizeof(struct sadb_x_policy); /* ipsecrequests */ for (i = 0, mp = m; i < num_bundles; i++, mp++) { /* old locator pair */ size_pol += sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(mp->old_family); /* new locator pair */ size_pol += sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(mp->new_family); } size += sizeof(struct sadb_msg) + size_pol; /* alloc buffer */ skb = alloc_skb(size, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_MIGRATE; hdr->sadb_msg_satype = pfkey_proto2satype(m->proto); hdr->sadb_msg_len = size / 8; hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = 0; hdr->sadb_msg_pid = 0; /* Addresses to be used by KM for negotiation, if ext is available */ if (k != NULL && (set_sadb_kmaddress(skb, k) < 0)) goto err; /* selector src */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_SRC, sel); /* selector dst */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_DST, sel); /* policy information */ pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = size_pol / 8; pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir + 1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = 0; pol->sadb_x_policy_priority = 0; for (i = 0, mp = m; i < num_bundles; i++, mp++) { /* old ipsecrequest */ int mode = pfkey_mode_from_xfrm(mp->mode); if (mode < 0) goto err; if (set_ipsecrequest(skb, mp->proto, mode, (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE), mp->reqid, mp->old_family, &mp->old_saddr, &mp->old_daddr) < 0) goto err; /* new ipsecrequest */ if (set_ipsecrequest(skb, mp->proto, mode, (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE), mp->reqid, mp->new_family, &mp->new_saddr, &mp->new_daddr) < 0) goto err; } /* broadcast migrate message to sockets */ pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); return 0; err: kfree_skb(skb); return -EINVAL; } #else static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } #endif static int pfkey_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb = NULL; struct sadb_msg *hdr = NULL; int err; struct net *net = sock_net(sk); err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) goto out; err = -EMSGSIZE; if ((unsigned int)len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = alloc_skb(len, GFP_KERNEL); if (skb == NULL) goto out; err = -EFAULT; if (memcpy_from_msg(skb_put(skb,len), msg, len)) goto out; hdr = pfkey_get_base_msg(skb, &err); if (!hdr) goto out; mutex_lock(&net->xfrm.xfrm_cfg_mutex); err = pfkey_process(sk, skb, hdr); mutex_unlock(&net->xfrm.xfrm_cfg_mutex); out: if (err && hdr && pfkey_error(hdr, err, sk) == 0) err = 0; kfree_skb(skb); return err ? : len; } static int pfkey_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct pfkey_sock *pfk = pfkey_sk(sk); struct sk_buff *skb; int copied, err; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) goto out; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; sock_recv_cmsgs(msg, sk, skb); err = (flags & MSG_TRUNC) ? skb->len : copied; if (pfk->dump.dump != NULL && 3 * atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) pfkey_do_dump(pfk); out_free: skb_free_datagram(sk, skb); out: return err; } static const struct proto_ops pfkey_ops = { .family = PF_KEY, .owner = THIS_MODULE, /* Operations that make no sense on pfkey sockets. */ .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, /* Now the operations that really occur. */ .release = pfkey_release, .poll = datagram_poll, .sendmsg = pfkey_sendmsg, .recvmsg = pfkey_recvmsg, }; static const struct net_proto_family pfkey_family_ops = { .family = PF_KEY, .create = pfkey_create, .owner = THIS_MODULE, }; #ifdef CONFIG_PROC_FS static int pfkey_seq_show(struct seq_file *f, void *v) { struct sock *s = sk_entry(v); if (v == SEQ_START_TOKEN) seq_printf(f ,"sk RefCnt Rmem Wmem User Inode\n"); else seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), from_kuid_munged(seq_user_ns(f), sock_i_uid(s)), sock_i_ino(s) ); return 0; } static void *pfkey_seq_start(struct seq_file *f, loff_t *ppos) __acquires(rcu) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); rcu_read_lock(); return seq_hlist_start_head_rcu(&net_pfkey->table, *ppos); } static void *pfkey_seq_next(struct seq_file *f, void *v, loff_t *ppos) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); return seq_hlist_next_rcu(v, &net_pfkey->table, ppos); } static void pfkey_seq_stop(struct seq_file *f, void *v) __releases(rcu) { rcu_read_unlock(); } static const struct seq_operations pfkey_seq_ops = { .start = pfkey_seq_start, .next = pfkey_seq_next, .stop = pfkey_seq_stop, .show = pfkey_seq_show, }; static int __net_init pfkey_init_proc(struct net *net) { struct proc_dir_entry *e; e = proc_create_net("pfkey", 0, net->proc_net, &pfkey_seq_ops, sizeof(struct seq_net_private)); if (e == NULL) return -ENOMEM; return 0; } static void __net_exit pfkey_exit_proc(struct net *net) { remove_proc_entry("pfkey", net->proc_net); } #else static inline int pfkey_init_proc(struct net *net) { return 0; } static inline void pfkey_exit_proc(struct net *net) { } #endif static struct xfrm_mgr pfkeyv2_mgr = { .notify = pfkey_send_notify, .acquire = pfkey_send_acquire, .compile_policy = pfkey_compile_policy, .new_mapping = pfkey_send_new_mapping, .notify_policy = pfkey_send_policy_notify, .migrate = pfkey_send_migrate, .is_alive = pfkey_is_alive, }; static int __net_init pfkey_net_init(struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); int rv; INIT_HLIST_HEAD(&net_pfkey->table); atomic_set(&net_pfkey->socks_nr, 0); rv = pfkey_init_proc(net); return rv; } static void __net_exit pfkey_net_exit(struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_exit_proc(net); WARN_ON(!hlist_empty(&net_pfkey->table)); } static struct pernet_operations pfkey_net_ops = { .init = pfkey_net_init, .exit = pfkey_net_exit, .id = &pfkey_net_id, .size = sizeof(struct netns_pfkey), }; static void __exit ipsec_pfkey_exit(void) { xfrm_unregister_km(&pfkeyv2_mgr); sock_unregister(PF_KEY); unregister_pernet_subsys(&pfkey_net_ops); proto_unregister(&key_proto); } static int __init ipsec_pfkey_init(void) { int err = proto_register(&key_proto, 0); if (err != 0) goto out; err = register_pernet_subsys(&pfkey_net_ops); if (err != 0) goto out_unregister_key_proto; err = sock_register(&pfkey_family_ops); if (err != 0) goto out_unregister_pernet; xfrm_register_km(&pfkeyv2_mgr); out: return err; out_unregister_pernet: unregister_pernet_subsys(&pfkey_net_ops); out_unregister_key_proto: proto_unregister(&key_proto); goto out; } module_init(ipsec_pfkey_init); module_exit(ipsec_pfkey_exit); MODULE_DESCRIPTION("PF_KEY socket helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_KEY); |
| 12 772 188 17444 41 2 5190 3 3 4918 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_MM_H #define _LINUX_SCHED_MM_H #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> #include <linux/sched/coredump.h> /* * Routines for handling mm_structs */ extern struct mm_struct *mm_alloc(void); /** * mmgrab() - Pin a &struct mm_struct. * @mm: The &struct mm_struct to pin. * * Make sure that @mm will not get freed even after the owning task * exits. This doesn't guarantee that the associated address space * will still exist later on and mmget_not_zero() has to be used before * accessing it. * * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) { atomic_inc(&mm->mm_count); } static inline void smp_mb__after_mmgrab(void) { smp_mb__after_atomic(); } extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is * required by the membarrier system call before returning to * user-space, after storing to rq->curr. */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } #ifdef CONFIG_PREEMPT_RT /* * RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is * by far the least expensive way to do that. */ static inline void __mmdrop_delayed(struct rcu_head *rhp) { struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); __mmdrop(mm); } /* * Invoked from finish_task_switch(). Delegates the heavy lifting on RT * kernels via RCU. */ static inline void mmdrop_sched(struct mm_struct *mm) { /* Provides a full memory barrier. See mmdrop() */ if (atomic_dec_and_test(&mm->mm_count)) call_rcu(&mm->delayed_drop, __mmdrop_delayed); } #else static inline void mmdrop_sched(struct mm_struct *mm) { mmdrop(mm); } #endif /* Helpers for lazy TLB mm refcounting */ static inline void mmgrab_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmgrab(mm); } static inline void mmdrop_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { mmdrop(mm); } else { /* * mmdrop_lazy_tlb must provide a full memory barrier, see the * membarrier comment finish_task_switch which relies on this. */ smp_mb(); } } static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmdrop_sched(mm); else smp_mb(); /* see mmdrop_lazy_tlb() above */ } /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. * * Make sure that the address space of the given &struct mm_struct doesn't * go away. This does not protect against parts of the address space being * modified or freed, however. * * Never use this function to pin this address space for an * unbounded/indefinite amount of time. * * Use mmput() to release the reference acquired by mmget(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) { atomic_inc(&mm->mm_users); } static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); #ifdef CONFIG_MMU /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ void mmput_async(struct mm_struct *); #endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* * Grab a reference to a task's mm, if it is not already going away * and ptrace_may_access with the mode parameter passed to it * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct on exit() */ extern void exit_mm_release(struct task_struct *, struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct on exec() */ extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); #else static inline void mm_update_next_owner(struct mm_struct *mm) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t); unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) { bool ret; /* * need RCU to access ->real_parent if CLONE_VM was used along with * CLONE_PARENT. * * We check real_parent->mm == tsk->mm because CLONE_VFORK does not * imply CLONE_VM * * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus * ->real_parent is not necessarily the task doing vfork(), so in * theory we can't rely on task_lock() if we want to dereference it. * * And in this case we can't trust the real_parent->mm == tsk->mm * check, it can be false negative. But we do not care, if init or * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); ret = tsk->vfork_done && rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; } /* * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } return flags; } #ifdef CONFIG_LOCKDEP extern void __fs_reclaim_acquire(unsigned long ip); extern void __fs_reclaim_release(unsigned long ip); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else static inline void __fs_reclaim_acquire(unsigned long ip) { } static inline void __fs_reclaim_release(unsigned long ip) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /* Any memory-allocation retry loop should use * memalloc_retry_wait(), and pass the flags for the most * constrained allocation attempt that might have failed. * This provides useful documentation of where loops are, * and a central place to fine tune the waiting as the MM * implementation changes. */ static inline void memalloc_retry_wait(gfp_t gfp_flags) { /* We use io_schedule_timeout because waiting for memory * typically included waiting for dirty pages to be * written out, which requires IO. */ __set_current_state(TASK_UNINTERRUPTIBLE); gfp_flags = current_gfp_context(gfp_flags); if (gfpflags_allow_blocking(gfp_flags) && !(gfp_flags & __GFP_NORETRY)) /* Probably waited already, no need for much more */ io_schedule_timeout(1); else /* Probably didn't wait, and has now released a lock, * so now is a good time to wait */ io_schedule_timeout(HZ/50); } /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate * * Similar to might_sleep() and other annotations, this can be used in functions * that might allocate, but often don't. Compiles to nothing without * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. */ static inline void might_alloc(gfp_t gfp_mask) { fs_reclaim_acquire(gfp_mask); fs_reclaim_release(gfp_mask); might_sleep_if(gfpflags_allow_blocking(gfp_mask)); } /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). */ static inline unsigned memalloc_flags_save(unsigned flags) { unsigned oldflags = ~current->flags & flags; current->flags |= flags; return oldflags; } static inline void memalloc_flags_restore(unsigned flags) { current->flags &= ~flags; } /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. * All further allocations will implicitly drop __GFP_IO flag and so * they are safe for the IO critical section from the allocation recursion * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_noio_restore. */ static inline unsigned int memalloc_noio_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOIO); } /** * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. * * This functions marks the beginning of the GFP_NOFS allocation scope. * All further allocations will implicitly drop __GFP_FS flag and so * they are safe for the FS critical section from the allocation recursion * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_nofs_restore. */ static inline unsigned int memalloc_nofs_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOFS); } /** * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_noreclaim_save - Marks implicit __GFP_MEMALLOC scope. * * This function marks the beginning of the __GFP_MEMALLOC allocation scope. * All further allocations will implicitly add the __GFP_MEMALLOC flag, which * prevents entering reclaim and allows access to all memory reserves. This * should only be used when the caller guarantees the allocation will allow more * memory to be freed very shortly, i.e. it needs to allocate some memory in * the process of freeing memory, and cannot reclaim due to potential recursion. * * Users of this scope have to be extremely careful to not deplete the reserves * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. Usage of a * pre-allocated pool (e.g. mempool) should be always considered before using * this scope. * * Individual allocations under the scope can opt out using __GFP_NOMEMALLOC * * Context: This function should not be used in an interrupt context as that one * does not give PF_MEMALLOC access to reserves. * See __gfp_pfmemalloc_flags(). * Return: The saved flags to be passed to memalloc_noreclaim_restore. */ static inline unsigned int memalloc_noreclaim_save(void) { return memalloc_flags_save(PF_MEMALLOC); } /** * memalloc_noreclaim_restore - Ends the implicit __GFP_MEMALLOC scope. * @flags: Flags to restore. * * Ends the implicit __GFP_MEMALLOC scope started by memalloc_noreclaim_save * function. Always make sure that the given flags is the return value from the * pairing memalloc_noreclaim_save call. */ static inline void memalloc_noreclaim_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_pin_save - Marks implicit ~__GFP_MOVABLE scope. * * This function marks the beginning of the ~__GFP_MOVABLE allocation scope. * All further allocations will implicitly remove the __GFP_MOVABLE flag, which * will constraint the allocations to zones that allow long term pinning, i.e. * not ZONE_MOVABLE zones. * * Return: The saved flags to be passed to memalloc_pin_restore. */ static inline unsigned int memalloc_pin_save(void) { return memalloc_flags_save(PF_MEMALLOC_PIN); } /** * memalloc_pin_restore - Ends the implicit ~__GFP_MOVABLE scope. * @flags: Flags to restore. * * Ends the implicit ~__GFP_MOVABLE scope started by memalloc_pin_save function. * Always make sure that the given flags is the return value from the pairing * memalloc_pin_save call. */ static inline void memalloc_pin_restore(unsigned int flags) { memalloc_flags_restore(flags); } #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * * Please, make sure that caller has a reference to the passed memcg structure, * so its lifetime is guaranteed to exceed the scope between two * set_active_memcg() calls. * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { struct mem_cgroup *old; if (!in_task()) { old = this_cpu_read(int_active_memcg); this_cpu_write(int_active_memcg, memcg); } else { old = current->active_memcg; current->active_memcg = memcg; } return old; } #else static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { return NULL; } #endif #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include <asm/membarrier.h> #endif static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return; sync_core_before_usermode(); } extern void membarrier_exec_mmap(struct mm_struct *mm); extern void membarrier_update_current_mm(struct mm_struct *next_mm); #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { } #endif static inline void membarrier_exec_mmap(struct mm_struct *mm) { } static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } static inline void membarrier_update_current_mm(struct mm_struct *next_mm) { } #endif #endif /* _LINUX_SCHED_MM_H */ |
| 5 117 116 3 12 105 157 3 6 152 121 105 105 3 73 100 1 1 203 2 201 40 156 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kexec.c - kexec_load system call * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/security.h> #include <linux/kexec.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/syscalls.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include "kexec_internal.h" static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, unsigned long nr_segments, struct kexec_segment *segments, unsigned long flags) { int ret; struct kimage *image; bool kexec_on_panic = flags & KEXEC_ON_CRASH; #ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Verify we have a valid entry point */ if ((entry < phys_to_boot_phys(crashk_res.start)) || (entry > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } #endif /* Allocate and initialize a controlling structure */ image = do_kimage_alloc_init(); if (!image) return -ENOMEM; image->start = entry; image->nr_segments = nr_segments; memcpy(image->segment, segments, nr_segments * sizeof(*segments)); #ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ image->control_page = crashk_res.start; image->type = KEXEC_TYPE_CRASH; } #endif ret = sanity_check_segment_list(image); if (ret) goto out_free_image; /* * Find a location for the control code buffer, and add it * the vector of segments so that it's pages will also be * counted as destination pages. */ ret = -ENOMEM; image->control_code_page = kimage_alloc_control_pages(image, get_order(KEXEC_CONTROL_PAGE_SIZE)); if (!image->control_code_page) { pr_err("Could not allocate control_code_buffer\n"); goto out_free_image; } if (!kexec_on_panic) { image->swap_page = kimage_alloc_control_pages(image, 0); if (!image->swap_page) { pr_err("Could not allocate swap buffer\n"); goto out_free_control_pages; } } *rimage = image; return 0; out_free_control_pages: kimage_free_page_list(&image->control_pages); out_free_image: kfree(image); return ret; } static int do_kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment *segments, unsigned long flags) { struct kimage **dest_image, *image; unsigned long i; int ret; /* * Because we write directly to the reserved memory region when loading * crash kernels we need a serialization here to prevent multiple crash * kernels from attempting to load simultaneously. */ if (!kexec_trylock()) return -EBUSY; #ifdef CONFIG_CRASH_DUMP if (flags & KEXEC_ON_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); } else #endif dest_image = &kexec_image; if (nr_segments == 0) { /* Uninstall image */ kimage_free(xchg(dest_image, NULL)); ret = 0; goto out_unlock; } if (flags & KEXEC_ON_CRASH) { /* * Loading another kernel to switch to if this one * crashes. Free any current crash dump kernel before * we corrupt it. */ kimage_free(xchg(&kexec_crash_image, NULL)); } ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags); if (ret) goto out_unlock; if (flags & KEXEC_PRESERVE_CONTEXT) image->preserve_context = 1; #ifdef CONFIG_CRASH_HOTPLUG if ((flags & KEXEC_ON_CRASH) && arch_crash_hotplug_support(image, flags)) image->hotplug_support = 1; #endif ret = machine_kexec_prepare(image); if (ret) goto out; /* * Some architecture(like S390) may touch the crash memory before * machine_kexec_prepare(), we must copy vmcoreinfo data after it. */ ret = kimage_crash_copy_vmcoreinfo(image); if (ret) goto out; for (i = 0; i < nr_segments; i++) { ret = kimage_load_segment(image, &image->segment[i]); if (ret) goto out; } kimage_terminate(image); ret = machine_kexec_post_load(image); if (ret) goto out; /* Install the new kernel and uninstall the old */ image = xchg(dest_image, image); out: #ifdef CONFIG_CRASH_DUMP if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); #endif kimage_free(image); out_unlock: kexec_unlock(); return ret; } /* * Exec Kernel system call: for obvious reasons only root may call it. * * This call breaks up into three pieces. * - A generic part which loads the new kernel from the current * address space, and very carefully places the data in the * allocated pages. * * - A generic part that interacts with the kernel and tells all of * the devices to shut down. Preventing on-going dmas, and placing * the devices in a consistent state so a later kernel can * reinitialize them. * * - A machine specific part that includes the syscall number * and then copies the image to it's final destination. And * jumps into the image at entry. * * kexec does not sync, or unmount filesystems so if you need * that to happen you need to do that yourself. */ static inline int kexec_load_check(unsigned long nr_segments, unsigned long flags) { int image_type = (flags & KEXEC_ON_CRASH) ? KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT; int result; /* We only trust the superuser with rebooting the system. */ if (!kexec_load_permitted(image_type)) return -EPERM; /* Permit LSMs and IMA to fail the kexec */ result = security_kernel_load_data(LOADING_KEXEC_IMAGE, false); if (result < 0) return result; /* * kexec can be used to circumvent module loading restrictions, so * prevent loading in that case */ result = security_locked_down(LOCKDOWN_KEXEC); if (result) return result; /* * Verify we have a legal set of flags * This leaves us room for future extensions. */ if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK)) return -EINVAL; /* Put an artificial cap on the number * of segments passed to kexec_load. */ if (nr_segments > KEXEC_SEGMENT_MAX) return -EINVAL; return 0; } SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, struct kexec_segment __user *, segments, unsigned long, flags) { struct kexec_segment *ksegments; unsigned long result; result = kexec_load_check(nr_segments, flags); if (result) return result; /* Verify we are on the appropriate architecture */ if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) && ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) return -EINVAL; ksegments = memdup_array_user(segments, nr_segments, sizeof(ksegments[0])); if (IS_ERR(ksegments)) return PTR_ERR(ksegments); result = do_kexec_load(entry, nr_segments, ksegments, flags); kfree(ksegments); return result; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, compat_ulong_t, nr_segments, struct compat_kexec_segment __user *, segments, compat_ulong_t, flags) { struct compat_kexec_segment in; struct kexec_segment *ksegments; unsigned long i, result; result = kexec_load_check(nr_segments, flags); if (result) return result; /* Don't allow clients that don't understand the native * architecture to do anything. */ if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT) return -EINVAL; ksegments = kmalloc_array(nr_segments, sizeof(ksegments[0]), GFP_KERNEL); if (!ksegments) return -ENOMEM; for (i = 0; i < nr_segments; i++) { result = copy_from_user(&in, &segments[i], sizeof(in)); if (result) goto fail; ksegments[i].buf = compat_ptr(in.buf); ksegments[i].bufsz = in.bufsz; ksegments[i].mem = in.mem; ksegments[i].memsz = in.memsz; } result = do_kexec_load(entry, nr_segments, ksegments, flags); fail: kfree(ksegments); return result; } #endif |
| 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 9 19 19 23 23 23 23 23 19 19 19 19 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 | // SPDX-License-Identifier: GPL-2.0-only /* Object lifetime handling and tracing. * * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/slab.h> #include <linux/mempool.h> #include <linux/delay.h> #include "internal.h" /* * Allocate an I/O request and initialise it. */ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct file *file, loff_t start, size_t len, enum netfs_io_origin origin) { static atomic_t debug_ids; struct inode *inode = file ? file_inode(file) : mapping->host; struct netfs_inode *ctx = netfs_inode(inode); struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; int ret; for (;;) { rreq = mempool_alloc(mempool, GFP_KERNEL); if (rreq) break; msleep(10); } memset(rreq, 0, kmem_cache_size(cache)); rreq->start = start; rreq->len = len; rreq->origin = origin; rreq->netfs_ops = ctx->ops; rreq->mapping = mapping; rreq->inode = inode; rreq->i_size = i_size_read(inode); rreq->debug_id = atomic_inc_return(&debug_ids); rreq->wsize = INT_MAX; rreq->io_streams[0].sreq_max_len = ULONG_MAX; rreq->io_streams[0].sreq_max_segs = 0; spin_lock_init(&rreq->lock); INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); init_waitqueue_head(&rreq->waitq); refcount_set(&rreq->ref, 1); if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || origin == NETFS_READ_GAPS || origin == NETFS_READ_SINGLE || origin == NETFS_READ_FOR_WRITE || origin == NETFS_DIO_READ) { INIT_WORK(&rreq->work, netfs_read_collection_worker); rreq->io_streams[0].avail = true; } else { INIT_WORK(&rreq->work, netfs_write_collection_worker); } __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { ret = rreq->netfs_ops->init_request(rreq, file); if (ret < 0) { mempool_free(rreq, rreq->netfs_ops->request_pool ?: &netfs_request_pool); return ERR_PTR(ret); } } atomic_inc(&ctx->io_count); trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new); netfs_proc_add_rreq(rreq); netfs_stat(&netfs_n_rh_rreq); return rreq; } void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what) { int r; __refcount_inc(&rreq->ref, &r); trace_netfs_rreq_ref(rreq->debug_id, r + 1, what); } void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async) { struct netfs_io_subrequest *subreq; struct netfs_io_stream *stream; int s; for (s = 0; s < ARRAY_SIZE(rreq->io_streams); s++) { stream = &rreq->io_streams[s]; while (!list_empty(&stream->subrequests)) { subreq = list_first_entry(&stream->subrequests, struct netfs_io_subrequest, rreq_link); list_del(&subreq->rreq_link); netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_clear); } } } static void netfs_free_request_rcu(struct rcu_head *rcu) { struct netfs_io_request *rreq = container_of(rcu, struct netfs_io_request, rcu); mempool_free(rreq, rreq->netfs_ops->request_pool ?: &netfs_request_pool); netfs_stat_d(&netfs_n_rh_rreq); } static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); struct netfs_inode *ictx = netfs_inode(rreq->inode); unsigned int i; trace_netfs_rreq(rreq, netfs_rreq_trace_free); netfs_proc_del_rreq(rreq); netfs_clear_subrequests(rreq, false); if (rreq->netfs_ops->free_request) rreq->netfs_ops->free_request(rreq); if (rreq->cache_resources.ops) rreq->cache_resources.ops->end_operation(&rreq->cache_resources); if (rreq->direct_bv) { for (i = 0; i < rreq->direct_bv_count; i++) { if (rreq->direct_bv[i].bv_page) { if (rreq->direct_bv_unpin) unpin_user_page(rreq->direct_bv[i].bv_page); } } kvfree(rreq->direct_bv); } rolling_buffer_clear(&rreq->buffer); if (atomic_dec_and_test(&ictx->io_count)) wake_up_var(&ictx->io_count); call_rcu(&rreq->rcu, netfs_free_request_rcu); } void netfs_put_request(struct netfs_io_request *rreq, bool was_async, enum netfs_rreq_ref_trace what) { unsigned int debug_id; bool dead; int r; if (rreq) { debug_id = rreq->debug_id; dead = __refcount_dec_and_test(&rreq->ref, &r); trace_netfs_rreq_ref(debug_id, r - 1, what); if (dead) { if (was_async) { rreq->work.func = netfs_free_request; if (!queue_work(system_unbound_wq, &rreq->work)) WARN_ON(1); } else { netfs_free_request(&rreq->work); } } } } /* * Allocate and partially initialise an I/O request structure. */ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; mempool_t *mempool = rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool; struct kmem_cache *cache = mempool->pool_data; for (;;) { subreq = mempool_alloc(rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool, GFP_KERNEL); if (subreq) break; msleep(10); } memset(subreq, 0, kmem_cache_size(cache)); INIT_WORK(&subreq->work, NULL); INIT_LIST_HEAD(&subreq->rreq_link); refcount_set(&subreq->ref, 2); subreq->rreq = rreq; subreq->debug_index = atomic_inc_return(&rreq->subreq_counter); netfs_get_request(rreq, netfs_rreq_trace_get_subreq); netfs_stat(&netfs_n_rh_sreq); return subreq; } void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what) { int r; __refcount_inc(&subreq->ref, &r); trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, r + 1, what); } static void netfs_free_subrequest(struct netfs_io_subrequest *subreq, bool was_async) { struct netfs_io_request *rreq = subreq->rreq; trace_netfs_sreq(subreq, netfs_sreq_trace_free); if (rreq->netfs_ops->free_subrequest) rreq->netfs_ops->free_subrequest(subreq); mempool_free(subreq, rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool); netfs_stat_d(&netfs_n_rh_sreq); netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq); } void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what) { unsigned int debug_index = subreq->debug_index; unsigned int debug_id = subreq->rreq->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&subreq->ref, &r); trace_netfs_sreq_ref(debug_id, debug_index, r - 1, what); if (dead) netfs_free_subrequest(subreq, was_async); } |
| 116 117 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <net/macsec.h> #include "netdevsim.h" static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci) { int i; for (i = 0; i < NSIM_MACSEC_MAX_SECY_COUNT; i++) { if (ns->macsec.nsim_secy[i].sci == sci) return i; } return -1; } static int nsim_macsec_find_rxsc(struct nsim_secy *ns_secy, sci_t sci) { int i; for (i = 0; i < NSIM_MACSEC_MAX_RXSC_COUNT; i++) { if (ns_secy->nsim_rxsc[i].sci == sci) return i; } return -1; } static int nsim_macsec_add_secy(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; if (ns->macsec.nsim_secy_count == NSIM_MACSEC_MAX_SECY_COUNT) return -ENOSPC; for (idx = 0; idx < NSIM_MACSEC_MAX_SECY_COUNT; idx++) { if (!ns->macsec.nsim_secy[idx].used) break; } if (idx == NSIM_MACSEC_MAX_SECY_COUNT) { netdev_err(ctx->netdev, "%s: nsim_secy_count not full but all SecYs used\n", __func__); return -ENOSPC; } netdev_dbg(ctx->netdev, "%s: adding new secy with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->secy->sci), idx); ns->macsec.nsim_secy[idx].used = true; ns->macsec.nsim_secy[idx].nsim_rxsc_count = 0; ns->macsec.nsim_secy[idx].sci = ctx->secy->sci; ns->macsec.nsim_secy_count++; return 0; } static int nsim_macsec_upd_secy(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: updating secy with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->secy->sci), idx); return 0; } static int nsim_macsec_del_secy(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: removing SecY with SCI %016llx at index %d\n", __func__, sci_to_cpu(ctx->secy->sci), idx); ns->macsec.nsim_secy[idx].used = false; memset(&ns->macsec.nsim_secy[idx], 0, sizeof(ns->macsec.nsim_secy[idx])); ns->macsec.nsim_secy_count--; return 0; } static int nsim_macsec_add_rxsc(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; if (secy->nsim_rxsc_count == NSIM_MACSEC_MAX_RXSC_COUNT) return -ENOSPC; for (idx = 0; idx < NSIM_MACSEC_MAX_RXSC_COUNT; idx++) { if (!secy->nsim_rxsc[idx].used) break; } if (idx == NSIM_MACSEC_MAX_RXSC_COUNT) netdev_err(ctx->netdev, "%s: nsim_rxsc_count not full but all RXSCs used\n", __func__); netdev_dbg(ctx->netdev, "%s: adding new rxsc with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->rx_sc->sci), idx); secy->nsim_rxsc[idx].used = true; secy->nsim_rxsc[idx].sci = ctx->rx_sc->sci; secy->nsim_rxsc_count++; return 0; } static int nsim_macsec_upd_rxsc(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->rx_sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: updating RXSC with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->rx_sc->sci), idx); return 0; } static int nsim_macsec_del_rxsc(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->rx_sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: removing RXSC with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->rx_sc->sci), idx); secy->nsim_rxsc[idx].used = false; memset(&secy->nsim_rxsc[idx], 0, sizeof(secy->nsim_rxsc[idx])); secy->nsim_rxsc_count--; return 0; } static int nsim_macsec_add_rxsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_upd_rxsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_del_rxsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_add_txsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_upd_txsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_del_txsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num); return 0; } static const struct macsec_ops nsim_macsec_ops = { .mdo_add_secy = nsim_macsec_add_secy, .mdo_upd_secy = nsim_macsec_upd_secy, .mdo_del_secy = nsim_macsec_del_secy, .mdo_add_rxsc = nsim_macsec_add_rxsc, .mdo_upd_rxsc = nsim_macsec_upd_rxsc, .mdo_del_rxsc = nsim_macsec_del_rxsc, .mdo_add_rxsa = nsim_macsec_add_rxsa, .mdo_upd_rxsa = nsim_macsec_upd_rxsa, .mdo_del_rxsa = nsim_macsec_del_rxsa, .mdo_add_txsa = nsim_macsec_add_txsa, .mdo_upd_txsa = nsim_macsec_upd_txsa, .mdo_del_txsa = nsim_macsec_del_txsa, }; void nsim_macsec_init(struct netdevsim *ns) { ns->netdev->macsec_ops = &nsim_macsec_ops; ns->netdev->features |= NETIF_F_HW_MACSEC; memset(&ns->macsec, 0, sizeof(ns->macsec)); } void nsim_macsec_teardown(struct netdevsim *ns) { } |
| 2 2 2 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2020 Facebook */ #include <linux/fs.h> #include <linux/anon_inodes.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/rcupdate_trace.h> struct bpf_iter_target_info { struct list_head list; const struct bpf_iter_reg *reg_info; u32 btf_id; /* cached value */ }; struct bpf_iter_link { struct bpf_link link; struct bpf_iter_aux_info aux; struct bpf_iter_target_info *tinfo; }; struct bpf_iter_priv_data { struct bpf_iter_target_info *tinfo; const struct bpf_iter_seq_info *seq_info; struct bpf_prog *prog; u64 session_id; u64 seq_num; bool done_stop; u8 target_private[] __aligned(8); }; static struct list_head targets = LIST_HEAD_INIT(targets); static DEFINE_MUTEX(targets_mutex); /* protect bpf_iter_link changes */ static DEFINE_MUTEX(link_mutex); /* incremented on every opened seq_file */ static atomic64_t session_id; static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, const struct bpf_iter_seq_info *seq_info); static void bpf_iter_inc_seq_num(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); iter_priv->seq_num++; } static void bpf_iter_dec_seq_num(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); iter_priv->seq_num--; } static void bpf_iter_done_stop(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); iter_priv->done_stop = true; } static inline bool bpf_iter_target_support_resched(const struct bpf_iter_target_info *tinfo) { return tinfo->reg_info->feature & BPF_ITER_RESCHED; } static bool bpf_iter_support_resched(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); return bpf_iter_target_support_resched(iter_priv->tinfo); } /* maximum visited objects before bailing out */ #define MAX_ITER_OBJECTS 1000000 /* bpf_seq_read, a customized and simpler version for bpf iterator. * The following are differences from seq_read(): * . fixed buffer size (PAGE_SIZE) * . assuming NULL ->llseek() * . stop() may call bpf program, handling potential overflow there */ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; int err = 0, num_objs = 0; bool can_resched; void *p; mutex_lock(&seq->lock); if (!seq->buf) { seq->size = PAGE_SIZE << 3; seq->buf = kvmalloc(seq->size, GFP_KERNEL); if (!seq->buf) { err = -ENOMEM; goto done; } } if (seq->count) { n = min(seq->count, size); err = copy_to_user(buf, seq->buf + seq->from, n); if (err) { err = -EFAULT; goto done; } seq->count -= n; seq->from += n; copied = n; goto done; } seq->from = 0; p = seq->op->start(seq, &seq->index); if (!p) goto stop; if (IS_ERR(p)) { err = PTR_ERR(p); seq->op->stop(seq, p); seq->count = 0; goto done; } err = seq->op->show(seq, p); if (err > 0) { /* object is skipped, decrease seq_num, so next * valid object can reuse the same seq_num. */ bpf_iter_dec_seq_num(seq); seq->count = 0; } else if (err < 0 || seq_has_overflowed(seq)) { if (!err) err = -E2BIG; seq->op->stop(seq, p); seq->count = 0; goto done; } can_resched = bpf_iter_support_resched(seq); while (1) { loff_t pos = seq->index; num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { pr_info_ratelimited("buggy seq_file .next function %ps " "did not updated position index\n", seq->op->next); seq->index++; } if (IS_ERR_OR_NULL(p)) break; /* got a valid next object, increase seq_num */ bpf_iter_inc_seq_num(seq); if (seq->count >= size) break; if (num_objs >= MAX_ITER_OBJECTS) { if (offs == 0) { err = -EAGAIN; seq->op->stop(seq, p); goto done; } break; } err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); seq->count = offs; } else if (err < 0 || seq_has_overflowed(seq)) { seq->count = offs; if (offs == 0) { if (!err) err = -E2BIG; seq->op->stop(seq, p); goto done; } break; } if (can_resched) cond_resched(); } stop: offs = seq->count; if (IS_ERR(p)) { seq->op->stop(seq, NULL); err = PTR_ERR(p); goto done; } /* bpf program called if !p */ seq->op->stop(seq, p); if (!p) { if (!seq_has_overflowed(seq)) { bpf_iter_done_stop(seq); } else { seq->count = offs; if (offs == 0) { err = -E2BIG; goto done; } } } n = min(seq->count, size); err = copy_to_user(buf, seq->buf, n); if (err) { err = -EFAULT; goto done; } copied = n; seq->count -= n; seq->from = n; done: if (!copied) copied = err; else *ppos += copied; mutex_unlock(&seq->lock); return copied; } static const struct bpf_iter_seq_info * __get_seq_info(struct bpf_iter_link *link) { const struct bpf_iter_seq_info *seq_info; if (link->aux.map) { seq_info = link->aux.map->ops->iter_seq_info; if (seq_info) return seq_info; } return link->tinfo->reg_info->seq_info; } static int iter_open(struct inode *inode, struct file *file) { struct bpf_iter_link *link = inode->i_private; return prepare_seq_file(file, link, __get_seq_info(link)); } static int iter_release(struct inode *inode, struct file *file) { struct bpf_iter_priv_data *iter_priv; struct seq_file *seq; seq = file->private_data; if (!seq) return 0; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); if (iter_priv->seq_info->fini_seq_private) iter_priv->seq_info->fini_seq_private(seq->private); bpf_prog_put(iter_priv->prog); seq->private = iter_priv; return seq_release_private(inode, file); } const struct file_operations bpf_iter_fops = { .open = iter_open, .read = bpf_seq_read, .release = iter_release, }; /* The argument reg_info will be cached in bpf_iter_target_info. * The common practice is to declare target reg_info as * a const static variable and passed as an argument to * bpf_iter_reg_target(). */ int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; tinfo = kzalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) return -ENOMEM; tinfo->reg_info = reg_info; INIT_LIST_HEAD(&tinfo->list); mutex_lock(&targets_mutex); list_add(&tinfo->list, &targets); mutex_unlock(&targets_mutex); return 0; } void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; bool found = false; mutex_lock(&targets_mutex); list_for_each_entry(tinfo, &targets, list) { if (reg_info == tinfo->reg_info) { list_del(&tinfo->list); kfree(tinfo); found = true; break; } } mutex_unlock(&targets_mutex); WARN_ON(found == false); } static void cache_btf_id(struct bpf_iter_target_info *tinfo, struct bpf_prog *prog) { tinfo->btf_id = prog->aux->attach_btf_id; } bool bpf_iter_prog_supported(struct bpf_prog *prog) { const char *attach_fname = prog->aux->attach_func_name; struct bpf_iter_target_info *tinfo = NULL, *iter; u32 prog_btf_id = prog->aux->attach_btf_id; const char *prefix = BPF_ITER_FUNC_PREFIX; int prefix_len = strlen(prefix); if (strncmp(attach_fname, prefix, prefix_len)) return false; mutex_lock(&targets_mutex); list_for_each_entry(iter, &targets, list) { if (iter->btf_id && iter->btf_id == prog_btf_id) { tinfo = iter; break; } if (!strcmp(attach_fname + prefix_len, iter->reg_info->target)) { cache_btf_id(iter, prog); tinfo = iter; break; } } mutex_unlock(&targets_mutex); if (tinfo) { prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size; prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info; } return tinfo != NULL; } const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_iter_target_info *tinfo; const struct bpf_func_proto *fn = NULL; mutex_lock(&targets_mutex); list_for_each_entry(tinfo, &targets, list) { if (tinfo->btf_id == prog->aux->attach_btf_id) { const struct bpf_iter_reg *reg_info; reg_info = tinfo->reg_info; if (reg_info->get_func_proto) fn = reg_info->get_func_proto(func_id, prog); break; } } mutex_unlock(&targets_mutex); return fn; } static void bpf_iter_link_release(struct bpf_link *link) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); if (iter_link->tinfo->reg_info->detach_target) iter_link->tinfo->reg_info->detach_target(&iter_link->aux); } static void bpf_iter_link_dealloc(struct bpf_link *link) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); kfree(iter_link); } static int bpf_iter_link_replace(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { int ret = 0; mutex_lock(&link_mutex); if (old_prog && link->prog != old_prog) { ret = -EPERM; goto out_unlock; } if (link->prog->type != new_prog->type || link->prog->expected_attach_type != new_prog->expected_attach_type || link->prog->aux->attach_btf_id != new_prog->aux->attach_btf_id) { ret = -EINVAL; goto out_unlock; } old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: mutex_unlock(&link_mutex); return ret; } static void bpf_iter_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); bpf_iter_show_fdinfo_t show_fdinfo; seq_printf(seq, "target_name:\t%s\n", iter_link->tinfo->reg_info->target); show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo; if (show_fdinfo) show_fdinfo(&iter_link->aux, seq); } static int bpf_iter_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); char __user *ubuf = u64_to_user_ptr(info->iter.target_name); bpf_iter_fill_link_info_t fill_link_info; u32 ulen = info->iter.target_name_len; const char *target_name; u32 target_len; if (!ulen ^ !ubuf) return -EINVAL; target_name = iter_link->tinfo->reg_info->target; target_len = strlen(target_name); info->iter.target_name_len = target_len + 1; if (ubuf) { if (ulen >= target_len + 1) { if (copy_to_user(ubuf, target_name, target_len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, target_name, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } } fill_link_info = iter_link->tinfo->reg_info->fill_link_info; if (fill_link_info) return fill_link_info(&iter_link->aux, info); return 0; } static const struct bpf_link_ops bpf_iter_link_lops = { .release = bpf_iter_link_release, .dealloc = bpf_iter_link_dealloc, .update_prog = bpf_iter_link_replace, .show_fdinfo = bpf_iter_link_show_fdinfo, .fill_link_info = bpf_iter_link_fill_link_info, }; bool bpf_link_is_iter(struct bpf_link *link) { return link->ops == &bpf_iter_link_lops; } int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog) { struct bpf_iter_target_info *tinfo = NULL, *iter; struct bpf_link_primer link_primer; union bpf_iter_link_info linfo; struct bpf_iter_link *link; u32 prog_btf_id, linfo_len; bpfptr_t ulinfo; int err; if (attr->link_create.target_fd || attr->link_create.flags) return -EINVAL; memset(&linfo, 0, sizeof(union bpf_iter_link_info)); ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel); linfo_len = attr->link_create.iter_info_len; if (bpfptr_is_null(ulinfo) ^ !linfo_len) return -EINVAL; if (!bpfptr_is_null(ulinfo)) { err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo), linfo_len); if (err) return err; linfo_len = min_t(u32, linfo_len, sizeof(linfo)); if (copy_from_bpfptr(&linfo, ulinfo, linfo_len)) return -EFAULT; } prog_btf_id = prog->aux->attach_btf_id; mutex_lock(&targets_mutex); list_for_each_entry(iter, &targets, list) { if (iter->btf_id == prog_btf_id) { tinfo = iter; break; } } mutex_unlock(&targets_mutex); if (!tinfo) return -ENOENT; /* Only allow sleepable program for resched-able iterator */ if (prog->sleepable && !bpf_iter_target_support_resched(tinfo)) return -EINVAL; link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); if (!link) return -ENOMEM; bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); link->tinfo = tinfo; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; } if (tinfo->reg_info->attach_target) { err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux); if (err) { bpf_link_cleanup(&link_primer); return err; } } return bpf_link_settle(&link_primer); } static void init_seq_meta(struct bpf_iter_priv_data *priv_data, struct bpf_iter_target_info *tinfo, const struct bpf_iter_seq_info *seq_info, struct bpf_prog *prog) { priv_data->tinfo = tinfo; priv_data->seq_info = seq_info; priv_data->prog = prog; priv_data->session_id = atomic64_inc_return(&session_id); priv_data->seq_num = 0; priv_data->done_stop = false; } static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, const struct bpf_iter_seq_info *seq_info) { struct bpf_iter_priv_data *priv_data; struct bpf_iter_target_info *tinfo; struct bpf_prog *prog; u32 total_priv_dsize; struct seq_file *seq; int err = 0; mutex_lock(&link_mutex); prog = link->link.prog; bpf_prog_inc(prog); mutex_unlock(&link_mutex); tinfo = link->tinfo; total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) + seq_info->seq_priv_size; priv_data = __seq_open_private(file, seq_info->seq_ops, total_priv_dsize); if (!priv_data) { err = -ENOMEM; goto release_prog; } if (seq_info->init_seq_private) { err = seq_info->init_seq_private(priv_data->target_private, &link->aux); if (err) goto release_seq_file; } init_seq_meta(priv_data, tinfo, seq_info, prog); seq = file->private_data; seq->private = priv_data->target_private; return 0; release_seq_file: seq_release_private(file->f_inode, file); file->private_data = NULL; release_prog: bpf_prog_put(prog); return err; } int bpf_iter_new_fd(struct bpf_link *link) { struct bpf_iter_link *iter_link; struct file *file; unsigned int flags; int err, fd; if (link->ops != &bpf_iter_link_lops) return -EINVAL; flags = O_RDONLY | O_CLOEXEC; fd = get_unused_fd_flags(flags); if (fd < 0) return fd; file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags); if (IS_ERR(file)) { err = PTR_ERR(file); goto free_fd; } iter_link = container_of(link, struct bpf_iter_link, link); err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link)); if (err) goto free_file; fd_install(fd, file); return fd; free_file: fput(file); free_fd: put_unused_fd(fd); return err; } struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop) { struct bpf_iter_priv_data *iter_priv; struct seq_file *seq; void *seq_priv; seq = meta->seq; if (seq->file->f_op != &bpf_iter_fops) return NULL; seq_priv = seq->private; iter_priv = container_of(seq_priv, struct bpf_iter_priv_data, target_private); if (in_stop && iter_priv->done_stop) return NULL; meta->session_id = iter_priv->session_id; meta->seq_num = iter_priv->seq_num; return iter_priv->prog; } int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) { struct bpf_run_ctx run_ctx, *old_run_ctx; int ret; if (prog->sleepable) { rcu_read_lock_trace(); migrate_disable(); might_fault(); old_run_ctx = bpf_set_run_ctx(&run_ctx); ret = bpf_prog_run(prog, ctx); bpf_reset_run_ctx(old_run_ctx); migrate_enable(); rcu_read_unlock_trace(); } else { rcu_read_lock(); migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx); ret = bpf_prog_run(prog, ctx); bpf_reset_run_ctx(old_run_ctx); migrate_enable(); rcu_read_unlock(); } /* bpf program can only return 0 or 1: * 0 : okay * 1 : retry the same object * The bpf_iter_run_prog() return value * will be seq_ops->show() return value. */ return ret == 0 ? 0 : -EAGAIN; } BPF_CALL_4(bpf_for_each_map_elem, struct bpf_map *, map, void *, callback_fn, void *, callback_ctx, u64, flags) { return map->ops->map_for_each_callback(map, callback_fn, callback_ctx, flags); } const struct bpf_func_proto bpf_for_each_map_elem_proto = { .func = bpf_for_each_map_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, u64, flags) { bpf_callback_t callback = (bpf_callback_t)callback_fn; u64 ret; u32 i; /* Note: these safety checks are also verified when bpf_loop * is inlined, be careful to modify this code in sync. See * function verifier.c:inline_bpf_loop. */ if (flags) return -EINVAL; if (nr_loops > BPF_MAX_LOOPS) return -E2BIG; for (i = 0; i < nr_loops; i++) { ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) return i + 1; } return i; } const struct bpf_func_proto bpf_loop_proto = { .func = bpf_loop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; struct bpf_iter_num_kern { int cur; /* current value, inclusive */ int end; /* final value, exclusive */ } __aligned(8); __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) { struct bpf_iter_num_kern *s = (void *)it; BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num)); BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num)); /* start == end is legit, it's an empty range and we'll just get NULL * on first (and any subsequent) bpf_iter_num_next() call */ if (start > end) { s->cur = s->end = 0; return -EINVAL; } /* avoid overflows, e.g., if start == INT_MIN and end == INT_MAX */ if ((s64)end - (s64)start > BPF_MAX_LOOPS) { s->cur = s->end = 0; return -E2BIG; } /* user will call bpf_iter_num_next() first, * which will set s->cur to exactly start value; * underflow shouldn't matter */ s->cur = start - 1; s->end = end; return 0; } __bpf_kfunc int *bpf_iter_num_next(struct bpf_iter_num* it) { struct bpf_iter_num_kern *s = (void *)it; /* check failed initialization or if we are done (same behavior); * need to be careful about overflow, so convert to s64 for checks, * e.g., if s->cur == s->end == INT_MAX, we can't just do * s->cur + 1 >= s->end */ if ((s64)(s->cur + 1) >= s->end) { s->cur = s->end = 0; return NULL; } s->cur++; return &s->cur; } __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it) { struct bpf_iter_num_kern *s = (void *)it; s->cur = s->end = 0; } __bpf_kfunc_end_defs(); |
| 16 60 60 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 | // SPDX-License-Identifier: GPL-2.0-only /* * Suspend support specific for i386/x86-64. * * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl> * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org> */ #include <linux/suspend.h> #include <linux/export.h> #include <linux/smp.h> #include <linux/perf_event.h> #include <linux/tboot.h> #include <linux/dmi.h> #include <linux/pgtable.h> #include <asm/proto.h> #include <asm/mtrr.h> #include <asm/page.h> #include <asm/mce.h> #include <asm/suspend.h> #include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/cacheinfo.h> #include <asm/mmu_context.h> #include <asm/cpu_device_id.h> #include <asm/microcode.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; __visible unsigned long saved_context_esp, saved_context_ebp; __visible unsigned long saved_context_esi, saved_context_edi; __visible unsigned long saved_context_eflags; #endif struct saved_context saved_context; static void msr_save_context(struct saved_context *ctxt) { struct saved_msr *msr = ctxt->saved_msrs.array; struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { if (msr->valid) rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } static void msr_restore_context(struct saved_context *ctxt) { struct saved_msr *msr = ctxt->saved_msrs.array; struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { if (msr->valid) wrmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } /** * __save_processor_state() - Save CPU registers before creating a * hibernation image and before restoring * the memory state from it * @ctxt: Structure to store the registers contents in. * * NOTE: If there is a CPU register the modification of which by the * boot kernel (ie. the kernel used for loading the hibernation image) * might affect the operations of the restored target kernel (ie. the one * saved in the hibernation image), then its contents must be saved by this * function. In other words, if kernel A is hibernated and different * kernel B is used for loading the hibernation image into memory, the * kernel A's __save_processor_state() function must save all registers * needed by kernel A, so that it can operate correctly after the resume * regardless of what kernel B does in the meantime. */ static void __save_processor_state(struct saved_context *ctxt) { #ifdef CONFIG_X86_32 mtrr_save_fixed_ranges(NULL); #endif kernel_fpu_begin(); /* * descriptor tables */ store_idt(&ctxt->idt); /* * We save it here, but restore it only in the hibernate case. * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit * mode in "secondary_startup_64". In 32-bit mode it is done via * 'pmode_gdt' in wakeup_start. */ ctxt->gdt_desc.size = GDT_SIZE - 1; ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id()); store_tr(ctxt->tr); /* XMM0..XMM15 should be handled by kernel_fpu_begin(). */ /* * segment registers */ savesegment(gs, ctxt->gs); #ifdef CONFIG_X86_64 savesegment(fs, ctxt->fs); savesegment(ds, ctxt->ds); savesegment(es, ctxt->es); rdmsrl(MSR_FS_BASE, ctxt->fs_base); rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); mtrr_save_fixed_ranges(NULL); rdmsrl(MSR_EFER, ctxt->efer); #endif /* * control registers */ ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); ctxt->cr3 = __read_cr3(); ctxt->cr4 = __read_cr4(); ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, &ctxt->misc_enable); msr_save_context(ctxt); } /* Needed by apm.c */ void save_processor_state(void) { __save_processor_state(&saved_context); x86_platform.save_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(save_processor_state); #endif static void do_fpu_end(void) { /* * Restore FPU regs if necessary. */ kernel_fpu_end(); } static void fix_processor_context(void) { int cpu = smp_processor_id(); #ifdef CONFIG_X86_64 struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif /* * We need to reload TR, which requires that we change the * GDT entry to indicate "available" first. * * XXX: This could probably all be replaced by a call to * force_reload_TR(). */ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); #ifdef CONFIG_X86_64 memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); tss.type = 0x9; /* The available 64-bit TSS (see AMD vol 2, pg 91 */ write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS); syscall_init(); /* This sets MSR_*STAR and related */ #else if (boot_cpu_has(X86_FEATURE_SEP)) enable_sep_cpu(); #endif load_TR_desc(); /* This does ltr */ load_mm_ldt(current->active_mm); /* This does lldt */ initialize_tlbstate_and_flush(); fpu__resume_cpu(); /* The processor is back on the direct GDT, load back the fixmap */ load_fixmap_gdt(cpu); } /** * __restore_processor_state() - Restore the contents of CPU registers saved * by __save_processor_state() * @ctxt: Structure to load the registers contents from. * * The asm code that gets us here will have restored a usable GDT, although * it will be pointing to the wrong alias. */ static void notrace __restore_processor_state(struct saved_context *ctxt) { struct cpuinfo_x86 *c; if (ctxt->misc_enable_saved) wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* * control registers */ /* cr4 was introduced in the Pentium CPU */ #ifdef CONFIG_X86_32 if (ctxt->cr4) __write_cr4(ctxt->cr4); #else /* CONFIG X86_64 */ wrmsrl(MSR_EFER, ctxt->efer); __write_cr4(ctxt->cr4); #endif write_cr3(ctxt->cr3); write_cr2(ctxt->cr2); write_cr0(ctxt->cr0); /* Restore the IDT. */ load_idt(&ctxt->idt); /* * Just in case the asm code got us here with the SS, DS, or ES * out of sync with the GDT, update them. */ loadsegment(ss, __KERNEL_DS); loadsegment(ds, __USER_DS); loadsegment(es, __USER_DS); /* * Restore percpu access. Percpu access can happen in exception * handlers or in complicated helpers like load_gs_index(). */ #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); #else loadsegment(fs, __KERNEL_PERCPU); #endif /* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */ fix_processor_context(); /* * Now that we have descriptor tables fully restored and working * exception handling, restore the usermode segments. */ #ifdef CONFIG_X86_64 loadsegment(ds, ctxt->es); loadsegment(es, ctxt->es); loadsegment(fs, ctxt->fs); load_gs_index(ctxt->gs); /* * Restore FSBASE and GSBASE after restoring the selectors, since * restoring the selectors clobbers the bases. Keep in mind * that MSR_KERNEL_GS_BASE is horribly misnamed. */ wrmsrl(MSR_FS_BASE, ctxt->fs_base); wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); #else loadsegment(gs, ctxt->gs); #endif do_fpu_end(); tsc_verify_tsc_adjust(true); x86_platform.restore_sched_clock_state(); cache_bp_restore(); perf_restore_debug_store(); c = &cpu_data(smp_processor_id()); if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) init_ia32_feat_ctl(c); microcode_bsp_resume(); /* * This needs to happen after the microcode has been updated upon resume * because some of the MSRs are "emulated" in microcode. */ msr_restore_context(ctxt); } /* Needed by apm.c */ void notrace restore_processor_state(void) { __restore_processor_state(&saved_context); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(restore_processor_state); #endif #if defined(CONFIG_HIBERNATION) && defined(CONFIG_HOTPLUG_CPU) static void __noreturn resume_play_dead(void) { play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); hlt_play_dead(); } int hibernate_resume_nonboot_cpu_disable(void) { void (*play_dead)(void) = smp_ops.play_dead; int ret; /* * Ensure that MONITOR/MWAIT will not be used in the "play dead" loop * during hibernate image restoration, because it is likely that the * monitored address will be actually written to at that time and then * the "dead" CPU will attempt to execute instructions again, but the * address in its instruction pointer may not be possible to resolve * any more at that point (the page tables used by it previously may * have been overwritten by hibernate image data). * * First, make sure that we wake up all the potentially disabled SMT * threads which have been initially brought up and then put into * mwait/cpuidle sleep. * Those will be put to proper (not interfering with hibernation * resume) sleep afterwards, and the resumed kernel will decide itself * what to do with them. */ ret = cpuhp_smt_enable(); if (ret) return ret; smp_ops.play_dead = resume_play_dead; ret = freeze_secondary_cpus(0); smp_ops.play_dead = play_dead; return ret; } #endif /* * When bsp_check() is called in hibernate and suspend, cpu hotplug * is disabled already. So it's unnecessary to handle race condition between * cpumask query and cpu hotplug. */ static int bsp_check(void) { if (cpumask_first(cpu_online_mask) != 0) { pr_warn("CPU0 is offline.\n"); return -ENODEV; } return 0; } static int bsp_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { int ret = 0; switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: ret = bsp_check(); break; default: break; } return notifier_from_errno(ret); } static int __init bsp_pm_check_init(void) { /* * Set this bsp_pm_callback as lower priority than * cpu_hotplug_pm_callback. So cpu_hotplug_pm_callback will be called * earlier to disable cpu hotplug before bsp online check. */ pm_notifier(bsp_pm_callback, -INT_MAX); return 0; } core_initcall(bsp_pm_check_init); static int msr_build_context(const u32 *msr_id, const int num) { struct saved_msrs *saved_msrs = &saved_context.saved_msrs; struct saved_msr *msr_array; int total_num; int i, j; total_num = saved_msrs->num + num; msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); if (!msr_array) { pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n"); return -ENOMEM; } if (saved_msrs->array) { /* * Multiple callbacks can invoke this function, so copy any * MSR save requests from previous invocations. */ memcpy(msr_array, saved_msrs->array, sizeof(struct saved_msr) * saved_msrs->num); kfree(saved_msrs->array); } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { u64 dummy; msr_array[i].info.msr_no = msr_id[j]; msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; saved_msrs->array = msr_array; return 0; } /* * The following sections are a quirk framework for problematic BIOSen: * Sometimes MSRs are modified by the BIOSen after suspended to * RAM, this might cause unexpected behavior after wakeup. * Thus we save/restore these specified MSRs across suspend/resume * in order to work around it. * * For any further problematic BIOSen/platforms, * please add your own function similar to msr_initialize_bdw. */ static int msr_initialize_bdw(const struct dmi_system_id *d) { /* Add any extra MSR ids into this array. */ u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); } static const struct dmi_system_id msr_save_dmi_table[] = { { .callback = msr_initialize_bdw, .ident = "BROADWELL BDX_EP", .matches = { DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"), DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"), }, }, {} }; static int msr_save_cpuid_features(const struct x86_cpu_id *c) { u32 cpuid_msr_id[] = { MSR_AMD64_CPUID_FN_1, }; pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n", c->family); return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id)); } static const struct x86_cpu_id msr_save_cpu_table[] = { X86_MATCH_VENDOR_FAM(AMD, 0x15, &msr_save_cpuid_features), X86_MATCH_VENDOR_FAM(AMD, 0x16, &msr_save_cpuid_features), {} }; typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *); static int pm_cpu_check(const struct x86_cpu_id *c) { const struct x86_cpu_id *m; int ret = 0; m = x86_match_cpu(msr_save_cpu_table); if (m) { pm_cpu_match_t fn; fn = (pm_cpu_match_t)m->driver_data; ret = fn(m); } return ret; } static void pm_save_spec_msr(void) { struct msr_enumeration { u32 msr_no; u32 feature; } msr_enum[] = { { MSR_IA32_SPEC_CTRL, X86_FEATURE_MSR_SPEC_CTRL }, { MSR_IA32_TSX_CTRL, X86_FEATURE_MSR_TSX_CTRL }, { MSR_TSX_FORCE_ABORT, X86_FEATURE_TSX_FORCE_ABORT }, { MSR_IA32_MCU_OPT_CTRL, X86_FEATURE_SRBDS_CTRL }, { MSR_AMD64_LS_CFG, X86_FEATURE_LS_CFG_SSBD }, { MSR_AMD64_DE_CFG, X86_FEATURE_LFENCE_RDTSC }, }; int i; for (i = 0; i < ARRAY_SIZE(msr_enum); i++) { if (boot_cpu_has(msr_enum[i].feature)) msr_build_context(&msr_enum[i].msr_no, 1); } } static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); pm_save_spec_msr(); return 0; } device_initcall(pm_check_save_msr); |
| 94 13 6 8 3 61 38 9 2 5 5 6 5 1790 5 1788 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); ), TP_printk("root=%d id=%llu level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_level ) __field( u64, dst_id ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("dst_root=%d dst_id=%llu dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); __entry->val = val; ), TP_printk("root=%d id=%llu level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DECLARE_EVENT_CLASS(cgroup_rstat, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __field( int, cpu ) __field( bool, contended ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __entry->cpu = cpu; __entry->contended = contended; ), TP_printk("root=%d id=%llu level=%d cpu=%d lock contended:%d", __entry->root, __entry->id, __entry->level, __entry->cpu, __entry->contended) ); /* Related to global: cgroup_rstat_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); /* Related to per CPU: cgroup_rstat_cpu_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 5 45 45 101 101 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mmap based event notifications for SELinux * * Author: KaiGai Kohei <kaigai@ak.jp.nec.com> * * Copyright (C) 2010 NEC corporation */ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/mutex.h> #include "avc.h" #include "security.h" /* * The selinux_status_page shall be exposed to userspace applications * using mmap interface on /selinux/status. * It enables to notify applications a few events that will cause reset * of userspace access vector without context switching. * * The selinux_kernel_status structure on the head of status page is * protected from concurrent accesses using seqlock logic, so userspace * application should reference the status page according to the seqlock * logic. * * Typically, application checks status->sequence at the head of access * control routine. If it is odd-number, kernel is updating the status, * so please wait for a moment. If it is changed from the last sequence * number, it means something happen, so application will reset userspace * avc, if needed. * In most cases, application shall confirm the kernel status is not * changed without any system call invocations. */ /* * selinux_kernel_status_page * * It returns a reference to selinux_status_page. If the status page is * not allocated yet, it also tries to allocate it at the first time. */ struct page *selinux_kernel_status_page(void) { struct selinux_kernel_status *status; struct page *result = NULL; mutex_lock(&selinux_state.status_lock); if (!selinux_state.status_page) { selinux_state.status_page = alloc_page(GFP_KERNEL|__GFP_ZERO); if (selinux_state.status_page) { status = page_address(selinux_state.status_page); status->version = SELINUX_KERNEL_STATUS_VERSION; status->sequence = 0; status->enforcing = enforcing_enabled(); /* * NOTE: the next policyload event shall set * a positive value on the status->policyload, * although it may not be 1, but never zero. * So, application can know it was updated. */ status->policyload = 0; status->deny_unknown = !security_get_allow_unknown(); } } result = selinux_state.status_page; mutex_unlock(&selinux_state.status_lock); return result; } /* * selinux_status_update_setenforce * * It updates status of the current enforcing/permissive mode. */ void selinux_status_update_setenforce(bool enforcing) { struct selinux_kernel_status *status; mutex_lock(&selinux_state.status_lock); if (selinux_state.status_page) { status = page_address(selinux_state.status_page); status->sequence++; smp_wmb(); status->enforcing = enforcing ? 1 : 0; smp_wmb(); status->sequence++; } mutex_unlock(&selinux_state.status_lock); } /* * selinux_status_update_policyload * * It updates status of the times of policy reloaded, and current * setting of deny_unknown. */ void selinux_status_update_policyload(u32 seqno) { struct selinux_kernel_status *status; mutex_lock(&selinux_state.status_lock); if (selinux_state.status_page) { status = page_address(selinux_state.status_page); status->sequence++; smp_wmb(); status->policyload = seqno; status->deny_unknown = !security_get_allow_unknown(); smp_wmb(); status->sequence++; } mutex_unlock(&selinux_state.status_lock); } |
| 5 5 38 38 38 37 5 5 5 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 | /* * Copyright (c) 2004, 2005 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004, 2005 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2005 Intel Corporation. All rights reserved. * Copyright (c) 2004, 2005 Topspin Corporation. All rights reserved. * Copyright (c) 2004-2007 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/slab.h> #include <linux/string.h> #include "agent.h" #include "smi.h" #include "mad_priv.h" #define SPFX "ib_agent: " struct ib_agent_port_private { struct list_head port_list; struct ib_mad_agent *agent[2]; }; static DEFINE_SPINLOCK(ib_agent_port_list_lock); static LIST_HEAD(ib_agent_port_list); static struct ib_agent_port_private * __ib_get_agent_port(const struct ib_device *device, int port_num) { struct ib_agent_port_private *entry; list_for_each_entry(entry, &ib_agent_port_list, port_list) { /* Need to check both agent[0] and agent[1], as an agent port * may only have one of them */ if (entry->agent[0] && entry->agent[0]->device == device && entry->agent[0]->port_num == port_num) return entry; if (entry->agent[1] && entry->agent[1]->device == device && entry->agent[1]->port_num == port_num) return entry; } return NULL; } static struct ib_agent_port_private * ib_get_agent_port(const struct ib_device *device, int port_num) { struct ib_agent_port_private *entry; unsigned long flags; spin_lock_irqsave(&ib_agent_port_list_lock, flags); entry = __ib_get_agent_port(device, port_num); spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); return entry; } void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh, const struct ib_wc *wc, const struct ib_device *device, int port_num, int qpn, size_t resp_mad_len, bool opa) { struct ib_agent_port_private *port_priv; struct ib_mad_agent *agent; struct ib_mad_send_buf *send_buf; struct ib_ah *ah; struct ib_mad_send_wr_private *mad_send_wr; if (rdma_cap_ib_switch(device)) port_priv = ib_get_agent_port(device, 0); else port_priv = ib_get_agent_port(device, port_num); if (!port_priv) { dev_err(&device->dev, "Unable to find port agent\n"); return; } agent = port_priv->agent[qpn]; ah = ib_create_ah_from_wc(agent->qp->pd, wc, grh, port_num); if (IS_ERR(ah)) { dev_err(&device->dev, "ib_create_ah_from_wc error %ld\n", PTR_ERR(ah)); return; } if (opa && mad_hdr->base_version != OPA_MGMT_BASE_VERSION) resp_mad_len = IB_MGMT_MAD_SIZE; send_buf = ib_create_send_mad(agent, wc->src_qp, wc->pkey_index, 0, IB_MGMT_MAD_HDR, resp_mad_len - IB_MGMT_MAD_HDR, GFP_KERNEL, mad_hdr->base_version); if (IS_ERR(send_buf)) { dev_err(&device->dev, "ib_create_send_mad error\n"); goto err1; } memcpy(send_buf->mad, mad_hdr, resp_mad_len); send_buf->ah = ah; if (rdma_cap_ib_switch(device)) { mad_send_wr = container_of(send_buf, struct ib_mad_send_wr_private, send_buf); mad_send_wr->send_wr.port_num = port_num; } if (ib_post_send_mad(send_buf, NULL)) { dev_err(&device->dev, "ib_post_send_mad error\n"); goto err2; } return; err2: ib_free_send_mad(send_buf); err1: rdma_destroy_ah(ah, RDMA_DESTROY_AH_SLEEPABLE); } static void agent_send_handler(struct ib_mad_agent *mad_agent, struct ib_mad_send_wc *mad_send_wc) { rdma_destroy_ah(mad_send_wc->send_buf->ah, RDMA_DESTROY_AH_SLEEPABLE); ib_free_send_mad(mad_send_wc->send_buf); } int ib_agent_port_open(struct ib_device *device, int port_num) { struct ib_agent_port_private *port_priv; unsigned long flags; int ret; /* Create new device info */ port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL); if (!port_priv) { ret = -ENOMEM; goto error1; } if (rdma_cap_ib_smi(device, port_num)) { /* Obtain send only MAD agent for SMI QP */ port_priv->agent[0] = ib_register_mad_agent(device, port_num, IB_QPT_SMI, NULL, 0, &agent_send_handler, NULL, NULL, 0); if (IS_ERR(port_priv->agent[0])) { ret = PTR_ERR(port_priv->agent[0]); goto error2; } } if (rdma_cap_ib_cm(device, port_num)) { /* Obtain send only MAD agent for GSI QP */ port_priv->agent[1] = ib_register_mad_agent(device, port_num, IB_QPT_GSI, NULL, 0, &agent_send_handler, NULL, NULL, 0); if (IS_ERR(port_priv->agent[1])) { ret = PTR_ERR(port_priv->agent[1]); goto error3; } } spin_lock_irqsave(&ib_agent_port_list_lock, flags); list_add_tail(&port_priv->port_list, &ib_agent_port_list); spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); return 0; error3: if (port_priv->agent[0]) ib_unregister_mad_agent(port_priv->agent[0]); error2: kfree(port_priv); error1: return ret; } int ib_agent_port_close(struct ib_device *device, int port_num) { struct ib_agent_port_private *port_priv; unsigned long flags; spin_lock_irqsave(&ib_agent_port_list_lock, flags); port_priv = __ib_get_agent_port(device, port_num); if (port_priv == NULL) { spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); dev_err(&device->dev, "Port %d not found\n", port_num); return -ENODEV; } list_del(&port_priv->port_list); spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); if (port_priv->agent[1]) ib_unregister_mad_agent(port_priv->agent[1]); if (port_priv->agent[0]) ib_unregister_mad_agent(port_priv->agent[0]); kfree(port_priv); return 0; } |
| 16290 315 16282 2500 16063 1291 6942 1405 16284 15438 537 487 487 108 487 487 487 486 1 487 487 487 7 1620 487 1978 1976 1652 11 325 157 1590 5 2 50 11 16 50 48 50 50 50 634 1 16277 16284 16289 15392 90 15414 461 16387 16270 15438 15415 49 15455 14075 12702 16311 27 16288 16285 16313 1976 17188 17219 8 15413 2402 2583 84 84 8066 154 6843 6853 92 92 91 63 62 63 12126 17232 15409 13996 1122 1157 1343 9 14 204 8 199 203 203 196 5 5 3 3 203 204 197 1 6 81 11 2 68 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) static void retrigger_next_event(void *arg); /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, }, .csd = CSD_INIT(retrigger_next_event, NULL) }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { /* Make sure we catch unsupported clockids */ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) { if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; else return likely(base->online); } /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * Check if the elected target is suitable considering its next * event and the hotplug state of the current CPU. * * If the elected target is remote and its next event is after the timer * to queue, then a remote reprogram is necessary. However there is no * guarantee the IPI handling the operation would arrive in time to meet * the high resolution deadline. In this case the local CPU becomes a * preferred target, unless it is offline. * * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, struct hrtimer_cpu_base *new_cpu_base, struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; /* * The local CPU clockevent can be reprogrammed. Also get_target_base() * guarantees it is online. */ if (new_cpu_base == this_cpu_base) return true; /* * The offline local CPU can't be the default target if the * next remote target event is after this timer. Keep the * elected new base. An IPI will we issued to reprogram * it as a last resort. */ if (!hrtimer_base_is_online(this_cpu_base)) return true; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires >= new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { if (!hrtimer_base_is_online(base)) { int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); return &per_cpu(hrtimer_bases, cpu); } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ((struct hrtimer *) addr)->function; } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_init(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_init_on_stack(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init_on_stack(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ if (!hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of the function hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns true when the new timer is the leftmost timer in the tree. */ static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; /* * Don't force local queuing if this enqueue happens on a unplugged * CPU after hrtimer_cpu_dying() has been invoked. */ force_local &= this_cpu_base->online; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) { /* * If the current CPU base is online, then the timer is * never queued on a remote CPU if it would be the first * expiring timer there. */ if (hrtimer_base_is_online(this_cpu_base)) return first; /* * Timer was enqueued remote because the current base is * already offline. If the timer is the first to expire, * kick the remote CPU to reprogram the clock event. */ if (first) { struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base; smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd); } return 0; } /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; if (WARN_ON_ONCE(!timer->function)) return; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } #ifdef CONFIG_SMP static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } #else static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } #endif /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling del_timer_sync() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { if (likely(clock_id < MAX_CLOCKS)) { int base = hrtimer_clock_to_base_table[clock_id]; if (likely(base != HRTIMER_MAX_CLOCK_BASES)) return base; } WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) { return HRTIMER_NORESTART; } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } static void __hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { __hrtimer_init(timer, clock_id, mode); if (WARN_ON_ONCE(!function)) timer->function = hrtimer_dummy_timeout; else timer->function = function; } /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init); /** * hrtimer_setup - initialize a timer to the given clock * @timer: the timer to be initialized * @function: the callback function * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup); /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized * @function: the callback function * @clock_id: The clock to be used * @mode: The timer mode * * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack * memory. */ void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_init_on_stack(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = timer->function; /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * __hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; sl->task = current; } /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_init_on_stack(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } int hrtimers_cpu_starting(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); /* Clear out any left over state from a CPU down operation */ cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); hrtimers_cpu_starting(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } |
| 4383 4384 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ACPI device specific properties support. * * Copyright (C) 2014 - 2023, Intel Corporation * All rights reserved. * * Authors: Mika Westerberg <mika.westerberg@linux.intel.com> * Darren Hart <dvhart@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * Sakari Ailus <sakari.ailus@linux.intel.com> */ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/acpi.h> #include <linux/device.h> #include <linux/export.h> #include "internal.h" static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj); /* * The GUIDs here are made equivalent to each other in order to avoid extra * complexity in the properties handling code, with the caveat that the * kernel will accept certain combinations of GUID and properties that are * not defined without a warning. For instance if any of the properties * from different GUID appear in a property list of another, it will be * accepted by the kernel. Firmware validation tools should catch these. * * References: * * [1] UEFI DSD Guide. * https://github.com/UEFI/DSD-Guide/blob/main/src/dsd-guide.adoc */ static const guid_t prp_guids[] = { /* ACPI _DSD device properties GUID [1]: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */ GUID_INIT(0xdaffd814, 0x6eba, 0x4d8c, 0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01), /* Hotplug in D3 GUID: 6211e2c0-58a3-4af3-90e1-927a4e0c55a4 */ GUID_INIT(0x6211e2c0, 0x58a3, 0x4af3, 0x90, 0xe1, 0x92, 0x7a, 0x4e, 0x0c, 0x55, 0xa4), /* External facing port GUID: efcc06cc-73ac-4bc3-bff0-76143807c389 */ GUID_INIT(0xefcc06cc, 0x73ac, 0x4bc3, 0xbf, 0xf0, 0x76, 0x14, 0x38, 0x07, 0xc3, 0x89), /* Thunderbolt GUID for IMR_VALID: c44d002f-69f9-4e7d-a904-a7baabdf43f7 */ GUID_INIT(0xc44d002f, 0x69f9, 0x4e7d, 0xa9, 0x04, 0xa7, 0xba, 0xab, 0xdf, 0x43, 0xf7), /* Thunderbolt GUID for WAKE_SUPPORTED: 6c501103-c189-4296-ba72-9bf5a26ebe5d */ GUID_INIT(0x6c501103, 0xc189, 0x4296, 0xba, 0x72, 0x9b, 0xf5, 0xa2, 0x6e, 0xbe, 0x5d), /* Storage device needs D3 GUID: 5025030f-842f-4ab4-a561-99a5189762d0 */ GUID_INIT(0x5025030f, 0x842f, 0x4ab4, 0xa5, 0x61, 0x99, 0xa5, 0x18, 0x97, 0x62, 0xd0), }; /* ACPI _DSD data subnodes GUID [1]: dbb8e3e6-5886-4ba6-8795-1319f52a966b */ static const guid_t ads_guid = GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6, 0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b); /* ACPI _DSD data buffer GUID [1]: edb12dd0-363d-4085-a3d2-49522ca160c4 */ static const guid_t buffer_prop_guid = GUID_INIT(0xedb12dd0, 0x363d, 0x4085, 0xa3, 0xd2, 0x49, 0x52, 0x2c, 0xa1, 0x60, 0xc4); static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent); static bool acpi_extract_properties(acpi_handle handle, union acpi_object *desc, struct acpi_device_data *data); static bool acpi_nondev_subnode_extract(union acpi_object *desc, acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_data_node *dn; bool result; if (acpi_graph_ignore_port(handle)) return false; dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return false; dn->name = link->package.elements[0].string.pointer; fwnode_init(&dn->fwnode, &acpi_data_fwnode_ops); dn->parent = parent; INIT_LIST_HEAD(&dn->data.properties); INIT_LIST_HEAD(&dn->data.subnodes); result = acpi_extract_properties(handle, desc, &dn->data); if (handle) { acpi_handle scope; acpi_status status; /* * The scope for the subnode object lookup is the one of the * namespace node (device) containing the object that has * returned the package. That is, it's the scope of that * object's parent. */ status = acpi_get_parent(handle, &scope); if (ACPI_SUCCESS(status) && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data, &dn->fwnode)) result = true; } else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data, &dn->fwnode)) { result = true; } if (result) { dn->handle = handle; dn->data.pointer = desc; list_add_tail(&dn->sibling, list); return true; } kfree(dn); acpi_handle_debug(handle, "Invalid properties/subnodes data, skipping\n"); return false; } static bool acpi_nondev_subnode_data_ok(acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; acpi_status status; status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) return false; if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list, parent)) return true; ACPI_FREE(buf.pointer); return false; } static bool acpi_nondev_subnode_ok(acpi_handle scope, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { acpi_handle handle; acpi_status status; if (!scope) return false; status = acpi_get_handle(scope, link->package.elements[1].string.pointer, &handle); if (ACPI_FAILURE(status)) return false; return acpi_nondev_subnode_data_ok(handle, link, list, parent); } static bool acpi_add_nondev_subnodes(acpi_handle scope, union acpi_object *links, struct list_head *list, struct fwnode_handle *parent) { bool ret = false; int i; for (i = 0; i < links->package.count; i++) { union acpi_object *link, *desc; acpi_handle handle; bool result; link = &links->package.elements[i]; /* Only two elements allowed. */ if (link->package.count != 2) continue; /* The first one must be a string. */ if (link->package.elements[0].type != ACPI_TYPE_STRING) continue; /* The second one may be a string, a reference or a package. */ switch (link->package.elements[1].type) { case ACPI_TYPE_STRING: result = acpi_nondev_subnode_ok(scope, link, list, parent); break; case ACPI_TYPE_LOCAL_REFERENCE: handle = link->package.elements[1].reference.handle; result = acpi_nondev_subnode_data_ok(handle, link, list, parent); break; case ACPI_TYPE_PACKAGE: desc = &link->package.elements[1]; result = acpi_nondev_subnode_extract(desc, NULL, link, list, parent); break; default: result = false; break; } ret = ret || result; } return ret; } static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent) { int i; /* Look for the ACPI data subnodes GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid; union acpi_object *links; guid = &desc->package.elements[i]; links = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || links->type != ACPI_TYPE_PACKAGE) break; if (!guid_equal((guid_t *)guid->buffer.pointer, &ads_guid)) continue; return acpi_add_nondev_subnodes(scope, links, &data->subnodes, parent); } return false; } static bool acpi_property_value_ok(const union acpi_object *value) { int j; /* * The value must be an integer, a string, a reference, or a package * whose every element must be an integer, a string, or a reference. */ switch (value->type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: return true; case ACPI_TYPE_PACKAGE: for (j = 0; j < value->package.count; j++) switch (value->package.elements[j].type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: continue; default: return false; } return true; } return false; } static bool acpi_properties_format_valid(const union acpi_object *properties) { int i; for (i = 0; i < properties->package.count; i++) { const union acpi_object *property; property = &properties->package.elements[i]; /* * Only two elements allowed, the first one must be a string and * the second one has to satisfy certain conditions. */ if (property->package.count != 2 || property->package.elements[0].type != ACPI_TYPE_STRING || !acpi_property_value_ok(&property->package.elements[1])) return false; } return true; } static void acpi_init_of_compatible(struct acpi_device *adev) { const union acpi_object *of_compatible; int ret; ret = acpi_data_get_property_array(&adev->data, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { ret = acpi_dev_get_property(adev, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { struct acpi_device *parent; parent = acpi_dev_parent(adev); if (parent && parent->flags.of_compatible_ok) goto out; return; } } adev->data.of_compatible = of_compatible; out: adev->flags.of_compatible_ok = 1; } static bool acpi_is_property_guid(const guid_t *guid) { int i; for (i = 0; i < ARRAY_SIZE(prp_guids); i++) { if (guid_equal(guid, &prp_guids[i])) return true; } return false; } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties) { struct acpi_device_properties *props; props = kzalloc(sizeof(*props), GFP_KERNEL); if (props) { INIT_LIST_HEAD(&props->list); props->guid = guid; props->properties = properties; list_add_tail(&props->list, &data->properties); } return props; } static void acpi_nondev_subnode_tag(acpi_handle handle, void *context) { } static void acpi_untie_nondev_subnodes(struct acpi_device_data *data) { struct acpi_data_node *dn; list_for_each_entry(dn, &data->subnodes, sibling) { acpi_detach_data(dn->handle, acpi_nondev_subnode_tag); acpi_untie_nondev_subnodes(&dn->data); } } static bool acpi_tie_nondev_subnodes(struct acpi_device_data *data) { struct acpi_data_node *dn; list_for_each_entry(dn, &data->subnodes, sibling) { acpi_status status; bool ret; status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn); if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) { acpi_handle_err(dn->handle, "Can't tag data node\n"); return false; } ret = acpi_tie_nondev_subnodes(&dn->data); if (!ret) return ret; } return true; } static void acpi_data_add_buffer_props(acpi_handle handle, struct acpi_device_data *data, union acpi_object *properties) { struct acpi_device_properties *props; union acpi_object *package; size_t alloc_size; unsigned int i; u32 *count; if (check_mul_overflow((size_t)properties->package.count, sizeof(*package) + sizeof(void *), &alloc_size) || check_add_overflow(sizeof(*props) + sizeof(*package), alloc_size, &alloc_size)) { acpi_handle_warn(handle, "can't allocate memory for %u buffer props", properties->package.count); return; } props = kvzalloc(alloc_size, GFP_KERNEL); if (!props) return; props->guid = &buffer_prop_guid; props->bufs = (void *)(props + 1); props->properties = (void *)(props->bufs + properties->package.count); /* Outer package */ package = props->properties; package->type = ACPI_TYPE_PACKAGE; package->package.elements = package + 1; count = &package->package.count; *count = 0; /* Inner packages */ package++; for (i = 0; i < properties->package.count; i++) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; union acpi_object *property = &properties->package.elements[i]; union acpi_object *prop, *obj, *buf_obj; acpi_status status; if (property->type != ACPI_TYPE_PACKAGE || property->package.count != 2) { acpi_handle_warn(handle, "buffer property %u has %u entries\n", i, property->package.count); continue; } prop = &property->package.elements[0]; obj = &property->package.elements[1]; if (prop->type != ACPI_TYPE_STRING || obj->type != ACPI_TYPE_STRING) { acpi_handle_warn(handle, "wrong object types %u and %u\n", prop->type, obj->type); continue; } status = acpi_evaluate_object_typed(handle, obj->string.pointer, NULL, &buf, ACPI_TYPE_BUFFER); if (ACPI_FAILURE(status)) { acpi_handle_warn(handle, "can't evaluate \"%*pE\" as buffer\n", obj->string.length, obj->string.pointer); continue; } package->type = ACPI_TYPE_PACKAGE; package->package.elements = prop; package->package.count = 2; buf_obj = buf.pointer; /* Replace the string object with a buffer object */ obj->type = ACPI_TYPE_BUFFER; obj->buffer.length = buf_obj->buffer.length; obj->buffer.pointer = buf_obj->buffer.pointer; props->bufs[i] = buf.pointer; package++; (*count)++; } if (*count) list_add(&props->list, &data->properties); else kvfree(props); } static bool acpi_extract_properties(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data) { int i; if (desc->package.count % 2) return false; /* Look for the device properties GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid; union acpi_object *properties; guid = &desc->package.elements[i]; properties = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || properties->type != ACPI_TYPE_PACKAGE) break; if (guid_equal((guid_t *)guid->buffer.pointer, &buffer_prop_guid)) { acpi_data_add_buffer_props(scope, data, properties); continue; } if (!acpi_is_property_guid((guid_t *)guid->buffer.pointer)) continue; /* * We found the matching GUID. Now validate the format of the * package immediately following it. */ if (!acpi_properties_format_valid(properties)) continue; acpi_data_add_props(data, (const guid_t *)guid->buffer.pointer, properties); } return !list_empty(&data->properties); } void acpi_init_properties(struct acpi_device *adev) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; struct acpi_hardware_id *hwid; acpi_status status; bool acpi_of = false; INIT_LIST_HEAD(&adev->data.properties); INIT_LIST_HEAD(&adev->data.subnodes); if (!adev->handle) return; /* * Check if ACPI_DT_NAMESPACE_HID is present and inthat case we fill in * Device Tree compatible properties for this device. */ list_for_each_entry(hwid, &adev->pnp.ids, list) { if (!strcmp(hwid->id, ACPI_DT_NAMESPACE_HID)) { acpi_of = true; break; } } status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) goto out; if (acpi_extract_properties(adev->handle, buf.pointer, &adev->data)) { adev->data.pointer = buf.pointer; if (acpi_of) acpi_init_of_compatible(adev); } if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer, &adev->data, acpi_fwnode_handle(adev))) adev->data.pointer = buf.pointer; if (!adev->data.pointer) { acpi_handle_debug(adev->handle, "Invalid _DSD data, skipping\n"); ACPI_FREE(buf.pointer); } else { if (!acpi_tie_nondev_subnodes(&adev->data)) acpi_untie_nondev_subnodes(&adev->data); } out: if (acpi_of && !adev->flags.of_compatible_ok) acpi_handle_info(adev->handle, ACPI_DT_NAMESPACE_HID " requires 'compatible' property\n"); if (!adev->data.pointer) acpi_extract_apple_properties(adev); } static void acpi_free_device_properties(struct list_head *list) { struct acpi_device_properties *props, *tmp; list_for_each_entry_safe(props, tmp, list, list) { u32 i; list_del(&props->list); /* Buffer data properties were separately allocated */ if (props->bufs) for (i = 0; i < props->properties->package.count; i++) ACPI_FREE(props->bufs[i]); kvfree(props); } } static void acpi_destroy_nondev_subnodes(struct list_head *list) { struct acpi_data_node *dn, *next; if (list_empty(list)) return; list_for_each_entry_safe_reverse(dn, next, list, sibling) { acpi_destroy_nondev_subnodes(&dn->data.subnodes); wait_for_completion(&dn->kobj_done); list_del(&dn->sibling); ACPI_FREE((void *)dn->data.pointer); acpi_free_device_properties(&dn->data.properties); kfree(dn); } } void acpi_free_properties(struct acpi_device *adev) { acpi_untie_nondev_subnodes(&adev->data); acpi_destroy_nondev_subnodes(&adev->data.subnodes); ACPI_FREE((void *)adev->data.pointer); adev->data.of_compatible = NULL; adev->data.pointer = NULL; acpi_free_device_properties(&adev->data.properties); } /** * acpi_data_get_property - return an ACPI property with given name * @data: ACPI device deta object to get the property from * @name: Name of the property * @type: Expected property type * @obj: Location to store the property value (if not %NULL) * * Look up a property with @name and store a pointer to the resulting ACPI * object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. These objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if property with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property value type doesn't match @type. */ static int acpi_data_get_property(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const struct acpi_device_properties *props; if (!data || !name) return -EINVAL; if (!data->pointer || list_empty(&data->properties)) return -EINVAL; list_for_each_entry(props, &data->properties, list) { const union acpi_object *properties; unsigned int i; properties = props->properties; for (i = 0; i < properties->package.count; i++) { const union acpi_object *propname, *propvalue; const union acpi_object *property; property = &properties->package.elements[i]; propname = &property->package.elements[0]; propvalue = &property->package.elements[1]; if (!strcmp(name, propname->string.pointer)) { if (type != ACPI_TYPE_ANY && propvalue->type != type) return -EPROTO; if (obj) *obj = propvalue; return 0; } } } return -EINVAL; } /** * acpi_dev_get_property - return an ACPI property with given name. * @adev: ACPI device to get the property from. * @name: Name of the property. * @type: Expected property type. * @obj: Location to store the property value (if not %NULL). */ int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return adev ? acpi_data_get_property(&adev->data, name, type, obj) : -EINVAL; } EXPORT_SYMBOL_GPL(acpi_dev_get_property); static const struct acpi_device_data * acpi_device_data_of_node(const struct fwnode_handle *fwnode) { if (is_acpi_device_node(fwnode)) { const struct acpi_device *adev = to_acpi_device_node(fwnode); return &adev->data; } if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return &dn->data; } return NULL; } /** * acpi_node_prop_get - return an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @valptr: Location to store a pointer to the property value (if not %NULL). */ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return acpi_data_get_property(acpi_device_data_of_node(fwnode), propname, ACPI_TYPE_ANY, (const union acpi_object **)valptr); } /** * acpi_data_get_property_array - return an ACPI array property with given name * @data: ACPI data object to get the property from * @name: Name of the property * @type: Expected type of array elements * @obj: Location to store a pointer to the property value (if not NULL) * * Look up an array property with @name and store a pointer to the resulting * ACPI object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. Those objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if array property (package) with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property is not a package or the type of its elements * doesn't match @type. */ static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const union acpi_object *prop; int ret, i; ret = acpi_data_get_property(data, name, ACPI_TYPE_PACKAGE, &prop); if (ret) return ret; if (type != ACPI_TYPE_ANY) { /* Check that all elements are of correct type. */ for (i = 0; i < prop->package.count; i++) if (prop->package.elements[i].type != type) return -EPROTO; } if (obj) *obj = prop; return 0; } static struct fwnode_handle * acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { if (is_acpi_data_node(child)) { if (acpi_data_node_match(child, childname)) return child; continue; } if (!strncmp(acpi_device_bid(to_acpi_device_node(child)), childname, ACPI_NAMESEG_SIZE)) return child; } return NULL; } static int acpi_get_ref_args(struct fwnode_reference_args *args, struct fwnode_handle *ref_fwnode, const union acpi_object **element, const union acpi_object *end, size_t num_args) { u32 nargs = 0, i; /* * Assume the following integer elements are all args. Stop counting on * the first reference (possibly represented as a string) or end of the * package arguments. In case of neither reference, nor integer, return * an error, we can't parse it. */ for (i = 0; (*element) + i < end && i < num_args; i++) { acpi_object_type type = (*element)[i].type; if (type == ACPI_TYPE_LOCAL_REFERENCE || type == ACPI_TYPE_STRING) break; if (type == ACPI_TYPE_INTEGER) nargs++; else return -EINVAL; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (args) { args->fwnode = ref_fwnode; args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = (*element)[i].integer.value; } (*element) += nargs; return 0; } static struct fwnode_handle *acpi_parse_string_ref(const struct fwnode_handle *fwnode, const char *refstring) { acpi_handle scope, handle; struct acpi_data_node *dn; struct acpi_device *device; acpi_status status; if (is_acpi_device_node(fwnode)) { scope = to_acpi_device_node(fwnode)->handle; } else if (is_acpi_data_node(fwnode)) { scope = to_acpi_data_node(fwnode)->handle; } else { pr_debug("Bad node type for node %pfw\n", fwnode); return NULL; } status = acpi_get_handle(scope, refstring, &handle); if (ACPI_FAILURE(status)) { acpi_handle_debug(scope, "Unable to get an ACPI handle for %s\n", refstring); return NULL; } device = acpi_fetch_acpi_dev(handle); if (device) return acpi_fwnode_handle(device); status = acpi_get_data_full(handle, acpi_nondev_subnode_tag, (void **)&dn, NULL); if (ACPI_FAILURE(status) || !dn) { acpi_handle_debug(handle, "Subnode not found\n"); return NULL; } return &dn->fwnode; } /** * __acpi_node_get_property_reference - returns handle to the referenced object * @fwnode: Firmware node to get the property from * @propname: Name of the property * @index: Index of the reference to return * @num_args: Maximum number of arguments after each reference * @args: Location to store the returned reference with optional arguments * (may be NULL) * * Find property with @name, verifify that it is a package containing at least * one object reference and if so, store the ACPI device object pointer to the * target object in @args->adev. If the reference includes arguments, store * them in the @args->args[] array. * * If there's more than one reference in the property value package, @index is * used to select the one to return. * * It is possible to leave holes in the property value set like in the * example below: * * Package () { * "cs-gpios", * Package () { * ^GPIO, 19, 0, 0, * ^GPIO, 20, 0, 0, * 0, * ^GPIO, 21, 0, 0, * } * } * * Calling this function with index %2 or index %3 return %-ENOENT. If the * property does not contain any more values %-ENOENT is returned. The NULL * entry must be single integer and preferably contain value %0. * * Return: %0 on success, negative error code on failure. */ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *propname, size_t index, size_t num_args, struct fwnode_reference_args *args) { const union acpi_object *element, *end; const union acpi_object *obj; const struct acpi_device_data *data; struct fwnode_handle *ref_fwnode; struct acpi_device *device; int ret, idx = 0; data = acpi_device_data_of_node(fwnode); if (!data) return -ENOENT; ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj); if (ret) return ret == -EINVAL ? -ENOENT : -EINVAL; switch (obj->type) { case ACPI_TYPE_LOCAL_REFERENCE: /* Plain single reference without arguments. */ if (index) return -ENOENT; device = acpi_fetch_acpi_dev(obj->reference.handle); if (!device) return -EINVAL; if (!args) return 0; args->fwnode = acpi_fwnode_handle(device); args->nargs = 0; return 0; case ACPI_TYPE_STRING: if (index) return -ENOENT; ref_fwnode = acpi_parse_string_ref(fwnode, obj->string.pointer); if (!ref_fwnode) return -EINVAL; args->fwnode = ref_fwnode; args->nargs = 0; return 0; case ACPI_TYPE_PACKAGE: /* * If it is not a single reference, then it is a package of * references, followed by number of ints as follows: * * Package () { REF, INT, REF, INT, INT } * * Here, REF may be either a local reference or a string. The * index argument is then used to determine which reference the * caller wants (along with the arguments). */ break; default: return -EINVAL; } if (index >= obj->package.count) return -ENOENT; element = obj->package.elements; end = element + obj->package.count; while (element < end) { switch (element->type) { case ACPI_TYPE_LOCAL_REFERENCE: device = acpi_fetch_acpi_dev(element->reference.handle); if (!device) return -EINVAL; element++; ret = acpi_get_ref_args(idx == index ? args : NULL, acpi_fwnode_handle(device), &element, end, num_args); if (ret < 0) return ret; if (idx == index) return 0; break; case ACPI_TYPE_STRING: ref_fwnode = acpi_parse_string_ref(fwnode, element->string.pointer); if (!ref_fwnode) return -EINVAL; element++; ret = acpi_get_ref_args(idx == index ? args : NULL, ref_fwnode, &element, end, num_args); if (ret < 0) return ret; if (idx == index) return 0; break; case ACPI_TYPE_INTEGER: if (idx == index) return -ENOENT; element++; break; default: return -EINVAL; } idx++; } return -ENOENT; } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); static int acpi_data_prop_read_single(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val) { const union acpi_object *obj; int ret = 0; if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) ret = acpi_data_get_property(data, propname, ACPI_TYPE_INTEGER, &obj); else if (proptype == DEV_PROP_STRING) ret = acpi_data_get_property(data, propname, ACPI_TYPE_STRING, &obj); if (ret) return ret; switch (proptype) { case DEV_PROP_U8: if (obj->integer.value > U8_MAX) return -EOVERFLOW; if (val) *(u8 *)val = obj->integer.value; break; case DEV_PROP_U16: if (obj->integer.value > U16_MAX) return -EOVERFLOW; if (val) *(u16 *)val = obj->integer.value; break; case DEV_PROP_U32: if (obj->integer.value > U32_MAX) return -EOVERFLOW; if (val) *(u32 *)val = obj->integer.value; break; case DEV_PROP_U64: if (val) *(u64 *)val = obj->integer.value; break; case DEV_PROP_STRING: if (val) *(char **)val = obj->string.pointer; return 1; default: return -EINVAL; } /* When no storage provided return number of available values */ return val ? 0 : 1; } #define acpi_copy_property_array_uint(items, val, nval) \ ({ \ typeof(items) __items = items; \ typeof(val) __val = val; \ typeof(nval) __nval = nval; \ size_t i; \ int ret = 0; \ \ for (i = 0; i < __nval; i++) { \ if (__items->type == ACPI_TYPE_BUFFER) { \ __val[i] = __items->buffer.pointer[i]; \ continue; \ } \ if (__items[i].type != ACPI_TYPE_INTEGER) { \ ret = -EPROTO; \ break; \ } \ if (__items[i].integer.value > _Generic(__val, \ u8 *: U8_MAX, \ u16 *: U16_MAX, \ u32 *: U32_MAX, \ u64 *: U64_MAX)) { \ ret = -EOVERFLOW; \ break; \ } \ \ __val[i] = __items[i].integer.value; \ } \ ret; \ }) static int acpi_copy_property_array_string(const union acpi_object *items, char **val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_STRING) return -EPROTO; val[i] = items[i].string.pointer; } return nval; } static int acpi_data_prop_read(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { const union acpi_object *obj; const union acpi_object *items; int ret; if (nval == 1 || !val) { ret = acpi_data_prop_read_single(data, propname, proptype, val); /* * The overflow error means that the property is there and it is * single-value, but its type does not match, so return. */ if (ret >= 0 || ret == -EOVERFLOW) return ret; /* * Reading this property as a single-value one failed, but its * value may still be represented as one-element array, so * continue. */ } ret = acpi_data_get_property_array(data, propname, ACPI_TYPE_ANY, &obj); if (ret && proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) ret = acpi_data_get_property(data, propname, ACPI_TYPE_BUFFER, &obj); if (ret) return ret; if (!val) { if (obj->type == ACPI_TYPE_BUFFER) return obj->buffer.length; return obj->package.count; } switch (proptype) { case DEV_PROP_STRING: break; default: if (obj->type == ACPI_TYPE_BUFFER) { if (nval > obj->buffer.length) return -EOVERFLOW; } else { if (nval > obj->package.count) return -EOVERFLOW; } break; } if (obj->type == ACPI_TYPE_BUFFER) { if (proptype != DEV_PROP_U8) return -EPROTO; items = obj; } else { items = obj->package.elements; } switch (proptype) { case DEV_PROP_U8: ret = acpi_copy_property_array_uint(items, (u8 *)val, nval); break; case DEV_PROP_U16: ret = acpi_copy_property_array_uint(items, (u16 *)val, nval); break; case DEV_PROP_U32: ret = acpi_copy_property_array_uint(items, (u32 *)val, nval); break; case DEV_PROP_U64: ret = acpi_copy_property_array_uint(items, (u64 *)val, nval); break; case DEV_PROP_STRING: nval = min_t(u32, nval, obj->package.count); if (nval == 0) return -ENODATA; ret = acpi_copy_property_array_string(items, (char **)val, nval); break; default: ret = -EINVAL; break; } return ret; } /** * acpi_node_prop_read - retrieve the value of an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @proptype: Expected property type. * @val: Location to store the property value (if not %NULL). * @nval: Size of the array pointed to by @val. * * If @val is %NULL, return the number of array elements comprising the value * of the property. Otherwise, read at most @nval values to the array at the * location pointed to by @val. */ static int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { return acpi_data_prop_read(acpi_device_data_of_node(fwnode), propname, proptype, val, nval); } static int stop_on_next(struct acpi_device *adev, void *data) { struct acpi_device **ret_p = data; if (!*ret_p) { *ret_p = adev; return 1; } /* Skip until the "previous" object is found. */ if (*ret_p == adev) *ret_p = NULL; return 0; } /** * acpi_get_next_subnode - Return the next child node handle for a fwnode * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the device's child nodes or a null handle. */ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct acpi_device *adev = to_acpi_device_node(fwnode); if ((!child || is_acpi_device_node(child)) && adev) { struct acpi_device *child_adev = to_acpi_device_node(child); acpi_dev_for_each_child(adev, stop_on_next, &child_adev); if (child_adev) return acpi_fwnode_handle(child_adev); child = NULL; } if (!child || is_acpi_data_node(child)) { const struct acpi_data_node *data = to_acpi_data_node(fwnode); const struct list_head *head; struct list_head *next; struct acpi_data_node *dn; /* * We can have a combination of device and data nodes, e.g. with * hierarchical _DSD properties. Make sure the adev pointer is * restored before going through data nodes, otherwise we will * be looking for data_nodes below the last device found instead * of the common fwnode shared by device_nodes and data_nodes. */ adev = to_acpi_device_node(fwnode); if (adev) head = &adev->data.subnodes; else if (data) head = &data->data.subnodes; else return NULL; if (list_empty(head)) return NULL; if (child) { dn = to_acpi_data_node(child); next = dn->sibling.next; if (next == head) return NULL; dn = list_entry(next, struct acpi_data_node, sibling); } else { dn = list_first_entry(head, struct acpi_data_node, sibling); } return &dn->fwnode; } return NULL; } /** * acpi_node_get_parent - Return parent fwnode of this fwnode * @fwnode: Firmware node whose parent to get * * Returns parent node of an ACPI device or data firmware node or %NULL if * not available. */ static struct fwnode_handle * acpi_node_get_parent(const struct fwnode_handle *fwnode) { if (is_acpi_data_node(fwnode)) { /* All data nodes have parent pointer so just return that */ return to_acpi_data_node(fwnode)->parent; } if (is_acpi_device_node(fwnode)) { struct acpi_device *parent; parent = acpi_dev_parent(to_acpi_device_node(fwnode)); if (parent) return acpi_fwnode_handle(parent); } return NULL; } /* * Return true if the node is an ACPI graph node. Called on either ports * or endpoints. */ static bool is_acpi_graph_node(struct fwnode_handle *fwnode, const char *str) { unsigned int len = strlen(str); const char *name; if (!len || !is_acpi_data_node(fwnode)) return false; name = to_acpi_data_node(fwnode)->name; return (fwnode_property_present(fwnode, "reg") && !strncmp(name, str, len) && name[len] == '@') || fwnode_property_present(fwnode, str); } /** * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first * * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns * %NULL if there is no next endpoint or in case of error. In case of success * the next endpoint is returned. */ static struct fwnode_handle *acpi_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *port = NULL; struct fwnode_handle *endpoint; if (!prev) { do { port = fwnode_get_next_child_node(fwnode, port); /* * The names of the port nodes begin with "port@" * followed by the number of the port node and they also * have a "reg" property that also has the number of the * port node. For compatibility reasons a node is also * recognised as a port node from the "port" property. */ if (is_acpi_graph_node(port, "port")) break; } while (port); } else { port = fwnode_get_parent(prev); } if (!port) return NULL; endpoint = fwnode_get_next_child_node(port, prev); while (!endpoint) { port = fwnode_get_next_child_node(fwnode, port); if (!port) break; if (is_acpi_graph_node(port, "port")) endpoint = fwnode_get_next_child_node(port, NULL); } /* * The names of the endpoint nodes begin with "endpoint@" followed by * the number of the endpoint node and they also have a "reg" property * that also has the number of the endpoint node. For compatibility * reasons a node is also recognised as an endpoint node from the * "endpoint" property. */ if (!is_acpi_graph_node(endpoint, "endpoint")) return NULL; return endpoint; } /** * acpi_graph_get_child_prop_value - Return a child with a given property value * @fwnode: device fwnode * @prop_name: The name of the property to look for * @val: the desired property value * * Return the port node corresponding to a given port number. Returns * the child node on success, NULL otherwise. */ static struct fwnode_handle *acpi_graph_get_child_prop_value( const struct fwnode_handle *fwnode, const char *prop_name, unsigned int val) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { u32 nr; if (fwnode_property_read_u32(child, prop_name, &nr)) continue; if (val == nr) return child; } return NULL; } /** * acpi_graph_get_remote_endpoint - Parses and returns remote end of an endpoint * @__fwnode: Endpoint firmware node pointing to a remote device * * Returns the remote endpoint corresponding to @__fwnode. NULL on error. */ static struct fwnode_handle * acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode) { struct fwnode_handle *fwnode; unsigned int port_nr, endpoint_nr; struct fwnode_reference_args args; int ret; memset(&args, 0, sizeof(args)); ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0, &args); if (ret) return NULL; /* Direct endpoint reference? */ if (!is_acpi_device_node(args.fwnode)) return args.nargs ? NULL : args.fwnode; /* * Always require two arguments with the reference: port and * endpoint indices. */ if (args.nargs != 2) return NULL; fwnode = args.fwnode; port_nr = args.args[0]; endpoint_nr = args.args[1]; fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr); return acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr); } static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) { if (!is_acpi_device_node(fwnode)) return true; return acpi_device_is_present(to_acpi_device_node(fwnode)); } static const void * acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { return acpi_device_get_match_data(dev); } static bool acpi_fwnode_device_dma_supported(const struct fwnode_handle *fwnode) { return acpi_dma_supported(to_acpi_device_node(fwnode)); } static enum dev_dma_attr acpi_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode) { return acpi_get_dma_attr(to_acpi_device_node(fwnode)); } static bool acpi_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { return !acpi_node_prop_get(fwnode, propname, NULL); } static int acpi_fwnode_property_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { enum dev_prop_type type; switch (elem_size) { case sizeof(u8): type = DEV_PROP_U8; break; case sizeof(u16): type = DEV_PROP_U16; break; case sizeof(u32): type = DEV_PROP_U32; break; case sizeof(u64): type = DEV_PROP_U64; break; default: return -ENXIO; } return acpi_node_prop_read(fwnode, propname, type, val, nval); } static int acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING, val, nval); } static int acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, unsigned int args_count, unsigned int index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, prop, index, args_count, args); } static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode) { const struct acpi_device *adev; struct fwnode_handle *parent; /* Is this the root node? */ parent = fwnode_get_parent(fwnode); if (!parent) return "\\"; fwnode_handle_put(parent); if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return dn->name; } adev = to_acpi_device_node(fwnode); if (WARN_ON(!adev)) return NULL; return acpi_device_bid(adev); } static const char * acpi_fwnode_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; /* Is this the root node? */ parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Is this 2nd node from the root? */ parent = fwnode_get_next_parent(parent); if (!parent) return ""; fwnode_handle_put(parent); /* ACPI device or data node. */ return "."; } static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { return acpi_node_get_parent(fwnode); } static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode); endpoint->local_fwnode = fwnode; if (fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port)) fwnode_property_read_u32(port_fwnode, "port", &endpoint->port); if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id)) fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id); return 0; } static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { struct resource res; int ret; ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); if (ret) return ret; return res.start; } #define DECLARE_ACPI_FWNODE_OPS(ops) \ const struct fwnode_operations ops = { \ .device_is_available = acpi_fwnode_device_is_available, \ .device_get_match_data = acpi_fwnode_device_get_match_data, \ .device_dma_supported = \ acpi_fwnode_device_dma_supported, \ .device_get_dma_attr = acpi_fwnode_device_get_dma_attr, \ .property_present = acpi_fwnode_property_present, \ .property_read_bool = acpi_fwnode_property_present, \ .property_read_int_array = \ acpi_fwnode_property_read_int_array, \ .property_read_string_array = \ acpi_fwnode_property_read_string_array, \ .get_parent = acpi_node_get_parent, \ .get_next_child_node = acpi_get_next_subnode, \ .get_named_child_node = acpi_fwnode_get_named_child_node, \ .get_name = acpi_fwnode_get_name, \ .get_name_prefix = acpi_fwnode_get_name_prefix, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ acpi_graph_get_next_endpoint, \ .graph_get_remote_endpoint = \ acpi_graph_get_remote_endpoint, \ .graph_get_port_parent = acpi_fwnode_get_parent, \ .graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \ .irq_get = acpi_fwnode_irq_get, \ }; \ EXPORT_SYMBOL_GPL(ops) DECLARE_ACPI_FWNODE_OPS(acpi_device_fwnode_ops); DECLARE_ACPI_FWNODE_OPS(acpi_data_fwnode_ops); const struct fwnode_operations acpi_static_fwnode_ops; bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_device_fwnode_ops; } EXPORT_SYMBOL(is_acpi_device_node); bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops; } EXPORT_SYMBOL(is_acpi_data_node); |
| 59 60 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/types.h> #include <linux/netfilter.h> #include <net/tcp.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_seqadj.h> int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_conn_seqadj *seqadj; struct nf_ct_seqadj *this_way; if (off == 0) return 0; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); seqadj = nfct_seqadj(ct); this_way = &seqadj->seq[dir]; this_way->offset_before = off; this_way->offset_after = off; return 0; } EXPORT_SYMBOL_GPL(nf_ct_seqadj_init); int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, __be32 seq, s32 off) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_ct_seqadj *this_way; if (off == 0) return 0; if (unlikely(!seqadj)) { WARN_ONCE(1, "Missing nfct_seqadj_ext_add() setup call\n"); return 0; } set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); spin_lock_bh(&ct->lock); this_way = &seqadj->seq[dir]; if (this_way->offset_before == this_way->offset_after || before(this_way->correction_pos, ntohl(seq))) { this_way->correction_pos = ntohl(seq); this_way->offset_before = this_way->offset_after; this_way->offset_after += off; } spin_unlock_bh(&ct->lock); return 0; } EXPORT_SYMBOL_GPL(nf_ct_seqadj_set); void nf_ct_tcp_seqadj_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off) { const struct tcphdr *th; if (nf_ct_protonum(ct) != IPPROTO_TCP) return; th = (struct tcphdr *)(skb_network_header(skb) + ip_hdrlen(skb)); nf_ct_seqadj_set(ct, ctinfo, th->seq, off); } EXPORT_SYMBOL_GPL(nf_ct_tcp_seqadj_set); /* Adjust one found SACK option including checksum correction */ static void nf_ct_sack_block_adjust(struct sk_buff *skb, struct tcphdr *tcph, unsigned int sackoff, unsigned int sackend, struct nf_ct_seqadj *seq) { while (sackoff < sackend) { struct tcp_sack_block_wire *sack; __be32 new_start_seq, new_end_seq; sack = (void *)skb->data + sackoff; if (after(ntohl(sack->start_seq) - seq->offset_before, seq->correction_pos)) new_start_seq = htonl(ntohl(sack->start_seq) - seq->offset_after); else new_start_seq = htonl(ntohl(sack->start_seq) - seq->offset_before); if (after(ntohl(sack->end_seq) - seq->offset_before, seq->correction_pos)) new_end_seq = htonl(ntohl(sack->end_seq) - seq->offset_after); else new_end_seq = htonl(ntohl(sack->end_seq) - seq->offset_before); pr_debug("sack_adjust: start_seq: %u->%u, end_seq: %u->%u\n", ntohl(sack->start_seq), ntohl(new_start_seq), ntohl(sack->end_seq), ntohl(new_end_seq)); inet_proto_csum_replace4(&tcph->check, skb, sack->start_seq, new_start_seq, false); inet_proto_csum_replace4(&tcph->check, skb, sack->end_seq, new_end_seq, false); sack->start_seq = new_start_seq; sack->end_seq = new_end_seq; sackoff += sizeof(*sack); } } /* TCP SACK sequence number adjustment */ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct tcphdr *tcph = (void *)skb->data + protoff; struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); unsigned int dir, optoff, optend; optoff = protoff + sizeof(struct tcphdr); optend = protoff + tcph->doff * 4; if (skb_ensure_writable(skb, optend)) return 0; tcph = (void *)skb->data + protoff; dir = CTINFO2DIR(ctinfo); while (optoff < optend) { /* Usually: option, length. */ unsigned char *op = skb->data + optoff; switch (op[0]) { case TCPOPT_EOL: return 1; case TCPOPT_NOP: optoff++; continue; default: /* no partial options */ if (optoff + 1 == optend || optoff + op[1] > optend || op[1] < 2) return 0; if (op[0] == TCPOPT_SACK && op[1] >= 2+TCPOLEN_SACK_PERBLOCK && ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) nf_ct_sack_block_adjust(skb, tcph, optoff + 2, optoff+op[1], &seqadj->seq[!dir]); optoff += op[1]; } } return 1; } /* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ int nf_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int protoff) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct tcphdr *tcph; __be32 newseq, newack; s32 seqoff, ackoff; struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *this_way, *other_way; int res = 1; this_way = &seqadj->seq[dir]; other_way = &seqadj->seq[!dir]; if (skb_ensure_writable(skb, protoff + sizeof(*tcph))) return 0; tcph = (void *)skb->data + protoff; spin_lock_bh(&ct->lock); if (after(ntohl(tcph->seq), this_way->correction_pos)) seqoff = this_way->offset_after; else seqoff = this_way->offset_before; newseq = htonl(ntohl(tcph->seq) + seqoff); inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, false); pr_debug("Adjusting sequence number from %u->%u\n", ntohl(tcph->seq), ntohl(newseq)); tcph->seq = newseq; if (!tcph->ack) goto out; if (after(ntohl(tcph->ack_seq) - other_way->offset_before, other_way->correction_pos)) ackoff = other_way->offset_after; else ackoff = other_way->offset_before; newack = htonl(ntohl(tcph->ack_seq) - ackoff); inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, false); pr_debug("Adjusting ack number from %u->%u, ack from %u->%u\n", ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), ntohl(newack)); tcph->ack_seq = newack; res = nf_ct_sack_adjust(skb, protoff, ct, ctinfo); out: spin_unlock_bh(&ct->lock); return res; } EXPORT_SYMBOL_GPL(nf_ct_seq_adjust); s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *this_way; if (!seqadj) return 0; this_way = &seqadj->seq[dir]; return after(seq, this_way->correction_pos) ? this_way->offset_after : this_way->offset_before; } EXPORT_SYMBOL_GPL(nf_ct_seq_offset); |
| 1 2 2 2 1 2 2 1 1 2 2 1 2 2 2 2 2 2 2 1 1 1 1 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP NV: TCP with Congestion Avoidance * * TCP-NV is a successor of TCP-Vegas that has been developed to * deal with the issues that occur in modern networks. * Like TCP-Vegas, TCP-NV supports true congestion avoidance, * the ability to detect congestion before packet losses occur. * When congestion (queue buildup) starts to occur, TCP-NV * predicts what the cwnd size should be for the current * throughput and it reduces the cwnd proportionally to * the difference between the current cwnd and the predicted cwnd. * * NV is only recommeneded for traffic within a data center, and when * all the flows are NV (at least those within the data center). This * is due to the inherent unfairness between flows using losses to * detect congestion (congestion control) and those that use queue * buildup to detect congestion (congestion avoidance). * * Note: High NIC coalescence values may lower the performance of NV * due to the increased noise in RTT values. In particular, we have * seen issues with rx-frames values greater than 8. * * TODO: * 1) Add mechanism to deal with reverse congestion. */ #include <linux/module.h> #include <linux/math64.h> #include <net/tcp.h> #include <linux/inet_diag.h> /* TCP NV parameters * * nv_pad Max number of queued packets allowed in network * nv_pad_buffer Do not grow cwnd if this closed to nv_pad * nv_reset_period How often (in) seconds)to reset min_rtt * nv_min_cwnd Don't decrease cwnd below this if there are no losses * nv_cong_dec_mult Decrease cwnd by X% (30%) of congestion when detected * nv_ssthresh_factor On congestion set ssthresh to this * <desired cwnd> / 8 * nv_rtt_factor RTT averaging factor * nv_loss_dec_factor Decrease cwnd to this (80%) when losses occur * nv_dec_eval_min_calls Wait this many RTT measurements before dec cwnd * nv_inc_eval_min_calls Wait this many RTT measurements before inc cwnd * nv_ssthresh_eval_min_calls Wait this many RTT measurements before stopping * slow-start due to congestion * nv_stop_rtt_cnt Only grow cwnd for this many RTTs after non-congestion * nv_rtt_min_cnt Wait these many RTTs before making congesion decision * nv_cwnd_growth_rate_neg * nv_cwnd_growth_rate_pos * How quickly to double growth rate (not rate) of cwnd when not * congested. One value (nv_cwnd_growth_rate_neg) for when * rate < 1 pkt/RTT (after losses). The other (nv_cwnd_growth_rate_pos) * otherwise. */ static int nv_pad __read_mostly = 10; static int nv_pad_buffer __read_mostly = 2; static int nv_reset_period __read_mostly = 5; /* in seconds */ static int nv_min_cwnd __read_mostly = 2; static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */ static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */ static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */ static int nv_loss_dec_factor __read_mostly = 819; /* => 80% */ static int nv_cwnd_growth_rate_neg __read_mostly = 8; static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */ static int nv_dec_eval_min_calls __read_mostly = 60; static int nv_inc_eval_min_calls __read_mostly = 20; static int nv_ssthresh_eval_min_calls __read_mostly = 30; static int nv_stop_rtt_cnt __read_mostly = 10; static int nv_rtt_min_cnt __read_mostly = 2; module_param(nv_pad, int, 0644); MODULE_PARM_DESC(nv_pad, "max queued packets allowed in network"); module_param(nv_reset_period, int, 0644); MODULE_PARM_DESC(nv_reset_period, "nv_min_rtt reset period (secs)"); module_param(nv_min_cwnd, int, 0644); MODULE_PARM_DESC(nv_min_cwnd, "NV will not decrease cwnd below this value" " without losses"); /* TCP NV Parameters */ struct tcpnv { unsigned long nv_min_rtt_reset_jiffies; /* when to switch to * nv_min_rtt_new */ s8 cwnd_growth_factor; /* Current cwnd growth factor, * < 0 => less than 1 packet/RTT */ u8 available8; u16 available16; u8 nv_allow_cwnd_growth:1, /* whether cwnd can grow */ nv_reset:1, /* whether to reset values */ nv_catchup:1; /* whether we are growing because * of temporary cwnd decrease */ u8 nv_eval_call_cnt; /* call count since last eval */ u8 nv_min_cwnd; /* nv won't make a ca decision if cwnd is * smaller than this. It may grow to handle * TSO, LRO and interrupt coalescence because * with these a small cwnd cannot saturate * the link. Note that this is different from * the file local nv_min_cwnd */ u8 nv_rtt_cnt; /* RTTs without making ca decision */; u32 nv_last_rtt; /* last rtt */ u32 nv_min_rtt; /* active min rtt. Used to determine slope */ u32 nv_min_rtt_new; /* min rtt for future use */ u32 nv_base_rtt; /* If non-zero it represents the threshold for * congestion */ u32 nv_lower_bound_rtt; /* Used in conjunction with nv_base_rtt. It is * set to 80% of nv_base_rtt. It helps reduce * unfairness between flows */ u32 nv_rtt_max_rate; /* max rate seen during current RTT */ u32 nv_rtt_start_seq; /* current RTT ends when packet arrives * acking beyond nv_rtt_start_seq */ u32 nv_last_snd_una; /* Previous value of tp->snd_una. It is * used to determine bytes acked since last * call to bictcp_acked */ u32 nv_no_cong_cnt; /* Consecutive no congestion decisions */ }; #define NV_INIT_RTT U32_MAX #define NV_MIN_CWND 4 #define NV_MIN_CWND_GROW 2 #define NV_TSO_CWND_BOUND 80 static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); ca->nv_reset = 0; ca->nv_no_cong_cnt = 0; ca->nv_rtt_cnt = 0; ca->nv_last_rtt = 0; ca->nv_rtt_max_rate = 0; ca->nv_rtt_start_seq = tp->snd_una; ca->nv_eval_call_cnt = 0; ca->nv_last_snd_una = tp->snd_una; } static void tcpnv_init(struct sock *sk) { struct tcpnv *ca = inet_csk_ca(sk); int base_rtt; tcpnv_reset(ca, sk); /* See if base_rtt is available from socket_ops bpf program. * It is meant to be used in environments, such as communication * within a datacenter, where we have reasonable estimates of * RTTs */ base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT, 0, NULL); if (base_rtt > 0) { ca->nv_base_rtt = base_rtt; ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */ } else { ca->nv_base_rtt = 0; ca->nv_lower_bound_rtt = 0; } ca->nv_allow_cwnd_growth = 1; ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ; ca->nv_min_rtt = NV_INIT_RTT; ca->nv_min_rtt_new = NV_INIT_RTT; ca->nv_min_cwnd = NV_MIN_CWND; ca->nv_catchup = 0; ca->cwnd_growth_factor = 0; } /* If provided, apply upper (base_rtt) and lower (lower_bound_rtt) * bounds to RTT. */ inline u32 nv_get_bounded_rtt(struct tcpnv *ca, u32 val) { if (ca->nv_lower_bound_rtt > 0 && val < ca->nv_lower_bound_rtt) return ca->nv_lower_bound_rtt; else if (ca->nv_base_rtt > 0 && val > ca->nv_base_rtt) return ca->nv_base_rtt; else return val; } static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct tcpnv *ca = inet_csk_ca(sk); u32 cnt; if (!tcp_is_cwnd_limited(sk)) return; /* Only grow cwnd if NV has not detected congestion */ if (!ca->nv_allow_cwnd_growth) return; if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } if (ca->cwnd_growth_factor < 0) { cnt = tcp_snd_cwnd(tp) << -ca->cwnd_growth_factor; tcp_cong_avoid_ai(tp, cnt, acked); } else { cnt = max(4U, tcp_snd_cwnd(tp) >> ca->cwnd_growth_factor); tcp_cong_avoid_ai(tp, cnt, acked); } } static u32 tcpnv_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max((tcp_snd_cwnd(tp) * nv_loss_dec_factor) >> 10, 2U); } static void tcpnv_state(struct sock *sk, u8 new_state) { struct tcpnv *ca = inet_csk_ca(sk); if (new_state == TCP_CA_Open && ca->nv_reset) { tcpnv_reset(ca, sk); } else if (new_state == TCP_CA_Loss || new_state == TCP_CA_CWR || new_state == TCP_CA_Recovery) { ca->nv_reset = 1; ca->nv_allow_cwnd_growth = 0; if (new_state == TCP_CA_Loss) { /* Reset cwnd growth factor to Reno value */ if (ca->cwnd_growth_factor > 0) ca->cwnd_growth_factor = 0; /* Decrease growth rate if allowed */ if (nv_cwnd_growth_rate_neg > 0 && ca->cwnd_growth_factor > -8) ca->cwnd_growth_factor--; } } } /* Do congestion avoidance calculations for TCP-NV */ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcpnv *ca = inet_csk_ca(sk); unsigned long now = jiffies; u64 rate64; u32 rate, max_win, cwnd_by_slope; u32 avg_rtt; u32 bytes_acked = 0; /* Some calls are for duplicates without timetamps */ if (sample->rtt_us < 0) return; /* If not in TCP_CA_Open or TCP_CA_Disorder states, skip. */ if (icsk->icsk_ca_state != TCP_CA_Open && icsk->icsk_ca_state != TCP_CA_Disorder) return; /* Stop cwnd growth if we were in catch up mode */ if (ca->nv_catchup && tcp_snd_cwnd(tp) >= nv_min_cwnd) { ca->nv_catchup = 0; ca->nv_allow_cwnd_growth = 0; } bytes_acked = tp->snd_una - ca->nv_last_snd_una; ca->nv_last_snd_una = tp->snd_una; if (sample->in_flight == 0) return; /* Calculate moving average of RTT */ if (nv_rtt_factor > 0) { if (ca->nv_last_rtt > 0) { avg_rtt = (((u64)sample->rtt_us) * nv_rtt_factor + ((u64)ca->nv_last_rtt) * (256 - nv_rtt_factor)) >> 8; } else { avg_rtt = sample->rtt_us; ca->nv_min_rtt = avg_rtt << 1; } ca->nv_last_rtt = avg_rtt; } else { avg_rtt = sample->rtt_us; } /* rate in 100's bits per second */ rate64 = ((u64)sample->in_flight) * 80000; do_div(rate64, avg_rtt ?: 1); rate = (u32)rate64; /* Remember the maximum rate seen during this RTT * Note: It may be more than one RTT. This function should be * called at least nv_dec_eval_min_calls times. */ if (ca->nv_rtt_max_rate < rate) ca->nv_rtt_max_rate = rate; /* We have valid information, increment counter */ if (ca->nv_eval_call_cnt < 255) ca->nv_eval_call_cnt++; /* Apply bounds to rtt. Only used to update min_rtt */ avg_rtt = nv_get_bounded_rtt(ca, avg_rtt); /* update min rtt if necessary */ if (avg_rtt < ca->nv_min_rtt) ca->nv_min_rtt = avg_rtt; /* update future min_rtt if necessary */ if (avg_rtt < ca->nv_min_rtt_new) ca->nv_min_rtt_new = avg_rtt; /* nv_min_rtt is updated with the minimum (possibley averaged) rtt * seen in the last sysctl_tcp_nv_reset_period seconds (i.e. a * warm reset). This new nv_min_rtt will be continued to be updated * and be used for another sysctl_tcp_nv_reset_period seconds, * when it will be updated again. * In practice we introduce some randomness, so the actual period used * is chosen randomly from the range: * [sysctl_tcp_nv_reset_period*3/4, sysctl_tcp_nv_reset_period*5/4) */ if (time_after_eq(now, ca->nv_min_rtt_reset_jiffies)) { unsigned char rand; ca->nv_min_rtt = ca->nv_min_rtt_new; ca->nv_min_rtt_new = NV_INIT_RTT; get_random_bytes(&rand, 1); ca->nv_min_rtt_reset_jiffies = now + ((nv_reset_period * (384 + rand) * HZ) >> 9); /* Every so often we decrease ca->nv_min_cwnd in case previous * value is no longer accurate. */ ca->nv_min_cwnd = max(ca->nv_min_cwnd / 2, NV_MIN_CWND); } /* Once per RTT check if we need to do congestion avoidance */ if (before(ca->nv_rtt_start_seq, tp->snd_una)) { ca->nv_rtt_start_seq = tp->snd_nxt; if (ca->nv_rtt_cnt < 0xff) /* Increase counter for RTTs without CA decision */ ca->nv_rtt_cnt++; /* If this function is only called once within an RTT * the cwnd is probably too small (in some cases due to * tso, lro or interrupt coalescence), so we increase * ca->nv_min_cwnd. */ if (ca->nv_eval_call_cnt == 1 && bytes_acked >= (ca->nv_min_cwnd - 1) * tp->mss_cache && ca->nv_min_cwnd < (NV_TSO_CWND_BOUND + 1)) { ca->nv_min_cwnd = min(ca->nv_min_cwnd + NV_MIN_CWND_GROW, NV_TSO_CWND_BOUND + 1); ca->nv_rtt_start_seq = tp->snd_nxt + ca->nv_min_cwnd * tp->mss_cache; ca->nv_eval_call_cnt = 0; ca->nv_allow_cwnd_growth = 1; return; } /* Find the ideal cwnd for current rate from slope * slope = 80000.0 * mss / nv_min_rtt * cwnd_by_slope = nv_rtt_max_rate / slope */ cwnd_by_slope = (u32) div64_u64(((u64)ca->nv_rtt_max_rate) * ca->nv_min_rtt, 80000ULL * tp->mss_cache); max_win = cwnd_by_slope + nv_pad; /* If cwnd > max_win, decrease cwnd * if cwnd < max_win, grow cwnd * else leave the same */ if (tcp_snd_cwnd(tp) > max_win) { /* there is congestion, check that it is ok * to make a CA decision * 1. We should have at least nv_dec_eval_min_calls * data points before making a CA decision * 2. We only make a congesion decision after * nv_rtt_min_cnt RTTs */ if (ca->nv_rtt_cnt < nv_rtt_min_cnt) { return; } else if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) { if (ca->nv_eval_call_cnt < nv_ssthresh_eval_min_calls) return; /* otherwise we will decrease cwnd */ } else if (ca->nv_eval_call_cnt < nv_dec_eval_min_calls) { if (ca->nv_allow_cwnd_growth && ca->nv_rtt_cnt > nv_stop_rtt_cnt) ca->nv_allow_cwnd_growth = 0; return; } /* We have enough data to determine we are congested */ ca->nv_allow_cwnd_growth = 0; tp->snd_ssthresh = (nv_ssthresh_factor * max_win) >> 3; if (tcp_snd_cwnd(tp) - max_win > 2) { /* gap > 2, we do exponential cwnd decrease */ int dec; dec = max(2U, ((tcp_snd_cwnd(tp) - max_win) * nv_cong_dec_mult) >> 7); tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - dec); } else if (nv_cong_dec_mult > 0) { tcp_snd_cwnd_set(tp, max_win); } if (ca->cwnd_growth_factor > 0) ca->cwnd_growth_factor = 0; ca->nv_no_cong_cnt = 0; } else if (tcp_snd_cwnd(tp) <= max_win - nv_pad_buffer) { /* There is no congestion, grow cwnd if allowed*/ if (ca->nv_eval_call_cnt < nv_inc_eval_min_calls) return; ca->nv_allow_cwnd_growth = 1; ca->nv_no_cong_cnt++; if (ca->cwnd_growth_factor < 0 && nv_cwnd_growth_rate_neg > 0 && ca->nv_no_cong_cnt > nv_cwnd_growth_rate_neg) { ca->cwnd_growth_factor++; ca->nv_no_cong_cnt = 0; } else if (ca->cwnd_growth_factor >= 0 && nv_cwnd_growth_rate_pos > 0 && ca->nv_no_cong_cnt > nv_cwnd_growth_rate_pos) { ca->cwnd_growth_factor++; ca->nv_no_cong_cnt = 0; } } else { /* cwnd is in-between, so do nothing */ return; } /* update state */ ca->nv_eval_call_cnt = 0; ca->nv_rtt_cnt = 0; ca->nv_rtt_max_rate = 0; /* Don't want to make cwnd < nv_min_cwnd * (it wasn't before, if it is now is because nv * decreased it). */ if (tcp_snd_cwnd(tp) < nv_min_cwnd) tcp_snd_cwnd_set(tp, nv_min_cwnd); } } /* Extract info for Tcp socket info provided via netlink */ static size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct tcpnv *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = ca->nv_rtt_cnt; info->vegas.tcpv_rtt = ca->nv_last_rtt; info->vegas.tcpv_minrtt = ca->nv_min_rtt; *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } static struct tcp_congestion_ops tcpnv __read_mostly = { .init = tcpnv_init, .ssthresh = tcpnv_recalc_ssthresh, .cong_avoid = tcpnv_cong_avoid, .set_state = tcpnv_state, .undo_cwnd = tcp_reno_undo_cwnd, .pkts_acked = tcpnv_acked, .get_info = tcpnv_get_info, .owner = THIS_MODULE, .name = "nv", }; static int __init tcpnv_register(void) { BUILD_BUG_ON(sizeof(struct tcpnv) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcpnv); } static void __exit tcpnv_unregister(void) { tcp_unregister_congestion_control(&tcpnv); } module_init(tcpnv_register); module_exit(tcpnv_unregister); MODULE_AUTHOR("Lawrence Brakmo"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP NV"); MODULE_VERSION("1.0"); |
| 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-only */ /* * Copyright (C) 1999-2002 Vojtech Pavlik */ #ifndef _SERIO_H #define _SERIO_H #include <linux/cleanup.h> #include <linux/types.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/mod_devicetable.h> #include <uapi/linux/serio.h> extern const struct bus_type serio_bus; struct serio { void *port_data; char name[32]; char phys[32]; char firmware_id[128]; bool manual_bind; struct serio_device_id id; /* Protects critical sections from port's interrupt handler */ spinlock_t lock; int (*write)(struct serio *, unsigned char); int (*open)(struct serio *); void (*close)(struct serio *); int (*start)(struct serio *); void (*stop)(struct serio *); struct serio *parent; /* Entry in parent->children list */ struct list_head child_node; struct list_head children; /* Level of nesting in serio hierarchy */ unsigned int depth; /* * serio->drv is accessed from interrupt handlers; when modifying * caller should acquire serio->drv_mutex and serio->lock. */ struct serio_driver *drv; /* Protects serio->drv so attributes can pin current driver */ struct mutex drv_mutex; struct device dev; struct list_head node; /* * For use by PS/2 layer when several ports share hardware and * may get indigestion when exposed to concurrent access (i8042). */ struct mutex *ps2_cmd_mutex; }; #define to_serio_port(d) container_of(d, struct serio, dev) struct serio_driver { const char *description; const struct serio_device_id *id_table; bool manual_bind; void (*write_wakeup)(struct serio *); irqreturn_t (*interrupt)(struct serio *, unsigned char, unsigned int); int (*connect)(struct serio *, struct serio_driver *drv); int (*reconnect)(struct serio *); int (*fast_reconnect)(struct serio *); void (*disconnect)(struct serio *); void (*cleanup)(struct serio *); struct device_driver driver; }; #define to_serio_driver(d) container_of_const(d, struct serio_driver, driver) int serio_open(struct serio *serio, struct serio_driver *drv); void serio_close(struct serio *serio); void serio_rescan(struct serio *serio); void serio_reconnect(struct serio *serio); irqreturn_t serio_interrupt(struct serio *serio, unsigned char data, unsigned int flags); void __serio_register_port(struct serio *serio, struct module *owner); /* use a define to avoid include chaining to get THIS_MODULE */ #define serio_register_port(serio) \ __serio_register_port(serio, THIS_MODULE) void serio_unregister_port(struct serio *serio); void serio_unregister_child_port(struct serio *serio); int __must_check __serio_register_driver(struct serio_driver *drv, struct module *owner, const char *mod_name); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define serio_register_driver(drv) \ __serio_register_driver(drv, THIS_MODULE, KBUILD_MODNAME) void serio_unregister_driver(struct serio_driver *drv); /** * module_serio_driver() - Helper macro for registering a serio driver * @__serio_driver: serio_driver struct * * Helper macro for serio drivers which do not do anything special in * module init/exit. This eliminates a lot of boilerplate. Each module * may only use this macro once, and calling it replaces module_init() * and module_exit(). */ #define module_serio_driver(__serio_driver) \ module_driver(__serio_driver, serio_register_driver, \ serio_unregister_driver) static inline int serio_write(struct serio *serio, unsigned char data) { if (serio->write) return serio->write(serio, data); else return -1; } static inline void serio_drv_write_wakeup(struct serio *serio) { if (serio->drv && serio->drv->write_wakeup) serio->drv->write_wakeup(serio); } /* * Use the following functions to manipulate serio's per-port * driver-specific data. */ static inline void *serio_get_drvdata(struct serio *serio) { return dev_get_drvdata(&serio->dev); } static inline void serio_set_drvdata(struct serio *serio, void *data) { dev_set_drvdata(&serio->dev, data); } /* * Use the following functions to protect critical sections in * driver code from port's interrupt handler */ static inline void serio_pause_rx(struct serio *serio) { spin_lock_irq(&serio->lock); } static inline void serio_continue_rx(struct serio *serio) { spin_unlock_irq(&serio->lock); } DEFINE_GUARD(serio_pause_rx, struct serio *, serio_pause_rx(_T), serio_continue_rx(_T)) #endif |
| 5193 5192 2832 2831 138 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/dir.c - sysfs core and dir operation implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #define pr_fmt(fmt) "sysfs: " fmt #include <linux/fs.h> #include <linux/kobject.h> #include <linux/slab.h> #include "sysfs.h" DEFINE_SPINLOCK(sysfs_symlink_target_lock); void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { char *buf; buf = kzalloc(PATH_MAX, GFP_KERNEL); if (buf) kernfs_path(parent, buf, PATH_MAX); pr_warn("cannot create duplicate filename '%s/%s'\n", buf, name); dump_stack(); kfree(buf); } /** * sysfs_create_dir_ns - create a directory for an object with a namespace tag * @kobj: object we're creating directory for * @ns: the namespace tag to use */ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { struct kernfs_node *parent, *kn; kuid_t uid; kgid_t gid; if (WARN_ON(!kobj)) return -EINVAL; if (kobj->parent) parent = kobj->parent->sd; else parent = sysfs_root_kn; if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid, kobj, ns); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, kobject_name(kobj)); return PTR_ERR(kn); } kobj->sd = kn; return 0; } /** * sysfs_remove_dir - remove an object's directory. * @kobj: object. * * The only thing special about this is that we remove any files in * the directory before we remove the directory, and we've inlined * what used to be sysfs_rmdir() below, instead of calling separately. */ void sysfs_remove_dir(struct kobject *kobj) { struct kernfs_node *kn = kobj->sd; /* * In general, kobject owner is responsible for ensuring removal * doesn't race with other operations and sysfs doesn't provide any * protection; however, when @kobj is used as a symlink target, the * symlinking entity usually doesn't own @kobj and thus has no * control over removal. @kobj->sd may be removed anytime * and symlink code may end up dereferencing an already freed node. * * sysfs_symlink_target_lock synchronizes @kobj->sd * disassociation against symlink operations so that symlink code * can safely dereference @kobj->sd. */ spin_lock(&sysfs_symlink_target_lock); kobj->sd = NULL; spin_unlock(&sysfs_symlink_target_lock); if (kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); kernfs_remove(kn); } } int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, const void *new_ns) { struct kernfs_node *parent; int ret; parent = kernfs_get_parent(kobj->sd); ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); kernfs_put(parent); return ret; } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns) { struct kernfs_node *kn = kobj->sd; struct kernfs_node *new_parent; new_parent = new_parent_kobj && new_parent_kobj->sd ? new_parent_kobj->sd : sysfs_root_kn; return kernfs_rename_ns(kn, new_parent, kn->name, new_ns); } /** * sysfs_create_mount_point - create an always empty directory * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to add */ int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *kn, *parent = parent_kobj->sd; kn = kernfs_create_empty_dir(parent, name); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, name); return PTR_ERR(kn); } return 0; } EXPORT_SYMBOL_GPL(sysfs_create_mount_point); /** * sysfs_remove_mount_point - remove an always empty directory. * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to remove * */ void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *parent = parent_kobj->sd; kernfs_remove_by_name_ns(parent, name, NULL); } EXPORT_SYMBOL_GPL(sysfs_remove_mount_point); |
| 11 1 1 2 4 3 1 2 2 6 1 6 4 2 5 1 6 6 5 5 4 4 1 5 502 502 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* net/sched/act_ctinfo.c netfilter ctinfo connmark actions * * Copyright (c) 2019 Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/pkt_cls.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_ctinfo.h> #include <net/tc_act/tc_ctinfo.h> #include <net/tc_wrapper.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_zones.h> static struct tc_action_ops act_ctinfo_ops; static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct tcf_ctinfo_params *cp, struct sk_buff *skb, int wlen, int proto) { u8 dscp, newdscp; newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { case NFPROTO_IPV4: dscp = ipv4_get_dsfield(ip_hdr(skb)) & ~INET_ECN_MASK; if (dscp != newdscp) { if (likely(!skb_try_make_writable(skb, wlen))) { ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, newdscp); ca->stats_dscp_set++; } else { ca->stats_dscp_error++; } } break; case NFPROTO_IPV6: dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK; if (dscp != newdscp) { if (likely(!skb_try_make_writable(skb, wlen))) { ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, newdscp); ca->stats_dscp_set++; } else { ca->stats_dscp_error++; } } break; default: break; } } static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct tcf_ctinfo_params *cp, struct sk_buff *skb) { ca->stats_cpmark_set++; skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } TC_INDIRECT_SCOPE int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { const struct nf_conntrack_tuple_hash *thash = NULL; struct tcf_ctinfo *ca = to_ctinfo(a); struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; enum ip_conntrack_info ctinfo; struct tcf_ctinfo_params *cp; struct nf_conn *ct; int proto, wlen; int action; cp = rcu_dereference_bh(ca->params); tcf_lastuse_update(&ca->tcf_tm); tcf_action_update_bstats(&ca->common, skb); action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV4; break; case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV6; break; default: goto out; } ct = nf_ct_get(skb, &ctinfo); if (!ct) { /* look harder, usually ingress */ if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, cp->net, &tuple)) goto out; zone.id = cp->zone; zone.dir = NF_CT_DEFAULT_ZONE_DIR; thash = nf_conntrack_find_get(cp->net, &zone, &tuple); if (!thash) goto out; ct = nf_ct_tuplehash_to_ctrack(thash); } if (cp->mode & CTINFO_MODE_DSCP) if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) tcf_ctinfo_cpmark_set(ct, ca, cp, skb); if (thash) nf_ct_put(ct); out: return action; } static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { [TCA_CTINFO_ACT] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)), [TCA_CTINFO_ZONE] = { .type = NLA_U16 }, [TCA_CTINFO_PARMS_DSCP_MASK] = { .type = NLA_U32 }, [TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 }, [TCA_CTINFO_PARMS_CPMARK_MASK] = { .type = NLA_U32 }, }; static int tcf_ctinfo_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_ctinfo_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; struct tcf_chain *goto_ch = NULL; struct tc_ctinfo *actparm; struct tcf_ctinfo *ci; u8 dscpmaskshift; int ret = 0, err; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "ctinfo requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested(tb, TCA_CTINFO_MAX, nla, ctinfo_policy, extack); if (err < 0) return err; if (!tb[TCA_CTINFO_ACT]) { NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_CTINFO_ACT attribute"); return -EINVAL; } actparm = nla_data(tb[TCA_CTINFO_ACT]); /* do some basic validation here before dynamically allocating things */ /* that we would otherwise have to clean up. */ if (tb[TCA_CTINFO_PARMS_DSCP_MASK]) { dscpmask = nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_MASK]); /* need contiguous 6 bit mask */ dscpmaskshift = dscpmask ? __ffs(dscpmask) : 0; if ((~0 & (dscpmask >> dscpmaskshift)) != 0x3f) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CTINFO_PARMS_DSCP_MASK], "dscp mask must be 6 contiguous bits"); return -EINVAL; } dscpstatemask = nla_get_u32_default(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK], 0); /* mask & statemask must not overlap */ if (dscpmask & dscpstatemask) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CTINFO_PARMS_DSCP_STATEMASK], "dscp statemask must not overlap dscp mask"); return -EINVAL; } } /* done the validation:now to the actual action allocation */ index = actparm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_ctinfo_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) /* don't 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(actparm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; ci = to_ctinfo(*a); cp_new = kzalloc(sizeof(*cp_new), GFP_KERNEL); if (unlikely(!cp_new)) { err = -ENOMEM; goto put_chain; } cp_new->net = net; cp_new->zone = nla_get_u16_default(tb[TCA_CTINFO_ZONE], 0); if (dscpmask) { cp_new->dscpmask = dscpmask; cp_new->dscpmaskshift = dscpmaskshift; cp_new->dscpstatemask = dscpstatemask; cp_new->mode |= CTINFO_MODE_DSCP; } if (tb[TCA_CTINFO_PARMS_CPMARK_MASK]) { cp_new->cpmarkmask = nla_get_u32(tb[TCA_CTINFO_PARMS_CPMARK_MASK]); cp_new->mode |= CTINFO_MODE_CPMARK; } spin_lock_bh(&ci->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch); cp_new = rcu_replace_pointer(ci->params, cp_new, lockdep_is_held(&ci->tcf_lock)); spin_unlock_bh(&ci->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (cp_new) kfree_rcu(cp_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; } static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { struct tcf_ctinfo *ci = to_ctinfo(a); struct tc_ctinfo opt = { .index = ci->tcf_index, .refcnt = refcount_read(&ci->tcf_refcnt) - ref, .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, }; unsigned char *b = skb_tail_pointer(skb); struct tcf_ctinfo_params *cp; struct tcf_t t; spin_lock_bh(&ci->tcf_lock); cp = rcu_dereference_protected(ci->params, lockdep_is_held(&ci->tcf_lock)); tcf_tm_dump(&t, &ci->tcf_tm); if (nla_put_64bit(skb, TCA_CTINFO_TM, sizeof(t), &t, TCA_CTINFO_PAD)) goto nla_put_failure; opt.action = ci->tcf_action; if (nla_put(skb, TCA_CTINFO_ACT, sizeof(opt), &opt)) goto nla_put_failure; if (nla_put_u16(skb, TCA_CTINFO_ZONE, cp->zone)) goto nla_put_failure; if (cp->mode & CTINFO_MODE_DSCP) { if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_MASK, cp->dscpmask)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_STATEMASK, cp->dscpstatemask)) goto nla_put_failure; } if (cp->mode & CTINFO_MODE_CPMARK) { if (nla_put_u32(skb, TCA_CTINFO_PARMS_CPMARK_MASK, cp->cpmarkmask)) goto nla_put_failure; } if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET, ci->stats_dscp_set, TCA_CTINFO_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR, ci->stats_dscp_error, TCA_CTINFO_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET, ci->stats_cpmark_set, TCA_CTINFO_PAD)) goto nla_put_failure; spin_unlock_bh(&ci->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&ci->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_ctinfo_cleanup(struct tc_action *a) { struct tcf_ctinfo *ci = to_ctinfo(a); struct tcf_ctinfo_params *cp; cp = rcu_dereference_protected(ci->params, 1); if (cp) kfree_rcu(cp, rcu); } static struct tc_action_ops act_ctinfo_ops = { .kind = "ctinfo", .id = TCA_ID_CTINFO, .owner = THIS_MODULE, .act = tcf_ctinfo_act, .dump = tcf_ctinfo_dump, .init = tcf_ctinfo_init, .cleanup= tcf_ctinfo_cleanup, .size = sizeof(struct tcf_ctinfo), }; MODULE_ALIAS_NET_ACT("ctinfo"); static __net_init int ctinfo_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_ctinfo_ops.net_id); return tc_action_net_init(net, tn, &act_ctinfo_ops); } static void __net_exit ctinfo_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_ctinfo_ops.net_id); } static struct pernet_operations ctinfo_net_ops = { .init = ctinfo_init_net, .exit_batch = ctinfo_exit_net, .id = &act_ctinfo_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init ctinfo_init_module(void) { return tcf_register_action(&act_ctinfo_ops, &ctinfo_net_ops); } static void __exit ctinfo_cleanup_module(void) { tcf_unregister_action(&act_ctinfo_ops, &ctinfo_net_ops); } module_init(ctinfo_init_module); module_exit(ctinfo_cleanup_module); MODULE_AUTHOR("Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>"); MODULE_DESCRIPTION("Connection tracking mark actions"); MODULE_LICENSE("GPL"); |
| 21 1 20 18 18 2 17 18 17 2 17 3 15 18 18 3 15 16 2 2 15 2 63 4 55 5 16 2 42 4 1 2 1 17 14 14 9 6 4 5 4 4 4 5 7 7 3 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * UDPv4 GSO support */ #include <linux/skbuff.h> #include <net/gro.h> #include <net/gso.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features), __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) partial = (__force __wsum)uh->len; else partial = (__force __wsum)htonl(skb->len); partial = csum_sub(csum_unfold(uh->check), partial); /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); skb->encap_hdr_csum = need_csum; remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and * instead set the flag based on our outer checksum offload value. */ if (remcsum) { features &= ~NETIF_F_CSUM_MASK; if (!need_csum || offload_csum) features |= NETIF_F_HW_CSUM; } /* segment inner packet. */ segs = gso_inner_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; do { unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); len = skb->len - udp_offset; uh = udp_hdr(skb); /* If we are only performing partial GSO the inner header * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); } else { uh->len = htons(len); } if (!need_csum) continue; uh->check = ~csum_fold(csum_add(partial, (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); } } while ((skb = skb->next)); out: return segs; } struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features); rcu_read_lock(); switch (skb->inner_protocol_type) { case ENCAP_TYPE_ETHER: protocol = skb->inner_protocol; gso_inner_segment = skb_mac_gso_segment; break; case ENCAP_TYPE_IPPROTO: offloads = is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[skb->inner_ipproto]); if (!ops || !ops->callbacks.gso_segment) goto out_unlock; gso_inner_segment = ops->callbacks.gso_segment; break; default: goto out_unlock; } segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment, protocol, is_ipv6); out_unlock: rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_udp_tunnel_segment); static void __udpv4_gso_segment_csum(struct sk_buff *seg, __be32 *oldip, __be32 *newip, __be16 *oldport, __be16 *newport) { struct udphdr *uh; struct iphdr *iph; if (*oldip == *newip && *oldport == *newport) return; uh = udp_hdr(seg); iph = ip_hdr(seg); if (uh->check) { inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldport = *newport; csum_replace4(&iph->check, *oldip, *newip); *oldip = *newip; } static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) { struct sk_buff *seg; struct udphdr *uh, *uh2; struct iphdr *iph, *iph2; seg = segs; uh = udp_hdr(seg); iph = ip_hdr(seg); if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ip_hdr(seg); __udpv4_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, &uh->source); __udpv4_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, &uh->dest); } return segs; } static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { unsigned int mss = skb_shinfo(skb)->gso_size; skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); if (IS_ERR(skb)) return skb; udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; struct sk_buff *segs, *seg; struct udphdr *uh; unsigned int mss; bool copy_dtor; __sum16 check; __be16 newlen; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != skb_transport_header(gso_skb) && !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); /* We don't know if egress device can segment and checksum the packet * when IPv6 extension headers are present. Fall back to software GSO. */ if (gso_skb->ip_summed != CHECKSUM_PARTIAL) features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), mss); return NULL; } if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); gso_skb->ip_summed = CHECKSUM_PARTIAL; uh = udp_hdr(gso_skb); if (is_ipv6) uh->check = ~udp_v6_check(gso_skb->len, &ipv6_hdr(gso_skb)->saddr, &ipv6_hdr(gso_skb)->daddr, 0); else uh->check = ~udp_v4_check(gso_skb->len, ip_hdr(gso_skb)->saddr, ip_hdr(gso_skb)->daddr, 0); } skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; if (copy_dtor) { gso_skb->destructor = NULL; gso_skb->sk = NULL; } segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { if (copy_dtor) { gso_skb->destructor = sock_wfree; gso_skb->sk = sk; } return segs; } /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; seg = segs; uh = udp_hdr(seg); /* preserve TX timestamp flags and TS key for first segment */ skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey; skb_shinfo(seg)->tx_flags |= (skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP); /* compute checksum adjustment based on old length versus new */ newlen = htons(sizeof(*uh) + mss); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); for (;;) { if (copy_dtor) { seg->destructor = sock_wfree; seg->sk = sk; sum_truesize += seg->truesize; } if (!seg->next) break; uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; seg = seg->next; uh = udp_hdr(seg); } /* last packet can be partial gso_size, account for that in checksum */ newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + seg->data_len); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; /* On the TX path, CHECKSUM_NONE and CHECKSUM_UNNECESSARY have the same * meaning. However, check for bad offloads in the GSO stack expects the * latter, if the checksum was calculated in software. To vouch for the * segment skbs we actually need to set it on the gso_skb. */ if (gso_skb->ip_summed == CHECKSUM_NONE) gso_skb->ip_summed = CHECKSUM_UNNECESSARY; /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); } return segs; } EXPORT_SYMBOL_GPL(__udp_gso_segment); static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; __wsum csum; struct udphdr *uh; struct iphdr *iph; if (skb->encapsulation && (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features, false); goto out; } if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as * HW cannot do checksum of UDP packets sent as multiple * IP fragments. */ uh = udp_hdr(skb); iph = ip_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() */ segs = skb_segment(skb, features); out: return segs; } #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; int ret = 0; int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* Do not deal with padded or malicious packets, sorry ! */ ulen = ntohs(uh->len); if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = udp_hdr(p); /* Match ports only, as csum is always non zero */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { NAPI_GRO_CB(skb)->flush = 1; return p; } flush = gro_receive_network_flush(uh, uh2, p); /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } if ((skb->ip_summed != p->ip_summed) || (skb->csum_level != p->csum_level)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); ret = skb_gro_receive(p, skb); } } if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; return pp; } /* mismatch, but we never need to flush */ return NULL; } struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; /* We can do L4 aggregation only if the packet can't land in a tunnel * otherwise we could corrupt the inner stream. Detecting such packets * cannot be foolproof and the aggregation might still happen in some * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { /* If the packet was locally encapsulated in a UDP tunnel that * wasn't detected above, do not GRO. */ if (skb->encapsulation) goto out; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ goto out; } if (NAPI_GRO_CB(skb)->encap_mark || (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = (struct udphdr *)(p->data + off); /* Match ports and either checksums are either both zero * or nonzero. */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) || (!uh->check ^ !uh2->check)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); int iif, sdif; inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, inet_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } static int udp_gro_complete_segment(struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); skb->csum_start = (unsigned char *)uh - skb->head; skb->csum_offset = offsetof(struct udphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup) { __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); struct sock *sk; int err; uh->len = newlen; sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; /* clear the encap mark, so that inner frag_list gro_complete * can take place */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Set encapsulation before calling into inner gro_complete() * functions to make them set up the inner offsets. */ skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); } else { err = udp_gro_complete_segment(skb); } if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; return err; } EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } int __init udpv4_offload_init(void) { net_hotdata.udpv4_offload = (struct net_offload) { .callbacks = { .gso_segment = udp4_ufo_fragment, .gro_receive = udp4_gro_receive, .gro_complete = udp4_gro_complete, }, }; return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } |
| 30 30 30 30 84 84 84 84 84 19 19 19 19 124 84 84 84 84 124 84 18 19 19 19 13 13 13 13 13 13 13 13 13 13 13 124 124 124 124 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "send.h" #include "main.h" #include <linux/atomic.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "log.h" #include "network-coding.h" #include "originator.h" #include "routing.h" #include "soft-interface.h" #include "translation-table.h" static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /** * batadv_send_skb_packet() - send an already prepared packet * @skb: the packet to send * @hard_iface: the interface to use to send the broadcast packet * @dst_addr: the payload destination * * Send out an already prepared packet to the given neighbor or broadcast it * using the specified interface. Either hard_iface or neigh_node must be not * NULL. * If neigh_node is NULL, then the packet is broadcasted using hard_iface, * otherwise it is sent as unicast to the given neighbor. * * Regardless of the return value, the skb is consumed. * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const u8 *dst_addr) { struct batadv_priv *bat_priv; struct ethhdr *ethhdr; int ret; bat_priv = netdev_priv(hard_iface->soft_iface); if (hard_iface->if_status != BATADV_IF_ACTIVE) goto send_skb_err; if (unlikely(!hard_iface->net_dev)) goto send_skb_err; if (!(hard_iface->net_dev->flags & IFF_UP)) { pr_warn("Interface %s is not up - can't send packet via that interface!\n", hard_iface->net_dev->name); goto send_skb_err; } /* push to the ethernet header. */ if (batadv_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr); ether_addr_copy(ethhdr->h_dest, dst_addr); ethhdr->h_proto = htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->protocol = htons(ETH_P_BATMAN); skb->dev = hard_iface->net_dev; /* Save a clone of the skb to use when decoding coded packets */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* dev_queue_xmit() returns a negative result on error. However on * congestion and traffic shaping, it drops and returns NET_XMIT_DROP * (which is > 0). This will not be treated as an error. */ ret = dev_queue_xmit(skb); return net_xmit_eval(ret); send_skb_err: kfree_skb(skb); return NET_XMIT_DROP; } /** * batadv_send_broadcast_skb() - Send broadcast packet via hard interface * @skb: packet to be transmitted (with batadv header and no outer eth header) * @hard_iface: outgoing interface * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { return batadv_send_skb_packet(skb, hard_iface, batadv_broadcast_addr); } /** * batadv_send_unicast_skb() - Send unicast packet to neighbor * @skb: packet to be transmitted (with batadv header and no outer eth header) * @neigh: neighbor which is used as next hop to destination * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh) { #ifdef CONFIG_BATMAN_ADV_BATMAN_V struct batadv_hardif_neigh_node *hardif_neigh; #endif int ret; ret = batadv_send_skb_packet(skb, neigh->if_incoming, neigh->addr); #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; batadv_hardif_neigh_put(hardif_neigh); #endif return ret; } /** * batadv_send_skb_to_orig() - Lookup next-hop and transmit skb. * @skb: Packet to be transmitted. * @orig_node: Final destination of the packet. * @recv_if: Interface used when receiving the packet (can be NULL). * * Looks up the best next-hop towards the passed originator and passes the * skb on for preparation of MAC header. If the packet originated from this * host, NULL can be passed as recv_if and no interface alternating is * attempted. * * Return: negative errno code on a failure, -EINPROGRESS if the skb is * buffered for later transmit or the NET_XMIT status returned by the * lower routine if the packet has been passed down. */ int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = orig_node->bat_priv; struct batadv_neigh_node *neigh_node; int ret; /* batadv_find_router() increases neigh_nodes refcount if found. */ neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) { ret = -EINVAL; goto free_skb; } /* Check if the skb is too large to send in one piece and fragment * it if needed. */ if (atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { /* Fragment and send packet. */ ret = batadv_frag_send_packet(skb, orig_node, neigh_node); /* skb was consumed */ skb = NULL; goto put_neigh_node; } /* try to network code the packet, if it is received on an interface * (i.e. being forwarded). If the packet originates from this node or if * network coding fails, then send the packet as usual. */ if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) ret = -EINPROGRESS; else ret = batadv_send_unicast_skb(skb, neigh_node); /* skb was consumed */ skb = NULL; put_neigh_node: batadv_neigh_node_put(neigh_node); free_skb: kfree_skb(skb); return ret; } /** * batadv_send_skb_push_fill_unicast() - extend the buffer and initialize the * common fields for unicast packets * @skb: the skb carrying the unicast header to initialize * @hdr_size: amount of bytes to push at the beginning of the skb * @orig_node: the destination node * * Return: false if the buffer extension was not possible or true otherwise. */ static bool batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node) { struct batadv_unicast_packet *unicast_packet; u8 ttvn = (u8)atomic_read(&orig_node->last_ttvn); if (batadv_skb_head_push(skb, hdr_size) < 0) return false; unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->version = BATADV_COMPAT_VERSION; /* batman packet type: unicast */ unicast_packet->packet_type = BATADV_UNICAST; /* set unicast ttl */ unicast_packet->ttl = BATADV_TTL; /* copy the destination for faster routing */ ether_addr_copy(unicast_packet->dest, orig_node->orig); /* set the destination tt version number */ unicast_packet->ttvn = ttvn; return true; } /** * batadv_send_skb_prepare_unicast() - encapsulate an skb with a unicast header * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * * Return: false if the payload could not be encapsulated or true otherwise. */ static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb, struct batadv_orig_node *orig_node) { size_t uni_size = sizeof(struct batadv_unicast_packet); return batadv_send_skb_push_fill_unicast(skb, uni_size, orig_node); } /** * batadv_send_skb_prepare_unicast_4addr() - encapsulate an skb with a * unicast 4addr header * @bat_priv: the bat priv with all the soft interface information * @skb: the skb containing the payload to encapsulate * @orig: the destination node * @packet_subtype: the unicast 4addr packet subtype to use * * Return: false if the payload could not be encapsulated or true otherwise. */ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig, int packet_subtype) { struct batadv_hard_iface *primary_if; struct batadv_unicast_4addr_packet *uc_4addr_packet; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* Pull the header space and fill the unicast_packet substructure. * We can do that because the first member of the uc_4addr_packet * is of type struct unicast_packet */ if (!batadv_send_skb_push_fill_unicast(skb, sizeof(*uc_4addr_packet), orig)) goto out; uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR; ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr); uc_4addr_packet->subtype = packet_subtype; uc_4addr_packet->reserved = 0; ret = true; out: batadv_hardif_put(primary_if); return ret; } /** * batadv_send_skb_unicast() - encapsulate and send an skb via unicast * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @orig_node: the originator to send the packet to * @vid: the vid to be used to search the translation table * * Wrap the given skb into a batman-adv unicast or unicast-4addr header * depending on whether BATADV_UNICAST or BATADV_UNICAST_4ADDR was supplied * as packet_type. Then send this frame to the given orig_node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) goto out; switch (packet_type) { case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It * should never be invoked with any other packet type */ goto out; } /* skb->data might have been reallocated by * batadv_send_skb_prepare_unicast{,_4addr}() */ ethhdr = eth_hdr(skb); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route * for this client. The destination will receive this packet and will * try to reroute it because the ttvn contained in the header is less * than the current one */ if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) unicast_packet->ttvn = unicast_packet->ttvn - 1; ret = batadv_send_skb_to_orig(skb, orig_node, NULL); /* skb was consumed */ skb = NULL; out: kfree_skb(skb); return ret; } /** * batadv_send_skb_via_tt_generic() - send an skb via TT lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet * header via the translation table. Wrap the given skb into a batman-adv * unicast or unicast-4addr header depending on whether BATADV_UNICAST or * BATADV_UNICAST_4ADDR was supplied as packet_type. Then send this frame * to the according destination node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, u8 *dst_hint, unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; u8 *src, *dst; int ret; src = ethhdr->h_source; dst = ethhdr->h_dest; /* if we got an hint! let's send the packet to this client (if any) */ if (dst_hint) { src = NULL; dst = dst_hint; } orig_node = batadv_transtable_search(bat_priv, src, dst, vid); ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_send_skb_via_gw() - send an skb via gateway lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @vid: the vid to be used to search the translation table * * Look up the currently selected gateway. Wrap the given skb into a batman-adv * unicast header and send this frame to this gateway node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret; orig_node = batadv_gw_get_selected_orig(bat_priv); ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, BATADV_P_DATA, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. */ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet, bool dropped) { if (dropped) kfree_skb(forw_packet->skb); else consume_skb(forw_packet->skb); batadv_hardif_put(forw_packet->if_incoming); batadv_hardif_put(forw_packet->if_outgoing); if (forw_packet->queue_left) atomic_inc(forw_packet->queue_left); kfree(forw_packet); } /** * batadv_forw_packet_alloc() - allocate a forwarding packet * @if_incoming: The (optional) if_incoming to be grabbed * @if_outgoing: The (optional) if_outgoing to be grabbed * @queue_left: The (optional) queue counter to decrease * @bat_priv: The bat_priv for the mesh of this forw_packet * @skb: The raw packet this forwarding packet shall contain * * Allocates a forwarding packet and tries to get a reference to the * (optional) if_incoming, if_outgoing and queue_left. If queue_left * is NULL then bat_priv is optional, too. * * Return: An allocated forwarding packet on success, NULL otherwise. */ struct batadv_forw_packet * batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing, atomic_t *queue_left, struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_forw_packet *forw_packet; const char *qname; if (queue_left && !batadv_atomic_dec_not_zero(queue_left)) { qname = "unknown"; if (queue_left == &bat_priv->bcast_queue_left) qname = "bcast"; if (queue_left == &bat_priv->batman_queue_left) qname = "batman"; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s queue is full\n", qname); return NULL; } forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); if (!forw_packet) goto err; if (if_incoming) kref_get(&if_incoming->refcount); if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&forw_packet->list); INIT_HLIST_NODE(&forw_packet->cleanup_list); forw_packet->skb = skb; forw_packet->queue_left = queue_left; forw_packet->if_incoming = if_incoming; forw_packet->if_outgoing = if_outgoing; forw_packet->num_packets = 0; return forw_packet; err: if (queue_left) atomic_inc(queue_left); return NULL; } /** * batadv_forw_packet_was_stolen() - check whether someone stole this packet * @forw_packet: the forwarding packet to check * * This function checks whether the given forwarding packet was claimed by * someone else for free(). * * Return: True if someone stole it, false otherwise. */ static bool batadv_forw_packet_was_stolen(struct batadv_forw_packet *forw_packet) { return !hlist_unhashed(&forw_packet->cleanup_list); } /** * batadv_forw_packet_steal() - claim a forw_packet for free() * @forw_packet: the forwarding packet to steal * @lock: a key to the store to steal from (e.g. forw_{bat,bcast}_list_lock) * * This function tries to steal a specific forw_packet from global * visibility for the purpose of getting it for free(). That means * the caller is *not* allowed to requeue it afterwards. * * Return: True if stealing was successful. False if someone else stole it * before us. */ bool batadv_forw_packet_steal(struct batadv_forw_packet *forw_packet, spinlock_t *lock) { /* did purging routine steal it earlier? */ spin_lock_bh(lock); if (batadv_forw_packet_was_stolen(forw_packet)) { spin_unlock_bh(lock); return false; } hlist_del_init(&forw_packet->list); /* Just to spot misuse of this function */ hlist_add_fake(&forw_packet->cleanup_list); spin_unlock_bh(lock); return true; } /** * batadv_forw_packet_list_steal() - claim a list of forward packets for free() * @forw_list: the to be stolen forward packets * @cleanup_list: a backup pointer, to be able to dispose the packet later * @hard_iface: the interface to steal forward packets from * * This function claims responsibility to free any forw_packet queued on the * given hard_iface. If hard_iface is NULL forwarding packets on all hard * interfaces will be claimed. * * The packets are being moved from the forw_list to the cleanup_list. This * makes it possible for already running threads to notice the claim. */ static void batadv_forw_packet_list_steal(struct hlist_head *forw_list, struct hlist_head *cleanup_list, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, forw_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if (hard_iface && forw_packet->if_incoming != hard_iface && forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); hlist_add_head(&forw_packet->cleanup_list, cleanup_list); } } /** * batadv_forw_packet_list_free() - free a list of forward packets * @head: a list of to be freed forw_packets * * This function cancels the scheduling of any packet in the provided list, * waits for any possibly running packet forwarding thread to finish and * finally, safely frees this forward packet. * * This function might sleep. */ static void batadv_forw_packet_list_free(struct hlist_head *head) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, head, cleanup_list) { cancel_delayed_work_sync(&forw_packet->delayed_work); hlist_del(&forw_packet->cleanup_list); batadv_forw_packet_free(forw_packet, true); } } /** * batadv_forw_packet_queue() - try to queue a forwarding packet * @forw_packet: the forwarding packet to queue * @lock: a key to the store (e.g. forw_{bat,bcast}_list_lock) * @head: the shelve to queue it on (e.g. forw_{bat,bcast}_list) * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a forwarding packet. Requeuing * is prevented if the according interface is shutting down * (e.g. if batadv_forw_packet_list_steal() was called for this * packet earlier). * * Calling batadv_forw_packet_queue() after a call to * batadv_forw_packet_steal() is forbidden! * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_queue(struct batadv_forw_packet *forw_packet, spinlock_t *lock, struct hlist_head *head, unsigned long send_time) { spin_lock_bh(lock); /* did purging routine steal it from us? */ if (batadv_forw_packet_was_stolen(forw_packet)) { /* If you got it for free() without trouble, then * don't get back into the queue after stealing... */ WARN_ONCE(hlist_fake(&forw_packet->cleanup_list), "Requeuing after batadv_forw_packet_steal() not allowed!\n"); spin_unlock_bh(lock); return; } hlist_del_init(&forw_packet->list); hlist_add_head(&forw_packet->list, head); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time - jiffies); spin_unlock_bh(lock); } /** * batadv_forw_packet_bcast_queue() - try to queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a broadcast packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_bcast_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bcast_list_lock, &bat_priv->forw_bcast_list, send_time); } /** * batadv_forw_packet_ogmv1_queue() - try to queue an OGMv1 packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue an OGMv1 packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bat_list_lock, &bat_priv->forw_bat_list, send_time); } /** * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to queue on * * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { struct batadv_forw_packet *forw_packet; unsigned long send_time = jiffies; struct sk_buff *newskb; newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) goto err; forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); if (!forw_packet) goto err_packet_free; forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); send_time += delay ? delay : msecs_to_jiffies(5); batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: kfree_skb(newskb); err: return NETDEV_TX_BUSY; } /** * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to forward to * * Transmits a broadcast packet on the specified interface either immediately * or if a delay is given after that. Furthermore, queues additional * retransmissions if this interface is a wireless one. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { unsigned int num_bcasts = if_out->num_bcasts; struct sk_buff *newskb; int ret = NETDEV_TX_OK; if (!delay) { newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) return NETDEV_TX_BUSY; batadv_send_broadcast_skb(newskb, if_out); num_bcasts--; } /* delayed broadcast or rebroadcasts? */ if (num_bcasts >= 1) { BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, own_packet, if_in, if_out); } return ret; } /** * batadv_send_no_broadcast() - check whether (re)broadcast is necessary * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to check * @own_packet: true if it is a self-generated broadcast packet * @if_out: the outgoing interface checked and considered for (re)broadcast * * Return: False if a packet needs to be (re)broadcasted on the given interface, * true otherwise. */ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, struct sk_buff *skb, bool own_packet, struct batadv_hard_iface *if_out) { struct batadv_hardif_neigh_node *neigh_node = NULL; struct batadv_bcast_packet *bcast_packet; u8 *orig_neigh; u8 *neigh_addr; char *type; int ret; if (!own_packet) { neigh_addr = eth_hdr(skb)->h_source; neigh_node = batadv_hardif_neigh_get(if_out, neigh_addr); } bcast_packet = (struct batadv_bcast_packet *)skb->data; orig_neigh = neigh_node ? neigh_node->orig : NULL; ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, orig_neigh); batadv_hardif_neigh_put(neigh_node); /* ok, may broadcast */ if (!ret) return false; /* no broadcast */ switch (ret) { case BATADV_HARDIF_BCAST_NORECIPIENT: type = "no neighbor"; break; case BATADV_HARDIF_BCAST_DUPFWD: type = "single neighbor is source"; break; case BATADV_HARDIF_BCAST_DUPORIG: type = "single neighbor is originator"; break; default: type = "unknown"; } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", bcast_packet->orig, if_out->net_dev->name, type); return true; } /** * __batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the given skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if; int ret = NETDEV_TX_OK; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return NETDEV_TX_BUSY; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != bat_priv->soft_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; if (batadv_send_no_broadcast(bat_priv, skb, own_packet, hard_iface)) { batadv_hardif_put(hard_iface); continue; } ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, own_packet, primary_if, hard_iface); batadv_hardif_put(hard_iface); if (ret == NETDEV_TX_BUSY) break; } rcu_read_unlock(); batadv_hardif_put(primary_if); return ret; } /** * batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); } /** * batadv_send_bcast_packet() - send and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Consumes the provided skb. */ void batadv_send_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); consume_skb(skb); } /** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check * * Checks whether a given packet has any (re)transmissions left on the provided * interface. * * hard_iface may be NULL: In that case the number of transmissions this skb had * so far is compared with the maximum amount of retransmissions independent of * any interface instead. * * Return: True if (re)transmissions are left, false otherwise. */ static bool batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet * @forw_packet: the packet to decrease the counter for */ static void batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** * batadv_forw_packet_is_rebroadcast() - check packet for previous transmissions * @forw_packet: the packet to check * * Return: True if this packet was transmitted before, false otherwise. */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; return num_bcasts != forw_packet->if_outgoing->num_bcasts; } /** * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet * @work: work queue item * * Transmits a queued broadcast packet and if necessary reschedules it. */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { unsigned long send_time = jiffies + msecs_to_jiffies(5); struct batadv_forw_packet *forw_packet; struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct sk_buff *skb1; bool dropped = false; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; goto out; } if (batadv_dat_drop_broadcast_packet(bat_priv, forw_packet)) { dropped = true; goto out; } /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (!skb1) goto out; batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); batadv_forw_packet_bcasts_dec(forw_packet); if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; } out: /* do we get something for free()? */ if (batadv_forw_packet_steal(forw_packet, &bat_priv->forw_bcast_list_lock)) batadv_forw_packet_free(forw_packet, dropped); } /** * batadv_purge_outstanding_packets() - stop/purge scheduled bcast/OGMv1 packets * @bat_priv: the bat priv with all the soft interface information * @hard_iface: the hard interface to cancel and purge bcast/ogm packets on * * This method cancels and purges any broadcast and OGMv1 packet on the given * hard_iface. If hard_iface is NULL, broadcast and OGMv1 packets on all hard * interfaces will be canceled and purged. * * This function might sleep. */ void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct hlist_head head = HLIST_HEAD_INIT; if (hard_iface) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s(): %s\n", __func__, hard_iface->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s()\n", __func__); /* claim bcast list for free() */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bcast_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* claim batman packet list for free() */ spin_lock_bh(&bat_priv->forw_bat_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bat_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bat_list_lock); /* then cancel or wait for packet workers to finish and free */ batadv_forw_packet_list_free(&head); } |
| 855 613 855 580 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM 9p #if !defined(_TRACE_9P_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_9P_H #include <linux/tracepoint.h> #define P9_MSG_T \ EM( P9_TLERROR, "P9_TLERROR" ) \ EM( P9_RLERROR, "P9_RLERROR" ) \ EM( P9_TSTATFS, "P9_TSTATFS" ) \ EM( P9_RSTATFS, "P9_RSTATFS" ) \ EM( P9_TLOPEN, "P9_TLOPEN" ) \ EM( P9_RLOPEN, "P9_RLOPEN" ) \ EM( P9_TLCREATE, "P9_TLCREATE" ) \ EM( P9_RLCREATE, "P9_RLCREATE" ) \ EM( P9_TSYMLINK, "P9_TSYMLINK" ) \ EM( P9_RSYMLINK, "P9_RSYMLINK" ) \ EM( P9_TMKNOD, "P9_TMKNOD" ) \ EM( P9_RMKNOD, "P9_RMKNOD" ) \ EM( P9_TRENAME, "P9_TRENAME" ) \ EM( P9_RRENAME, "P9_RRENAME" ) \ EM( P9_TREADLINK, "P9_TREADLINK" ) \ EM( P9_RREADLINK, "P9_RREADLINK" ) \ EM( P9_TGETATTR, "P9_TGETATTR" ) \ EM( P9_RGETATTR, "P9_RGETATTR" ) \ EM( P9_TSETATTR, "P9_TSETATTR" ) \ EM( P9_RSETATTR, "P9_RSETATTR" ) \ EM( P9_TXATTRWALK, "P9_TXATTRWALK" ) \ EM( P9_RXATTRWALK, "P9_RXATTRWALK" ) \ EM( P9_TXATTRCREATE, "P9_TXATTRCREATE" ) \ EM( P9_RXATTRCREATE, "P9_RXATTRCREATE" ) \ EM( P9_TREADDIR, "P9_TREADDIR" ) \ EM( P9_RREADDIR, "P9_RREADDIR" ) \ EM( P9_TFSYNC, "P9_TFSYNC" ) \ EM( P9_RFSYNC, "P9_RFSYNC" ) \ EM( P9_TLOCK, "P9_TLOCK" ) \ EM( P9_RLOCK, "P9_RLOCK" ) \ EM( P9_TGETLOCK, "P9_TGETLOCK" ) \ EM( P9_RGETLOCK, "P9_RGETLOCK" ) \ EM( P9_TLINK, "P9_TLINK" ) \ EM( P9_RLINK, "P9_RLINK" ) \ EM( P9_TMKDIR, "P9_TMKDIR" ) \ EM( P9_RMKDIR, "P9_RMKDIR" ) \ EM( P9_TRENAMEAT, "P9_TRENAMEAT" ) \ EM( P9_RRENAMEAT, "P9_RRENAMEAT" ) \ EM( P9_TUNLINKAT, "P9_TUNLINKAT" ) \ EM( P9_RUNLINKAT, "P9_RUNLINKAT" ) \ EM( P9_TVERSION, "P9_TVERSION" ) \ EM( P9_RVERSION, "P9_RVERSION" ) \ EM( P9_TAUTH, "P9_TAUTH" ) \ EM( P9_RAUTH, "P9_RAUTH" ) \ EM( P9_TATTACH, "P9_TATTACH" ) \ EM( P9_RATTACH, "P9_RATTACH" ) \ EM( P9_TERROR, "P9_TERROR" ) \ EM( P9_RERROR, "P9_RERROR" ) \ EM( P9_TFLUSH, "P9_TFLUSH" ) \ EM( P9_RFLUSH, "P9_RFLUSH" ) \ EM( P9_TWALK, "P9_TWALK" ) \ EM( P9_RWALK, "P9_RWALK" ) \ EM( P9_TOPEN, "P9_TOPEN" ) \ EM( P9_ROPEN, "P9_ROPEN" ) \ EM( P9_TCREATE, "P9_TCREATE" ) \ EM( P9_RCREATE, "P9_RCREATE" ) \ EM( P9_TREAD, "P9_TREAD" ) \ EM( P9_RREAD, "P9_RREAD" ) \ EM( P9_TWRITE, "P9_TWRITE" ) \ EM( P9_RWRITE, "P9_RWRITE" ) \ EM( P9_TCLUNK, "P9_TCLUNK" ) \ EM( P9_RCLUNK, "P9_RCLUNK" ) \ EM( P9_TREMOVE, "P9_TREMOVE" ) \ EM( P9_RREMOVE, "P9_RREMOVE" ) \ EM( P9_TSTAT, "P9_TSTAT" ) \ EM( P9_RSTAT, "P9_RSTAT" ) \ EM( P9_TWSTAT, "P9_TWSTAT" ) \ EMe(P9_RWSTAT, "P9_RWSTAT" ) #define P9_FID_REFTYPE \ EM( P9_FID_REF_CREATE, "create " ) \ EM( P9_FID_REF_GET, "get " ) \ EM( P9_FID_REF_PUT, "put " ) \ EMe(P9_FID_REF_DESTROY, "destroy" ) /* Define EM() to export the enums to userspace via TRACE_DEFINE_ENUM() */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); P9_MSG_T P9_FID_REFTYPE /* And also use EM/EMe to define helper enums -- once */ #ifndef __9P_DECLARE_TRACE_ENUMS_ONLY_ONCE #define __9P_DECLARE_TRACE_ENUMS_ONLY_ONCE #undef EM #undef EMe #define EM(a, b) a, #define EMe(a, b) a enum p9_fid_reftype { P9_FID_REFTYPE } __mode(byte); #endif /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } #define show_9p_op(type) \ __print_symbolic(type, P9_MSG_T) #define show_9p_fid_reftype(type) \ __print_symbolic(type, P9_FID_REFTYPE) TRACE_EVENT(9p_client_req, TP_PROTO(struct p9_client *clnt, int8_t type, int tag), TP_ARGS(clnt, type, tag), TP_STRUCT__entry( __field( void *, clnt ) __field( __u8, type ) __field( __u32, tag ) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = type; __entry->tag = tag; ), TP_printk("client %lu request %s tag %d", (long)__entry->clnt, show_9p_op(__entry->type), __entry->tag) ); TRACE_EVENT(9p_client_res, TP_PROTO(struct p9_client *clnt, int8_t type, int tag, int err), TP_ARGS(clnt, type, tag, err), TP_STRUCT__entry( __field( void *, clnt ) __field( __u8, type ) __field( __u32, tag ) __field( __u32, err ) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = type; __entry->tag = tag; __entry->err = err; ), TP_printk("client %lu response %s tag %d err %d", (long)__entry->clnt, show_9p_op(__entry->type), __entry->tag, __entry->err) ); /* dump 32 bytes of protocol data */ #define P9_PROTO_DUMP_SZ 32 TRACE_EVENT(9p_protocol_dump, TP_PROTO(struct p9_client *clnt, struct p9_fcall *pdu), TP_ARGS(clnt, pdu), TP_STRUCT__entry( __field( void *, clnt ) __field( __u8, type ) __field( __u16, tag ) __dynamic_array(unsigned char, line, min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ)) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = pdu->id; __entry->tag = pdu->tag; memcpy(__get_dynamic_array(line), pdu->sdata, __get_dynamic_array_len(line)); ), TP_printk("clnt %lu %s(tag = %d)\n%*ph\n", (unsigned long)__entry->clnt, show_9p_op(__entry->type), __entry->tag, __get_dynamic_array_len(line), __get_dynamic_array(line)) ); TRACE_EVENT(9p_fid_ref, TP_PROTO(struct p9_fid *fid, __u8 type), TP_ARGS(fid, type), TP_STRUCT__entry( __field( int, fid ) __field( int, refcount ) __field( __u8, type ) ), TP_fast_assign( __entry->fid = fid->fid; __entry->refcount = refcount_read(&fid->count); __entry->type = type; ), TP_printk("%s fid %d, refcount %d", show_9p_fid_reftype(__entry->type), __entry->fid, __entry->refcount) ); #endif /* _TRACE_9P_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 125 94 33 94 33 111 66 68 115 3 57 27 9 27 27 28 90 91 11 9 4 4 2 58 57 2 57 59 28 32 115 28 88 42 57 29 29 29 29 20 20 20 20 4 4 4 41 88 123 7 116 5 114 122 122 59 55 56 57 3 3 3 3 31 81 5 3 12 113 22 10 10 1 3 3 26 130 9 1 121 39 39 25 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2007 Alan Stern * Copyright (C) IBM Corporation, 2009 * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com> * * Thanks to Ingo Molnar for his many suggestions. * * Authors: Alan Stern <stern@rowland.harvard.edu> * K.Prasad <prasad@linux.vnet.ibm.com> * Frederic Weisbecker <fweisbec@gmail.com> */ /* * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, * using the CPU's debug registers. * This file contains the arch-independent routines. */ #include <linux/hw_breakpoint.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/export.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/kdebug.h> #include <linux/kernel.h> #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/percpu-rwsem.h> #include <linux/percpu.h> #include <linux/rhashtable.h> #include <linux/sched.h> #include <linux/slab.h> /* * Datastructure to track the total uses of N slots across tasks or CPUs; * bp_slots_histogram::count[N] is the number of assigned N+1 breakpoint slots. */ struct bp_slots_histogram { #ifdef hw_breakpoint_slots atomic_t count[hw_breakpoint_slots(0)]; #else atomic_t *count; #endif }; /* * Per-CPU constraints data. */ struct bp_cpuinfo { /* Number of pinned CPU breakpoints in a CPU. */ unsigned int cpu_pinned; /* Histogram of pinned task breakpoints in a CPU. */ struct bp_slots_histogram tsk_pinned; }; static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]); static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type) { return per_cpu_ptr(bp_cpuinfo + type, cpu); } /* Number of pinned CPU breakpoints globally. */ static struct bp_slots_histogram cpu_pinned[TYPE_MAX]; /* Number of pinned CPU-independent task breakpoints. */ static struct bp_slots_histogram tsk_pinned_all[TYPE_MAX]; /* Keep track of the breakpoints attached to tasks */ static struct rhltable task_bps_ht; static const struct rhashtable_params task_bps_ht_params = { .head_offset = offsetof(struct hw_perf_event, bp_list), .key_offset = offsetof(struct hw_perf_event, target), .key_len = sizeof_field(struct hw_perf_event, target), .automatic_shrinking = true, }; static bool constraints_initialized __ro_after_init; /* * Synchronizes accesses to the per-CPU constraints; the locking rules are: * * 1. Atomic updates to bp_cpuinfo::tsk_pinned only require a held read-lock * (due to bp_slots_histogram::count being atomic, no update are lost). * * 2. Holding a write-lock is required for computations that require a * stable snapshot of all bp_cpuinfo::tsk_pinned. * * 3. In all other cases, non-atomic accesses require the appropriately held * lock (read-lock for read-only accesses; write-lock for reads/writes). */ DEFINE_STATIC_PERCPU_RWSEM(bp_cpuinfo_sem); /* * Return mutex to serialize accesses to per-task lists in task_bps_ht. Since * rhltable synchronizes concurrent insertions/deletions, independent tasks may * insert/delete concurrently; therefore, a mutex per task is sufficient. * * Uses task_struct::perf_event_mutex, to avoid extending task_struct with a * hw_breakpoint-only mutex, which may be infrequently used. The caveat here is * that hw_breakpoint may contend with per-task perf event list management. The * assumption is that perf usecases involving hw_breakpoints are very unlikely * to result in unnecessary contention. */ static inline struct mutex *get_task_bps_mutex(struct perf_event *bp) { struct task_struct *tsk = bp->hw.target; return tsk ? &tsk->perf_event_mutex : NULL; } static struct mutex *bp_constraints_lock(struct perf_event *bp) { struct mutex *tsk_mtx = get_task_bps_mutex(bp); if (tsk_mtx) { /* * Fully analogous to the perf_try_init_event() nesting * argument in the comment near perf_event_ctx_lock_nested(); * this child->perf_event_mutex cannot ever deadlock against * the parent->perf_event_mutex usage from * perf_event_task_{en,dis}able(). * * Specifically, inherited events will never occur on * ->perf_event_list. */ mutex_lock_nested(tsk_mtx, SINGLE_DEPTH_NESTING); percpu_down_read(&bp_cpuinfo_sem); } else { percpu_down_write(&bp_cpuinfo_sem); } return tsk_mtx; } static void bp_constraints_unlock(struct mutex *tsk_mtx) { if (tsk_mtx) { percpu_up_read(&bp_cpuinfo_sem); mutex_unlock(tsk_mtx); } else { percpu_up_write(&bp_cpuinfo_sem); } } static bool bp_constraints_is_locked(struct perf_event *bp) { struct mutex *tsk_mtx = get_task_bps_mutex(bp); return percpu_is_write_locked(&bp_cpuinfo_sem) || (tsk_mtx ? mutex_is_locked(tsk_mtx) : percpu_is_read_locked(&bp_cpuinfo_sem)); } static inline void assert_bp_constraints_lock_held(struct perf_event *bp) { struct mutex *tsk_mtx = get_task_bps_mutex(bp); if (tsk_mtx) lockdep_assert_held(tsk_mtx); lockdep_assert_held(&bp_cpuinfo_sem); } #ifdef hw_breakpoint_slots /* * Number of breakpoint slots is constant, and the same for all types. */ static_assert(hw_breakpoint_slots(TYPE_INST) == hw_breakpoint_slots(TYPE_DATA)); static inline int hw_breakpoint_slots_cached(int type) { return hw_breakpoint_slots(type); } static inline int init_breakpoint_slots(void) { return 0; } #else /* * Dynamic number of breakpoint slots. */ static int __nr_bp_slots[TYPE_MAX] __ro_after_init; static inline int hw_breakpoint_slots_cached(int type) { return __nr_bp_slots[type]; } static __init bool bp_slots_histogram_alloc(struct bp_slots_histogram *hist, enum bp_type_idx type) { hist->count = kcalloc(hw_breakpoint_slots_cached(type), sizeof(*hist->count), GFP_KERNEL); return hist->count; } static __init void bp_slots_histogram_free(struct bp_slots_histogram *hist) { kfree(hist->count); } static __init int init_breakpoint_slots(void) { int i, cpu, err_cpu; for (i = 0; i < TYPE_MAX; i++) __nr_bp_slots[i] = hw_breakpoint_slots(i); for_each_possible_cpu(cpu) { for (i = 0; i < TYPE_MAX; i++) { struct bp_cpuinfo *info = get_bp_info(cpu, i); if (!bp_slots_histogram_alloc(&info->tsk_pinned, i)) goto err; } } for (i = 0; i < TYPE_MAX; i++) { if (!bp_slots_histogram_alloc(&cpu_pinned[i], i)) goto err; if (!bp_slots_histogram_alloc(&tsk_pinned_all[i], i)) goto err; } return 0; err: for_each_possible_cpu(err_cpu) { for (i = 0; i < TYPE_MAX; i++) bp_slots_histogram_free(&get_bp_info(err_cpu, i)->tsk_pinned); if (err_cpu == cpu) break; } for (i = 0; i < TYPE_MAX; i++) { bp_slots_histogram_free(&cpu_pinned[i]); bp_slots_histogram_free(&tsk_pinned_all[i]); } return -ENOMEM; } #endif static inline void bp_slots_histogram_add(struct bp_slots_histogram *hist, int old, int val) { const int old_idx = old - 1; const int new_idx = old_idx + val; if (old_idx >= 0) WARN_ON(atomic_dec_return_relaxed(&hist->count[old_idx]) < 0); if (new_idx >= 0) WARN_ON(atomic_inc_return_relaxed(&hist->count[new_idx]) < 0); } static int bp_slots_histogram_max(struct bp_slots_histogram *hist, enum bp_type_idx type) { for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) { const int count = atomic_read(&hist->count[i]); /* Catch unexpected writers; we want a stable snapshot. */ ASSERT_EXCLUSIVE_WRITER(hist->count[i]); if (count > 0) return i + 1; WARN(count < 0, "inconsistent breakpoint slots histogram"); } return 0; } static int bp_slots_histogram_max_merge(struct bp_slots_histogram *hist1, struct bp_slots_histogram *hist2, enum bp_type_idx type) { for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) { const int count1 = atomic_read(&hist1->count[i]); const int count2 = atomic_read(&hist2->count[i]); /* Catch unexpected writers; we want a stable snapshot. */ ASSERT_EXCLUSIVE_WRITER(hist1->count[i]); ASSERT_EXCLUSIVE_WRITER(hist2->count[i]); if (count1 + count2 > 0) return i + 1; WARN(count1 < 0, "inconsistent breakpoint slots histogram"); WARN(count2 < 0, "inconsistent breakpoint slots histogram"); } return 0; } #ifndef hw_breakpoint_weight static inline int hw_breakpoint_weight(struct perf_event *bp) { return 1; } #endif static inline enum bp_type_idx find_slot_idx(u64 bp_type) { if (bp_type & HW_BREAKPOINT_RW) return TYPE_DATA; return TYPE_INST; } /* * Return the maximum number of pinned breakpoints a task has in this CPU. */ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type) { struct bp_slots_histogram *tsk_pinned = &get_bp_info(cpu, type)->tsk_pinned; /* * At this point we want to have acquired the bp_cpuinfo_sem as a * writer to ensure that there are no concurrent writers in * toggle_bp_task_slot() to tsk_pinned, and we get a stable snapshot. */ lockdep_assert_held_write(&bp_cpuinfo_sem); return bp_slots_histogram_max_merge(tsk_pinned, &tsk_pinned_all[type], type); } /* * Count the number of breakpoints of the same type and same task. * The given event must be not on the list. * * If @cpu is -1, but the result of task_bp_pinned() is not CPU-independent, * returns a negative value. */ static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type) { struct rhlist_head *head, *pos; struct perf_event *iter; int count = 0; /* * We need a stable snapshot of the per-task breakpoint list. */ assert_bp_constraints_lock_held(bp); rcu_read_lock(); head = rhltable_lookup(&task_bps_ht, &bp->hw.target, task_bps_ht_params); if (!head) goto out; rhl_for_each_entry_rcu(iter, pos, head, hw.bp_list) { if (find_slot_idx(iter->attr.bp_type) != type) continue; if (iter->cpu >= 0) { if (cpu == -1) { count = -1; goto out; } else if (cpu != iter->cpu) continue; } count += hw_breakpoint_weight(iter); } out: rcu_read_unlock(); return count; } static const struct cpumask *cpumask_of_bp(struct perf_event *bp) { if (bp->cpu >= 0) return cpumask_of(bp->cpu); return cpu_possible_mask; } /* * Returns the max pinned breakpoint slots in a given * CPU (cpu > -1) or across all of them (cpu = -1). */ static int max_bp_pinned_slots(struct perf_event *bp, enum bp_type_idx type) { const struct cpumask *cpumask = cpumask_of_bp(bp); int pinned_slots = 0; int cpu; if (bp->hw.target && bp->cpu < 0) { int max_pinned = task_bp_pinned(-1, bp, type); if (max_pinned >= 0) { /* * Fast path: task_bp_pinned() is CPU-independent and * returns the same value for any CPU. */ max_pinned += bp_slots_histogram_max(&cpu_pinned[type], type); return max_pinned; } } for_each_cpu(cpu, cpumask) { struct bp_cpuinfo *info = get_bp_info(cpu, type); int nr; nr = info->cpu_pinned; if (!bp->hw.target) nr += max_task_bp_pinned(cpu, type); else nr += task_bp_pinned(cpu, bp, type); pinned_slots = max(nr, pinned_slots); } return pinned_slots; } /* * Add/remove the given breakpoint in our constraint table */ static int toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, int weight) { int cpu, next_tsk_pinned; if (!enable) weight = -weight; if (!bp->hw.target) { /* * Update the pinned CPU slots, in per-CPU bp_cpuinfo and in the * global histogram. */ struct bp_cpuinfo *info = get_bp_info(bp->cpu, type); lockdep_assert_held_write(&bp_cpuinfo_sem); bp_slots_histogram_add(&cpu_pinned[type], info->cpu_pinned, weight); info->cpu_pinned += weight; return 0; } /* * If bp->hw.target, tsk_pinned is only modified, but not used * otherwise. We can permit concurrent updates as long as there are no * other uses: having acquired bp_cpuinfo_sem as a reader allows * concurrent updates here. Uses of tsk_pinned will require acquiring * bp_cpuinfo_sem as a writer to stabilize tsk_pinned's value. */ lockdep_assert_held_read(&bp_cpuinfo_sem); /* * Update the pinned task slots, in per-CPU bp_cpuinfo and in the global * histogram. We need to take care of 4 cases: * * 1. This breakpoint targets all CPUs (cpu < 0), and there may only * exist other task breakpoints targeting all CPUs. In this case we * can simply update the global slots histogram. * * 2. This breakpoint targets a specific CPU (cpu >= 0), but there may * only exist other task breakpoints targeting all CPUs. * * a. On enable: remove the existing breakpoints from the global * slots histogram and use the per-CPU histogram. * * b. On disable: re-insert the existing breakpoints into the global * slots histogram and remove from per-CPU histogram. * * 3. Some other existing task breakpoints target specific CPUs. Only * update the per-CPU slots histogram. */ if (!enable) { /* * Remove before updating histograms so we can determine if this * was the last task breakpoint for a specific CPU. */ int ret = rhltable_remove(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params); if (ret) return ret; } /* * Note: If !enable, next_tsk_pinned will not count the to-be-removed breakpoint. */ next_tsk_pinned = task_bp_pinned(-1, bp, type); if (next_tsk_pinned >= 0) { if (bp->cpu < 0) { /* Case 1: fast path */ if (!enable) next_tsk_pinned += hw_breakpoint_weight(bp); bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned, weight); } else if (enable) { /* Case 2.a: slow path */ /* Add existing to per-CPU histograms. */ for_each_possible_cpu(cpu) { bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned, 0, next_tsk_pinned); } /* Add this first CPU-pinned task breakpoint. */ bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned, next_tsk_pinned, weight); /* Rebalance global task pinned histogram. */ bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned, -next_tsk_pinned); } else { /* Case 2.b: slow path */ /* Remove this last CPU-pinned task breakpoint. */ bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned, next_tsk_pinned + hw_breakpoint_weight(bp), weight); /* Remove all from per-CPU histograms. */ for_each_possible_cpu(cpu) { bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned, next_tsk_pinned, -next_tsk_pinned); } /* Rebalance global task pinned histogram. */ bp_slots_histogram_add(&tsk_pinned_all[type], 0, next_tsk_pinned); } } else { /* Case 3: slow path */ const struct cpumask *cpumask = cpumask_of_bp(bp); for_each_cpu(cpu, cpumask) { next_tsk_pinned = task_bp_pinned(cpu, bp, type); if (!enable) next_tsk_pinned += hw_breakpoint_weight(bp); bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned, next_tsk_pinned, weight); } } /* * Readers want a stable snapshot of the per-task breakpoint list. */ assert_bp_constraints_lock_held(bp); if (enable) return rhltable_insert(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params); return 0; } /* * Constraints to check before allowing this new breakpoint counter. * * Note: Flexible breakpoints are currently unimplemented, but outlined in the * below algorithm for completeness. The implementation treats flexible as * pinned due to no guarantee that we currently always schedule flexible events * before a pinned event in a same CPU. * * == Non-pinned counter == (Considered as pinned for now) * * - If attached to a single cpu, check: * * (per_cpu(info->flexible, cpu) || (per_cpu(info->cpu_pinned, cpu) * + max(per_cpu(info->tsk_pinned, cpu)))) < HBP_NUM * * -> If there are already non-pinned counters in this cpu, it means * there is already a free slot for them. * Otherwise, we check that the maximum number of per task * breakpoints (for this cpu) plus the number of per cpu breakpoint * (for this cpu) doesn't cover every registers. * * - If attached to every cpus, check: * * (per_cpu(info->flexible, *) || (max(per_cpu(info->cpu_pinned, *)) * + max(per_cpu(info->tsk_pinned, *)))) < HBP_NUM * * -> This is roughly the same, except we check the number of per cpu * bp for every cpu and we keep the max one. Same for the per tasks * breakpoints. * * * == Pinned counter == * * - If attached to a single cpu, check: * * ((per_cpu(info->flexible, cpu) > 1) + per_cpu(info->cpu_pinned, cpu) * + max(per_cpu(info->tsk_pinned, cpu))) < HBP_NUM * * -> Same checks as before. But now the info->flexible, if any, must keep * one register at least (or they will never be fed). * * - If attached to every cpus, check: * * ((per_cpu(info->flexible, *) > 1) + max(per_cpu(info->cpu_pinned, *)) * + max(per_cpu(info->tsk_pinned, *))) < HBP_NUM */ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type) { enum bp_type_idx type; int max_pinned_slots; int weight; /* We couldn't initialize breakpoint constraints on boot */ if (!constraints_initialized) return -ENOMEM; /* Basic checks */ if (bp_type == HW_BREAKPOINT_EMPTY || bp_type == HW_BREAKPOINT_INVALID) return -EINVAL; type = find_slot_idx(bp_type); weight = hw_breakpoint_weight(bp); /* Check if this new breakpoint can be satisfied across all CPUs. */ max_pinned_slots = max_bp_pinned_slots(bp, type) + weight; if (max_pinned_slots > hw_breakpoint_slots_cached(type)) return -ENOSPC; return toggle_bp_slot(bp, true, type, weight); } int reserve_bp_slot(struct perf_event *bp) { struct mutex *mtx = bp_constraints_lock(bp); int ret = __reserve_bp_slot(bp, bp->attr.bp_type); bp_constraints_unlock(mtx); return ret; } static void __release_bp_slot(struct perf_event *bp, u64 bp_type) { enum bp_type_idx type; int weight; type = find_slot_idx(bp_type); weight = hw_breakpoint_weight(bp); WARN_ON(toggle_bp_slot(bp, false, type, weight)); } void release_bp_slot(struct perf_event *bp) { struct mutex *mtx = bp_constraints_lock(bp); __release_bp_slot(bp, bp->attr.bp_type); bp_constraints_unlock(mtx); } static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int err; __release_bp_slot(bp, old_type); err = __reserve_bp_slot(bp, new_type); if (err) { /* * Reserve the old_type slot back in case * there's no space for the new type. * * This must succeed, because we just released * the old_type slot in the __release_bp_slot * call above. If not, something is broken. */ WARN_ON(__reserve_bp_slot(bp, old_type)); } return err; } static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { struct mutex *mtx = bp_constraints_lock(bp); int ret = __modify_bp_slot(bp, old_type, new_type); bp_constraints_unlock(mtx); return ret; } /* * Allow the kernel debugger to reserve breakpoint slots without * taking a lock using the dbg_* variant of for the reserve and * release breakpoint slots. */ int dbg_reserve_bp_slot(struct perf_event *bp) { int ret; if (bp_constraints_is_locked(bp)) return -1; /* Locks aren't held; disable lockdep assert checking. */ lockdep_off(); ret = __reserve_bp_slot(bp, bp->attr.bp_type); lockdep_on(); return ret; } int dbg_release_bp_slot(struct perf_event *bp) { if (bp_constraints_is_locked(bp)) return -1; /* Locks aren't held; disable lockdep assert checking. */ lockdep_off(); __release_bp_slot(bp, bp->attr.bp_type); lockdep_on(); return 0; } static int hw_breakpoint_parse(struct perf_event *bp, const struct perf_event_attr *attr, struct arch_hw_breakpoint *hw) { int err; err = hw_breakpoint_arch_parse(bp, attr, hw); if (err) return err; if (arch_check_bp_in_kernelspace(hw)) { if (attr->exclude_kernel) return -EINVAL; /* * Don't let unprivileged users set a breakpoint in the trap * path to avoid trap recursion attacks. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; } return 0; } int register_perf_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint hw = { }; int err; err = reserve_bp_slot(bp); if (err) return err; err = hw_breakpoint_parse(bp, &bp->attr, &hw); if (err) { release_bp_slot(bp); return err; } bp->hw.info = hw; return 0; } /** * register_user_hw_breakpoint - register a hardware breakpoint for user space * @attr: breakpoint attributes * @triggered: callback to trigger when we hit the breakpoint * @context: context data could be used in the triggered callback * @tsk: pointer to 'task_struct' of the process to which the address belongs */ struct perf_event * register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, void *context, struct task_struct *tsk) { return perf_event_create_kernel_counter(attr, -1, tsk, triggered, context); } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); static void hw_breakpoint_copy_attr(struct perf_event_attr *to, struct perf_event_attr *from) { to->bp_addr = from->bp_addr; to->bp_type = from->bp_type; to->bp_len = from->bp_len; to->disabled = from->disabled; } int modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, bool check) { struct arch_hw_breakpoint hw = { }; int err; err = hw_breakpoint_parse(bp, attr, &hw); if (err) return err; if (check) { struct perf_event_attr old_attr; old_attr = bp->attr; hw_breakpoint_copy_attr(&old_attr, attr); if (memcmp(&old_attr, attr, sizeof(*attr))) return -EINVAL; } if (bp->attr.bp_type != attr->bp_type) { err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type); if (err) return err; } hw_breakpoint_copy_attr(&bp->attr, attr); bp->hw.info = hw; return 0; } /** * modify_user_hw_breakpoint - modify a user-space hardware breakpoint * @bp: the breakpoint structure to modify * @attr: new breakpoint attributes */ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { int err; /* * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it * will not be possible to raise IPIs that invoke __perf_event_disable. * So call the function directly after making sure we are targeting the * current task. */ if (irqs_disabled() && bp->ctx && bp->ctx->task == current) perf_event_disable_local(bp); else perf_event_disable(bp); err = modify_user_hw_breakpoint_check(bp, attr, false); if (!bp->attr.disabled) perf_event_enable(bp); return err; } EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); /** * unregister_hw_breakpoint - unregister a user-space hardware breakpoint * @bp: the breakpoint structure to unregister */ void unregister_hw_breakpoint(struct perf_event *bp) { if (!bp) return; perf_event_release_kernel(bp); } EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); /** * register_wide_hw_breakpoint - register a wide breakpoint in the kernel * @attr: breakpoint attributes * @triggered: callback to trigger when we hit the breakpoint * @context: context data could be used in the triggered callback * * @return a set of per_cpu pointers to perf events */ struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, void *context) { struct perf_event * __percpu *cpu_events, *bp; long err = 0; int cpu; cpu_events = alloc_percpu(typeof(*cpu_events)); if (!cpu_events) return ERR_PTR_PCPU(-ENOMEM); cpus_read_lock(); for_each_online_cpu(cpu) { bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered, context); if (IS_ERR(bp)) { err = PTR_ERR(bp); break; } per_cpu(*cpu_events, cpu) = bp; } cpus_read_unlock(); if (likely(!err)) return cpu_events; unregister_wide_hw_breakpoint(cpu_events); return ERR_PTR_PCPU(err); } EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); /** * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel * @cpu_events: the per cpu set of events to unregister */ void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { int cpu; for_each_possible_cpu(cpu) unregister_hw_breakpoint(per_cpu(*cpu_events, cpu)); free_percpu(cpu_events); } EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint); /** * hw_breakpoint_is_used - check if breakpoints are currently used * * Returns: true if breakpoints are used, false otherwise. */ bool hw_breakpoint_is_used(void) { int cpu; if (!constraints_initialized) return false; for_each_possible_cpu(cpu) { for (int type = 0; type < TYPE_MAX; ++type) { struct bp_cpuinfo *info = get_bp_info(cpu, type); if (info->cpu_pinned) return true; for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) { if (atomic_read(&info->tsk_pinned.count[slot])) return true; } } } for (int type = 0; type < TYPE_MAX; ++type) { for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) { /* * Warn, because if there are CPU pinned counters, * should never get here; bp_cpuinfo::cpu_pinned should * be consistent with the global cpu_pinned histogram. */ if (WARN_ON(atomic_read(&cpu_pinned[type].count[slot]))) return true; if (atomic_read(&tsk_pinned_all[type].count[slot])) return true; } } return false; } static struct notifier_block hw_breakpoint_exceptions_nb = { .notifier_call = hw_breakpoint_exceptions_notify, /* we need to be notified first */ .priority = 0x7fffffff }; static void bp_perf_event_destroy(struct perf_event *event) { release_bp_slot(event); } static int hw_breakpoint_event_init(struct perf_event *bp) { int err; if (bp->attr.type != PERF_TYPE_BREAKPOINT) return -ENOENT; /* * no branch sampling for breakpoint events */ if (has_branch_stack(bp)) return -EOPNOTSUPP; err = register_perf_hw_breakpoint(bp); if (err) return err; bp->destroy = bp_perf_event_destroy; return 0; } static int hw_breakpoint_add(struct perf_event *bp, int flags) { if (!(flags & PERF_EF_START)) bp->hw.state = PERF_HES_STOPPED; if (is_sampling_event(bp)) { bp->hw.last_period = bp->hw.sample_period; perf_swevent_set_period(bp); } return arch_install_hw_breakpoint(bp); } static void hw_breakpoint_del(struct perf_event *bp, int flags) { arch_uninstall_hw_breakpoint(bp); } static void hw_breakpoint_start(struct perf_event *bp, int flags) { bp->hw.state = 0; } static void hw_breakpoint_stop(struct perf_event *bp, int flags) { bp->hw.state = PERF_HES_STOPPED; } static struct pmu perf_breakpoint = { .task_ctx_nr = perf_sw_context, /* could eventually get its own */ .event_init = hw_breakpoint_event_init, .add = hw_breakpoint_add, .del = hw_breakpoint_del, .start = hw_breakpoint_start, .stop = hw_breakpoint_stop, .read = hw_breakpoint_pmu_read, }; int __init init_hw_breakpoint(void) { int ret; ret = rhltable_init(&task_bps_ht, &task_bps_ht_params); if (ret) return ret; ret = init_breakpoint_slots(); if (ret) return ret; constraints_initialized = true; perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT); return register_die_notifier(&hw_breakpoint_exceptions_nb); } |
| 43122 8581 34201 41428 30 56 3 5650 1255 205 4326 2907 58 114 6885 114 504 2010 2011 141 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the pageflags directly. Use the PageFoo macros. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_writeback, /* Page is under writeback */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_head, /* Must be in bit 6 */ PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ PG_dropbehind, /* drop pages on IO completion */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, /* Anonymous memory (and shmem) */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Some filesystems */ PG_checked = PG_owner_priv_1, /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped * THP), PG_anon_exclusive may be set only for the head page or for * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ PG_anon_exclusive = PG_owner_2, /* * Set if all buffer heads in the folio are mapped. * Filesystems which do not use BHs can use it for their own purpose. */ PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, #ifdef CONFIG_MEMORY_HOTPLUG /* For self-hosted memmap pages */ PG_vmemmap_self_hosted = PG_owner_priv_1, #endif /* * Flags only valid for compound pages. Stored in first tail page's * flags word. Cannot use the first 8 flags or any flag marked as * PF_ANY. */ /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) #ifndef __GENERATING_BOUNDS_H #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); /* * Return the real head page struct iff the @page is a fake head page, otherwise * return the @page itself. See Documentation/mm/vmemmap_dedup.rst. */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) return page; /* * Only addresses aligned with PAGE_SIZE of struct page may be fake head * struct page. The alignment check aims to avoid access the fields ( * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) * cold cacheline in some cases. */ if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && test_bit(PG_head, &page->flags)) { /* * We can safely access the field of the @page[1] with PG_head * because the @page is a compound page composed with at least * two contiguous pages. */ unsigned long head = READ_ONCE(page[1].compound_head); if (likely(head & 1)) return (const struct page *)(head - 1); } return page; } #else static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } #endif static __always_inline int page_is_fake_head(const struct page *page) { return page_fixed_fake_head(page) != page; } static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) /** * page_folio - Converts from page to folio. * @p: The page. * * Every page is part of a folio. This function cannot be called on a * NULL pointer. * * Context: No reference, nor lock is required on @page. If the caller * does not hold a reference, this call may race with a folio split, so * it should re-check the folio still contains this page after gaining * a reference on the folio. * Return: The folio which contains this page. */ #define page_folio(p) (_Generic((p), \ const struct page *: (const struct folio *)_compound_head(p), \ struct page *: (struct folio *)_compound_head(p))) /** * folio_page - Return a page from a folio. * @folio: The folio. * @n: The page number to return. * * @n is relative to the start of the folio. This function does not * check that the page number lies within @folio; the caller is presumed * to have a reference to the page. */ #define folio_page(folio, n) nth_page(&(folio)->page, n) static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags) || READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif static const unsigned long *const_folio_flags(const struct folio *folio, unsigned n) { const struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* Which page is the flag stored in */ #define FOLIO_PF_ANY 0 #define FOLIO_PF_HEAD 0 #define FOLIO_PF_NO_TAIL 0 #define FOLIO_PF_NO_COMPOUND 0 #define FOLIO_PF_SECOND 1 #define FOLIO_HEAD_PAGE 0 #define FOLIO_SECOND_PAGE 1 /* * Macros to create function definitions for page flags */ #define FOLIO_TEST_FLAG(name, page) \ static __always_inline bool folio_test_##name(const struct folio *folio) \ { return test_bit(PG_##name, const_folio_flags(folio, page)); } #define FOLIO_SET_FLAG(name, page) \ static __always_inline void folio_set_##name(struct folio *folio) \ { set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void folio_clear_##name(struct folio *folio) \ { clear_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_SET_FLAG(name, page) \ static __always_inline void __folio_set_##name(struct folio *folio) \ { __set_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void __folio_clear_##name(struct folio *folio) \ { __clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_SET_FLAG(name, page) \ static __always_inline bool folio_test_set_##name(struct folio *folio) \ { return test_and_set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_CLEAR_FLAG(name, page) \ static __always_inline bool folio_test_clear_##name(struct folio *folio) \ { return test_and_clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_FLAG(name, page) \ FOLIO_TEST_FLAG(name, page) \ FOLIO_SET_FLAG(name, page) \ FOLIO_CLEAR_FLAG(name, page) #define TESTPAGEFLAG(uname, lname, policy) \ FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ static __always_inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ __FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ __FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define FOLIO_TEST_FLAG_FALSE(name) \ static inline bool folio_test_##name(const struct folio *folio) \ { return false; } #define FOLIO_SET_FLAG_NOOP(name) \ static inline void folio_set_##name(struct folio *folio) { } #define FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void folio_clear_##name(struct folio *folio) { } #define __FOLIO_SET_FLAG_NOOP(name) \ static inline void __folio_set_##name(struct folio *folio) { } #define __FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void __folio_clear_##name(struct folio *folio) { } #define FOLIO_TEST_SET_FLAG_FALSE(name) \ static inline bool folio_test_set_##name(struct folio *folio) \ { return false; } #define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ static inline bool folio_test_clear_##name(struct folio *folio) \ { return false; } #define FOLIO_FLAG_FALSE(name) \ FOLIO_TEST_FLAG_FALSE(name) \ FOLIO_SET_FLAG_NOOP(name) \ FOLIO_CLEAR_FLAG_NOOP(name) #define TESTPAGEFLAG_FALSE(uname, lname) \ FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ __FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) #define TESTSCFLAG_FALSE(uname, lname) \ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) FOLIO_FLAG(active, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f)) #else PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { return folio_test_swapbacked(folio) && test_bit(PG_swapcache, const_folio_flags(folio, 0)); } FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(swapcache) #endif FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(mlocked) __FOLIO_CLEAR_FLAG_NOOP(mlocked) FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif #ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif /* See page_idle.h for !64BIT workaround */ #else /* !CONFIG_PAGE_IDLE_FLAG */ FOLIO_FLAG_FALSE(young) FOLIO_TEST_CLEAR_FLAG_FALSE(young) FOLIO_FLAG_FALSE(idle) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #ifdef CONFIG_MEMORY_HOTPLUG PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) #else PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* * On an anonymous folio mapped into a user virtual memory area, * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then folio->mapping points to a struct movable_operations. * * Please note that, confusingly, "folio_mapping" refers to the inode * address_space which maps the folio from disk; whereas "folio_mapped" * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its * internal states, the folio->mapping does not exist as such, nor do * these flags below. So in order to avoid testing non-existent bits, * please make sure that folio_test_slab(folio) actually evaluates to * false before calling the following functions (e.g., folio_test_anon). * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) /* * Different with flags above, this flag is used only for fsdax mode. It * indicates that this page->mapping is now under reflink case. */ #define PAGE_MAPPING_DAX_SHARED ((void *)0x1) static __always_inline bool folio_mapping_flags(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline bool PageAnonNotKsm(const struct page *page) { unsigned long flags = (unsigned long)page_folio(page)->mapping; return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON; } static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } static __always_inline bool __folio_test_movable(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline bool folio_test_ksm(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } #else FOLIO_TEST_FLAG_FALSE(ksm) #endif u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. * @folio: The folio. * @mask: Bits set in this word will be changed. * * This must only be used for flags which are changed with the folio * lock held. For example, it is unsafe to use for PG_dirty as that * can be set without the folio lock held. It can also only be used * on flags which are in the range 0-6 as some of the implementations * only affect those bits. * * Return: Whether there are tasks waiting on the folio. */ static inline bool folio_xor_flags_has_waiters(struct folio *folio, unsigned long mask) { return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0)); } /** * folio_test_uptodate - Is this folio up to date? * @folio: The folio. * * The uptodate flag is set on a folio when every byte in the folio is * at least as new as the corresponding bytes on storage. Anonymous * and CoW folios are always uptodate. If the folio is not uptodate, * some of the bytes in it may be; see the is_partially_uptodate() * address_space operation. */ static inline bool folio_test_uptodate(const struct folio *folio) { bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0)); /* * Must ensure that the data we read out of the folio is loaded * _after_ we've loaded folio->flags to check the uptodate bit. * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } static __always_inline void __folio_mark_uptodate(struct folio *folio) { smp_wmb(); __set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void folio_mark_uptodate(struct folio *folio) { /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the folio * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void __SetPageUptodate(struct page *page) { __folio_mark_uptodate((struct folio *)page); } static __always_inline void SetPageUptodate(struct page *page) { folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) void __folio_start_writeback(struct folio *folio, bool keep_write); void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) static __always_inline bool folio_test_head(const struct folio *folio) { return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY)); } static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); } __SETPAGEFLAG(Head, head, PF_ANY) __CLEARPAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. * * Return: True if the folio is larger than one page. */ static inline bool folio_test_large(const struct folio *folio) { return folio_test_head(folio); } static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(const struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) /* * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the * compound page. * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(has_hwpoisoned) #endif /* * For pages that do not use mapcount, page_type may be used. * The low 24 bits of pagetype may be used for your own purposes, as long * as you are careful to not affect the top 8 bits. The low bits of * pagetype will be overwritten when you clear the page_type from the page. */ enum pagetype { /* 0x00-0x7f are positive numbers, ie mapcount */ /* Reserve 0x80-0xef for mapcount overflow. */ PGTY_buddy = 0xf0, PGTY_offline = 0xf1, PGTY_table = 0xf2, PGTY_guard = 0xf3, PGTY_hugetlb = 0xf4, PGTY_slab = 0xf5, PGTY_zsmalloc = 0xf6, PGTY_unaccepted = 0xf7, PGTY_mapcount_underflow = 0xff }; static inline bool page_type_has_type(int page_type) { return page_type < (PGTY_mapcount_underflow << 24); } /* This takes a mapcount which is one more than page->_mapcount */ static inline bool page_mapcount_is_type(unsigned int mapcount) { return page_type_has_type(mapcount - 1); } static inline bool page_has_type(const struct page *page) { return page_mapcount_is_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ if (folio_test_##fname(folio)) \ return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ if (folio->page.page_type == UINT_MAX) \ return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ if (Page##uname(page)) \ return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ if (page->page_type == UINT_MAX) \ return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * When a memory block gets onlined, all pages are initialized with a * refcount of 1 and PageOffline(). generic_online_page() will * take care of clearing PageOffline(). * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free (unmanaged) * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require not giving them to the buddy via generic_online_page(). * * Memory offlining code will not adjust the managed page count for any * PageOffline() pages, treating them like they were never exposed to the * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random * pages should check PageOffline() and synchronize with such drivers using * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline, offline) extern void page_offline_freeze(void); extern void page_offline_thaw(void); extern void page_offline_begin(void); extern void page_offline_end(void); /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table, pgtable) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard, guard) FOLIO_TYPE_OPS(slab, slab) /** * PageSlab - Determine if the page belongs to the slab allocator * @page: The page to test. * * Context: Any context. * Return: True for slab pages, false for any other kind of page. */ static inline bool PageSlab(const struct page *page) { return folio_test_slab(page_folio(page)); } #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) /* * Mark pages that has to be accepted before touched for the first time. * * Serialized with zone lock. */ PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. * * Context: Any context. * Return: True for hugetlbfs pages, false for anon pages or pages * belonging to other filesystems. */ static inline bool PageHuge(const struct page *page) { return folio_test_hugetlb(page_folio(page)); } /* * Check if a page is currently marked HWPoisoned. Note that this check is * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ static inline bool is_page_hwpoison(const struct page *page) { const struct folio *folio; if (PageHWPoison(page)) return true; folio = page_folio(page); return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); /* * HugeTLB stores this information on the head page; THP keeps it per * page */ if (PageHuge(page)) page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void SetPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void __ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) /* * Flags stored in the second page of a compound page. They may overlap * the CHECK_AT_FREE flags above, so need to be cleared. */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * folio_has_private - Determine if folio has private stuff * @folio: The folio to be checked * * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ static inline int folio_has_private(const struct folio *folio) { return !!(folio->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 25 23 23 23 2 2 2 2 1601 145 3279 2 48 48 49 48 48 30 47 48 48 3 48 48 49 49 49 49 49 49 49 45 49 49 49 3281 1724 3279 1722 1723 3279 3279 1228 1227 1226 433 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memcontrol.h> #include <linux/rwsem.h> #include <linux/shrinker.h> #include <linux/rculist.h> #include <trace/events/vmscan.h> #include "internal.h" LIST_HEAD(shrinker_list); DEFINE_MUTEX(shrinker_mutex); #ifdef CONFIG_MEMCG static int shrinker_nr_max; static inline int shrinker_unit_size(int nr_items) { return (DIV_ROUND_UP(nr_items, SHRINKER_UNIT_BITS) * sizeof(struct shrinker_info_unit *)); } static inline void shrinker_unit_free(struct shrinker_info *info, int start) { struct shrinker_info_unit **unit; int nr, i; if (!info) return; unit = info->unit; nr = DIV_ROUND_UP(info->map_nr_max, SHRINKER_UNIT_BITS); for (i = start; i < nr; i++) { if (!unit[i]) break; kfree(unit[i]); unit[i] = NULL; } } static inline int shrinker_unit_alloc(struct shrinker_info *new, struct shrinker_info *old, int nid) { struct shrinker_info_unit *unit; int nr = DIV_ROUND_UP(new->map_nr_max, SHRINKER_UNIT_BITS); int start = old ? DIV_ROUND_UP(old->map_nr_max, SHRINKER_UNIT_BITS) : 0; int i; for (i = start; i < nr; i++) { unit = kzalloc_node(sizeof(*unit), GFP_KERNEL, nid); if (!unit) { shrinker_unit_free(new, start); return -ENOMEM; } new->unit[i] = unit; } return 0; } void free_shrinker_info(struct mem_cgroup *memcg) { struct mem_cgroup_per_node *pn; struct shrinker_info *info; int nid; for_each_node(nid) { pn = memcg->nodeinfo[nid]; info = rcu_dereference_protected(pn->shrinker_info, true); shrinker_unit_free(info, 0); kvfree(info); rcu_assign_pointer(pn->shrinker_info, NULL); } } int alloc_shrinker_info(struct mem_cgroup *memcg) { int nid, ret = 0; int array_size = 0; mutex_lock(&shrinker_mutex); array_size = shrinker_unit_size(shrinker_nr_max); for_each_node(nid) { struct shrinker_info *info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); if (!info) goto err; info->map_nr_max = shrinker_nr_max; if (shrinker_unit_alloc(info, NULL, nid)) { kvfree(info); goto err; } rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } mutex_unlock(&shrinker_mutex); return ret; err: mutex_unlock(&shrinker_mutex); free_shrinker_info(memcg); return -ENOMEM; } static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, lockdep_is_held(&shrinker_mutex)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, int old_size, int new_nr_max) { struct shrinker_info *new, *old; struct mem_cgroup_per_node *pn; int nid; for_each_node(nid) { pn = memcg->nodeinfo[nid]; old = shrinker_info_protected(memcg, nid); /* Not yet online memcg */ if (!old) return 0; /* Already expanded this shrinker_info */ if (new_nr_max <= old->map_nr_max) continue; new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); if (!new) return -ENOMEM; new->map_nr_max = new_nr_max; memcpy(new->unit, old->unit, old_size); if (shrinker_unit_alloc(new, old, nid)) { kvfree(new); return -ENOMEM; } rcu_assign_pointer(pn->shrinker_info, new); kvfree_rcu(old, rcu); } return 0; } static int expand_shrinker_info(int new_id) { int ret = 0; int new_nr_max = round_up(new_id + 1, SHRINKER_UNIT_BITS); int new_size, old_size = 0; struct mem_cgroup *memcg; if (!root_mem_cgroup) goto out; lockdep_assert_held(&shrinker_mutex); new_size = shrinker_unit_size(new_nr_max); old_size = shrinker_unit_size(shrinker_nr_max); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { ret = expand_one_shrinker_info(memcg, new_size, old_size, new_nr_max); if (ret) { mem_cgroup_iter_break(NULL, memcg); goto out; } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); out: if (!ret) shrinker_nr_max = new_nr_max; return ret; } static inline int shrinker_id_to_index(int shrinker_id) { return shrinker_id / SHRINKER_UNIT_BITS; } static inline int shrinker_id_to_offset(int shrinker_id) { return shrinker_id % SHRINKER_UNIT_BITS; } static inline int calc_shrinker_id(int index, int offset) { return index * SHRINKER_UNIT_BITS + offset; } void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; struct shrinker_info_unit *unit; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); unit = info->unit[shrinker_id_to_index(shrinker_id)]; if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id_to_offset(shrinker_id), unit->map); } rcu_read_unlock(); } } static DEFINE_IDR(shrinker_idr); static int shrinker_memcg_alloc(struct shrinker *shrinker) { int id, ret = -ENOMEM; if (mem_cgroup_disabled()) return -ENOSYS; mutex_lock(&shrinker_mutex); id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { if (expand_shrinker_info(id)) { idr_remove(&shrinker_idr, id); goto unlock; } } shrinker->id = id; ret = 0; unlock: mutex_unlock(&shrinker_mutex); return ret; } static void shrinker_memcg_remove(struct shrinker *shrinker) { int id = shrinker->id; BUG_ON(id < 0); lockdep_assert_held(&shrinker_mutex); idr_remove(&shrinker_idr, id); } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { struct shrinker_info *info; struct shrinker_info_unit *unit; long nr_deferred; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); unit = info->unit[shrinker_id_to_index(shrinker->id)]; nr_deferred = atomic_long_xchg(&unit->nr_deferred[shrinker_id_to_offset(shrinker->id)], 0); rcu_read_unlock(); return nr_deferred; } static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { struct shrinker_info *info; struct shrinker_info_unit *unit; long nr_deferred; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); unit = info->unit[shrinker_id_to_index(shrinker->id)]; nr_deferred = atomic_long_add_return(nr, &unit->nr_deferred[shrinker_id_to_offset(shrinker->id)]); rcu_read_unlock(); return nr_deferred; } void reparent_shrinker_deferred(struct mem_cgroup *memcg) { int nid, index, offset; long nr; struct mem_cgroup *parent; struct shrinker_info *child_info, *parent_info; struct shrinker_info_unit *child_unit, *parent_unit; parent = parent_mem_cgroup(memcg); if (!parent) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ mutex_lock(&shrinker_mutex); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); for (index = 0; index < shrinker_id_to_index(child_info->map_nr_max); index++) { child_unit = child_info->unit[index]; parent_unit = parent_info->unit[index]; for (offset = 0; offset < SHRINKER_UNIT_BITS; offset++) { nr = atomic_long_read(&child_unit->nr_deferred[offset]); atomic_long_add(nr, &parent_unit->nr_deferred[offset]); } } } mutex_unlock(&shrinker_mutex); } #else static int shrinker_memcg_alloc(struct shrinker *shrinker) { return -ENOSYS; } static void shrinker_memcg_remove(struct shrinker *shrinker) { } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { return 0; } static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { return 0; } #endif /* CONFIG_MEMCG */ static long xchg_nr_deferred(struct shrinker *shrinker, struct shrink_control *sc) { int nid = sc->nid; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; if (sc->memcg && (shrinker->flags & SHRINKER_MEMCG_AWARE)) return xchg_nr_deferred_memcg(nid, shrinker, sc->memcg); return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); } static long add_nr_deferred(long nr, struct shrinker *shrinker, struct shrink_control *sc) { int nid = sc->nid; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; if (sc->memcg && (shrinker->flags & SHRINKER_MEMCG_AWARE)) return add_nr_deferred_memcg(nr, nid, shrinker, sc->memcg); return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); } #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, struct shrinker *shrinker, int priority) { unsigned long freed = 0; unsigned long long delta; long total_scan; long freeable; long nr; long new_nr; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; /* * copy the current shrinker scan count into a local variable * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ nr = xchg_nr_deferred(shrinker, shrinkctl); if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan = nr >> priority; total_scan += delta; total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); total_scan -= shrinkctl->nr_scanned; scanned += shrinkctl->nr_scanned; cond_resched(); } /* * The deferred work is increased by any new work (delta) that wasn't * done, decreased by old deferred work that was done now. * * And it is capped to two times of the freeable items. */ next_deferred = max_t(long, (nr + delta - scanned), 0); next_deferred = min(next_deferred, (2 * freeable)); /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. */ new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); return freed; } #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct shrinker_info *info; unsigned long ret, freed = 0; int offset, index = 0; if (!mem_cgroup_online(memcg)) return 0; /* * lockless algorithm of memcg shrink. * * The shrinker_info may be freed asynchronously via RCU in the * expand_one_shrinker_info(), so the rcu_read_lock() needs to be used * to ensure the existence of the shrinker_info. * * The shrinker_info_unit is never freed unless its corresponding memcg * is destroyed. Here we already hold the refcount of memcg, so the * memcg will not be destroyed, and of course shrinker_info_unit will * not be freed. * * So in the memcg shrink: * step 1: use rcu_read_lock() to guarantee existence of the * shrinker_info. * step 2: after getting shrinker_info_unit we can safely release the * RCU lock. * step 3: traverse the bitmap and calculate shrinker_id * step 4: use rcu_read_lock() to guarantee existence of the shrinker. * step 5: use shrinker_id to find the shrinker, then use * shrinker_try_get() to guarantee existence of the shrinker, * then we can release the RCU lock to do do_shrink_slab() that * may sleep. * step 6: do shrinker_put() paired with step 5 to put the refcount, * if the refcount reaches 0, then wake up the waiter in * shrinker_free() by calling complete(). * Note: here is different from the global shrink, we don't * need to acquire the RCU lock to guarantee existence of * the shrinker, because we don't need to use this * shrinker to traverse the next shrinker in the bitmap. * step 7: we have already exited the read-side of rcu critical section * before calling do_shrink_slab(), the shrinker_info may be * released in expand_one_shrinker_info(), so go back to step 1 * to reacquire the shrinker_info. */ again: rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); if (unlikely(!info)) goto unlock; if (index < shrinker_id_to_index(info->map_nr_max)) { struct shrinker_info_unit *unit; unit = info->unit[index]; rcu_read_unlock(); for_each_set_bit(offset, unit->map, SHRINKER_UNIT_BITS) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; struct shrinker *shrinker; int shrinker_id = calc_shrinker_id(index, offset); rcu_read_lock(); shrinker = idr_find(&shrinker_idr, shrinker_id); if (unlikely(!shrinker || !shrinker_try_get(shrinker))) { clear_bit(offset, unit->map); rcu_read_unlock(); continue; } rcu_read_unlock(); /* Call non-slab shrinkers even though kmem is disabled */ if (!memcg_kmem_online() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(offset, unit->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in * the memcg shrinker map, a new object might have been * added. To make sure, we have the bit set in this * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in * set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() * <MB> <MB> * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; else set_shrinker_bit(memcg, nid, shrinker_id); } freed += ret; shrinker_put(shrinker); } index++; goto again; } unlock: rcu_read_unlock(); return freed; } #else /* !CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } #endif /* CONFIG_MEMCG */ /** * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target * @memcg: memory cgroup whose slab caches to target * @priority: the reclaim priority * * Call the shrink functions to age shrinkable caches. * * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * * @memcg specifies the memory cgroup to target. Unaware shrinkers * are called only if it is the root cgroup. * * @priority is sc->priority, we take the number of objects and >> by priority * in order to get the scan target. * * Returns the number of reclaimed slab objects. */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { unsigned long ret, freed = 0; struct shrinker *shrinker; /* * The root memcg might be allocated even though memcg is disabled * via "cgroup_disable=memory" boot parameter. This could make * mem_cgroup_is_root() return false, then just run memcg slab * shrink, but skip global shrink. This may result in premature * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); /* * lockless algorithm of global shrink. * * In the unregistration setp, the shrinker will be freed asynchronously * via RCU after its refcount reaches 0. So both rcu_read_lock() and * shrinker_try_get() can be used to ensure the existence of the shrinker. * * So in the global shrink: * step 1: use rcu_read_lock() to guarantee existence of the shrinker * and the validity of the shrinker_list walk. * step 2: use shrinker_try_get() to try get the refcount, if successful, * then the existence of the shrinker can also be guaranteed, * so we can release the RCU lock to do do_shrink_slab() that * may sleep. * step 3: *MUST* to reacquire the RCU lock before calling shrinker_put(), * which ensures that neither this shrinker nor the next shrinker * will be freed in the next traversal operation. * step 4: do shrinker_put() paired with step 2 to put the refcount, * if the refcount reaches 0, then wake up the waiter in * shrinker_free() by calling complete(). */ rcu_read_lock(); list_for_each_entry_rcu(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; if (!shrinker_try_get(shrinker)) continue; rcu_read_unlock(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; rcu_read_lock(); shrinker_put(shrinker); } rcu_read_unlock(); cond_resched(); return freed; } struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...) { struct shrinker *shrinker; unsigned int size; va_list ap; int err; shrinker = kzalloc(sizeof(struct shrinker), GFP_KERNEL); if (!shrinker) return NULL; va_start(ap, fmt); err = shrinker_debugfs_name_alloc(shrinker, fmt, ap); va_end(ap); if (err) goto err_name; shrinker->flags = flags | SHRINKER_ALLOCATED; shrinker->seeks = DEFAULT_SEEKS; if (flags & SHRINKER_MEMCG_AWARE) { err = shrinker_memcg_alloc(shrinker); if (err == -ENOSYS) { /* Memcg is not supported, fallback to non-memcg-aware shrinker. */ shrinker->flags &= ~SHRINKER_MEMCG_AWARE; goto non_memcg; } if (err) goto err_flags; return shrinker; } non_memcg: /* * The nr_deferred is available on per memcg level for memcg aware * shrinkers, so only allocate nr_deferred in the following cases: * - non-memcg-aware shrinkers * - !CONFIG_MEMCG * - memcg is disabled by kernel command line */ size = sizeof(*shrinker->nr_deferred); if (flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); if (!shrinker->nr_deferred) goto err_flags; return shrinker; err_flags: shrinker_debugfs_name_free(shrinker); err_name: kfree(shrinker); return NULL; } EXPORT_SYMBOL_GPL(shrinker_alloc); void shrinker_register(struct shrinker *shrinker) { if (unlikely(!(shrinker->flags & SHRINKER_ALLOCATED))) { pr_warn("Must use shrinker_alloc() to dynamically allocate the shrinker"); return; } mutex_lock(&shrinker_mutex); list_add_tail_rcu(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); mutex_unlock(&shrinker_mutex); init_completion(&shrinker->done); /* * Now the shrinker is fully set up, take the first reference to it to * indicate that lookup operations are now allowed to use it via * shrinker_try_get(). */ refcount_set(&shrinker->refcount, 1); } EXPORT_SYMBOL_GPL(shrinker_register); static void shrinker_free_rcu_cb(struct rcu_head *head) { struct shrinker *shrinker = container_of(head, struct shrinker, rcu); kfree(shrinker->nr_deferred); kfree(shrinker); } void shrinker_free(struct shrinker *shrinker) { struct dentry *debugfs_entry = NULL; int debugfs_id; if (!shrinker) return; if (shrinker->flags & SHRINKER_REGISTERED) { /* drop the initial refcount */ shrinker_put(shrinker); /* * Wait for all lookups of the shrinker to complete, after that, * no shrinker is running or will run again, then we can safely * free it asynchronously via RCU and safely free the structure * where the shrinker is located, such as super_block etc. */ wait_for_completion(&shrinker->done); } mutex_lock(&shrinker_mutex); if (shrinker->flags & SHRINKER_REGISTERED) { /* * Now we can safely remove it from the shrinker_list and then * free it. */ list_del_rcu(&shrinker->list); debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); shrinker->flags &= ~SHRINKER_REGISTERED; } shrinker_debugfs_name_free(shrinker); if (shrinker->flags & SHRINKER_MEMCG_AWARE) shrinker_memcg_remove(shrinker); mutex_unlock(&shrinker_mutex); if (debugfs_entry) shrinker_debugfs_remove(debugfs_entry, debugfs_id); call_rcu(&shrinker->rcu, shrinker_free_rcu_cb); } EXPORT_SYMBOL_GPL(shrinker_free); |
| 10141 9680 1865 795 2 13 1452 1 402 7 1059 540 867 312 312 23 23 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal schedule timeout and sleeping functions */ #include <linux/delay.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include "tick-internal.h" /* * Since schedule_timeout()'s timer is defined on the stack, it must store * the target task on the stack as well. */ struct process_timer { struct timer_list timer; struct task_struct *task; }; static void process_timeout(struct timer_list *t) { struct process_timer *timeout = from_timer(timeout, t, timer); wake_up_process(timeout->task); } /** * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * * Make the current task sleep until @timeout jiffies have elapsed. * The function behavior depends on the current task state * (see also set_current_state() description): * * %TASK_RUNNING - the scheduler is called, but the task does not sleep * at all. That happens because sched_submit_work() does nothing for * tasks in %TASK_RUNNING state. * * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be %TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule * the CPU away without a bound on the timeout. In this case the return * value will be %MAX_SCHEDULE_TIMEOUT. * * Returns: 0 when the timer has expired otherwise the remaining time in * jiffies will be returned. In all cases the return value is guaranteed * to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) { struct process_timer timer; unsigned long expire; switch (timeout) { case MAX_SCHEDULE_TIMEOUT: /* * These two special cases are useful to be comfortable * in the caller. Nothing more. We could take * MAX_SCHEDULE_TIMEOUT from one of the negative value * but I' d like to return a valid offset (>=0) to allow * the caller to do everything it want with the retval. */ schedule(); goto out; default: /* * Another bit of PARANOID. Note that the retval will be * 0 since no piece of kernel is supposed to do a check * for a negative retval of schedule_timeout() (since it * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ if (timeout < 0) { pr_err("%s: wrong timeout value %lx\n", __func__, timeout); dump_stack(); __set_current_state(TASK_RUNNING); goto out; } } expire = timeout + jiffies; timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); timer.timer.expires = expire; add_timer(&timer.timer); schedule(); del_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } EXPORT_SYMBOL(schedule_timeout); /* * __set_current_state() can be used in schedule_timeout_*() functions, because * schedule_timeout() calls schedule() unconditionally. */ /** * schedule_timeout_interruptible - sleep until timeout (interruptible) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_INTERRUPTIBLE before starting the timeout. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { __set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_interruptible); /** * schedule_timeout_killable - sleep until timeout (killable) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_KILLABLE before starting the timeout. */ signed long __sched schedule_timeout_killable(signed long timeout) { __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_killable); /** * schedule_timeout_uninterruptible - sleep until timeout (uninterruptible) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_UNINTERRUPTIBLE before starting the timeout. */ signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_uninterruptible); /** * schedule_timeout_idle - sleep until timeout (idle) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_IDLE before starting the timeout. It is similar to * schedule_timeout_uninterruptible(), except this task will not contribute to * load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { __set_current_state(TASK_IDLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_idle); /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * @clock_id: timer clock to be used * * Details are explained in schedule_hrtimeout_range() function description as * this function is commonly used. */ int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id) { struct hrtimer_sleeper t; /* * Optimize when a zero timeout value is given. It does not * matter whether this is an absolute or a relative time. */ if (expires && *expires == 0) { __set_current_state(TASK_RUNNING); return 0; } /* * A NULL parameter means "infinite" */ if (!expires) { schedule(); return -EINTR; } hrtimer_setup_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); if (likely(t.task)) schedule(); hrtimer_cancel(&t.timer); destroy_hrtimer_on_stack(&t.timer); __set_current_state(TASK_RUNNING); return !t.task ? 0 : -EINTR; } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has * elapsed. The routine will return immediately unless * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the * actual wakeup to a time that is both power and performance friendly * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * * You can set the task state as follows - * * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Returns: 0 when the timer has expired. If the task was woken before the * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or * by an explicit wakeup, it returns -EINTR. */ int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { return schedule_hrtimeout_range_clock(expires, delta, mode, CLOCK_MONOTONIC); } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); /** * schedule_hrtimeout - sleep until timeout * @expires: timeout value (ktime_t) * @mode: timer mode * * See schedule_hrtimeout_range() for details. @delta argument of * schedule_hrtimeout_range() is set to 0 and has therefore no impact. */ int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode) { return schedule_hrtimeout_range(expires, 0, mode); } EXPORT_SYMBOL_GPL(schedule_hrtimeout); /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Requested sleep duration in milliseconds * * msleep() uses jiffy based timeouts for the sleep duration. Because of the * design of the timer wheel, the maximum additional percentage delay (slack) is * 12.5%. This is only valid for timers which will end up in level 1 or a higher * level of the timer wheel. For explanation of those 12.5% please check the * detailed description about the basics of the timer wheel. * * The slack of timers which will end up in level 0 depends on sleep duration * (msecs) and HZ configuration and can be calculated in the following way (with * the timer wheel design restriction that the slack is not less than 12.5%): * * ``slack = MSECS_PER_TICK / msecs`` * * When the allowed slack of the callsite is known, the calculation could be * turned around to find the minimal allowed sleep duration to meet the * constraints. For example: * * * ``HZ=1000`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 1 / (1/4) = 4``: * all sleep durations greater or equal 4ms will meet the constraints. * * ``HZ=1000`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 1 / (1/8) = 8``: * all sleep durations greater or equal 8ms will meet the constraints. * * ``HZ=250`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 4 / (1/4) = 16``: * all sleep durations greater or equal 16ms will meet the constraints. * * ``HZ=250`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 4 / (1/8) = 32``: * all sleep durations greater or equal 32ms will meet the constraints. * * See also the signal aware variant msleep_interruptible(). */ void msleep(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs); while (timeout) timeout = schedule_timeout_uninterruptible(timeout); } EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals * @msecs: Requested sleep duration in milliseconds * * See msleep() for some basic information. * * The difference between msleep() and msleep_interruptible() is that the sleep * could be interrupted by a signal delivery and then returns early. * * Returns: The remaining time of the sleep duration transformed to msecs (see * schedule_timeout() for details). */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs); while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); /** * usleep_range_state - Sleep for an approximate time in a given state * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep * @state: State of the current task that will be while sleeping * * usleep_range_state() sleeps at least for the minimum specified time but not * longer than the maximum specified amount of time. The range might reduce * power usage by allowing hrtimers to coalesce an already scheduled interrupt * with this hrtimer. In the worst case, an interrupt is scheduled for the upper * bound. * * The sleeping task is set to the specified state before starting the sleep. * * In non-atomic context where the exact wakeup time is flexible, use * usleep_range() or its variants instead of udelay(). The sleep improves * responsiveness by avoiding the CPU-hogging busy-wait of udelay(). */ void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; if (WARN_ON_ONCE(max < min)) delta = 0; for (;;) { __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } EXPORT_SYMBOL(usleep_range_state); |
| 8 8 34 1 502 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * UDPLITEv6 An implementation of the UDP-Lite protocol over IPv6. * See also net/ipv4/udplite.c * * Authors: Gerrit Renker <gerrit@erg.abdn.ac.uk> * * Changes: * Fixes: */ #define pr_fmt(fmt) "UDPLite6: " fmt #include <linux/export.h> #include <linux/proc_fs.h> #include "udp_impl.h" static int udplitev6_sk_init(struct sock *sk) { udpv6_init_sock(sk); pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, " "please contact the netdev mailing list\n"); return 0; } static int udplitev6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); } static int udplitev6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { return __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); } static const struct inet6_protocol udplitev6_protocol = { .handler = udplitev6_rcv, .err_handler = udplitev6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; struct proto udplitev6_prot = { .name = "UDPLITEv6", .owner = THIS_MODULE, .close = udp_lib_close, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udplitev6_sk_init, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6), .h.udp_table = &udplite_table, }; static struct inet_protosw udplite6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_UDPLITE, .prot = &udplitev6_prot, .ops = &inet6_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }; int __init udplitev6_init(void) { int ret; ret = inet6_add_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); if (ret) goto out; ret = inet6_register_protosw(&udplite6_protosw); if (ret) goto out_udplitev6_protocol; out: return ret; out_udplitev6_protocol: inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); goto out; } void udplitev6_exit(void) { inet6_unregister_protosw(&udplite6_protosw); inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); } #ifdef CONFIG_PROC_FS static struct udp_seq_afinfo udplite6_seq_afinfo = { .family = AF_INET6, .udp_table = &udplite_table, }; static int __net_init udplite6_proc_init_net(struct net *net) { if (!proc_create_net_data("udplite6", 0444, net->proc_net, &udp6_seq_ops, sizeof(struct udp_iter_state), &udplite6_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit udplite6_proc_exit_net(struct net *net) { remove_proc_entry("udplite6", net->proc_net); } static struct pernet_operations udplite6_net_ops = { .init = udplite6_proc_init_net, .exit = udplite6_proc_exit_net, }; int __init udplite6_proc_init(void) { return register_pernet_subsys(&udplite6_net_ops); } void udplite6_proc_exit(void) { unregister_pernet_subsys(&udplite6_net_ops); } #endif |
| 274 273 2 273 265 38 17 4 2 4 171 150 171 16 171 1 1 1 130 179 167 130 46 46 61 61 22 1 179 179 179 271 176 171 46 3 48 222 203 182 176 177 146 175 6 3 3 5 2 3 117 129 10 10 88 87 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; generic parts * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/rculist.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_stp.h" /* since time values in bpdu are in jiffies and then scaled (1/256) * before sending, make sure that is at least one STP tick. */ #define MESSAGE_AGE_INCR ((HZ / 256) + 1) static const char *const br_port_state_names[] = { [BR_STATE_DISABLED] = "disabled", [BR_STATE_LISTENING] = "listening", [BR_STATE_LEARNING] = "learning", [BR_STATE_FORWARDING] = "forwarding", [BR_STATE_BLOCKING] = "blocking", }; void br_set_state(struct net_bridge_port *p, unsigned int state) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, .flags = SWITCHDEV_F_DEFER, .u.stp_state = state, }; int err; /* Don't change the state of the ports if they are driven by a different * protocol. */ if (p->flags & BR_MRP_AWARE) return; p->state = state; if (br_opt_get(p->br, BROPT_MST_ENABLED)) { err = br_mst_set_state(p, 0, state, NULL); if (err) br_warn(p->br, "error setting MST state on port %u(%s)\n", p->port_no, netdev_name(p->dev)); } err = switchdev_port_attr_set(p->dev, &attr, NULL); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); else br_info(p->br, "port %u(%s) entered %s state\n", (unsigned int) p->port_no, p->dev->name, br_port_state_names[p->state]); if (p->br->stp_enabled == BR_KERNEL_STP) { switch (p->state) { case BR_STATE_BLOCKING: p->stp_xstats.transition_blk++; break; case BR_STATE_FORWARDING: p->stp_xstats.transition_fwd++; break; } } } u8 br_port_get_stp_state(const struct net_device *dev) { struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_rtnl(dev); if (!p) return BR_STATE_DISABLED; return p->state; } EXPORT_SYMBOL_GPL(br_port_get_stp_state); /* called under bridge lock */ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { struct net_bridge_port *p; list_for_each_entry_rcu(p, &br->port_list, list, lockdep_is_held(&br->lock)) { if (p->port_no == port_no) return p; } return NULL; } /* called under bridge lock */ static int br_should_become_root_port(const struct net_bridge_port *p, u16 root_port) { struct net_bridge *br; struct net_bridge_port *rp; int t; br = p->br; if (p->state == BR_STATE_DISABLED || br_is_designated_port(p)) return 0; if (memcmp(&br->bridge_id, &p->designated_root, 8) <= 0) return 0; if (!root_port) return 1; rp = br_get_port(br, root_port); t = memcmp(&p->designated_root, &rp->designated_root, 8); if (t < 0) return 1; else if (t > 0) return 0; if (p->designated_cost + p->path_cost < rp->designated_cost + rp->path_cost) return 1; else if (p->designated_cost + p->path_cost > rp->designated_cost + rp->path_cost) return 0; t = memcmp(&p->designated_bridge, &rp->designated_bridge, 8); if (t < 0) return 1; else if (t > 0) return 0; if (p->designated_port < rp->designated_port) return 1; else if (p->designated_port > rp->designated_port) return 0; if (p->port_id < rp->port_id) return 1; return 0; } static void br_root_port_block(const struct net_bridge *br, struct net_bridge_port *p) { br_notice(br, "port %u(%s) tried to become root port (blocked)", (unsigned int) p->port_no, p->dev->name); br_set_state(p, BR_STATE_LISTENING); br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (br->forward_delay > 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } /* called under bridge lock */ static void br_root_selection(struct net_bridge *br) { struct net_bridge_port *p; u16 root_port = 0; list_for_each_entry(p, &br->port_list, list) { if (!br_should_become_root_port(p, root_port)) continue; if (p->flags & BR_ROOT_BLOCK) br_root_port_block(br, p); else root_port = p->port_no; } br->root_port = root_port; if (!root_port) { br->designated_root = br->bridge_id; br->root_path_cost = 0; } else { p = br_get_port(br, root_port); br->designated_root = p->designated_root; br->root_path_cost = p->designated_cost + p->path_cost; } } /* called under bridge lock */ void br_become_root_bridge(struct net_bridge *br) { br->max_age = br->bridge_max_age; br->hello_time = br->bridge_hello_time; br->forward_delay = br->bridge_forward_delay; br_topology_change_detection(br); del_timer(&br->tcn_timer); if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); mod_timer(&br->hello_timer, jiffies + br->hello_time); } } /* called under bridge lock */ void br_transmit_config(struct net_bridge_port *p) { struct br_config_bpdu bpdu; struct net_bridge *br; if (timer_pending(&p->hold_timer)) { p->config_pending = 1; return; } br = p->br; bpdu.topology_change = br->topology_change; bpdu.topology_change_ack = p->topology_change_ack; bpdu.root = br->designated_root; bpdu.root_path_cost = br->root_path_cost; bpdu.bridge_id = br->bridge_id; bpdu.port_id = p->port_id; if (br_is_root_bridge(br)) bpdu.message_age = 0; else { struct net_bridge_port *root = br_get_port(br, br->root_port); bpdu.message_age = (jiffies - root->designated_age) + MESSAGE_AGE_INCR; } bpdu.max_age = br->max_age; bpdu.hello_time = br->hello_time; bpdu.forward_delay = br->forward_delay; if (bpdu.message_age < br->max_age) { br_send_config_bpdu(p, &bpdu); p->topology_change_ack = 0; p->config_pending = 0; if (p->br->stp_enabled == BR_KERNEL_STP) mod_timer(&p->hold_timer, round_jiffies(jiffies + BR_HOLD_TIME)); } } /* called under bridge lock */ static void br_record_config_information(struct net_bridge_port *p, const struct br_config_bpdu *bpdu) { p->designated_root = bpdu->root; p->designated_cost = bpdu->root_path_cost; p->designated_bridge = bpdu->bridge_id; p->designated_port = bpdu->port_id; p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies + (bpdu->max_age - bpdu->message_age)); } /* called under bridge lock */ static void br_record_config_timeout_values(struct net_bridge *br, const struct br_config_bpdu *bpdu) { br->max_age = bpdu->max_age; br->hello_time = bpdu->hello_time; br->forward_delay = bpdu->forward_delay; __br_set_topology_change(br, bpdu->topology_change); } /* called under bridge lock */ void br_transmit_tcn(struct net_bridge *br) { struct net_bridge_port *p; p = br_get_port(br, br->root_port); if (p) br_send_tcn_bpdu(p); else br_notice(br, "root port %u not found for topology notice\n", br->root_port); } /* called under bridge lock */ static int br_should_become_designated_port(const struct net_bridge_port *p) { struct net_bridge *br; int t; br = p->br; if (br_is_designated_port(p)) return 1; if (memcmp(&p->designated_root, &br->designated_root, 8)) return 1; if (br->root_path_cost < p->designated_cost) return 1; else if (br->root_path_cost > p->designated_cost) return 0; t = memcmp(&br->bridge_id, &p->designated_bridge, 8); if (t < 0) return 1; else if (t > 0) return 0; if (p->port_id < p->designated_port) return 1; return 0; } /* called under bridge lock */ static void br_designated_port_selection(struct net_bridge *br) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED && br_should_become_designated_port(p)) br_become_designated_port(p); } } /* called under bridge lock */ static int br_supersedes_port_info(const struct net_bridge_port *p, const struct br_config_bpdu *bpdu) { int t; t = memcmp(&bpdu->root, &p->designated_root, 8); if (t < 0) return 1; else if (t > 0) return 0; if (bpdu->root_path_cost < p->designated_cost) return 1; else if (bpdu->root_path_cost > p->designated_cost) return 0; t = memcmp(&bpdu->bridge_id, &p->designated_bridge, 8); if (t < 0) return 1; else if (t > 0) return 0; if (memcmp(&bpdu->bridge_id, &p->br->bridge_id, 8)) return 1; if (bpdu->port_id <= p->designated_port) return 1; return 0; } /* called under bridge lock */ static void br_topology_change_acknowledged(struct net_bridge *br) { br->topology_change_detected = 0; del_timer(&br->tcn_timer); } /* called under bridge lock */ void br_topology_change_detection(struct net_bridge *br) { int isroot = br_is_root_bridge(br); if (br->stp_enabled != BR_KERNEL_STP) return; br_info(br, "topology change detected, %s\n", isroot ? "propagating" : "sending tcn bpdu"); if (isroot) { __br_set_topology_change(br, 1); mod_timer(&br->topology_change_timer, jiffies + br->bridge_forward_delay + br->bridge_max_age); } else if (!br->topology_change_detected) { br_transmit_tcn(br); mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } br->topology_change_detected = 1; } /* called under bridge lock */ void br_config_bpdu_generation(struct net_bridge *br) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED && br_is_designated_port(p)) br_transmit_config(p); } } /* called under bridge lock */ static void br_reply(struct net_bridge_port *p) { br_transmit_config(p); } /* called under bridge lock */ void br_configuration_update(struct net_bridge *br) { br_root_selection(br); br_designated_port_selection(br); } /* called under bridge lock */ void br_become_designated_port(struct net_bridge_port *p) { struct net_bridge *br; br = p->br; p->designated_root = br->designated_root; p->designated_cost = br->root_path_cost; p->designated_bridge = br->bridge_id; p->designated_port = p->port_id; } /* called under bridge lock */ static void br_make_blocking(struct net_bridge_port *p) { if (p->state != BR_STATE_DISABLED && p->state != BR_STATE_BLOCKING) { if (p->state == BR_STATE_FORWARDING || p->state == BR_STATE_LEARNING) br_topology_change_detection(p->br); br_set_state(p, BR_STATE_BLOCKING); br_ifinfo_notify(RTM_NEWLINK, NULL, p); del_timer(&p->forward_delay_timer); } } /* called under bridge lock */ static void br_make_forwarding(struct net_bridge_port *p) { struct net_bridge *br = p->br; if (p->state != BR_STATE_BLOCKING) return; if (br->stp_enabled == BR_NO_STP || br->forward_delay == 0) { br_set_state(p, BR_STATE_FORWARDING); br_topology_change_detection(br); del_timer(&p->forward_delay_timer); } else if (br->stp_enabled == BR_KERNEL_STP) br_set_state(p, BR_STATE_LISTENING); else br_set_state(p, BR_STATE_LEARNING); br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (br->forward_delay != 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } /* called under bridge lock */ void br_port_state_selection(struct net_bridge *br) { struct net_bridge_port *p; unsigned int liveports = 0; list_for_each_entry(p, &br->port_list, list) { if (p->state == BR_STATE_DISABLED) continue; /* Don't change port states if userspace is handling STP */ if (br->stp_enabled != BR_USER_STP) { if (p->port_no == br->root_port) { p->config_pending = 0; p->topology_change_ack = 0; br_make_forwarding(p); } else if (br_is_designated_port(p)) { del_timer(&p->message_age_timer); br_make_forwarding(p); } else { p->config_pending = 0; p->topology_change_ack = 0; br_make_blocking(p); } } if (p->state != BR_STATE_BLOCKING) br_multicast_enable_port(p); /* Multicast is not disabled for the port when it goes in * blocking state because the timers will expire and stop by * themselves without sending more queries. */ if (p->state == BR_STATE_FORWARDING) ++liveports; } if (liveports == 0) netif_carrier_off(br->dev); else netif_carrier_on(br->dev); } /* called under bridge lock */ static void br_topology_change_acknowledge(struct net_bridge_port *p) { p->topology_change_ack = 1; br_transmit_config(p); } /* called under bridge lock */ void br_received_config_bpdu(struct net_bridge_port *p, const struct br_config_bpdu *bpdu) { struct net_bridge *br; int was_root; p->stp_xstats.rx_bpdu++; br = p->br; was_root = br_is_root_bridge(br); if (br_supersedes_port_info(p, bpdu)) { br_record_config_information(p, bpdu); br_configuration_update(br); br_port_state_selection(br); if (!br_is_root_bridge(br) && was_root) { del_timer(&br->hello_timer); if (br->topology_change_detected) { del_timer(&br->topology_change_timer); br_transmit_tcn(br); mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } } if (p->port_no == br->root_port) { br_record_config_timeout_values(br, bpdu); br_config_bpdu_generation(br); if (bpdu->topology_change_ack) br_topology_change_acknowledged(br); } } else if (br_is_designated_port(p)) { br_reply(p); } } /* called under bridge lock */ void br_received_tcn_bpdu(struct net_bridge_port *p) { p->stp_xstats.rx_tcn++; if (br_is_designated_port(p)) { br_info(p->br, "port %u(%s) received tcn bpdu\n", (unsigned int) p->port_no, p->dev->name); br_topology_change_detection(p->br); br_topology_change_acknowledge(p); } } /* Change bridge STP parameter */ int br_set_hello_time(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); if (t < BR_MIN_HELLO_TIME || t > BR_MAX_HELLO_TIME) return -ERANGE; spin_lock_bh(&br->lock); br->bridge_hello_time = t; if (br_is_root_bridge(br)) br->hello_time = br->bridge_hello_time; spin_unlock_bh(&br->lock); return 0; } int br_set_max_age(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); if (t < BR_MIN_MAX_AGE || t > BR_MAX_MAX_AGE) return -ERANGE; spin_lock_bh(&br->lock); br->bridge_max_age = t; if (br_is_root_bridge(br)) br->max_age = br->bridge_max_age; spin_unlock_bh(&br->lock); return 0; } /* called under bridge lock */ int __set_ageing_time(struct net_device *dev, unsigned long t) { struct switchdev_attr attr = { .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP | SWITCHDEV_F_DEFER, .u.ageing_time = jiffies_to_clock_t(t), }; int err; err = switchdev_port_attr_set(dev, &attr, NULL); if (err && err != -EOPNOTSUPP) return err; return 0; } /* Set time interval that dynamic forwarding entries live * For pure software bridge, allow values outside the 802.1 * standard specification for special cases: * 0 - entry never ages (all permanent) * 1 - entry disappears (no persistence) * * Offloaded switch entries maybe more restrictive */ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) { unsigned long t = clock_t_to_jiffies(ageing_time); int err; err = __set_ageing_time(br->dev, t); if (err) return err; spin_lock_bh(&br->lock); br->bridge_ageing_time = t; br->ageing_time = t; spin_unlock_bh(&br->lock); mod_delayed_work(system_long_wq, &br->gc_work, 0); return 0; } clock_t br_get_ageing_time(const struct net_device *br_dev) { const struct net_bridge *br; if (!netif_is_bridge_master(br_dev)) return 0; br = netdev_priv(br_dev); return jiffies_to_clock_t(br->ageing_time); } EXPORT_SYMBOL_GPL(br_get_ageing_time); /* called under bridge lock */ void __br_set_topology_change(struct net_bridge *br, unsigned char val) { unsigned long t; int err; if (br->stp_enabled == BR_KERNEL_STP && br->topology_change != val) { /* On topology change, set the bridge ageing time to twice the * forward delay. Otherwise, restore its default ageing time. */ if (val) { t = 2 * br->forward_delay; br_debug(br, "decreasing ageing time to %lu\n", t); } else { t = br->bridge_ageing_time; br_debug(br, "restoring ageing time to %lu\n", t); } err = __set_ageing_time(br->dev, t); if (err) br_warn(br, "error offloading ageing time\n"); else br->ageing_time = t; } br->topology_change = val; } void __br_set_forward_delay(struct net_bridge *br, unsigned long t) { br->bridge_forward_delay = t; if (br_is_root_bridge(br)) br->forward_delay = br->bridge_forward_delay; } int br_set_forward_delay(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); int err = -ERANGE; spin_lock_bh(&br->lock); if (br->stp_enabled != BR_NO_STP && (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) goto unlock; __br_set_forward_delay(br, t); err = 0; unlock: spin_unlock_bh(&br->lock); return err; } |
| 36 36 36 2 34 8 8 8 8 8 8 8 8 5 3 2 18 18 18 20 20 18 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 | /* * llc_sap.c - driver routines for SAP component. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <net/llc.h> #include <net/llc_if.h> #include <net/llc_conn.h> #include <net/llc_pdu.h> #include <net/llc_sap.h> #include <net/llc_s_ac.h> #include <net/llc_s_ev.h> #include <net/llc_s_st.h> #include <net/sock.h> #include <net/tcp_states.h> #include <linux/llc.h> #include <linux/slab.h> static int llc_mac_header_len(unsigned short devtype) { switch (devtype) { case ARPHRD_ETHER: case ARPHRD_LOOPBACK: return sizeof(struct ethhdr); } return 0; } /** * llc_alloc_frame - allocates sk_buff for frame * @sk: socket to allocate frame to * @dev: network device this skb will be sent over * @type: pdu type to allocate * @data_size: data size to allocate * * Allocates an sk_buff for frame and initializes sk_buff fields. * Returns allocated skb or %NULL when out of memory. */ struct sk_buff *llc_alloc_frame(struct sock *sk, struct net_device *dev, u8 type, u32 data_size) { int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; struct sk_buff *skb; hlen += llc_mac_header_len(dev->type); skb = alloc_skb(hlen + data_size, GFP_ATOMIC); if (skb) { skb_reset_mac_header(skb); skb_reserve(skb, hlen); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->protocol = htons(ETH_P_802_2); skb->dev = dev; if (sk != NULL) skb_set_owner_w(skb, sk); } return skb; } void llc_save_primitive(struct sock *sk, struct sk_buff *skb, u8 prim) { struct sockaddr_llc *addr; /* save primitive for use by the user. */ addr = llc_ui_skb_cb(skb); memset(addr, 0, sizeof(*addr)); addr->sllc_family = sk->sk_family; addr->sllc_arphrd = skb->dev->type; addr->sllc_test = prim == LLC_TEST_PRIM; addr->sllc_xid = prim == LLC_XID_PRIM; addr->sllc_ua = prim == LLC_DATAUNIT_PRIM; llc_pdu_decode_sa(skb, addr->sllc_mac); llc_pdu_decode_ssap(skb, &addr->sllc_sap); } /** * llc_sap_rtn_pdu - Informs upper layer on rx of an UI, XID or TEST pdu. * @sap: pointer to SAP * @skb: received pdu */ void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); switch (LLC_U_PDU_RSP(pdu)) { case LLC_1_PDU_CMD_TEST: ev->prim = LLC_TEST_PRIM; break; case LLC_1_PDU_CMD_XID: ev->prim = LLC_XID_PRIM; break; case LLC_1_PDU_CMD_UI: ev->prim = LLC_DATAUNIT_PRIM; break; } ev->ind_cfm_flag = LLC_IND; } /** * llc_find_sap_trans - finds transition for event * @sap: pointer to SAP * @skb: happened event * * This function finds transition that matches with happened event. * Returns the pointer to found transition on success or %NULL for * failure. */ static const struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap, struct sk_buff *skb) { int i = 0; const struct llc_sap_state_trans *rc = NULL; const struct llc_sap_state_trans **next_trans; struct llc_sap_state *curr_state = &llc_sap_state_table[sap->state - 1]; /* * Search thru events for this state until list exhausted or until * its obvious the event is not valid for the current state */ for (next_trans = curr_state->transitions; next_trans[i]->ev; i++) if (!next_trans[i]->ev(sap, skb)) { rc = next_trans[i]; /* got event match; return it */ break; } return rc; } /** * llc_exec_sap_trans_actions - execute actions related to event * @sap: pointer to SAP * @trans: pointer to transition that it's actions must be performed * @skb: happened event. * * This function executes actions that is related to happened event. * Returns 0 for success and 1 for failure of at least one action. */ static int llc_exec_sap_trans_actions(struct llc_sap *sap, const struct llc_sap_state_trans *trans, struct sk_buff *skb) { int rc = 0; const llc_sap_action_t *next_action = trans->ev_actions; for (; next_action && *next_action; next_action++) if ((*next_action)(sap, skb)) rc = 1; return rc; } /** * llc_sap_next_state - finds transition, execs actions & change SAP state * @sap: pointer to SAP * @skb: happened event * * This function finds transition that matches with happened event, then * executes related actions and finally changes state of SAP. It returns * 0 on success and 1 for failure. */ static int llc_sap_next_state(struct llc_sap *sap, struct sk_buff *skb) { const struct llc_sap_state_trans *trans; int rc = 1; if (sap->state > LLC_NR_SAP_STATES) goto out; trans = llc_find_sap_trans(sap, skb); if (!trans) goto out; /* * Got the state to which we next transition; perform the actions * associated with this transition before actually transitioning to the * next state */ rc = llc_exec_sap_trans_actions(sap, trans, skb); if (rc) goto out; /* * Transition SAP to next state if all actions execute successfully */ sap->state = trans->next_state; out: return rc; } /** * llc_sap_state_process - sends event to SAP state machine * @sap: sap to use * @skb: pointer to occurred event * * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. * * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { llc_save_primitive(skb->sk, skb, ev->prim); /* queue skb to the user. */ if (sock_queue_rcv_skb(skb->sk, skb) == 0) return; } kfree_skb(skb); } /** * llc_build_and_send_test_pkt - TEST interface for upper layers. * @sap: sap to use * @skb: packet to send * @dmac: destination mac address * @dsap: destination sap * * This function is called when upper layer wants to send a TEST pdu. * Returns 0 for success, 1 otherwise. */ void llc_build_and_send_test_pkt(struct llc_sap *sap, struct sk_buff *skb, u8 *dmac, u8 dsap) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->saddr.lsap = sap->laddr.lsap; ev->daddr.lsap = dsap; memcpy(ev->saddr.mac, skb->dev->dev_addr, IFHWADDRLEN); memcpy(ev->daddr.mac, dmac, IFHWADDRLEN); ev->type = LLC_SAP_EV_TYPE_PRIM; ev->prim = LLC_TEST_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; llc_sap_state_process(sap, skb); } /** * llc_build_and_send_xid_pkt - XID interface for upper layers * @sap: sap to use * @skb: packet to send * @dmac: destination mac address * @dsap: destination sap * * This function is called when upper layer wants to send a XID pdu. * Returns 0 for success, 1 otherwise. */ void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb, u8 *dmac, u8 dsap) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->saddr.lsap = sap->laddr.lsap; ev->daddr.lsap = dsap; memcpy(ev->saddr.mac, skb->dev->dev_addr, IFHWADDRLEN); memcpy(ev->daddr.mac, dmac, IFHWADDRLEN); ev->type = LLC_SAP_EV_TYPE_PRIM; ev->prim = LLC_XID_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; llc_sap_state_process(sap, skb); } /** * llc_sap_rcv - sends received pdus to the sap state machine * @sap: current sap component structure. * @skb: received frame. * @sk: socket to associate to frame * * Sends received pdus to the sap state machine. */ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, struct sock *sk) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->type = LLC_SAP_EV_TYPE_PDU; ev->reason = 0; skb_orphan(skb); sock_hold(sk); skb->sk = sk; skb->destructor = sock_efree; llc_sap_state_process(sap, skb); } static inline bool llc_dgram_match(const struct llc_sap *sap, const struct llc_addr *laddr, const struct sock *sk, const struct net *net) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && net_eq(sock_net(sk), net) && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP * @laddr: address of local LLC (MAC + SAP) * @net: netns to look up a socket in * * Search socket list of the SAP and finds connection using the local * mac, and local sap. Returns pointer for socket found, %NULL otherwise. */ static struct sock *llc_lookup_dgram(struct llc_sap *sap, const struct llc_addr *laddr, const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; int slot = llc_sk_laddr_hashfn(sap, laddr); struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; rcu_read_lock_bh(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_dgram_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_dgram_match(sap, laddr, rc, net))) { sock_put(rc); continue; } goto found; } } rc = NULL; /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (unlikely(get_nulls_value(node) != slot)) goto again; found: rcu_read_unlock_bh(); return rc; } static inline bool llc_mcast_match(const struct llc_sap *sap, const struct llc_addr *laddr, const struct sk_buff *skb, const struct sock *sk) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && llc->laddr.lsap == laddr->lsap && llc->dev == skb->dev; } static void llc_do_mcast(struct llc_sap *sap, struct sk_buff *skb, struct sock **stack, int count) { struct sk_buff *skb1; int i; for (i = 0; i < count; i++) { skb1 = skb_clone(skb, GFP_ATOMIC); if (!skb1) { sock_put(stack[i]); continue; } llc_sap_rcv(sap, skb1, stack[i]); sock_put(stack[i]); } } /** * llc_sap_mcast - Deliver multicast PDU's to all matching datagram sockets. * @sap: SAP * @laddr: address of local LLC (MAC + SAP) * @skb: PDU to deliver * * Search socket list of the SAP and finds connections with same sap. * Deliver clone to each. */ static void llc_sap_mcast(struct llc_sap *sap, const struct llc_addr *laddr, struct sk_buff *skb) { int i = 0; struct sock *sk; struct sock *stack[256 / sizeof(struct sock *)]; struct llc_sock *llc; struct hlist_head *dev_hb = llc_sk_dev_hash(sap, skb->dev->ifindex); spin_lock_bh(&sap->sk_lock); hlist_for_each_entry(llc, dev_hb, dev_hash_node) { sk = &llc->sk; if (!llc_mcast_match(sap, laddr, skb, sk)) continue; sock_hold(sk); if (i < ARRAY_SIZE(stack)) stack[i++] = sk; else { llc_do_mcast(sap, skb, stack, i); i = 0; } } spin_unlock_bh(&sap->sk_lock); llc_do_mcast(sap, skb, stack, i); } void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) { struct llc_addr laddr; llc_pdu_decode_da(skb, laddr.mac); llc_pdu_decode_dsap(skb, &laddr.lsap); if (is_multicast_ether_addr(laddr.mac)) { llc_sap_mcast(sap, &laddr, skb); kfree_skb(skb); } else { struct sock *sk = llc_lookup_dgram(sap, &laddr, dev_net(skb->dev)); if (sk) { llc_sap_rcv(sap, skb, sk); sock_put(sk); } else kfree_skb(skb); } } |
| 54 54 502 502 502 502 501 502 501 570 567 38 570 502 570 10 7 9 9 9 9 6 5 9 6 502 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_est.c: simple rate estimator for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * Network name space (netns) aware. * Global data moved to netns i.e struct netns_ipvs * Affected data: est_list and est_lock. * estimation_timer() runs with timer per netns. * get_stats()) do the per cpu summing. */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/types.h> #include <linux/interrupt.h> #include <linux/sysctl.h> #include <linux/list.h> #include <linux/rcupdate_wait.h> #include <net/ip_vs.h> /* This code is to estimate rate in a shorter interval (such as 8 seconds) for virtual services and real servers. For measure rate in a long interval, it is easy to implement a user level daemon which periodically reads those statistical counters and measure rate. We measure rate during the last 8 seconds every 2 seconds: avgrate = avgrate*(1-W) + rate*W where W = 2^(-2) NOTES. * Average bps is scaled by 2^5, while average pps and cps are scaled by 2^10. * Netlink users can see 64-bit values but sockopt users are restricted to 32-bit values for conns, packets, bps, cps and pps. * A lot of code is taken from net/core/gen_estimator.c KEY POINTS: - cpustats counters are updated per-cpu in SoftIRQ context with BH disabled - kthreads read the cpustats to update the estimators (svcs, dests, total) - the states of estimators can be read (get stats) or modified (zero stats) from processes KTHREADS: - estimators are added initially to est_temp_list and later kthread 0 distributes them to one or many kthreads for estimation - kthread contexts are created and attached to array - the kthread tasks are started when first service is added, before that the total stats are not estimated - when configuration (cpulist/nice) is changed, the tasks are restarted by work (est_reload_work) - kthread tasks are stopped while the cpulist is empty - the kthread context holds lists with estimators (chains) which are processed every 2 seconds - as estimators can be added dynamically and in bursts, we try to spread them to multiple chains which are estimated at different time - on start, kthread 0 enters calculation phase to determine the chain limits and the limit of estimators per kthread - est_add_ktid: ktid where to add new ests, can point to empty slot where we should add kt data */ static struct lock_class_key __ipvs_est_key; static void ip_vs_est_calc_phase(struct netns_ipvs *ipvs); static void ip_vs_est_drain_temp_list(struct netns_ipvs *ipvs); static void ip_vs_chain_estimation(struct hlist_head *chain) { struct ip_vs_estimator *e; struct ip_vs_cpu_stats *c; struct ip_vs_stats *s; u64 rate; hlist_for_each_entry_rcu(e, chain, list) { u64 conns, inpkts, outpkts, inbytes, outbytes; u64 kconns = 0, kinpkts = 0, koutpkts = 0; u64 kinbytes = 0, koutbytes = 0; unsigned int start; int i; if (kthread_should_stop()) break; s = container_of(e, struct ip_vs_stats, est); for_each_possible_cpu(i) { c = per_cpu_ptr(s->cpustats, i); do { start = u64_stats_fetch_begin(&c->syncp); conns = u64_stats_read(&c->cnt.conns); inpkts = u64_stats_read(&c->cnt.inpkts); outpkts = u64_stats_read(&c->cnt.outpkts); inbytes = u64_stats_read(&c->cnt.inbytes); outbytes = u64_stats_read(&c->cnt.outbytes); } while (u64_stats_fetch_retry(&c->syncp, start)); kconns += conns; kinpkts += inpkts; koutpkts += outpkts; kinbytes += inbytes; koutbytes += outbytes; } spin_lock(&s->lock); s->kstats.conns = kconns; s->kstats.inpkts = kinpkts; s->kstats.outpkts = koutpkts; s->kstats.inbytes = kinbytes; s->kstats.outbytes = koutbytes; /* scaled by 2^10, but divided 2 seconds */ rate = (s->kstats.conns - e->last_conns) << 9; e->last_conns = s->kstats.conns; e->cps += ((s64)rate - (s64)e->cps) >> 2; rate = (s->kstats.inpkts - e->last_inpkts) << 9; e->last_inpkts = s->kstats.inpkts; e->inpps += ((s64)rate - (s64)e->inpps) >> 2; rate = (s->kstats.outpkts - e->last_outpkts) << 9; e->last_outpkts = s->kstats.outpkts; e->outpps += ((s64)rate - (s64)e->outpps) >> 2; /* scaled by 2^5, but divided 2 seconds */ rate = (s->kstats.inbytes - e->last_inbytes) << 4; e->last_inbytes = s->kstats.inbytes; e->inbps += ((s64)rate - (s64)e->inbps) >> 2; rate = (s->kstats.outbytes - e->last_outbytes) << 4; e->last_outbytes = s->kstats.outbytes; e->outbps += ((s64)rate - (s64)e->outbps) >> 2; spin_unlock(&s->lock); } } static void ip_vs_tick_estimation(struct ip_vs_est_kt_data *kd, int row) { struct ip_vs_est_tick_data *td; int cid; rcu_read_lock(); td = rcu_dereference(kd->ticks[row]); if (!td) goto out; for_each_set_bit(cid, td->present, IPVS_EST_TICK_CHAINS) { if (kthread_should_stop()) break; ip_vs_chain_estimation(&td->chains[cid]); cond_resched_rcu(); td = rcu_dereference(kd->ticks[row]); if (!td) break; } out: rcu_read_unlock(); } static int ip_vs_estimation_kthread(void *data) { struct ip_vs_est_kt_data *kd = data; struct netns_ipvs *ipvs = kd->ipvs; int row = kd->est_row; unsigned long now; int id = kd->id; long gap; if (id > 0) { if (!ipvs->est_chain_max) return 0; } else { if (!ipvs->est_chain_max) { ipvs->est_calc_phase = 1; /* commit est_calc_phase before reading est_genid */ smp_mb(); } /* kthread 0 will handle the calc phase */ if (ipvs->est_calc_phase) ip_vs_est_calc_phase(ipvs); } while (1) { if (!id && !hlist_empty(&ipvs->est_temp_list)) ip_vs_est_drain_temp_list(ipvs); set_current_state(TASK_IDLE); if (kthread_should_stop()) break; /* before estimation, check if we should sleep */ now = jiffies; gap = kd->est_timer - now; if (gap > 0) { if (gap > IPVS_EST_TICK) { kd->est_timer = now - IPVS_EST_TICK; gap = IPVS_EST_TICK; } schedule_timeout(gap); } else { __set_current_state(TASK_RUNNING); if (gap < -8 * IPVS_EST_TICK) kd->est_timer = now; } if (kd->tick_len[row]) ip_vs_tick_estimation(kd, row); row++; if (row >= IPVS_EST_NTICKS) row = 0; WRITE_ONCE(kd->est_row, row); kd->est_timer += IPVS_EST_TICK; } __set_current_state(TASK_RUNNING); return 0; } /* Schedule stop/start for kthread tasks */ void ip_vs_est_reload_start(struct netns_ipvs *ipvs) { /* Ignore reloads before first service is added */ if (!ipvs->enable) return; ip_vs_est_stopped_recalc(ipvs); /* Bump the kthread configuration genid */ atomic_inc(&ipvs->est_genid); queue_delayed_work(system_long_wq, &ipvs->est_reload_work, 0); } /* Start kthread task with current configuration */ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, struct ip_vs_est_kt_data *kd) { unsigned long now; int ret = 0; long gap; lockdep_assert_held(&ipvs->est_mutex); if (kd->task) goto out; now = jiffies; gap = kd->est_timer - now; /* Sync est_timer if task is starting later */ if (abs(gap) > 4 * IPVS_EST_TICK) kd->est_timer = now; kd->task = kthread_create(ip_vs_estimation_kthread, kd, "ipvs-e:%d:%d", ipvs->gen, kd->id); if (IS_ERR(kd->task)) { ret = PTR_ERR(kd->task); kd->task = NULL; goto out; } set_user_nice(kd->task, sysctl_est_nice(ipvs)); set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); out: return ret; } void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd) { if (kd->task) { pr_info("stopping estimator thread %d...\n", kd->id); kthread_stop(kd->task); kd->task = NULL; } } /* Apply parameters to kthread */ static void ip_vs_est_set_params(struct netns_ipvs *ipvs, struct ip_vs_est_kt_data *kd) { kd->chain_max = ipvs->est_chain_max; /* We are using single chain on RCU preemption */ if (IPVS_EST_TICK_CHAINS == 1) kd->chain_max *= IPVS_EST_CHAIN_FACTOR; kd->tick_max = IPVS_EST_TICK_CHAINS * kd->chain_max; kd->est_max_count = IPVS_EST_NTICKS * kd->tick_max; } /* Create and start estimation kthread in a free or new array slot */ static int ip_vs_est_add_kthread(struct netns_ipvs *ipvs) { struct ip_vs_est_kt_data *kd = NULL; int id = ipvs->est_kt_count; int ret = -ENOMEM; void *arr = NULL; int i; if ((unsigned long)ipvs->est_kt_count >= ipvs->est_max_threads && ipvs->enable && ipvs->est_max_threads) return -EINVAL; mutex_lock(&ipvs->est_mutex); for (i = 0; i < id; i++) { if (!ipvs->est_kt_arr[i]) break; } if (i >= id) { arr = krealloc_array(ipvs->est_kt_arr, id + 1, sizeof(struct ip_vs_est_kt_data *), GFP_KERNEL); if (!arr) goto out; ipvs->est_kt_arr = arr; } else { id = i; } kd = kzalloc(sizeof(*kd), GFP_KERNEL); if (!kd) goto out; kd->ipvs = ipvs; bitmap_fill(kd->avail, IPVS_EST_NTICKS); kd->est_timer = jiffies; kd->id = id; ip_vs_est_set_params(ipvs, kd); /* Pre-allocate stats used in calc phase */ if (!id && !kd->calc_stats) { kd->calc_stats = ip_vs_stats_alloc(); if (!kd->calc_stats) goto out; } /* Start kthread tasks only when services are present */ if (ipvs->enable && !ip_vs_est_stopped(ipvs)) { ret = ip_vs_est_kthread_start(ipvs, kd); if (ret < 0) goto out; } if (arr) ipvs->est_kt_count++; ipvs->est_kt_arr[id] = kd; kd = NULL; /* Use most recent kthread for new ests */ ipvs->est_add_ktid = id; ret = 0; out: mutex_unlock(&ipvs->est_mutex); if (kd) { ip_vs_stats_free(kd->calc_stats); kfree(kd); } return ret; } /* Select ktid where to add new ests: available, unused or new slot */ static void ip_vs_est_update_ktid(struct netns_ipvs *ipvs) { int ktid, best = ipvs->est_kt_count; struct ip_vs_est_kt_data *kd; for (ktid = 0; ktid < ipvs->est_kt_count; ktid++) { kd = ipvs->est_kt_arr[ktid]; if (kd) { if (kd->est_count < kd->est_max_count) { best = ktid; break; } } else if (ktid < best) { best = ktid; } } ipvs->est_add_ktid = best; } /* Add estimator to current kthread (est_add_ktid) */ static int ip_vs_enqueue_estimator(struct netns_ipvs *ipvs, struct ip_vs_estimator *est) { struct ip_vs_est_kt_data *kd = NULL; struct ip_vs_est_tick_data *td; int ktid, row, crow, cid, ret; int delay = est->ktrow; BUILD_BUG_ON_MSG(IPVS_EST_TICK_CHAINS > 127, "Too many chains for ktcid"); if (ipvs->est_add_ktid < ipvs->est_kt_count) { kd = ipvs->est_kt_arr[ipvs->est_add_ktid]; if (kd) goto add_est; } ret = ip_vs_est_add_kthread(ipvs); if (ret < 0) goto out; kd = ipvs->est_kt_arr[ipvs->est_add_ktid]; add_est: ktid = kd->id; /* For small number of estimators prefer to use few ticks, * otherwise try to add into the last estimated row. * est_row and add_row point after the row we should use */ if (kd->est_count >= 2 * kd->tick_max || delay < IPVS_EST_NTICKS - 1) crow = READ_ONCE(kd->est_row); else crow = kd->add_row; crow += delay; if (crow >= IPVS_EST_NTICKS) crow -= IPVS_EST_NTICKS; /* Assume initial delay ? */ if (delay >= IPVS_EST_NTICKS - 1) { /* Preserve initial delay or decrease it if no space in tick */ row = crow; if (crow < IPVS_EST_NTICKS - 1) { crow++; row = find_last_bit(kd->avail, crow); } if (row >= crow) row = find_last_bit(kd->avail, IPVS_EST_NTICKS); } else { /* Preserve delay or increase it if no space in tick */ row = IPVS_EST_NTICKS; if (crow > 0) row = find_next_bit(kd->avail, IPVS_EST_NTICKS, crow); if (row >= IPVS_EST_NTICKS) row = find_first_bit(kd->avail, IPVS_EST_NTICKS); } td = rcu_dereference_protected(kd->ticks[row], 1); if (!td) { td = kzalloc(sizeof(*td), GFP_KERNEL); if (!td) { ret = -ENOMEM; goto out; } rcu_assign_pointer(kd->ticks[row], td); } cid = find_first_zero_bit(td->full, IPVS_EST_TICK_CHAINS); kd->est_count++; kd->tick_len[row]++; if (!td->chain_len[cid]) __set_bit(cid, td->present); td->chain_len[cid]++; est->ktid = ktid; est->ktrow = row; est->ktcid = cid; hlist_add_head_rcu(&est->list, &td->chains[cid]); if (td->chain_len[cid] >= kd->chain_max) { __set_bit(cid, td->full); if (kd->tick_len[row] >= kd->tick_max) __clear_bit(row, kd->avail); } /* Update est_add_ktid to point to first available/empty kt slot */ if (kd->est_count == kd->est_max_count) ip_vs_est_update_ktid(ipvs); ret = 0; out: return ret; } /* Start estimation for stats */ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { struct ip_vs_estimator *est = &stats->est; int ret; if (!ipvs->est_max_threads && ipvs->enable) ipvs->est_max_threads = ip_vs_est_max_threads(ipvs); est->ktid = -1; est->ktrow = IPVS_EST_NTICKS - 1; /* Initial delay */ /* We prefer this code to be short, kthread 0 will requeue the * estimator to available chain. If tasks are disabled, we * will not allocate much memory, just for kt 0. */ ret = 0; if (!ipvs->est_kt_count || !ipvs->est_kt_arr[0]) ret = ip_vs_est_add_kthread(ipvs); if (ret >= 0) hlist_add_head(&est->list, &ipvs->est_temp_list); else INIT_HLIST_NODE(&est->list); return ret; } static void ip_vs_est_kthread_destroy(struct ip_vs_est_kt_data *kd) { if (kd) { if (kd->task) { pr_info("stop unused estimator thread %d...\n", kd->id); kthread_stop(kd->task); } ip_vs_stats_free(kd->calc_stats); kfree(kd); } } /* Unlink estimator from chain */ void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { struct ip_vs_estimator *est = &stats->est; struct ip_vs_est_tick_data *td; struct ip_vs_est_kt_data *kd; int ktid = est->ktid; int row = est->ktrow; int cid = est->ktcid; /* Failed to add to chain ? */ if (hlist_unhashed(&est->list)) return; /* On return, estimator can be freed, dequeue it now */ /* In est_temp_list ? */ if (ktid < 0) { hlist_del(&est->list); goto end_kt0; } hlist_del_rcu(&est->list); kd = ipvs->est_kt_arr[ktid]; td = rcu_dereference_protected(kd->ticks[row], 1); __clear_bit(cid, td->full); td->chain_len[cid]--; if (!td->chain_len[cid]) __clear_bit(cid, td->present); kd->tick_len[row]--; __set_bit(row, kd->avail); if (!kd->tick_len[row]) { RCU_INIT_POINTER(kd->ticks[row], NULL); kfree_rcu(td, rcu_head); } kd->est_count--; if (kd->est_count) { /* This kt slot can become available just now, prefer it */ if (ktid < ipvs->est_add_ktid) ipvs->est_add_ktid = ktid; return; } if (ktid > 0) { mutex_lock(&ipvs->est_mutex); ip_vs_est_kthread_destroy(kd); ipvs->est_kt_arr[ktid] = NULL; if (ktid == ipvs->est_kt_count - 1) { ipvs->est_kt_count--; while (ipvs->est_kt_count > 1 && !ipvs->est_kt_arr[ipvs->est_kt_count - 1]) ipvs->est_kt_count--; } mutex_unlock(&ipvs->est_mutex); /* This slot is now empty, prefer another available kt slot */ if (ktid == ipvs->est_add_ktid) ip_vs_est_update_ktid(ipvs); } end_kt0: /* kt 0 is freed after all other kthreads and chains are empty */ if (ipvs->est_kt_count == 1 && hlist_empty(&ipvs->est_temp_list)) { kd = ipvs->est_kt_arr[0]; if (!kd || !kd->est_count) { mutex_lock(&ipvs->est_mutex); if (kd) { ip_vs_est_kthread_destroy(kd); ipvs->est_kt_arr[0] = NULL; } ipvs->est_kt_count--; mutex_unlock(&ipvs->est_mutex); ipvs->est_add_ktid = 0; } } } /* Register all ests from est_temp_list to kthreads */ static void ip_vs_est_drain_temp_list(struct netns_ipvs *ipvs) { struct ip_vs_estimator *est; while (1) { int max = 16; mutex_lock(&__ip_vs_mutex); while (max-- > 0) { est = hlist_entry_safe(ipvs->est_temp_list.first, struct ip_vs_estimator, list); if (est) { if (kthread_should_stop()) goto unlock; hlist_del_init(&est->list); if (ip_vs_enqueue_estimator(ipvs, est) >= 0) continue; est->ktid = -1; hlist_add_head(&est->list, &ipvs->est_temp_list); /* Abort, some entries will not be estimated * until next attempt */ } goto unlock; } mutex_unlock(&__ip_vs_mutex); cond_resched(); } unlock: mutex_unlock(&__ip_vs_mutex); } /* Calculate limits for all kthreads */ static int ip_vs_est_calc_limits(struct netns_ipvs *ipvs, int *chain_max) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct ip_vs_est_kt_data *kd; struct hlist_head chain; struct ip_vs_stats *s; int cache_factor = 4; int i, loops, ntest; s32 min_est = 0; ktime_t t1, t2; int max = 8; int ret = 1; s64 diff; u64 val; INIT_HLIST_HEAD(&chain); mutex_lock(&__ip_vs_mutex); kd = ipvs->est_kt_arr[0]; mutex_unlock(&__ip_vs_mutex); s = kd ? kd->calc_stats : NULL; if (!s) goto out; hlist_add_head(&s->est.list, &chain); loops = 1; /* Get best result from many tests */ for (ntest = 0; ntest < 12; ntest++) { if (!(ntest & 3)) { /* Wait for cpufreq frequency transition */ wait_event_idle_timeout(wq, kthread_should_stop(), HZ / 50); if (!ipvs->enable || kthread_should_stop()) goto stop; } local_bh_disable(); rcu_read_lock(); /* Put stats in cache */ ip_vs_chain_estimation(&chain); t1 = ktime_get(); for (i = loops * cache_factor; i > 0; i--) ip_vs_chain_estimation(&chain); t2 = ktime_get(); rcu_read_unlock(); local_bh_enable(); if (!ipvs->enable || kthread_should_stop()) goto stop; cond_resched(); diff = ktime_to_ns(ktime_sub(t2, t1)); if (diff <= 1 * NSEC_PER_USEC) { /* Do more loops on low time resolution */ loops *= 2; continue; } if (diff >= NSEC_PER_SEC) continue; val = diff; do_div(val, loops); if (!min_est || val < min_est) { min_est = val; /* goal: 95usec per chain */ val = 95 * NSEC_PER_USEC; if (val >= min_est) { do_div(val, min_est); max = (int)val; } else { max = 1; } } } out: if (s) hlist_del_init(&s->est.list); *chain_max = max; return ret; stop: ret = 0; goto out; } /* Calculate the parameters and apply them in context of kt #0 * ECP: est_calc_phase * ECM: est_chain_max * ECP ECM Insert Chain enable Description * --------------------------------------------------------------------------- * 0 0 est_temp_list 0 create kt #0 context * 0 0 est_temp_list 0->1 service added, start kthread #0 task * 0->1 0 est_temp_list 1 kt task #0 started, enters calc phase * 1 0 est_temp_list 1 kt #0: determine est_chain_max, * stop tasks, move ests to est_temp_list * and free kd for kthreads 1..last * 1->0 0->N kt chains 1 ests can go to kthreads * 0 N kt chains 1 drain est_temp_list, create new kthread * contexts, start tasks, estimate */ static void ip_vs_est_calc_phase(struct netns_ipvs *ipvs) { int genid = atomic_read(&ipvs->est_genid); struct ip_vs_est_tick_data *td; struct ip_vs_est_kt_data *kd; struct ip_vs_estimator *est; struct ip_vs_stats *stats; int id, row, cid, delay; bool last, last_td; int chain_max; int step; if (!ip_vs_est_calc_limits(ipvs, &chain_max)) return; mutex_lock(&__ip_vs_mutex); /* Stop all other tasks, so that we can immediately move the * estimators to est_temp_list without RCU grace period */ mutex_lock(&ipvs->est_mutex); for (id = 1; id < ipvs->est_kt_count; id++) { /* netns clean up started, abort */ if (!ipvs->enable) goto unlock2; kd = ipvs->est_kt_arr[id]; if (!kd) continue; ip_vs_est_kthread_stop(kd); } mutex_unlock(&ipvs->est_mutex); /* Move all estimators to est_temp_list but carefully, * all estimators and kthread data can be released while * we reschedule. Even for kthread 0. */ step = 0; /* Order entries in est_temp_list in ascending delay, so now * walk delay(desc), id(desc), cid(asc) */ delay = IPVS_EST_NTICKS; next_delay: delay--; if (delay < 0) goto end_dequeue; last_kt: /* Destroy contexts backwards */ id = ipvs->est_kt_count; next_kt: if (!ipvs->enable || kthread_should_stop()) goto unlock; id--; if (id < 0) goto next_delay; kd = ipvs->est_kt_arr[id]; if (!kd) goto next_kt; /* kt 0 can exist with empty chains */ if (!id && kd->est_count <= 1) goto next_delay; row = kd->est_row + delay; if (row >= IPVS_EST_NTICKS) row -= IPVS_EST_NTICKS; td = rcu_dereference_protected(kd->ticks[row], 1); if (!td) goto next_kt; cid = 0; walk_chain: if (kthread_should_stop()) goto unlock; step++; if (!(step & 63)) { /* Give chance estimators to be added (to est_temp_list) * and deleted (releasing kthread contexts) */ mutex_unlock(&__ip_vs_mutex); cond_resched(); mutex_lock(&__ip_vs_mutex); /* Current kt released ? */ if (id >= ipvs->est_kt_count) goto last_kt; if (kd != ipvs->est_kt_arr[id]) goto next_kt; /* Current td released ? */ if (td != rcu_dereference_protected(kd->ticks[row], 1)) goto next_kt; /* No fatal changes on the current kd and td */ } est = hlist_entry_safe(td->chains[cid].first, struct ip_vs_estimator, list); if (!est) { cid++; if (cid >= IPVS_EST_TICK_CHAINS) goto next_kt; goto walk_chain; } /* We can cheat and increase est_count to protect kt 0 context * from release but we prefer to keep the last estimator */ last = kd->est_count <= 1; /* Do not free kt #0 data */ if (!id && last) goto next_delay; last_td = kd->tick_len[row] <= 1; stats = container_of(est, struct ip_vs_stats, est); ip_vs_stop_estimator(ipvs, stats); /* Tasks are stopped, move without RCU grace period */ est->ktid = -1; est->ktrow = row - kd->est_row; if (est->ktrow < 0) est->ktrow += IPVS_EST_NTICKS; hlist_add_head(&est->list, &ipvs->est_temp_list); /* kd freed ? */ if (last) goto next_kt; /* td freed ? */ if (last_td) goto next_kt; goto walk_chain; end_dequeue: /* All estimators removed while calculating ? */ if (!ipvs->est_kt_count) goto unlock; kd = ipvs->est_kt_arr[0]; if (!kd) goto unlock; kd->add_row = kd->est_row; ipvs->est_chain_max = chain_max; ip_vs_est_set_params(ipvs, kd); pr_info("using max %d ests per chain, %d per kthread\n", kd->chain_max, kd->est_max_count); /* Try to keep tot_stats in kt0, enqueue it early */ if (ipvs->tot_stats && !hlist_unhashed(&ipvs->tot_stats->s.est.list) && ipvs->tot_stats->s.est.ktid == -1) { hlist_del(&ipvs->tot_stats->s.est.list); hlist_add_head(&ipvs->tot_stats->s.est.list, &ipvs->est_temp_list); } mutex_lock(&ipvs->est_mutex); /* We completed the calc phase, new calc phase not requested */ if (genid == atomic_read(&ipvs->est_genid)) ipvs->est_calc_phase = 0; unlock2: mutex_unlock(&ipvs->est_mutex); unlock: mutex_unlock(&__ip_vs_mutex); } void ip_vs_zero_estimator(struct ip_vs_stats *stats) { struct ip_vs_estimator *est = &stats->est; struct ip_vs_kstats *k = &stats->kstats; /* reset counters, caller must hold the stats->lock lock */ est->last_inbytes = k->inbytes; est->last_outbytes = k->outbytes; est->last_conns = k->conns; est->last_inpkts = k->inpkts; est->last_outpkts = k->outpkts; est->cps = 0; est->inpps = 0; est->outpps = 0; est->inbps = 0; est->outbps = 0; } /* Get decoded rates */ void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats) { struct ip_vs_estimator *e = &stats->est; dst->cps = (e->cps + 0x1FF) >> 10; dst->inpps = (e->inpps + 0x1FF) >> 10; dst->outpps = (e->outpps + 0x1FF) >> 10; dst->inbps = (e->inbps + 0xF) >> 5; dst->outbps = (e->outbps + 0xF) >> 5; } int __net_init ip_vs_estimator_net_init(struct netns_ipvs *ipvs) { INIT_HLIST_HEAD(&ipvs->est_temp_list); ipvs->est_kt_arr = NULL; ipvs->est_max_threads = 0; ipvs->est_calc_phase = 0; ipvs->est_chain_max = 0; ipvs->est_kt_count = 0; ipvs->est_add_ktid = 0; atomic_set(&ipvs->est_genid, 0); atomic_set(&ipvs->est_genid_done, 0); __mutex_init(&ipvs->est_mutex, "ipvs->est_mutex", &__ipvs_est_key); return 0; } void __net_exit ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs) { int i; for (i = 0; i < ipvs->est_kt_count; i++) ip_vs_est_kthread_destroy(ipvs->est_kt_arr[i]); kfree(ipvs->est_kt_arr); mutex_destroy(&ipvs->est_mutex); } |
| 41 531 532 41 532 531 532 1483 936 73 532 910 957 58 58 1 1 1 1 60 59 67 1 66 66 66 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 | // SPDX-License-Identifier: GPL-2.0-only /* * Pid namespaces * * Authors: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/pid.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/syscalls.h> #include <linux/cred.h> #include <linux/err.h> #include <linux/acct.h> #include <linux/slab.h> #include <linux/proc_ns.h> #include <linux/reboot.h> #include <linux/export.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/idr.h> #include <uapi/linux/wait.h> #include "pid_sysctl.h" static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; /* Write once array, filled from the beginning. */ static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL]; /* * creates the kmem cache to allocate pids from. * @level: pid namespace level */ static struct kmem_cache *create_pid_cachep(unsigned int level) { /* Level 0 is init_pid_ns.pid_cachep */ struct kmem_cache **pkc = &pid_cache[level - 1]; struct kmem_cache *kc; char name[4 + 10 + 1]; unsigned int len; kc = READ_ONCE(*pkc); if (kc) return kc; snprintf(name, sizeof(name), "pid_%u", level + 1); len = struct_size_t(struct pid, numbers, level + 1); mutex_lock(&pid_caches_mutex); /* Name collision forces to do allocation under mutex. */ if (!*pkc) *pkc = kmem_cache_create(name, len, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); mutex_unlock(&pid_caches_mutex); /* current can fail, but someone else can succeed. */ return READ_ONCE(*pkc); } static struct ucounts *inc_pid_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES); } static void dec_pid_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_PID_NAMESPACES); } static void destroy_pid_namespace_work(struct work_struct *work); static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; unsigned int level = parent_pid_ns->level + 1; struct ucounts *ucounts; int err; err = -EINVAL; if (!in_userns(parent_pid_ns->user_ns, user_ns)) goto out; err = -ENOSPC; if (level > MAX_PID_NS_LEVEL) goto out; ucounts = inc_pid_namespaces(user_ns); if (!ucounts) goto out; err = -ENOMEM; ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL); if (ns == NULL) goto out_dec; idr_init(&ns->idr); ns->pid_cachep = create_pid_cachep(level); if (ns->pid_cachep == NULL) goto out_free_idr; err = ns_alloc_inum(&ns->ns); if (err) goto out_free_idr; ns->ns.ops = &pidns_operations; ns->pid_max = PID_MAX_LIMIT; err = register_pidns_sysctls(ns); if (err) goto out_free_inum; refcount_set(&ns->ns.count, 1); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; INIT_WORK(&ns->work, destroy_pid_namespace_work); #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) ns->memfd_noexec_scope = pidns_memfd_noexec_scope(parent_pid_ns); #endif return ns; out_free_inum: ns_free_inum(&ns->ns); out_free_idr: idr_destroy(&ns->idr); kmem_cache_free(pid_ns_cachep, ns); out_dec: dec_pid_namespaces(ucounts); out: return ERR_PTR(err); } static void delayed_free_pidns(struct rcu_head *p) { struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu); dec_pid_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kmem_cache_free(pid_ns_cachep, ns); } static void destroy_pid_namespace(struct pid_namespace *ns) { unregister_pidns_sysctls(ns); ns_free_inum(&ns->ns); idr_destroy(&ns->idr); call_rcu(&ns->rcu, delayed_free_pidns); } static void destroy_pid_namespace_work(struct work_struct *work) { struct pid_namespace *ns = container_of(work, struct pid_namespace, work); do { struct pid_namespace *parent; parent = ns->parent; destroy_pid_namespace(ns); ns = parent; } while (ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count)); } struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *old_ns) { if (!(flags & CLONE_NEWPID)) return get_pid_ns(old_ns); if (task_active_pid_ns(current) != old_ns) return ERR_PTR(-EINVAL); return create_pid_namespace(user_ns, old_ns); } void put_pid_ns(struct pid_namespace *ns) { if (ns && ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count)) schedule_work(&ns->work); } EXPORT_SYMBOL_GPL(put_pid_ns); void zap_pid_ns_processes(struct pid_namespace *pid_ns) { int nr; int rc; struct task_struct *task, *me = current; int init_pids = thread_group_leader(me) ? 1 : 2; struct pid *pid; /* Don't allow any more processes into the pid namespace */ disable_pid_allocation(pid_ns); /* * Ignore SIGCHLD causing any terminated children to autoreap. * This speeds up the namespace shutdown, plus see the comment * below. */ spin_lock_irq(&me->sighand->siglock); me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN; spin_unlock_irq(&me->sighand->siglock); /* * The last thread in the cgroup-init thread group is terminating. * Find remaining pid_ts in the namespace, signal and wait for them * to exit. * * Note: This signals each threads in the namespace - even those that * belong to the same thread group, To avoid this, we would have * to walk the entire tasklist looking a processes in this * namespace, but that could be unnecessarily expensive if the * pid namespace has just a few processes. Or we need to * maintain a tasklist for each pid namespace. * */ rcu_read_lock(); read_lock(&tasklist_lock); nr = 2; idr_for_each_entry_continue(&pid_ns->idr, pid, nr) { task = pid_task(pid, PIDTYPE_PID); if (task && !__fatal_signal_pending(task)) group_send_sig_info(SIGKILL, SEND_SIG_PRIV, task, PIDTYPE_MAX); } read_unlock(&tasklist_lock); rcu_read_unlock(); /* * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD. * kernel_wait4() will also block until our children traced from the * parent namespace are detached and become EXIT_DEAD. */ do { clear_thread_flag(TIF_SIGPENDING); clear_thread_flag(TIF_NOTIFY_SIGNAL); rc = kernel_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); /* * kernel_wait4() misses EXIT_DEAD children, and EXIT_ZOMBIE * process whose parents processes are outside of the pid * namespace. Such processes are created with setns()+fork(). * * If those EXIT_ZOMBIE processes are not reaped by their * parents before their parents exit, they will be reparented * to pid_ns->child_reaper. Thus pidns->child_reaper needs to * stay valid until they all go away. * * The code relies on the pid_ns->child_reaper ignoring * SIGCHILD to cause those EXIT_ZOMBIE processes to be * autoreaped if reparented. * * Semantically it is also desirable to wait for EXIT_ZOMBIE * processes before allowing the child_reaper to be reaped, as * that gives the invariant that when the init process of a * pid namespace is reaped all of the processes in the pid * namespace are gone. * * Once all of the other tasks are gone from the pid_namespace * free_pid() will awaken this task. */ for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->pid_allocated == init_pids) break; schedule(); } __set_current_state(TASK_RUNNING); if (pid_ns->reboot) current->signal->group_exit_code = pid_ns->reboot; acct_exit_ns(pid_ns); return; } #ifdef CONFIG_CHECKPOINT_RESTORE static int pid_ns_ctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct pid_namespace *pid_ns = task_active_pid_ns(current); struct ctl_table tmp = *table; int ret, next; if (write && !checkpoint_restore_ns_capable(pid_ns->user_ns)) return -EPERM; next = idr_get_cursor(&pid_ns->idr) - 1; tmp.data = &next; tmp.extra2 = &pid_ns->pid_max; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (!ret && write) idr_set_cursor(&pid_ns->idr, next + 1); return ret; } static const struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, .extra1 = SYSCTL_ZERO, .extra2 = &init_pid_ns.pid_max, }, }; #endif /* CONFIG_CHECKPOINT_RESTORE */ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { if (pid_ns == &init_pid_ns) return 0; switch (cmd) { case LINUX_REBOOT_CMD_RESTART2: case LINUX_REBOOT_CMD_RESTART: pid_ns->reboot = SIGHUP; break; case LINUX_REBOOT_CMD_POWER_OFF: case LINUX_REBOOT_CMD_HALT: pid_ns->reboot = SIGINT; break; default: return -EINVAL; } read_lock(&tasklist_lock); send_sig(SIGKILL, pid_ns->child_reaper, 1); read_unlock(&tasklist_lock); do_exit(0); /* Not reached */ return 0; } static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) { return container_of(ns, struct pid_namespace, ns); } static struct ns_common *pidns_get(struct task_struct *task) { struct pid_namespace *ns; rcu_read_lock(); ns = task_active_pid_ns(task); if (ns) get_pid_ns(ns); rcu_read_unlock(); return ns ? &ns->ns : NULL; } static struct ns_common *pidns_for_children_get(struct task_struct *task) { struct pid_namespace *ns = NULL; task_lock(task); if (task->nsproxy) { ns = task->nsproxy->pid_ns_for_children; get_pid_ns(ns); } task_unlock(task); if (ns) { read_lock(&tasklist_lock); if (!ns->child_reaper) { put_pid_ns(ns); ns = NULL; } read_unlock(&tasklist_lock); } return ns ? &ns->ns : NULL; } static void pidns_put(struct ns_common *ns) { put_pid_ns(to_pid_ns(ns)); } static int pidns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *ancestor, *new = to_pid_ns(ns); if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* * Only allow entering the current active pid namespace * or a child of the current active pid namespace. * * This is required for fork to return a usable pid value and * this maintains the property that processes and their * children can not escape their current pid namespace. */ if (new->level < active->level) return -EINVAL; ancestor = new; while (ancestor->level > active->level) ancestor = ancestor->parent; if (ancestor != active) return -EINVAL; put_pid_ns(nsproxy->pid_ns_for_children); nsproxy->pid_ns_for_children = get_pid_ns(new); return 0; } static struct ns_common *pidns_get_parent(struct ns_common *ns) { struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *pid_ns, *p; /* See if the parent is in the current namespace */ pid_ns = p = to_pid_ns(ns)->parent; for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == active) break; p = p->parent; } return &get_pid_ns(pid_ns)->ns; } static struct user_namespace *pidns_owner(struct ns_common *ns) { return to_pid_ns(ns)->user_ns; } const struct proc_ns_operations pidns_operations = { .name = "pid", .type = CLONE_NEWPID, .get = pidns_get, .put = pidns_put, .install = pidns_install, .owner = pidns_owner, .get_parent = pidns_get_parent, }; const struct proc_ns_operations pidns_for_children_operations = { .name = "pid_for_children", .real_ns_name = "pid", .type = CLONE_NEWPID, .get = pidns_for_children_get, .put = pidns_put, .install = pidns_install, .owner = pidns_owner, .get_parent = pidns_get_parent, }; static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC | SLAB_ACCOUNT); #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_init("kernel", pid_ns_ctl_table); #endif register_pid_ns_sysctl_table_vm(); return 0; } __initcall(pid_namespaces_init); |
| 6617 6617 7 7 9212 6616 6616 6617 6617 6618 6618 6617 6616 6614 6617 6616 6616 6616 6616 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 | // SPDX-License-Identifier: GPL-2.0 /* * ring buffer based function tracer * * Copyright (C) 2007-2012 Steven Rostedt <srostedt@redhat.com> * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> * * Originally taken from the RT patch by: * Arnaldo Carvalho de Melo <acme@redhat.com> * * Based on code from the latency_tracer, that is: * Copyright (C) 2004-2006 Ingo Molnar * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/ring_buffer.h> #include <linux/utsname.h> #include <linux/stacktrace.h> #include <linux/writeback.h> #include <linux/kallsyms.h> #include <linux/security.h> #include <linux/seq_file.h> #include <linux/irqflags.h> #include <linux/debugfs.h> #include <linux/tracefs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> #include <linux/linkage.h> #include <linux/uaccess.h> #include <linux/cleanup.h> #include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/splice.h> #include <linux/kdebug.h> #include <linux/string.h> #include <linux/mount.h> #include <linux/rwsem.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/init.h> #include <linux/panic_notifier.h> #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> #include <linux/trace.h> #include <linux/sched/clock.h> #include <linux/sched/rt.h> #include <linux/fsnotify.h> #include <linux/irq_work.h> #include <linux/workqueue.h> #include <asm/setup.h> /* COMMAND_LINE_SIZE */ #include "trace.h" #include "trace_output.h" #ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the * entries inserted during the selftest although some concurrent * insertions into the ring-buffer such as trace_printk could occurred * at the same time, giving false positive or negative results. */ static bool __read_mostly tracing_selftest_running; /* * If boot-time tracing including tracers/events via kernel cmdline * is running, we do not want to run SELFTEST. */ bool __read_mostly tracing_selftest_disabled; void __init disable_tracing_selftest(const char *reason) { if (!tracing_selftest_disabled) { tracing_selftest_disabled = true; pr_info("Ftrace startup test is disabled due to %s\n", reason); } } #else #define tracing_selftest_running 0 #define tracing_selftest_disabled 0 #endif /* Pipe tracepoints to printk */ static struct trace_iterator *tracepoint_print_iter; int tracepoint_printk; static bool tracepoint_printk_stop_on_boot __initdata; static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key); /* For tracers that don't implement custom flags */ static struct tracer_opt dummy_tracer_opt[] = { { } }; static int dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return 0; } /* * To prevent the comm cache from being overwritten when no * tracing is active, only save the comm when a trace event * occurred. */ DEFINE_PER_CPU(bool, trace_taskinfo_save); /* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization * of the tracer is successful. But that is the only place that sets * this back to zero. */ static int tracing_disabled = 1; cpumask_var_t __read_mostly tracing_buffer_mask; /* * ftrace_dump_on_oops - variable to dump ftrace buffer on oops * * If there is an oops (or kernel panic) and the ftrace_dump_on_oops * is set, then ftrace_dump is called. This will output the contents * of the ftrace buffers to the console. This is very useful for * capturing traces that lead to crashes and outputing it to a * serial console. * * It is default off, but you can enable it with either specifying * "ftrace_dump_on_oops" in the kernel command line, or setting * /proc/sys/kernel/ftrace_dump_on_oops * Set 1 if you want to dump buffers of all CPUs * Set 2 if you want to dump the buffer of the CPU that triggered oops * Set instance name if you want to dump the specific trace instance * Multiple instance dump is also supported, and instances are seperated * by commas. */ /* Set to string format zero to disable by default */ char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; /* When set, tracing will stop when a WARN*() is hit */ int __disable_trace_on_warning; #ifdef CONFIG_TRACE_EVAL_MAP_FILE /* Map of enums to their values, for "eval_map" file */ struct trace_eval_map_head { struct module *mod; unsigned long length; }; union trace_eval_map_item; struct trace_eval_map_tail { /* * "end" is first and points to NULL as it must be different * than "mod" or "eval_string" */ union trace_eval_map_item *next; const char *end; /* points to NULL */ }; static DEFINE_MUTEX(trace_eval_mutex); /* * The trace_eval_maps are saved in an array with two extra elements, * one at the beginning, and one at the end. The beginning item contains * the count of the saved maps (head.length), and the module they * belong to if not built in (head.mod). The ending item contains a * pointer to the next array of saved eval_map items. */ union trace_eval_map_item { struct trace_eval_map map; struct trace_eval_map_head head; struct trace_eval_map_tail tail; }; static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ int tracing_set_tracer(struct trace_array *tr, const char *buf); static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx); static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; static bool allocate_snapshot; static bool snapshot_at_boot; static char boot_instance_info[COMMAND_LINE_SIZE] __initdata; static int boot_instance_index; static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata; static int boot_snapshot_index; static int __init set_cmdline_ftrace(char *str) { strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ trace_set_ring_buffer_expanded(NULL); return 1; } __setup("ftrace=", set_cmdline_ftrace); int ftrace_dump_on_oops_enabled(void) { if (!strcmp("0", ftrace_dump_on_oops)) return 0; else return 1; } static int __init set_ftrace_dump_on_oops(char *str) { if (!*str) { strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); return 1; } if (*str == ',') { strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); strscpy(ftrace_dump_on_oops + 1, str, MAX_TRACER_SIZE - 1); return 1; } if (*str++ == '=') { strscpy(ftrace_dump_on_oops, str, MAX_TRACER_SIZE); return 1; } return 0; } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); static int __init stop_trace_on_warning(char *str) { if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) __disable_trace_on_warning = 1; return 1; } __setup("traceoff_on_warning", stop_trace_on_warning); static int __init boot_alloc_snapshot(char *str) { char *slot = boot_snapshot_info + boot_snapshot_index; int left = sizeof(boot_snapshot_info) - boot_snapshot_index; int ret; if (str[0] == '=') { str++; if (strlen(str) >= left) return -1; ret = snprintf(slot, left, "%s\t", str); boot_snapshot_index += ret; } else { allocate_snapshot = true; /* We also need the main ring buffer expanded */ trace_set_ring_buffer_expanded(NULL); } return 1; } __setup("alloc_snapshot", boot_alloc_snapshot); static int __init boot_snapshot(char *str) { snapshot_at_boot = true; boot_alloc_snapshot(str); return 1; } __setup("ftrace_boot_snapshot", boot_snapshot); static int __init boot_instance(char *str) { char *slot = boot_instance_info + boot_instance_index; int left = sizeof(boot_instance_info) - boot_instance_index; int ret; if (strlen(str) >= left) return -1; ret = snprintf(slot, left, "%s\t", str); boot_instance_index += ret; return 1; } __setup("trace_instance=", boot_instance); static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) { strscpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); return 1; } __setup("trace_options=", set_trace_boot_options); static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata; static char *trace_boot_clock __initdata; static int __init set_trace_boot_clock(char *str) { strscpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); trace_boot_clock = trace_boot_clock_buf; return 1; } __setup("trace_clock=", set_trace_boot_clock); static int __init set_tracepoint_printk(char *str) { /* Ignore the "tp_printk_stop_on_boot" param */ if (*str == '_') return 0; if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) tracepoint_printk = 1; return 1; } __setup("tp_printk", set_tracepoint_printk); static int __init set_tracepoint_printk_stop(char *str) { tracepoint_printk_stop_on_boot = true; return 1; } __setup("tp_printk_stop_on_boot", set_tracepoint_printk_stop); unsigned long long ns2usecs(u64 nsec) { nsec += 500; do_div(nsec, 1000); return nsec; } static void trace_process_export(struct trace_export *export, struct ring_buffer_event *event, int flag) { struct trace_entry *entry; unsigned int size = 0; if (export->flags & flag) { entry = ring_buffer_event_data(event); size = ring_buffer_event_length(event); export->write(export, entry, size); } } static DEFINE_MUTEX(ftrace_export_lock); static struct trace_export __rcu *ftrace_exports_list __read_mostly; static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled); static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled); static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled); static inline void ftrace_exports_enable(struct trace_export *export) { if (export->flags & TRACE_EXPORT_FUNCTION) static_branch_inc(&trace_function_exports_enabled); if (export->flags & TRACE_EXPORT_EVENT) static_branch_inc(&trace_event_exports_enabled); if (export->flags & TRACE_EXPORT_MARKER) static_branch_inc(&trace_marker_exports_enabled); } static inline void ftrace_exports_disable(struct trace_export *export) { if (export->flags & TRACE_EXPORT_FUNCTION) static_branch_dec(&trace_function_exports_enabled); if (export->flags & TRACE_EXPORT_EVENT) static_branch_dec(&trace_event_exports_enabled); if (export->flags & TRACE_EXPORT_MARKER) static_branch_dec(&trace_marker_exports_enabled); } static void ftrace_exports(struct ring_buffer_event *event, int flag) { struct trace_export *export; preempt_disable_notrace(); export = rcu_dereference_raw_check(ftrace_exports_list); while (export) { trace_process_export(export, event, flag); export = rcu_dereference_raw_check(export->next); } preempt_enable_notrace(); } static inline void add_trace_export(struct trace_export **list, struct trace_export *export) { rcu_assign_pointer(export->next, *list); /* * We are entering export into the list but another * CPU might be walking that list. We need to make sure * the export->next pointer is valid before another CPU sees * the export pointer included into the list. */ rcu_assign_pointer(*list, export); } static inline int rm_trace_export(struct trace_export **list, struct trace_export *export) { struct trace_export **p; for (p = list; *p != NULL; p = &(*p)->next) if (*p == export) break; if (*p != export) return -1; rcu_assign_pointer(*p, (*p)->next); return 0; } static inline void add_ftrace_export(struct trace_export **list, struct trace_export *export) { ftrace_exports_enable(export); add_trace_export(list, export); } static inline int rm_ftrace_export(struct trace_export **list, struct trace_export *export) { int ret; ret = rm_trace_export(list, export); ftrace_exports_disable(export); return ret; } int register_ftrace_export(struct trace_export *export) { if (WARN_ON_ONCE(!export->write)) return -1; mutex_lock(&ftrace_export_lock); add_ftrace_export(&ftrace_exports_list, export); mutex_unlock(&ftrace_export_lock); return 0; } EXPORT_SYMBOL_GPL(register_ftrace_export); int unregister_ftrace_export(struct trace_export *export) { int ret; mutex_lock(&ftrace_export_lock); ret = rm_ftrace_export(&ftrace_exports_list, export); mutex_unlock(&ftrace_export_lock); return ret; } EXPORT_SYMBOL_GPL(unregister_ftrace_export); /* trace_flags holds trace_options default values */ #define TRACE_DEFAULT_FLAGS \ (FUNCTION_DEFAULT_FLAGS | \ TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | \ TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | \ TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | \ TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | \ TRACE_ITER_HASH_PTR | TRACE_ITER_TRACE_PRINTK) /* trace_options that are only supported by global_trace */ #define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK | \ TRACE_ITER_PRINTK_MSGONLY | TRACE_ITER_RECORD_CMD) /* trace_flags that are default zero for instances */ #define ZEROED_TRACE_FLAGS \ (TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK | TRACE_ITER_TRACE_PRINTK) /* * The global_trace is the descriptor that holds the top-level tracing * buffers for the live tracing. */ static struct trace_array global_trace = { .trace_flags = TRACE_DEFAULT_FLAGS, }; static struct trace_array *printk_trace = &global_trace; static __always_inline bool printk_binsafe(struct trace_array *tr) { /* * The binary format of traceprintk can cause a crash if used * by a buffer from another boot. Force the use of the * non binary version of trace_printk if the trace_printk * buffer is a boot mapped ring buffer. */ return !(tr->flags & TRACE_ARRAY_FL_BOOT); } static void update_printk_trace(struct trace_array *tr) { if (printk_trace == tr) return; printk_trace->trace_flags &= ~TRACE_ITER_TRACE_PRINTK; printk_trace = tr; tr->trace_flags |= TRACE_ITER_TRACE_PRINTK; } void trace_set_ring_buffer_expanded(struct trace_array *tr) { if (!tr) tr = &global_trace; tr->ring_buffer_expanded = true; } LIST_HEAD(ftrace_trace_arrays); int trace_array_get(struct trace_array *this_tr) { struct trace_array *tr; guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr == this_tr) { tr->ref++; return 0; } } return -ENODEV; } static void __trace_array_put(struct trace_array *this_tr) { WARN_ON(!this_tr->ref); this_tr->ref--; } /** * trace_array_put - Decrement the reference counter for this trace array. * @this_tr : pointer to the trace array * * NOTE: Use this when we no longer need the trace array returned by * trace_array_get_by_name(). This ensures the trace array can be later * destroyed. * */ void trace_array_put(struct trace_array *this_tr) { if (!this_tr) return; mutex_lock(&trace_types_lock); __trace_array_put(this_tr); mutex_unlock(&trace_types_lock); } EXPORT_SYMBOL_GPL(trace_array_put); int tracing_check_open_get_tr(struct trace_array *tr) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; if (tracing_disabled) return -ENODEV; if (tr && trace_array_get(tr) < 0) return -ENODEV; return 0; } /** * trace_find_filtered_pid - check if a pid exists in a filtered_pid list * @filtered_pids: The list of pids to check * @search_pid: The PID to find in @filtered_pids * * Returns true if @search_pid is found in @filtered_pids, and false otherwise. */ bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) { return trace_pid_list_is_set(filtered_pids, search_pid); } /** * trace_ignore_this_task - should a task be ignored for tracing * @filtered_pids: The list of pids to check * @filtered_no_pids: The list of pids not to be traced * @task: The task that should be ignored if not filtered * * Checks if @task should be traced or not from @filtered_pids. * Returns true if @task should *NOT* be traced. * Returns false if @task should be traced. */ bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct trace_pid_list *filtered_no_pids, struct task_struct *task) { /* * If filtered_no_pids is not empty, and the task's pid is listed * in filtered_no_pids, then return true. * Otherwise, if filtered_pids is empty, that means we can * trace all tasks. If it has content, then only trace pids * within filtered_pids. */ return (filtered_pids && !trace_find_filtered_pid(filtered_pids, task->pid)) || (filtered_no_pids && trace_find_filtered_pid(filtered_no_pids, task->pid)); } /** * trace_filter_add_remove_task - Add or remove a task from a pid_list * @pid_list: The list to modify * @self: The current task for fork or NULL for exit * @task: The task to add or remove * * If adding a task, if @self is defined, the task is only added if @self * is also included in @pid_list. This happens on fork and tasks should * only be added when the parent is listed. If @self is NULL, then the * @task pid will be removed from the list, which would happen on exit * of a task. */ void trace_filter_add_remove_task(struct trace_pid_list *pid_list, struct task_struct *self, struct task_struct *task) { if (!pid_list) return; /* For forks, we only add if the forking task is listed */ if (self) { if (!trace_find_filtered_pid(pid_list, self->pid)) return; } /* "self" is set for forks, and NULL for exits */ if (self) trace_pid_list_set(pid_list, task->pid); else trace_pid_list_clear(pid_list, task->pid); } /** * trace_pid_next - Used for seq_file to get to the next pid of a pid_list * @pid_list: The pid list to show * @v: The last pid that was shown (+1 the actual pid to let zero be displayed) * @pos: The position of the file * * This is used by the seq_file "next" operation to iterate the pids * listed in a trace_pid_list structure. * * Returns the pid+1 as we want to display pid of zero, but NULL would * stop the iteration. */ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) { long pid = (unsigned long)v; unsigned int next; (*pos)++; /* pid already is +1 of the actual previous bit */ if (trace_pid_list_next(pid_list, pid, &next) < 0) return NULL; pid = next; /* Return pid + 1 to allow zero to be represented */ return (void *)(pid + 1); } /** * trace_pid_start - Used for seq_file to start reading pid lists * @pid_list: The pid list to show * @pos: The position of the file * * This is used by seq_file "start" operation to start the iteration * of listing pids. * * Returns the pid+1 as we want to display pid of zero, but NULL would * stop the iteration. */ void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos) { unsigned long pid; unsigned int first; loff_t l = 0; if (trace_pid_list_first(pid_list, &first) < 0) return NULL; pid = first; /* Return pid + 1 so that zero can be the exit value */ for (pid++; pid && l < *pos; pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l)) ; return (void *)pid; } /** * trace_pid_show - show the current pid in seq_file processing * @m: The seq_file structure to write into * @v: A void pointer of the pid (+1) value to display * * Can be directly used by seq_file operations to display the current * pid value. */ int trace_pid_show(struct seq_file *m, void *v) { unsigned long pid = (unsigned long)v - 1; seq_printf(m, "%lu\n", pid); return 0; } /* 128 should be much more than enough */ #define PID_BUF_SIZE 127 int trace_pid_write(struct trace_pid_list *filtered_pids, struct trace_pid_list **new_pid_list, const char __user *ubuf, size_t cnt) { struct trace_pid_list *pid_list; struct trace_parser parser; unsigned long val; int nr_pids = 0; ssize_t read = 0; ssize_t ret; loff_t pos; pid_t pid; if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1)) return -ENOMEM; /* * Always recreate a new array. The write is an all or nothing * operation. Always create a new array when adding new pids by * the user. If the operation fails, then the current list is * not modified. */ pid_list = trace_pid_list_alloc(); if (!pid_list) { trace_parser_put(&parser); return -ENOMEM; } if (filtered_pids) { /* copy the current bits to the new max */ ret = trace_pid_list_first(filtered_pids, &pid); while (!ret) { trace_pid_list_set(pid_list, pid); ret = trace_pid_list_next(filtered_pids, pid + 1, &pid); nr_pids++; } } ret = 0; while (cnt > 0) { pos = 0; ret = trace_get_user(&parser, ubuf, cnt, &pos); if (ret < 0) break; read += ret; ubuf += ret; cnt -= ret; if (!trace_parser_loaded(&parser)) break; ret = -EINVAL; if (kstrtoul(parser.buffer, 0, &val)) break; pid = (pid_t)val; if (trace_pid_list_set(pid_list, pid) < 0) { ret = -1; break; } nr_pids++; trace_parser_clear(&parser); ret = 0; } trace_parser_put(&parser); if (ret < 0) { trace_pid_list_free(pid_list); return ret; } if (!nr_pids) { /* Cleared the list of pids */ trace_pid_list_free(pid_list); pid_list = NULL; } *new_pid_list = pid_list; return read; } static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu) { u64 ts; /* Early boot up does not have a buffer yet */ if (!buf->buffer) return trace_clock_local(); ts = ring_buffer_time_stamp(buf->buffer); ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); return ts; } u64 ftrace_now(int cpu) { return buffer_ftrace_now(&global_trace.array_buffer, cpu); } /** * tracing_is_enabled - Show if global_trace has been enabled * * Shows if the global trace has been enabled or not. It uses the * mirror flag "buffer_disabled" to be used in fast paths such as for * the irqsoff tracer. But it may be inaccurate due to races. If you * need to know the accurate state, use tracing_is_on() which is a little * slower, but accurate. */ int tracing_is_enabled(void) { /* * For quick access (irqsoff uses this in fast path), just * return the mirror variable of the state of the ring buffer. * It's a little racy, but we don't really care. */ smp_rmb(); return !global_trace.buffer_disabled; } /* * trace_buf_size is the size in bytes that is allocated * for a buffer. Note, the number of bytes is always rounded * to page size. * * This number is purposely set to a low number of 16384. * If the dump on oops happens, it will be much appreciated * to not have to wait for all that output. Anyway this can be * boot time and run time configurable. */ #define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; /* trace_types holds a link list of available tracers. */ static struct tracer *trace_types __read_mostly; /* * trace_types_lock is used to protect the trace_types list. */ DEFINE_MUTEX(trace_types_lock); /* * serialize the access of the ring buffer * * ring buffer serializes readers, but it is low level protection. * The validity of the events (which returns by ring_buffer_peek() ..etc) * are not protected by ring buffer. * * The content of events may become garbage if we allow other process consumes * these events concurrently: * A) the page of the consumed events may become a normal page * (not reader page) in ring buffer, and this page will be rewritten * by events producer. * B) The page of the consumed events may become a page for splice_read, * and this page will be returned to system. * * These primitives allow multi process access to different cpu ring buffer * concurrently. * * These primitives don't distinguish read-only and read-consume access. * Multi read-only access are also serialized. */ #ifdef CONFIG_SMP static DECLARE_RWSEM(all_cpu_access_lock); static DEFINE_PER_CPU(struct mutex, cpu_access_lock); static inline void trace_access_lock(int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { /* gain it for accessing the whole ring buffer. */ down_write(&all_cpu_access_lock); } else { /* gain it for accessing a cpu ring buffer. */ /* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */ down_read(&all_cpu_access_lock); /* Secondly block other access to this @cpu ring buffer. */ mutex_lock(&per_cpu(cpu_access_lock, cpu)); } } static inline void trace_access_unlock(int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { up_write(&all_cpu_access_lock); } else { mutex_unlock(&per_cpu(cpu_access_lock, cpu)); up_read(&all_cpu_access_lock); } } static inline void trace_access_lock_init(void) { int cpu; for_each_possible_cpu(cpu) mutex_init(&per_cpu(cpu_access_lock, cpu)); } #else static DEFINE_MUTEX(access_lock); static inline void trace_access_lock(int cpu) { (void)cpu; mutex_lock(&access_lock); } static inline void trace_access_unlock(int cpu) { (void)cpu; mutex_unlock(&access_lock); } static inline void trace_access_lock_init(void) { } #endif #ifdef CONFIG_STACKTRACE static void __ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs); static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs); #else static inline void __ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs) { } static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned long trace_ctx, int skip, struct pt_regs *regs) { } #endif static __always_inline void trace_event_setup(struct ring_buffer_event *event, int type, unsigned int trace_ctx) { struct trace_entry *ent = ring_buffer_event_data(event); tracing_generic_entry_update(ent, type, trace_ctx); } static __always_inline struct ring_buffer_event * __trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned int trace_ctx) { struct ring_buffer_event *event; event = ring_buffer_lock_reserve(buffer, len); if (event != NULL) trace_event_setup(event, type, trace_ctx); return event; } void tracer_tracing_on(struct trace_array *tr) { if (tr->array_buffer.buffer) ring_buffer_record_on(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to * know if the ring buffer has been disabled, but it can handle * races of where it gets disabled but we still do a record. * As the check is in the fast path of the tracers, it is more * important to be fast than accurate. */ tr->buffer_disabled = 0; /* Make the flag seen by readers */ smp_wmb(); } /** * tracing_on - enable tracing buffers * * This function enables tracing buffers that may have been * disabled with tracing_off. */ void tracing_on(void) { tracer_tracing_on(&global_trace); } EXPORT_SYMBOL_GPL(tracing_on); static __always_inline void __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_taskinfo_save, true); /* If this is the temp buffer, we need to commit fully */ if (this_cpu_read(trace_buffered_event) == event) { /* Length is in event->array[0] */ ring_buffer_write(buffer, event->array[0], &event->array[1]); /* Release the temp buffer */ this_cpu_dec(trace_buffered_event_cnt); /* ring_buffer_unlock_commit() enables preemption */ preempt_enable_notrace(); } else ring_buffer_unlock_commit(buffer); } int __trace_array_puts(struct trace_array *tr, unsigned long ip, const char *str, int size) { struct ring_buffer_event *event; struct trace_buffer *buffer; struct print_entry *entry; unsigned int trace_ctx; int alloc; if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; if (unlikely(tracing_selftest_running && tr == &global_trace)) return 0; if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, trace_ctx); if (!event) { size = 0; goto out; } entry = ring_buffer_event_data(event); entry->ip = ip; memcpy(&entry->buf, str, size); /* Add a newline if necessary */ if (entry->buf[size - 1] != '\n') { entry->buf[size] = '\n'; entry->buf[size + 1] = '\0'; } else entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); out: ring_buffer_nest_end(buffer); return size; } EXPORT_SYMBOL_GPL(__trace_array_puts); /** * __trace_puts - write a constant string into the trace buffer. * @ip: The address of the caller * @str: The constant string to write * @size: The size of the string. */ int __trace_puts(unsigned long ip, const char *str, int size) { return __trace_array_puts(printk_trace, ip, str, size); } EXPORT_SYMBOL_GPL(__trace_puts); /** * __trace_bputs - write the pointer to a constant string into trace buffer * @ip: The address of the caller * @str: The constant string to write to the buffer to */ int __trace_bputs(unsigned long ip, const char *str) { struct trace_array *tr = READ_ONCE(printk_trace); struct ring_buffer_event *event; struct trace_buffer *buffer; struct bputs_entry *entry; unsigned int trace_ctx; int size = sizeof(struct bputs_entry); int ret = 0; if (!printk_binsafe(tr)) return __trace_puts(ip, str, strlen(str)); if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; entry->str = str; __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); ret = 1; out: ring_buffer_nest_end(buffer); return ret; } EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT static void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; if (in_nmi()) { trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); trace_array_puts(tr, "*** snapshot is being ignored ***\n"); return; } if (!tr->allocated_snapshot) { trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); trace_array_puts(tr, "*** stopping trace here! ***\n"); tracer_tracing_off(tr); return; } /* Note, snapshot can not be used when the tracer uses it */ if (tracer->use_max_tr) { trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } if (tr->mapped) { trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } local_irq_save(flags); update_max_tr(tr, current, smp_processor_id(), cond_data); local_irq_restore(flags); } void tracing_snapshot_instance(struct trace_array *tr) { tracing_snapshot_instance_cond(tr, NULL); } /** * tracing_snapshot - take a snapshot of the current buffer. * * This causes a swap between the snapshot buffer and the current live * tracing buffer. You can use this to take snapshots of the live * trace when some condition is triggered, but continue to trace. * * Note, make sure to allocate the snapshot with either * a tracing_snapshot_alloc(), or by doing it manually * with: echo 1 > /sys/kernel/tracing/snapshot * * If the snapshot buffer is not allocated, it will stop tracing. * Basically making a permanent snapshot. */ void tracing_snapshot(void) { struct trace_array *tr = &global_trace; tracing_snapshot_instance(tr); } EXPORT_SYMBOL_GPL(tracing_snapshot); /** * tracing_snapshot_cond - conditionally take a snapshot of the current buffer. * @tr: The tracing instance to snapshot * @cond_data: The data to be tested conditionally, and possibly saved * * This is the same as tracing_snapshot() except that the snapshot is * conditional - the snapshot will only happen if the * cond_snapshot.update() implementation receiving the cond_data * returns true, which means that the trace array's cond_snapshot * update() operation used the cond_data to determine whether the * snapshot should be taken, and if it was, presumably saved it along * with the snapshot. */ void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) { tracing_snapshot_instance_cond(tr, cond_data); } EXPORT_SYMBOL_GPL(tracing_snapshot_cond); /** * tracing_cond_snapshot_data - get the user data associated with a snapshot * @tr: The tracing instance * * When the user enables a conditional snapshot using * tracing_snapshot_cond_enable(), the user-defined cond_data is saved * with the snapshot. This accessor is used to retrieve it. * * Should not be called from cond_snapshot.update(), since it takes * the tr->max_lock lock, which the code calling * cond_snapshot.update() has already done. * * Returns the cond_data associated with the trace array's snapshot. */ void *tracing_cond_snapshot_data(struct trace_array *tr) { void *cond_data = NULL; local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) cond_data = tr->cond_snapshot->cond_data; arch_spin_unlock(&tr->max_lock); local_irq_enable(); return cond_data; } EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, struct array_buffer *size_buf, int cpu_id); static void set_buffer_entries(struct array_buffer *buf, unsigned long val); int tracing_alloc_snapshot_instance(struct trace_array *tr) { int order; int ret; if (!tr->allocated_snapshot) { /* Make the snapshot buffer have the same order as main buffer */ order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); if (ret < 0) return ret; /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; tr->allocated_snapshot = true; } return 0; } static void free_snapshot(struct trace_array *tr) { /* * We don't free the ring buffer. instead, resize it because * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0); ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_buffer); tr->allocated_snapshot = false; } static int tracing_arm_snapshot_locked(struct trace_array *tr) { int ret; lockdep_assert_held(&trace_types_lock); spin_lock(&tr->snapshot_trigger_lock); if (tr->snapshot == UINT_MAX || tr->mapped) { spin_unlock(&tr->snapshot_trigger_lock); return -EBUSY; } tr->snapshot++; spin_unlock(&tr->snapshot_trigger_lock); ret = tracing_alloc_snapshot_instance(tr); if (ret) { spin_lock(&tr->snapshot_trigger_lock); tr->snapshot--; spin_unlock(&tr->snapshot_trigger_lock); } return ret; } int tracing_arm_snapshot(struct trace_array *tr) { int ret; mutex_lock(&trace_types_lock); ret = tracing_arm_snapshot_locked(tr); mutex_unlock(&trace_types_lock); return ret; } void tracing_disarm_snapshot(struct trace_array *tr) { spin_lock(&tr->snapshot_trigger_lock); if (!WARN_ON(!tr->snapshot)) tr->snapshot--; spin_unlock(&tr->snapshot_trigger_lock); } /** * tracing_alloc_snapshot - allocate snapshot buffer. * * This only allocates the snapshot buffer if it isn't already * allocated - it doesn't also take a snapshot. * * This is meant to be used in cases where the snapshot buffer needs * to be set up for events that can't sleep but need to be able to * trigger a snapshot. */ int tracing_alloc_snapshot(void) { struct trace_array *tr = &global_trace; int ret; ret = tracing_alloc_snapshot_instance(tr); WARN_ON(ret < 0); return ret; } EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); /** * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer. * * This is similar to tracing_snapshot(), but it will allocate the * snapshot buffer if it isn't already allocated. Use this only * where it is safe to sleep, as the allocation may sleep. * * This causes a swap between the snapshot buffer and the current live * tracing buffer. You can use this to take snapshots of the live * trace when some condition is triggered, but continue to trace. */ void tracing_snapshot_alloc(void) { int ret; ret = tracing_alloc_snapshot(); if (ret < 0) return; tracing_snapshot(); } EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); /** * tracing_snapshot_cond_enable - enable conditional snapshot for an instance * @tr: The tracing instance * @cond_data: User data to associate with the snapshot * @update: Implementation of the cond_snapshot update function * * Check whether the conditional snapshot for the given instance has * already been enabled, or if the current tracer is already using a * snapshot; if so, return -EBUSY, else create a cond_snapshot and * save the cond_data and update function inside. * * Returns 0 if successful, error otherwise. */ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) { struct cond_snapshot *cond_snapshot __free(kfree) = kzalloc(sizeof(*cond_snapshot), GFP_KERNEL); int ret; if (!cond_snapshot) return -ENOMEM; cond_snapshot->cond_data = cond_data; cond_snapshot->update = update; guard(mutex)(&trace_types_lock); if (tr->current_trace->use_max_tr) return -EBUSY; /* * The cond_snapshot can only change to NULL without the * trace_types_lock. We don't care if we race with it going * to NULL, but we want to make sure that it's not set to * something other than NULL when we get here, which we can * do safely with only holding the trace_types_lock and not * having to take the max_lock. */ if (tr->cond_snapshot) return -EBUSY; ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; local_irq_disable(); arch_spin_lock(&tr->max_lock); tr->cond_snapshot = no_free_ptr(cond_snapshot); arch_spin_unlock(&tr->max_lock); local_irq_enable(); return 0; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); /** * tracing_snapshot_cond_disable - disable conditional snapshot for an instance * @tr: The tracing instance * * Check whether the conditional snapshot for the given instance is * enabled; if so, free the cond_snapshot associated with it, * otherwise return -EINVAL. * * Returns 0 if successful, error otherwise. */ int tracing_snapshot_cond_disable(struct trace_array *tr) { int ret = 0; local_irq_disable(); arch_spin_lock(&tr->max_lock); if (!tr->cond_snapshot) ret = -EINVAL; else { kfree(tr->cond_snapshot); tr->cond_snapshot = NULL; } arch_spin_unlock(&tr->max_lock); local_irq_enable(); tracing_disarm_snapshot(tr); return ret; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); #else void tracing_snapshot(void) { WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); } EXPORT_SYMBOL_GPL(tracing_snapshot); void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) { WARN_ONCE(1, "Snapshot feature not enabled, but internal conditional snapshot used"); } EXPORT_SYMBOL_GPL(tracing_snapshot_cond); int tracing_alloc_snapshot(void) { WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used"); return -ENODEV; } EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); void tracing_snapshot_alloc(void) { /* Give warning */ tracing_snapshot(); } EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); void *tracing_cond_snapshot_data(struct trace_array *tr) { return NULL; } EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) { return -ENODEV; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); int tracing_snapshot_cond_disable(struct trace_array *tr) { return false; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); #define free_snapshot(tr) do { } while (0) #define tracing_arm_snapshot_locked(tr) ({ -EBUSY; }) #endif /* CONFIG_TRACER_SNAPSHOT */ void tracer_tracing_off(struct trace_array *tr) { if (tr->array_buffer.buffer) ring_buffer_record_off(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to * know if the ring buffer has been disabled, but it can handle * races of where it gets disabled but we still do a record. * As the check is in the fast path of the tracers, it is more * important to be fast than accurate. */ tr->buffer_disabled = 1; /* Make the flag seen by readers */ smp_wmb(); } /** * tracing_off - turn off tracing buffers * * This function stops the tracing buffers from recording data. * It does not disable any overhead the tracers themselves may * be causing. This function simply causes all recording to * the ring buffers to fail. */ void tracing_off(void) { tracer_tracing_off(&global_trace); } EXPORT_SYMBOL_GPL(tracing_off); void disable_trace_on_warning(void) { if (__disable_trace_on_warning) { trace_array_printk_buf(global_trace.array_buffer.buffer, _THIS_IP_, "Disabling tracing due to warning\n"); tracing_off(); } } /** * tracer_tracing_is_on - show real state of ring buffer enabled * @tr : the trace array to know if ring buffer is enabled * * Shows real state of the ring buffer if it is enabled or not. */ bool tracer_tracing_is_on(struct trace_array *tr) { if (tr->array_buffer.buffer) return ring_buffer_record_is_set_on(tr->array_buffer.buffer); return !tr->buffer_disabled; } /** * tracing_is_on - show state of ring buffers enabled */ int tracing_is_on(void) { return tracer_tracing_is_on(&global_trace); } EXPORT_SYMBOL_GPL(tracing_is_on); static int __init set_buf_size(char *str) { unsigned long buf_size; if (!str) return 0; buf_size = memparse(str, &str); /* * nr_entries can not be zero and the startup * tests require some buffer space. Therefore * ensure we have at least 4096 bytes of buffer. */ trace_buf_size = max(4096UL, buf_size); return 1; } __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { unsigned long threshold; int ret; if (!str) return 0; ret = kstrtoul(str, 0, &threshold); if (ret < 0) return 0; tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); unsigned long nsecs_to_usecs(unsigned long nsecs) { return nsecs / 1000; } /* * TRACE_FLAGS is defined as a tuple matching bit masks with strings. * It uses C(a, b) where 'a' is the eval (enum) name and 'b' is the string that * matches it. By defining "C(a, b) b", TRACE_FLAGS becomes a list * of strings in the order that the evals (enum) were defined. */ #undef C #define C(a, b) b /* These must match the bit positions in trace_iterator_flags */ static const char *trace_options[] = { TRACE_FLAGS NULL }; static struct { u64 (*func)(void); const char *name; int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, { trace_clock_jiffies, "uptime", 0 }, { trace_clock, "perf", 1 }, { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, { ktime_get_boot_fast_ns, "boot", 1 }, { ktime_get_tai_fast_ns, "tai", 1 }, ARCH_TRACE_CLOCKS }; bool trace_clock_in_ns(struct trace_array *tr) { if (trace_clocks[tr->clock_id].in_ns) return true; return false; } /* * trace_parser_get_init - gets the buffer for trace parser */ int trace_parser_get_init(struct trace_parser *parser, int size) { memset(parser, 0, sizeof(*parser)); parser->buffer = kmalloc(size, GFP_KERNEL); if (!parser->buffer) return 1; parser->size = size; return 0; } /* * trace_parser_put - frees the buffer for trace parser */ void trace_parser_put(struct trace_parser *parser) { kfree(parser->buffer); parser->buffer = NULL; } /* * trace_get_user - reads the user input string separated by space * (matched by isspace(ch)) * * For each string found the 'struct trace_parser' is updated, * and the function returns. * * Returns number of bytes read. * * See kernel/trace/trace.h for 'struct trace_parser' details. */ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, size_t cnt, loff_t *ppos) { char ch; size_t read = 0; ssize_t ret; if (!*ppos) trace_parser_clear(parser); ret = get_user(ch, ubuf++); if (ret) goto out; read++; cnt--; /* * The parser is not finished with the last write, * continue reading the user input without skipping spaces. */ if (!parser->cont) { /* skip white space */ while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); if (ret) goto out; read++; cnt--; } parser->idx = 0; /* only spaces were written */ if (isspace(ch) || !ch) { *ppos += read; ret = read; goto out; } } /* read the non-space input */ while (cnt && !isspace(ch) && ch) { if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; else { ret = -EINVAL; goto out; } ret = get_user(ch, ubuf++); if (ret) goto out; read++; cnt--; } /* We either got finished input or we have to wait for another call. */ if (isspace(ch) || !ch) { parser->buffer[parser->idx] = 0; parser->cont = false; } else if (parser->idx < parser->size - 1) { parser->cont = true; parser->buffer[parser->idx++] = ch; /* Make sure the parsed string always terminates with '\0'. */ parser->buffer[parser->idx] = 0; } else { ret = -EINVAL; goto out; } *ppos += read; ret = read; out: return ret; } /* TODO add a seq_buf_to_buffer() */ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; if (trace_seq_used(s) <= s->readpos) return -EBUSY; len = trace_seq_used(s) - s->readpos; if (cnt > len) cnt = len; memcpy(buf, s->buffer + s->readpos, cnt); s->readpos += cnt; return cnt; } unsigned long __read_mostly tracing_thresh; #ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops; #ifdef LATENCY_FS_NOTIFY static struct workqueue_struct *fsnotify_wq; static void latency_fsnotify_workfn(struct work_struct *work) { struct trace_array *tr = container_of(work, struct trace_array, fsnotify_work); fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY); } static void latency_fsnotify_workfn_irq(struct irq_work *iwork) { struct trace_array *tr = container_of(iwork, struct trace_array, fsnotify_irqwork); queue_work(fsnotify_wq, &tr->fsnotify_work); } static void trace_create_maxlat_file(struct trace_array *tr, struct dentry *d_tracer) { INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn); init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); tr->d_max_latency = trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, d_tracer, tr, &tracing_max_lat_fops); } __init static int latency_fsnotify_init(void) { fsnotify_wq = alloc_workqueue("tr_max_lat_wq", WQ_UNBOUND | WQ_HIGHPRI, 0); if (!fsnotify_wq) { pr_err("Unable to allocate tr_max_lat_wq\n"); return -ENOMEM; } return 0; } late_initcall_sync(latency_fsnotify_init); void latency_fsnotify(struct trace_array *tr) { if (!fsnotify_wq) return; /* * We cannot call queue_work(&tr->fsnotify_work) from here because it's * possible that we are called from __schedule() or do_idle(), which * could cause a deadlock. */ irq_work_queue(&tr->fsnotify_irqwork); } #else /* !LATENCY_FS_NOTIFY */ #define trace_create_maxlat_file(tr, d_tracer) \ trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, \ d_tracer, tr, &tracing_max_lat_fops) #endif /* * Copy the new maximum trace into the separate maximum-trace * structure. (this way the maximum trace is permanently saved, * for later retrieval via /sys/kernel/tracing/tracing_max_latency) */ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct array_buffer *trace_buf = &tr->array_buffer; struct array_buffer *max_buf = &tr->max_buffer; struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); max_buf->cpu = cpu; max_buf->time_start = data->preempt_timestamp; max_data->saved_latency = tr->max_latency; max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; strscpy(max_data->comm, tsk->comm); max_data->pid = tsk->pid; /* * If tsk == current, then use current_uid(), as that does not use * RCU. The irq tracer can be called out of RCU scope. */ if (tsk == current) max_data->uid = current_uid(); else max_data->uid = task_uid(tsk); max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; max_data->policy = tsk->policy; max_data->rt_priority = tsk->rt_priority; /* record this tasks comm */ tracing_record_cmdline(tsk); latency_fsnotify(tr); } /** * update_max_tr - snapshot all trace buffers from global_trace to max_tr * @tr: tracer * @tsk: the task with the latency * @cpu: The cpu that initiated the trace. * @cond_data: User data associated with a conditional snapshot * * Flip the buffers between the @tr and the max_tr and record information * about which task was the cause of this latency. */ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, void *cond_data) { if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); if (!tr->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ WARN_ON_ONCE(tr->current_trace != &nop_trace); return; } arch_spin_lock(&tr->max_lock); /* Inherit the recordable setting from array_buffer */ if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) ring_buffer_record_on(tr->max_buffer.buffer); else ring_buffer_record_off(tr->max_buffer.buffer); #ifdef CONFIG_TRACER_SNAPSHOT if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { arch_spin_unlock(&tr->max_lock); return; } #endif swap(tr->array_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); /* Any waiters on the old snapshot buffer need to wake up */ ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); } /** * update_max_tr_single - only copy one trace over, and reset the rest * @tr: tracer * @tsk: task with the latency * @cpu: the cpu of the buffer to copy. * * Flip the trace of a single CPU buffer between the @tr and the max_tr. */ void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { int ret; if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); if (!tr->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ WARN_ON_ONCE(tr->current_trace != &nop_trace); return; } arch_spin_lock(&tr->max_lock); ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_buffer.buffer, cpu); if (ret == -EBUSY) { /* * We failed to swap the buffer due to a commit taking * place on this CPU. We fail to record, but we reset * the max trace buffer (no one writes directly to it) * and flag that it failed. * Another reason is resize is in progress. */ trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, "Failed to swap buffers due to commit or resize in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); } #endif /* CONFIG_TRACER_MAX_TRACE */ struct pipe_wait { struct trace_iterator *iter; int wait_index; }; static bool wait_pipe_cond(void *data) { struct pipe_wait *pwait = data; struct trace_iterator *iter = pwait->iter; if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) return true; return iter->closed; } static int wait_on_pipe(struct trace_iterator *iter, int full) { struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; pwait.wait_index = atomic_read_acquire(&iter->wait_index); pwait.iter = iter; ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* * Make sure this is still the snapshot buffer, as if a snapshot were * to happen, this would now be the main buffer. */ if (iter->snapshot) iter->array_buffer = &iter->tr->max_buffer; #endif return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST static bool selftests_can_run; struct trace_selftests { struct list_head list; struct tracer *type; }; static LIST_HEAD(postponed_selftests); static int save_selftest(struct tracer *type) { struct trace_selftests *selftest; selftest = kmalloc(sizeof(*selftest), GFP_KERNEL); if (!selftest) return -ENOMEM; selftest->type = type; list_add(&selftest->list, &postponed_selftests); return 0; } static int run_tracer_selftest(struct tracer *type) { struct trace_array *tr = &global_trace; struct tracer *saved_tracer = tr->current_trace; int ret; if (!type->selftest || tracing_selftest_disabled) return 0; /* * If a tracer registers early in boot up (before scheduling is * initialized and such), then do not run its selftests yet. * Instead, run it a little later in the boot process. */ if (!selftests_can_run) return save_selftest(type); if (!tracing_is_on()) { pr_warn("Selftest for tracer %s skipped due to tracing disabled\n", type->name); return 0; } /* * Run a selftest on this tracer. * Here we reset the trace buffer, and set the current * tracer to be this tracer. The tracer can then run some * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ tracing_reset_online_cpus(&tr->array_buffer); tr->current_trace = type; #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { /* If we expanded the buffers, make sure the max is expanded too */ if (tr->ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); tr->allocated_snapshot = true; } #endif /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); ret = type->selftest(type, tr); /* the test is responsible for resetting too */ tr->current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); /* Add the warning after printing 'FAILED' */ WARN_ON(1); return -1; } /* Only reset on passing, to avoid touching corrupted buffers */ tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { tr->allocated_snapshot = false; /* Shrink the max buffer again */ if (tr->ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); } #endif printk(KERN_CONT "PASSED\n"); return 0; } static int do_run_tracer_selftest(struct tracer *type) { int ret; /* * Tests can take a long time, especially if they are run one after the * other, as does happen during bootup when all the tracers are * registered. This could cause the soft lockup watchdog to trigger. */ cond_resched(); tracing_selftest_running = true; ret = run_tracer_selftest(type); tracing_selftest_running = false; return ret; } static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; struct tracer *t, **last; int ret; selftests_can_run = true; guard(mutex)(&trace_types_lock); if (list_empty(&postponed_selftests)) return 0; pr_info("Running postponed tracer tests:\n"); tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { /* This loop can take minutes when sanitizers are enabled, so * lets make sure we allow RCU processing. */ cond_resched(); ret = run_tracer_selftest(p->type); /* If the test fails, then warn and remove from available_tracers */ if (ret < 0) { WARN(1, "tracer: %s failed selftest, disabling\n", p->type->name); last = &trace_types; for (t = trace_types; t; t = t->next) { if (t == p->type) { *last = t->next; break; } last = &t->next; } } list_del(&p->list); kfree(p); } tracing_selftest_running = false; return 0; } core_initcall(init_trace_selftests); #else static inline int do_run_tracer_selftest(struct tracer *type) { return 0; } #endif /* CONFIG_FTRACE_STARTUP_TEST */ static void add_tracer_options(struct trace_array *tr, struct tracer *t); static void __init apply_trace_boot_options(void); /** * register_tracer - register a tracer with the ftrace system. * @type: the plugin for the tracer * * Register a new plugin tracer. */ int __init register_tracer(struct tracer *type) { struct tracer *t; int ret = 0; if (!type->name) { pr_info("Tracer must have a name\n"); return -1; } if (strlen(type->name) >= MAX_TRACER_SIZE) { pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE); return -1; } if (security_locked_down(LOCKDOWN_TRACEFS)) { pr_warn("Can not register tracer %s due to lockdown\n", type->name); return -EPERM; } mutex_lock(&trace_types_lock); for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ pr_info("Tracer %s already registered\n", type->name); ret = -1; goto out; } } if (!type->set_flag) type->set_flag = &dummy_set_flag; if (!type->flags) { /*allocate a dummy tracer_flags*/ type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); if (!type->flags) { ret = -ENOMEM; goto out; } type->flags->val = 0; type->flags->opts = dummy_tracer_opt; } else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; /* store the tracer for __set_tracer_option */ type->flags->trace = type; ret = do_run_tracer_selftest(type); if (ret < 0) goto out; type->next = trace_types; trace_types = type; add_tracer_options(&global_trace, type); out: mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) goto out_unlock; if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE)) goto out_unlock; printk(KERN_INFO "Starting tracer '%s'\n", type->name); /* Do we want this tracer to start on bootup? */ tracing_set_tracer(&global_trace, type->name); default_bootup_tracer = NULL; apply_trace_boot_options(); /* disable other selftests, since this will break it. */ disable_tracing_selftest("running a tracer"); out_unlock: return ret; } static void tracing_reset_cpu(struct array_buffer *buf, int cpu) { struct trace_buffer *buffer = buf->buffer; if (!buffer) return; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_rcu(); ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } void tracing_reset_online_cpus(struct array_buffer *buf) { struct trace_buffer *buffer = buf->buffer; if (!buffer) return; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_rcu(); buf->time_start = buffer_ftrace_now(buf, buf->cpu); ring_buffer_reset_online_cpus(buffer); ring_buffer_record_enable(buffer); } static void tracing_reset_all_cpus(struct array_buffer *buf) { struct trace_buffer *buffer = buf->buffer; if (!buffer) return; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_rcu(); buf->time_start = buffer_ftrace_now(buf, buf->cpu); ring_buffer_reset(buffer); ring_buffer_record_enable(buffer); } /* Must have trace_types_lock held */ void tracing_reset_all_online_cpus_unlocked(void) { struct trace_array *tr; lockdep_assert_held(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->clear_trace) continue; tr->clear_trace = false; tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE tracing_reset_online_cpus(&tr->max_buffer); #endif } } void tracing_reset_all_online_cpus(void) { mutex_lock(&trace_types_lock); tracing_reset_all_online_cpus_unlocked(); mutex_unlock(&trace_types_lock); } int is_tracing_stopped(void) { return global_trace.stop_count; } static void tracing_start_tr(struct trace_array *tr) { struct trace_buffer *buffer; unsigned long flags; if (tracing_disabled) return; raw_spin_lock_irqsave(&tr->start_lock, flags); if (--tr->stop_count) { if (WARN_ON_ONCE(tr->stop_count < 0)) { /* Someone screwed up their debugging */ tr->stop_count = 0; } goto out; } /* Prevent the buffers from switching */ arch_spin_lock(&tr->max_lock); buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #endif arch_spin_unlock(&tr->max_lock); out: raw_spin_unlock_irqrestore(&tr->start_lock, flags); } /** * tracing_start - quick start of the tracer * * If tracing is enabled but was stopped by tracing_stop, * this will start the tracer back up. */ void tracing_start(void) { return tracing_start_tr(&global_trace); } static void tracing_stop_tr(struct trace_array *tr) { struct trace_buffer *buffer; unsigned long flags; raw_spin_lock_irqsave(&tr->start_lock, flags); if (tr->stop_count++) goto out; /* Prevent the buffers from switching */ arch_spin_lock(&tr->max_lock); buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #endif arch_spin_unlock(&tr->max_lock); out: raw_spin_unlock_irqrestore(&tr->start_lock, flags); } /** * tracing_stop - quick stop of the tracer * * Light weight way to stop tracing. Use in conjunction with * tracing_start. */ void tracing_stop(void) { return tracing_stop_tr(&global_trace); } /* * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function * simplifies those functions and keeps them in sync. */ enum print_line_t trace_handle_return(struct trace_seq *s) { return trace_seq_has_overflowed(s) ? TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED; } EXPORT_SYMBOL_GPL(trace_handle_return); static unsigned short migration_disable_value(void) { #if defined(CONFIG_SMP) return current->migration_disabled; #else return 0; #endif } unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) { unsigned int trace_flags = irqs_status; unsigned int pc; pc = preempt_count(); if (pc & NMI_MASK) trace_flags |= TRACE_FLAG_NMI; if (pc & HARDIRQ_MASK) trace_flags |= TRACE_FLAG_HARDIRQ; if (in_serving_softirq()) trace_flags |= TRACE_FLAG_SOFTIRQ; if (softirq_count() >> (SOFTIRQ_SHIFT + 1)) trace_flags |= TRACE_FLAG_BH_OFF; if (tif_need_resched()) trace_flags |= TRACE_FLAG_NEED_RESCHED; if (test_preempt_need_resched()) trace_flags |= TRACE_FLAG_PREEMPT_RESCHED; if (IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY) && tif_test_bit(TIF_NEED_RESCHED_LAZY)) trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY; return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) | (min_t(unsigned int, migration_disable_value(), 0xf)) << 4; } struct ring_buffer_event * trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned int trace_ctx) { return __trace_buffer_lock_reserve(buffer, type, len, trace_ctx); } DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); DEFINE_PER_CPU(int, trace_buffered_event_cnt); static int trace_buffered_event_ref; /** * trace_buffered_event_enable - enable buffering events * * When events are being filtered, it is quicker to use a temporary * buffer to write the event data into if there's a likely chance * that it will not be committed. The discard of the ring buffer * is not as fast as committing, and is much slower than copying * a commit. * * When an event is to be filtered, allocate per cpu buffers to * write the event data into, and if the event is filtered and discarded * it is simply dropped, otherwise, the entire data is to be committed * in one shot. */ void trace_buffered_event_enable(void) { struct ring_buffer_event *event; struct page *page; int cpu; WARN_ON_ONCE(!mutex_is_locked(&event_mutex)); if (trace_buffered_event_ref++) return; for_each_tracing_cpu(cpu) { page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); /* This is just an optimization and can handle failures */ if (!page) { pr_err("Failed to allocate event buffer\n"); break; } event = page_address(page); memset(event, 0, sizeof(*event)); per_cpu(trace_buffered_event, cpu) = event; preempt_disable(); if (cpu == smp_processor_id() && __this_cpu_read(trace_buffered_event) != per_cpu(trace_buffered_event, cpu)) WARN_ON_ONCE(1); preempt_enable(); } } static void enable_trace_buffered_event(void *data) { /* Probably not needed, but do it anyway */ smp_rmb(); this_cpu_dec(trace_buffered_event_cnt); } static void disable_trace_buffered_event(void *data) { this_cpu_inc(trace_buffered_event_cnt); } /** * trace_buffered_event_disable - disable buffering events * * When a filter is removed, it is faster to not use the buffered * events, and to commit directly into the ring buffer. Free up * the temp buffers when there are no more users. This requires * special synchronization with current events. */ void trace_buffered_event_disable(void) { int cpu; WARN_ON_ONCE(!mutex_is_locked(&event_mutex)); if (WARN_ON_ONCE(!trace_buffered_event_ref)) return; if (--trace_buffered_event_ref) return; /* For each CPU, set the buffer as used. */ on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event, NULL, true); /* Wait for all current users to finish */ synchronize_rcu(); for_each_tracing_cpu(cpu) { free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); per_cpu(trace_buffered_event, cpu) = NULL; } /* * Wait for all CPUs that potentially started checking if they can use * their event buffer only after the previous synchronize_rcu() call and * they still read a valid pointer from trace_buffered_event. It must be * ensured they don't see cleared trace_buffered_event_cnt else they * could wrongly decide to use the pointed-to buffer which is now freed. */ synchronize_rcu(); /* For each CPU, relinquish the buffer */ on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL, true); } static struct trace_buffer *temp_buffer; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, struct trace_event_file *trace_file, int type, unsigned long len, unsigned int trace_ctx) { struct ring_buffer_event *entry; struct trace_array *tr = trace_file->tr; int val; *current_rb = tr->array_buffer.buffer; if (!tr->no_filter_buffering_ref && (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) { preempt_disable_notrace(); /* * Filtering is on, so try to use the per cpu buffer first. * This buffer will simulate a ring_buffer_event, * where the type_len is zero and the array[0] will * hold the full length. * (see include/linux/ring-buffer.h for details on * how the ring_buffer_event is structured). * * Using a temp buffer during filtering and copying it * on a matched filter is quicker than writing directly * into the ring buffer and then discarding it when * it doesn't match. That is because the discard * requires several atomic operations to get right. * Copying on match and doing nothing on a failed match * is still quicker than no copy on match, but having * to discard out of the ring buffer on a failed match. */ if ((entry = __this_cpu_read(trace_buffered_event))) { int max_len = PAGE_SIZE - struct_size(entry, array, 1); val = this_cpu_inc_return(trace_buffered_event_cnt); /* * Preemption is disabled, but interrupts and NMIs * can still come in now. If that happens after * the above increment, then it will have to go * back to the old method of allocating the event * on the ring buffer, and if the filter fails, it * will have to call ring_buffer_discard_commit() * to remove it. * * Need to also check the unlikely case that the * length is bigger than the temp buffer size. * If that happens, then the reserve is pretty much * guaranteed to fail, as the ring buffer currently * only allows events less than a page. But that may * change in the future, so let the ring buffer reserve * handle the failure in that case. */ if (val == 1 && likely(len <= max_len)) { trace_event_setup(entry, type, trace_ctx); entry->array[0] = len; /* Return with preemption disabled */ return entry; } this_cpu_dec(trace_buffered_event_cnt); } /* __trace_buffer_lock_reserve() disables preemption */ preempt_enable_notrace(); } entry = __trace_buffer_lock_reserve(*current_rb, type, len, trace_ctx); /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer * to store the trace event for the trigger to use. It's recursive * safe and will not be recorded anywhere. */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { *current_rb = temp_buffer; entry = __trace_buffer_lock_reserve(*current_rb, type, len, trace_ctx); } return entry; } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock); static DEFINE_MUTEX(tracepoint_printk_mutex); static void output_printk(struct trace_event_buffer *fbuffer) { struct trace_event_call *event_call; struct trace_event_file *file; struct trace_event *event; unsigned long flags; struct trace_iterator *iter = tracepoint_print_iter; /* We should never get here if iter is NULL */ if (WARN_ON_ONCE(!iter)) return; event_call = fbuffer->trace_file->event_call; if (!event_call || !event_call->event.funcs || !event_call->event.funcs->trace) return; file = fbuffer->trace_file; if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && !filter_match_preds(file->filter, fbuffer->entry))) return; event = &fbuffer->trace_file->event_call->event; raw_spin_lock_irqsave(&tracepoint_iter_lock, flags); trace_seq_init(&iter->seq); iter->ent = fbuffer->entry; event_call->event.funcs->trace(iter, 0, event); trace_seq_putc(&iter->seq, 0); printk("%s", iter->seq.buffer); raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags); } int tracepoint_printk_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int save_tracepoint_printk; int ret; guard(mutex)(&tracepoint_printk_mutex); save_tracepoint_printk = tracepoint_printk; ret = proc_dointvec(table, write, buffer, lenp, ppos); /* * This will force exiting early, as tracepoint_printk * is always zero when tracepoint_printk_iter is not allocated */ if (!tracepoint_print_iter) tracepoint_printk = 0; if (save_tracepoint_printk == tracepoint_printk) return ret; if (tracepoint_printk) static_key_enable(&tracepoint_printk_key.key); else static_key_disable(&tracepoint_printk_key.key); return ret; } void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) { enum event_trigger_type tt = ETT_NONE; struct trace_event_file *file = fbuffer->trace_file; if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event, fbuffer->entry, &tt)) goto discard; if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); if (static_branch_unlikely(&trace_event_exports_enabled)) ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer, fbuffer->event, fbuffer->trace_ctx, fbuffer->regs); discard: if (tt) event_triggers_post_call(file, tt); } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); /* * Skip 3: * * trace_buffer_unlock_commit_regs() * trace_event_buffer_commit() * trace_event_raw_event_xxx() */ # define STACK_SKIP 3 void trace_buffer_unlock_commit_regs(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned int trace_ctx, struct pt_regs *regs) { __buffer_unlock_commit(buffer, event); /* * If regs is not set, then skip the necessary functions. * Note, we can still get here via blktrace, wakeup tracer * and mmiotrace, but that's ok if they lose a function or * two. They are not that meaningful. */ ftrace_trace_stack(tr, buffer, trace_ctx, regs ? 0 : STACK_SKIP, regs); ftrace_trace_userstack(tr, buffer, trace_ctx); } /* * Similar to trace_buffer_unlock_commit_regs() but do not dump stack. */ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event) { __buffer_unlock_commit(buffer, event); } void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned int trace_ctx) { struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; event = __trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); entry->ip = ip; entry->parent_ip = parent_ip; if (static_branch_unlikely(&trace_function_exports_enabled)) ftrace_exports(event, TRACE_EXPORT_FUNCTION); __buffer_unlock_commit(buffer, event); } #ifdef CONFIG_STACKTRACE /* Allow 4 levels of nesting: normal, softirq, irq, NMI */ #define FTRACE_KSTACK_NESTING 4 #define FTRACE_KSTACK_ENTRIES (SZ_4K / FTRACE_KSTACK_NESTING) struct ftrace_stack { unsigned long calls[FTRACE_KSTACK_ENTRIES]; }; struct ftrace_stacks { struct ftrace_stack stacks[FTRACE_KSTACK_NESTING]; }; static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); static void __ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs) { struct ring_buffer_event *event; unsigned int size, nr_entries; struct ftrace_stack *fstack; struct stack_entry *entry; int stackidx; /* * Add one, for this function and the call to save_stack_trace() * If regs is set, then these functions will not be in the way. */ #ifndef CONFIG_UNWINDER_ORC if (!regs) skip++; #endif preempt_disable_notrace(); stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; /* This should never happen. If it does, yell once and skip */ if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING)) goto out; /* * The above __this_cpu_inc_return() is 'atomic' cpu local. An * interrupt will either see the value pre increment or post * increment. If the interrupt happens pre increment it will have * restored the counter when it returns. We just need a barrier to * keep gcc from moving things around. */ barrier(); fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx; size = ARRAY_SIZE(fstack->calls); if (regs) { nr_entries = stack_trace_save_regs(regs, fstack->calls, size, skip); } else { nr_entries = stack_trace_save(fstack->calls, size, skip); } #ifdef CONFIG_DYNAMIC_FTRACE /* Mark entry of stack trace as trampoline code */ if (tr->ops && tr->ops->trampoline) { unsigned long tramp_start = tr->ops->trampoline; unsigned long tramp_end = tramp_start + tr->ops->trampoline_size; unsigned long *calls = fstack->calls; for (int i = 0; i < nr_entries; i++) { if (calls[i] >= tramp_start && calls[i] < tramp_end) calls[i] = FTRACE_TRAMPOLINE_MARKER; } } #endif event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, struct_size(entry, caller, nr_entries), trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->size = nr_entries; memcpy(&entry->caller, fstack->calls, flex_array_size(entry, caller, nr_entries)); __buffer_unlock_commit(buffer, event); out: /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); preempt_enable_notrace(); } static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs) { if (!(tr->trace_flags & TRACE_ITER_STACKTRACE)) return; __ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs); } void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip) { struct trace_buffer *buffer = tr->array_buffer.buffer; if (rcu_is_watching()) { __ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL); return; } if (WARN_ON_ONCE(IS_ENABLED(CONFIG_GENERIC_ENTRY))) return; /* * When an NMI triggers, RCU is enabled via ct_nmi_enter(), * but if the above rcu_is_watching() failed, then the NMI * triggered someplace critical, and ct_irq_enter() should * not be called from NMI. */ if (unlikely(in_nmi())) return; ct_irq_enter_irqson(); __ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL); ct_irq_exit_irqson(); } /** * trace_dump_stack - record a stack back trace in the trace buffer * @skip: Number of functions to skip (helper handlers) */ void trace_dump_stack(int skip) { if (tracing_disabled || tracing_selftest_running) return; #ifndef CONFIG_UNWINDER_ORC /* Skip 1 to skip this function. */ skip++; #endif __ftrace_trace_stack(printk_trace, printk_trace->array_buffer.buffer, tracing_gen_ctx(), skip, NULL); } EXPORT_SYMBOL_GPL(trace_dump_stack); #ifdef CONFIG_USER_STACKTRACE_SUPPORT static DEFINE_PER_CPU(int, user_stack_count); static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx) { struct ring_buffer_event *event; struct userstack_entry *entry; if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* * NMIs can not handle page faults, even with fix ups. * The save user stack can (and often does) fault. */ if (unlikely(in_nmi())) return; /* * prevent recursion, since the user stack tracing may * trigger other kernel events. */ preempt_disable(); if (__this_cpu_read(user_stack_count)) goto out; __this_cpu_inc(user_stack_count); event = __trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, sizeof(*entry), trace_ctx); if (!event) goto out_drop_count; entry = ring_buffer_event_data(event); entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES); __buffer_unlock_commit(buffer, event); out_drop_count: __this_cpu_dec(user_stack_count); out: preempt_enable(); } #else /* CONFIG_USER_STACKTRACE_SUPPORT */ static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx) { } #endif /* !CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* CONFIG_STACKTRACE */ static inline void func_repeats_set_delta_ts(struct func_repeats_entry *entry, unsigned long long delta) { entry->bottom_delta_ts = delta & U32_MAX; entry->top_delta_ts = (delta >> 32); } void trace_last_func_repeats(struct trace_array *tr, struct trace_func_repeats *last_info, unsigned int trace_ctx) { struct trace_buffer *buffer = tr->array_buffer.buffer; struct func_repeats_entry *entry; struct ring_buffer_event *event; u64 delta; event = __trace_buffer_lock_reserve(buffer, TRACE_FUNC_REPEATS, sizeof(*entry), trace_ctx); if (!event) return; delta = ring_buffer_event_time_stamp(buffer, event) - last_info->ts_last_call; entry = ring_buffer_event_data(event); entry->ip = last_info->ip; entry->parent_ip = last_info->parent_ip; entry->count = last_info->count; func_repeats_set_delta_ts(entry, delta); __buffer_unlock_commit(buffer, event); } /* created for use with alloc_percpu */ struct trace_buffer_struct { int nesting; char buffer[4][TRACE_BUF_SIZE]; }; static struct trace_buffer_struct __percpu *trace_percpu_buffer; /* * This allows for lockless recording. If we're nested too deeply, then * this returns NULL. */ static char *get_trace_buf(void) { struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); if (!trace_percpu_buffer || buffer->nesting >= 4) return NULL; buffer->nesting++; /* Interrupts must see nesting incremented before we use the buffer */ barrier(); return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) { /* Don't let the decrement of nesting leak before this */ barrier(); this_cpu_dec(trace_percpu_buffer->nesting); } static int alloc_percpu_trace_buffer(void) { struct trace_buffer_struct __percpu *buffers; if (trace_percpu_buffer) return 0; buffers = alloc_percpu(struct trace_buffer_struct); if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer")) return -ENOMEM; trace_percpu_buffer = buffers; return 0; } static int buffers_allocated; void trace_printk_init_buffers(void) { if (buffers_allocated) return; if (alloc_percpu_trace_buffer()) return; /* trace_printk() is for debug use only. Don't use it in production. */ pr_warn("\n"); pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** trace_printk() being used. Allocating extra memory. **\n"); pr_warn("** **\n"); pr_warn("** This means that this is a DEBUG kernel and it is **\n"); pr_warn("** unsafe for production use. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your vendor! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); /* Expand the buffers to set size */ tracing_update_buffers(&global_trace); buffers_allocated = 1; /* * trace_printk_init_buffers() can be called by modules. * If that happens, then we need to start cmdline recording * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ if (global_trace.array_buffer.buffer) tracing_start_cmdline_record(); } EXPORT_SYMBOL_GPL(trace_printk_init_buffers); void trace_printk_start_comm(void) { /* Start tracing comms if trace printk is set */ if (!buffers_allocated) return; tracing_start_cmdline_record(); } static void trace_printk_start_stop_comm(int enabled) { if (!buffers_allocated) return; if (enabled) tracing_start_cmdline_record(); else tracing_stop_cmdline_record(); } /** * trace_vbprintk - write binary msg to tracing buffer * @ip: The address of the caller * @fmt: The string format to write to the buffer * @args: Arguments for @fmt */ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { struct ring_buffer_event *event; struct trace_buffer *buffer; struct trace_array *tr = READ_ONCE(printk_trace); struct bprint_entry *entry; unsigned int trace_ctx; char *tbuffer; int len = 0, size; if (!printk_binsafe(tr)) return trace_vprintk(ip, fmt, args); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; goto out_nobuffer; } len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) goto out_put; size = sizeof(*entry) + sizeof(u32) * len; buffer = tr->array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; entry->fmt = fmt; memcpy(entry->buf, tbuffer, sizeof(u32) * len); __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); out: ring_buffer_nest_end(buffer); out_put: put_trace_buf(); out_nobuffer: preempt_enable_notrace(); unpause_graph_tracing(); return len; } EXPORT_SYMBOL_GPL(trace_vbprintk); __printf(3, 0) static int __trace_array_vprintk(struct trace_buffer *buffer, unsigned long ip, const char *fmt, va_list args) { struct ring_buffer_event *event; int len = 0, size; struct print_entry *entry; unsigned int trace_ctx; char *tbuffer; if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; goto out_nobuffer; } len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); size = sizeof(*entry) + len + 1; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; memcpy(&entry->buf, tbuffer, len + 1); __buffer_unlock_commit(buffer, event); ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); out: ring_buffer_nest_end(buffer); put_trace_buf(); out_nobuffer: preempt_enable_notrace(); unpause_graph_tracing(); return len; } __printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { if (tracing_selftest_running && tr == &global_trace) return 0; return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } /** * trace_array_printk - Print a message to a specific instance * @tr: The instance trace_array descriptor * @ip: The instruction pointer that this is called from. * @fmt: The format to print (printf format) * * If a subsystem sets up its own instance, they have the right to * printk strings into their tracing instance buffer using this * function. Note, this function will not write into the top level * buffer (use trace_printk() for that), as writing into the top level * buffer should only have events that can be individually disabled. * trace_printk() is only used for debugging a kernel, and should not * be ever incorporated in normal use. * * trace_array_printk() can be used, as it will not add noise to the * top level tracing buffer. * * Note, trace_array_init_printk() must be called on @tr before this * can be used. */ __printf(3, 0) int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; if (!tr) return -ENOENT; /* This is only allowed for created instances */ if (tr == &global_trace) return 0; if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); return ret; } EXPORT_SYMBOL_GPL(trace_array_printk); /** * trace_array_init_printk - Initialize buffers for trace_array_printk() * @tr: The trace array to initialize the buffers for * * As trace_array_printk() only writes into instances, they are OK to * have in the kernel (unlike trace_printk()). This needs to be called * before trace_array_printk() can be used on a trace_array. */ int trace_array_init_printk(struct trace_array *tr) { if (!tr) return -ENOENT; /* This is only allowed for created instances */ if (tr == &global_trace) return -EINVAL; return alloc_percpu_trace_buffer(); } EXPORT_SYMBOL_GPL(trace_array_init_printk); __printf(3, 4) int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; if (!(printk_trace->trace_flags & TRACE_ITER_PRINTK)) return 0; va_start(ap, fmt); ret = __trace_array_vprintk(buffer, ip, fmt, ap); va_end(ap); return ret; } __printf(2, 0) int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(printk_trace, ip, fmt, args); } EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); iter->idx++; if (buf_iter) ring_buffer_iter_advance(buf_iter); } static struct trace_entry * peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { event = ring_buffer_iter_peek(buf_iter, ts); if (lost_events) *lost_events = ring_buffer_iter_dropped(buf_iter) ? (unsigned long)-1 : 0; } else { event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts, lost_events); } if (event) { iter->ent_size = ring_buffer_event_length(event); return ring_buffer_event_data(event); } iter->ent_size = 0; return NULL; } static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { struct trace_buffer *buffer = iter->array_buffer->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; int next_size = 0; int cpu; /* * If we are in a per_cpu trace file, don't bother by iterating over * all cpu and peek directly. */ if (cpu_file > RING_BUFFER_ALL_CPUS) { if (ring_buffer_empty_cpu(buffer, cpu_file)) return NULL; ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events); if (ent_cpu) *ent_cpu = cpu_file; return ent; } for_each_tracing_cpu(cpu) { if (ring_buffer_empty_cpu(buffer, cpu)) continue; ent = peek_next_entry(iter, cpu, &ts, &lost_events); /* * Pick the entry with the smallest timestamp: */ if (ent && (!next || ts < next_ts)) { next = ent; next_cpu = cpu; next_ts = ts; next_lost = lost_events; next_size = iter->ent_size; } } iter->ent_size = next_size; if (ent_cpu) *ent_cpu = next_cpu; if (ent_ts) *ent_ts = next_ts; if (missing_events) *missing_events = next_lost; return next; } #define STATIC_FMT_BUF_SIZE 128 static char static_fmt_buf[STATIC_FMT_BUF_SIZE]; char *trace_iter_expand_format(struct trace_iterator *iter) { char *tmp; /* * iter->tr is NULL when used with tp_printk, which makes * this get called where it is not safe to call krealloc(). */ if (!iter->tr || iter->fmt == static_fmt_buf) return NULL; tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE, GFP_KERNEL); if (tmp) { iter->fmt_size += STATIC_FMT_BUF_SIZE; iter->fmt = tmp; } return tmp; } /* Returns true if the string is safe to dereference from an event */ static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) return true; /* OK if part of the temp seq buffer */ if ((addr >= (unsigned long)iter->tmp_seq.buffer) && (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE)) return true; /* Core rodata can not be freed */ if (is_kernel_rodata(addr)) return true; if (trace_is_tracepoint_string(str)) return true; /* * Now this could be a module event, referencing core module * data, which is OK. */ if (!iter->ent) return false; trace_event = ftrace_find_event(iter->ent->type); if (!trace_event) return false; event = container_of(trace_event, struct trace_event_call, event); if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module) return false; /* Would rather have rodata, but this will suffice */ if (within_module_core(addr, event->module)) return true; return false; } /** * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed * * At boot up, test_event_printk() will flag any event that dereferences * a string with "%s" that does exist in the ring buffer. It may still * be valid, as the string may point to a static string in the kernel * rodata that never gets freed. But if the string pointer is pointing * to something that was allocated, there's a chance that it can be freed * by the time the user reads the trace. This would cause a bad memory * access by the kernel and possibly crash the system. * * This function will check if the event has any fields flagged as needing * to be checked at runtime and perform those checks. * * If it is found that a field is unsafe, it will write into the @iter->seq * a message stating what was found to be unsafe. * * @return: true if the event is unsafe and should be ignored, * false otherwise. */ bool ignore_event(struct trace_iterator *iter) { struct ftrace_event_field *field; struct trace_event *trace_event; struct trace_event_call *event; struct list_head *head; struct trace_seq *seq; const void *ptr; trace_event = ftrace_find_event(iter->ent->type); seq = &iter->seq; if (!trace_event) { trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); return true; } event = container_of(trace_event, struct trace_event_call, event); if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) return false; head = trace_get_fields(event); if (!head) { trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", trace_event_name(event)); return true; } /* Offsets are from the iter->ent that points to the raw event */ ptr = iter->ent; list_for_each_entry(field, head, link) { const char *str; bool good; if (!field->needs_test) continue; str = *(const char **)(ptr + field->offset); good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the * trace event in question used %s on a string that * was saved at the time of the event, but may not be * around when the trace is read. Use __string(), * __assign_str() and __get_str() helpers in the TRACE_EVENT() * instead. See samples/trace_events/trace-events-sample.h * for reference. */ if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", trace_event_name(event), field->name)) { trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", trace_event_name(event), field->name); return true; } } return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) { const char *p, *new_fmt; char *q; if (WARN_ON_ONCE(!fmt)) return fmt; if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR) return fmt; p = fmt; new_fmt = q = iter->fmt; while (*p) { if (unlikely(q - new_fmt + 3 > iter->fmt_size)) { if (!trace_iter_expand_format(iter)) return fmt; q += iter->fmt - new_fmt; new_fmt = iter->fmt; } *q++ = *p++; /* Replace %p with %px */ if (p[-1] == '%') { if (p[0] == '%') { *q++ = *p++; } else if (p[0] == 'p' && !isalnum(p[1])) { *q++ = *p++; *q++ = 'x'; } } } *q = '\0'; return new_fmt; } #define STATIC_TEMP_BUF_SIZE 128 static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { /* __find_next_entry will reset ent_size */ int ent_size = iter->ent_size; struct trace_entry *entry; /* * If called from ftrace_dump(), then the iter->temp buffer * will be the static_temp_buf and not created from kmalloc. * If the entry size is greater than the buffer, we can * not save it. Just return NULL in that case. This is only * used to add markers when two consecutive events' time * stamps have a large delta. See trace_print_lat_context() */ if (iter->temp == static_temp_buf && STATIC_TEMP_BUF_SIZE < ent_size) return NULL; /* * The __find_next_entry() may call peek_next_entry(), which may * call ring_buffer_peek() that may make the contents of iter->ent * undefined. Need to copy iter->ent now. */ if (iter->ent && iter->ent != iter->temp) { if ((!iter->temp || iter->temp_size < iter->ent_size) && !WARN_ON_ONCE(iter->temp == static_temp_buf)) { void *temp; temp = kmalloc(iter->ent_size, GFP_KERNEL); if (!temp) return NULL; kfree(iter->temp); iter->temp = temp; iter->temp_size = iter->ent_size; } memcpy(iter->temp, iter->ent, iter->ent_size); iter->ent = iter->temp; } entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts); /* Put back the original ent_size */ iter->ent_size = ent_size; return entry; } /* Find the next real entry, and increment the iterator to the next entry */ void *trace_find_next_entry_inc(struct trace_iterator *iter) { iter->ent = __find_next_entry(iter, &iter->cpu, &iter->lost_events, &iter->ts); if (iter->ent) trace_iterator_increment(iter); return iter->ent ? iter : NULL; } static void trace_consume(struct trace_iterator *iter) { ring_buffer_consume(iter->array_buffer->buffer, iter->cpu, &iter->ts, &iter->lost_events); } static void *s_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_iterator *iter = m->private; int i = (int)*pos; void *ent; WARN_ON_ONCE(iter->leftover); (*pos)++; /* can't go backwards */ if (iter->idx > i) return NULL; if (iter->idx < 0) ent = trace_find_next_entry_inc(iter); else ent = iter; while (ent && iter->idx < i) ent = trace_find_next_entry_inc(iter); iter->pos = *pos; return ent; } void tracing_iter_reset(struct trace_iterator *iter, int cpu) { struct ring_buffer_iter *buf_iter; unsigned long entries = 0; u64 ts; per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) return; ring_buffer_iter_reset(buf_iter); /* * We could have the case with the max latency tracers * that a reset never took place on a cpu. This is evident * by the timestamp being before the start of the buffer. */ while (ring_buffer_iter_peek(buf_iter, &ts)) { if (ts >= iter->array_buffer->time_start) break; entries++; ring_buffer_iter_advance(buf_iter); /* This could be a big loop */ cond_resched(); } per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries; } /* * The current tracer is copied to avoid a global locking * all around. */ static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; int cpu; mutex_lock(&trace_types_lock); if (unlikely(tr->current_trace != iter->trace)) { /* Close iter->trace before switching to the new current tracer */ if (iter->trace->close) iter->trace->close(iter); iter->trace = tr->current_trace; /* Reopen the new current tracer */ if (iter->trace->open) iter->trace->open(iter); } mutex_unlock(&trace_types_lock); #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return ERR_PTR(-EBUSY); #endif if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; iter->idx = -1; if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) tracing_iter_reset(iter, cpu); } else tracing_iter_reset(iter, cpu_file); iter->leftover = 0; for (p = iter; p && l < *pos; p = s_next(m, p, &l)) ; } else { /* * If we overflowed the seq_file before, then we want * to just reuse the trace_seq buffer again. */ if (iter->leftover) p = iter; else { l = *pos - 1; p = s_next(m, p, &l); } } trace_event_read_lock(); trace_access_lock(cpu_file); return p; } static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return; #endif trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } static void get_total_entries_cpu(struct array_buffer *buf, unsigned long *total, unsigned long *entries, int cpu) { unsigned long count; count = ring_buffer_entries_cpu(buf->buffer, cpu); /* * If this buffer has skipped entries, then we hold all * entries for the trace and we need to ignore the * ones before the time stamp. */ if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; /* total is the same as the entries */ *total = count; } else *total = count + ring_buffer_overrun_cpu(buf->buffer, cpu); *entries = count; } static void get_total_entries(struct array_buffer *buf, unsigned long *total, unsigned long *entries) { unsigned long t, e; int cpu; *total = 0; *entries = 0; for_each_tracing_cpu(cpu) { get_total_entries_cpu(buf, &t, &e, cpu); *total += t; *entries += e; } } unsigned long trace_total_entries_cpu(struct trace_array *tr, int cpu) { unsigned long total, entries; if (!tr) tr = &global_trace; get_total_entries_cpu(&tr->array_buffer, &total, &entries, cpu); return entries; } unsigned long trace_total_entries(struct trace_array *tr) { unsigned long total, entries; if (!tr) tr = &global_trace; get_total_entries(&tr->array_buffer, &total, &entries); return entries; } static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n" "# / _-----=> irqs-off/BH-disabled\n" "# | / _----=> need-resched \n" "# || / _---=> hardirq/softirq \n" "# ||| / _--=> preempt-depth \n" "# |||| / _-=> migrate-disable \n" "# ||||| / delay \n" "# cmd pid |||||| time | caller \n" "# \\ / |||||| \\ | / \n"); } static void print_event_info(struct array_buffer *buf, struct seq_file *m) { unsigned long total; unsigned long entries; get_total_entries(buf, &total, &entries); seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n", entries, total, num_online_cpus()); seq_puts(m, "#\n"); } static void print_func_help_header(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; print_event_info(buf, m); seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; static const char space[] = " "; int prec = tgid ? 12 : 2; print_event_info(buf, m); seq_printf(m, "# %.*s _-----=> irqs-off/BH-disabled\n", prec, space); seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); seq_printf(m, "# %.*s||| / _-=> migrate-disable\n", prec, space); seq_printf(m, "# %.*s|||| / delay\n", prec, space); seq_printf(m, "# TASK-PID %.*s CPU# ||||| TIMESTAMP FUNCTION\n", prec, " TGID "); seq_printf(m, "# | | %.*s | ||||| | |\n", prec, " | "); } void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (global_trace.trace_flags & TRACE_ITER_SYM_MASK); struct array_buffer *buf = iter->array_buffer; struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); struct tracer *type = iter->trace; unsigned long entries; unsigned long total; const char *name = type->name; get_total_entries(buf, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, init_utsname()->release); seq_puts(m, "# -----------------------------------" "---------------------------------\n"); seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" " (M:%s VP:%d, KP:%d, SP:%d HP:%d", nsecs_to_usecs(data->saved_latency), entries, total, buf->cpu, preempt_model_none() ? "server" : preempt_model_voluntary() ? "desktop" : preempt_model_full() ? "preempt" : preempt_model_lazy() ? "lazy" : preempt_model_rt() ? "preempt_rt" : "unknown", /* These are reserved for later use */ 0, 0, 0, 0); #ifdef CONFIG_SMP seq_printf(m, " #P:%d)\n", num_online_cpus()); #else seq_puts(m, ")\n"); #endif seq_puts(m, "# -----------------\n"); seq_printf(m, "# | task: %.16s-%d " "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", data->comm, data->pid, from_kuid_munged(seq_user_ns(m), data->uid), data->nice, data->policy, data->rt_priority); seq_puts(m, "# -----------------\n"); if (data->critical_start) { seq_puts(m, "# => started at: "); seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); trace_print_seq(m, &iter->seq); seq_puts(m, "\n# => ended at: "); seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); trace_print_seq(m, &iter->seq); seq_puts(m, "\n#\n"); } seq_puts(m, "#\n"); } static void test_cpu_buff_start(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_array *tr = iter->tr; if (!(tr->trace_flags & TRACE_ITER_ANNOTATE)) return; if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) return; if (cpumask_available(iter->started) && cpumask_test_cpu(iter->cpu, iter->started)) return; if (per_cpu_ptr(iter->array_buffer->data, iter->cpu)->skipped_entries) return; if (cpumask_available(iter->started)) cpumask_set_cpu(iter->cpu, iter->started); /* Don't print started cpu buffer for the first entry of the trace */ if (iter->idx > 1) trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu); } static enum print_line_t print_trace_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; unsigned long sym_flags = (tr->trace_flags & TRACE_ITER_SYM_MASK); struct trace_entry *entry; struct trace_event *event; entry = iter->ent; test_cpu_buff_start(iter); event = ftrace_find_event(entry->type); if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { if (iter->iter_flags & TRACE_FILE_LAT_FMT) trace_print_lat_context(iter); else trace_print_context(iter); } if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); /* * For TRACE_EVENT() events, the print_fmt is not * safe to use if the array has delta offsets * Force printing via the fields. */ if ((tr->text_delta || tr->data_delta) && event->type > __TRACE_LAST_TYPE) return print_event_fields(iter, event); return event->funcs->trace(iter, sym_flags, event); } trace_seq_printf(s, "Unknown type %d\n", entry->type); return trace_handle_return(s); } static enum print_line_t print_raw_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) trace_seq_printf(s, "%d %d %llu ", entry->pid, iter->cpu, iter->ts); if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; event = ftrace_find_event(entry->type); if (event) return event->funcs->raw(iter, 0, event); trace_seq_printf(s, "%d ?\n", entry->type); return trace_handle_return(s); } static enum print_line_t print_hex_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; unsigned char newline = '\n'; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { SEQ_PUT_HEX_FIELD(s, entry->pid); SEQ_PUT_HEX_FIELD(s, iter->cpu); SEQ_PUT_HEX_FIELD(s, iter->ts); if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; } event = ftrace_find_event(entry->type); if (event) { enum print_line_t ret = event->funcs->hex(iter, 0, event); if (ret != TRACE_TYPE_HANDLED) return ret; } SEQ_PUT_FIELD(s, newline); return trace_handle_return(s); } static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { SEQ_PUT_FIELD(s, entry->pid); SEQ_PUT_FIELD(s, iter->cpu); SEQ_PUT_FIELD(s, iter->ts); if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; } event = ftrace_find_event(entry->type); return event ? event->funcs->binary(iter, 0, event) : TRACE_TYPE_HANDLED; } int trace_empty(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { cpu = iter->cpu_file; buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } return 1; } for_each_tracing_cpu(cpu) { buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } } return 1; } /* Called with trace_event_read_lock() held. */ enum print_line_t print_trace_line(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; unsigned long trace_flags = tr->trace_flags; enum print_line_t ret; if (iter->lost_events) { if (iter->lost_events == (unsigned long)-1) trace_seq_printf(&iter->seq, "CPU:%d [LOST EVENTS]\n", iter->cpu); else trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", iter->cpu, iter->lost_events); if (trace_seq_has_overflowed(&iter->seq)) return TRACE_TYPE_PARTIAL_LINE; } if (iter->trace && iter->trace->print_line) { ret = iter->trace->print_line(iter); if (ret != TRACE_TYPE_UNHANDLED) return ret; } if (iter->ent->type == TRACE_BPUTS && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_bputs_msg_only(iter); if (iter->ent->type == TRACE_BPRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_bprintk_msg_only(iter); if (iter->ent->type == TRACE_PRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_printk_msg_only(iter); if (trace_flags & TRACE_ITER_BIN) return print_bin_fmt(iter); if (trace_flags & TRACE_ITER_HEX) return print_hex_fmt(iter); if (trace_flags & TRACE_ITER_RAW) return print_raw_fmt(iter); return print_trace_fmt(iter); } void trace_latency_header(struct seq_file *m) { struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) print_trace_header(m, iter); if (!(tr->trace_flags & TRACE_ITER_VERBOSE)) print_lat_help_header(m); } void trace_default_header(struct seq_file *m) { struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; unsigned long trace_flags = tr->trace_flags; if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) { /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; print_trace_header(m, iter); if (!(trace_flags & TRACE_ITER_VERBOSE)) print_lat_help_header(m); } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) print_func_help_header_irq(iter->array_buffer, m, trace_flags); else print_func_help_header(iter->array_buffer, m, trace_flags); } } } static void test_ftrace_alive(struct seq_file *m) { if (!ftrace_is_dead()) return; seq_puts(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n" "# MAY BE MISSING FUNCTION EVENTS\n"); } #ifdef CONFIG_TRACER_MAX_TRACE static void show_snapshot_main_help(struct seq_file *m) { seq_puts(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n" "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" "# Takes a snapshot of the main buffer.\n" "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n" "# (Doesn't have to be '2' works with any number that\n" "# is not a '0' or '1')\n"); } static void show_snapshot_percpu_help(struct seq_file *m) { seq_puts(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP seq_puts(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" "# Takes a snapshot of the main buffer for this cpu.\n"); #else seq_puts(m, "# echo 1 > snapshot : Not supported with this kernel.\n" "# Must use main snapshot file to allocate.\n"); #endif seq_puts(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n" "# (Doesn't have to be '2' works with any number that\n" "# is not a '0' or '1')\n"); } static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { if (iter->tr->allocated_snapshot) seq_puts(m, "#\n# * Snapshot is allocated *\n#\n"); else seq_puts(m, "#\n# * Snapshot is freed *\n#\n"); seq_puts(m, "# Snapshot commands:\n"); if (iter->cpu_file == RING_BUFFER_ALL_CPUS) show_snapshot_main_help(m); else show_snapshot_percpu_help(m); } #else /* Should never be called */ static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { } #endif static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; int ret; if (iter->ent == NULL) { if (iter->tr) { seq_printf(m, "# tracer: %s\n", iter->trace->name); seq_puts(m, "#\n"); test_ftrace_alive(m); } if (iter->snapshot && trace_empty(iter)) print_snapshot_help(m, iter); else if (iter->trace && iter->trace->print_header) iter->trace->print_header(m); else trace_default_header(m); } else if (iter->leftover) { /* * If we filled the seq_file buffer earlier, we * want to just show it now. */ ret = trace_print_seq(m, &iter->seq); /* ret should this time be zero, but you never know */ iter->leftover = ret; } else { ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { iter->seq.full = 0; trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will * ask us for this data again at start up. * Use that instead. * ret is 0 if seq_file write succeeded. * -1 otherwise. */ iter->leftover = ret; } return 0; } /* * Should be used after trace_array_get(), trace_types_lock * ensures that i_cdev was already initialized. */ static inline int tracing_get_cpu(struct inode *inode) { if (inode->i_cdev) /* See trace_create_cpu_file() */ return (long)inode->i_cdev - 1; return RING_BUFFER_ALL_CPUS; } static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show, }; /* * Note, as iter itself can be allocated and freed in different * ways, this function is only used to free its content, and not * the iterator itself. The only requirement to all the allocations * is that it must zero all fields (kzalloc), as freeing works with * ethier allocated content or NULL. */ static void free_trace_iter_content(struct trace_iterator *iter) { /* The fmt is either NULL, allocated or points to static_fmt_buf */ if (iter->fmt != static_fmt_buf) kfree(iter->fmt); kfree(iter->temp); kfree(iter->buffer_iter); mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); } static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int cpu; if (tracing_disabled) return ERR_PTR(-ENODEV); iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter)); if (!iter) return ERR_PTR(-ENOMEM); iter->buffer_iter = kcalloc(nr_cpu_ids, sizeof(*iter->buffer_iter), GFP_KERNEL); if (!iter->buffer_iter) goto release; /* * trace_find_next_entry() may need to save off iter->ent. * It will place it into the iter->temp buffer. As most * events are less than 128, allocate a buffer of that size. * If one is greater, then trace_find_next_entry() will * allocate a new buffer to adjust for the bigger iter->ent. * It's not critical if it fails to get allocated here. */ iter->temp = kmalloc(128, GFP_KERNEL); if (iter->temp) iter->temp_size = 128; /* * trace_event_printf() may need to modify given format * string to replace %p with %px so that it shows real address * instead of hash value. However, that is only for the event * tracing, other tracer may not need. Defer the allocation * until it is needed. */ iter->fmt = NULL; iter->fmt_size = 0; mutex_lock(&trace_types_lock); iter->trace = tr->current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; iter->tr = tr; #ifdef CONFIG_TRACER_MAX_TRACE /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) iter->array_buffer = &tr->max_buffer; else #endif iter->array_buffer = &tr->array_buffer; iter->snapshot = snapshot; iter->pos = -1; iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); /* Notify the tracer early; before we stop tracing. */ if (iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; /* * If pause-on-trace is enabled, then stop the trace while * dumping, unless this is the "snapshot" file */ if (!iter->snapshot && (tr->trace_flags & TRACE_ITER_PAUSE_ON_TRACE)) tracing_stop_tr(tr); if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = ring_buffer_read_prepare(iter->array_buffer->buffer, cpu, GFP_KERNEL); } ring_buffer_read_prepare_sync(); for_each_tracing_cpu(cpu) { ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); } } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = ring_buffer_read_prepare(iter->array_buffer->buffer, cpu, GFP_KERNEL); ring_buffer_read_prepare_sync(); ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); } mutex_unlock(&trace_types_lock); return iter; fail: mutex_unlock(&trace_types_lock); free_trace_iter_content(iter); release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } int tracing_open_generic(struct inode *inode, struct file *filp) { int ret; ret = tracing_check_open_get_tr(NULL); if (ret) return ret; filp->private_data = inode->i_private; return 0; } bool tracing_is_disabled(void) { return (tracing_disabled) ? true: false; } /* * Open and update trace_array ref count. * Must have the current trace_array passed to it. */ int tracing_open_generic_tr(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; filp->private_data = inode->i_private; return 0; } /* * The private pointer of the inode is the trace_event_file. * Update the tr ref count associated to it. */ int tracing_open_file_tr(struct inode *inode, struct file *filp) { struct trace_event_file *file = inode->i_private; int ret; ret = tracing_check_open_get_tr(file->tr); if (ret) return ret; mutex_lock(&event_mutex); /* Fail if the file is marked for removal */ if (file->flags & EVENT_FILE_FL_FREED) { trace_array_put(file->tr); ret = -ENODEV; } else { event_file_get(file); } mutex_unlock(&event_mutex); if (ret) return ret; filp->private_data = inode->i_private; return 0; } int tracing_release_file_tr(struct inode *inode, struct file *filp) { struct trace_event_file *file = inode->i_private; trace_array_put(file->tr); event_file_put(file); return 0; } int tracing_single_release_file_tr(struct inode *inode, struct file *filp) { tracing_release_file_tr(inode, filp); return single_release(inode, filp); } static int tracing_mark_open(struct inode *inode, struct file *filp) { stream_open(inode, filp); return tracing_open_generic_tr(inode, filp); } static int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct seq_file *m = file->private_data; struct trace_iterator *iter; int cpu; if (!(file->f_mode & FMODE_READ)) { trace_array_put(tr); return 0; } /* Writes do not use seq_file */ iter = m->private; mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); } if (iter->trace && iter->trace->close) iter->trace->close(iter); if (!iter->snapshot && tr->stop_count) /* reenable tracing if it was previously enabled */ tracing_start_tr(tr); __trace_array_put(tr); mutex_unlock(&trace_types_lock); free_trace_iter_content(iter); seq_release_private(inode, file); return 0; } int tracing_release_generic_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return 0; } static int tracing_single_release_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return single_release(inode, file); } static int tracing_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); struct array_buffer *trace_buf = &tr->array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE if (tr->current_trace->print_max) trace_buf = &tr->max_buffer; #endif if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(trace_buf); else tracing_reset_cpu(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, false); if (IS_ERR(iter)) ret = PTR_ERR(iter); else if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; } if (ret < 0) trace_array_put(tr); return ret; } /* * Some tracers are not suitable for instance buffers. * A tracer is always available for the global array (toplevel) * or if it explicitly states that it is. */ static bool trace_ok_for_array(struct tracer *t, struct trace_array *tr) { #ifdef CONFIG_TRACER_SNAPSHOT /* arrays with mapped buffer range do not have snapshots */ if (tr->range_addr_start && t->use_max_tr) return false; #endif return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; } /* Find the next tracer that this trace array may use */ static struct tracer * get_tracer_for_array(struct trace_array *tr, struct tracer *t) { while (t && !trace_ok_for_array(t, tr)) t = t->next; return t; } static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; struct tracer *t = v; (*pos)++; if (t) t = get_tracer_for_array(tr, t->next); return t; } static void *t_start(struct seq_file *m, loff_t *pos) { struct trace_array *tr = m->private; struct tracer *t; loff_t l = 0; mutex_lock(&trace_types_lock); t = get_tracer_for_array(tr, trace_types); for (; t && l < *pos; t = t_next(m, t, &l)) ; return t; } static void t_stop(struct seq_file *m, void *p) { mutex_unlock(&trace_types_lock); } static int t_show(struct seq_file *m, void *v) { struct tracer *t = v; if (!t) return 0; seq_puts(m, t->name); if (t->next) seq_putc(m, ' '); else seq_putc(m, '\n'); return 0; } static const struct seq_operations show_traces_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, .show = t_show, }; static int show_traces_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct seq_file *m; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = seq_open(file, &show_traces_seq_ops); if (ret) { trace_array_put(tr); return ret; } m = file->private_data; m->private = tr; return 0; } static int tracing_seq_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return seq_release(inode, file); } static ssize_t tracing_write_stub(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { return count; } loff_t tracing_lseek(struct file *file, loff_t offset, int whence) { int ret; if (file->f_mode & FMODE_READ) ret = seq_lseek(file, offset, whence); else file->f_pos = ret = 0; return ret; } static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, .read_iter = seq_read_iter, .splice_read = copy_splice_read, .write = tracing_write_stub, .llseek = tracing_lseek, .release = tracing_release, }; static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_seq_release, }; static ssize_t tracing_cpumask_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct trace_array *tr = file_inode(filp)->i_private; char *mask_str; int len; len = snprintf(NULL, 0, "%*pb\n", cpumask_pr_args(tr->tracing_cpumask)) + 1; mask_str = kmalloc(len, GFP_KERNEL); if (!mask_str) return -ENOMEM; len = snprintf(mask_str, len, "%*pb\n", cpumask_pr_args(tr->tracing_cpumask)); if (len >= count) { count = -EINVAL; goto out_err; } count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len); out_err: kfree(mask_str); return count; } int tracing_set_cpumask(struct trace_array *tr, cpumask_var_t tracing_cpumask_new) { int cpu; if (!tr) return -EINVAL; local_irq_disable(); arch_spin_lock(&tr->max_lock); for_each_tracing_cpu(cpu) { /* * Increase/decrease the disabled counter if we are * about to flip a bit in the cpumask: */ if (cpumask_test_cpu(cpu, tr->tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); #endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); #endif } } arch_spin_unlock(&tr->max_lock); local_irq_enable(); cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new); return 0; } static ssize_t tracing_cpumask_write(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { struct trace_array *tr = file_inode(filp)->i_private; cpumask_var_t tracing_cpumask_new; int err; if (count == 0 || count > KMALLOC_MAX_SIZE) return -EINVAL; if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); if (err) goto err_free; err = tracing_set_cpumask(tr, tracing_cpumask_new); if (err) goto err_free; free_cpumask_var(tracing_cpumask_new); return count; err_free: free_cpumask_var(tracing_cpumask_new); return err; } static const struct file_operations tracing_cpumask_fops = { .open = tracing_open_generic_tr, .read = tracing_cpumask_read, .write = tracing_cpumask_write, .release = tracing_release_generic_tr, .llseek = generic_file_llseek, }; static int tracing_trace_options_show(struct seq_file *m, void *v) { struct tracer_opt *trace_opts; struct trace_array *tr = m->private; u32 tracer_flags; int i; guard(mutex)(&trace_types_lock); tracer_flags = tr->current_trace->flags->val; trace_opts = tr->current_trace->flags->opts; for (i = 0; trace_options[i]; i++) { if (tr->trace_flags & (1 << i)) seq_printf(m, "%s\n", trace_options[i]); else seq_printf(m, "no%s\n", trace_options[i]); } for (i = 0; trace_opts[i].name; i++) { if (tracer_flags & trace_opts[i].bit) seq_printf(m, "%s\n", trace_opts[i].name); else seq_printf(m, "no%s\n", trace_opts[i].name); } return 0; } static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { struct tracer *trace = tracer_flags->trace; int ret; ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); if (ret) return ret; if (neg) tracer_flags->val &= ~opts->bit; else tracer_flags->val |= opts->bit; return 0; } /* Try to assign a tracer specific option */ static int set_tracer_option(struct trace_array *tr, char *cmp, int neg) { struct tracer *trace = tr->current_trace; struct tracer_flags *tracer_flags = trace->flags; struct tracer_opt *opts = NULL; int i; for (i = 0; tracer_flags->opts[i].name; i++) { opts = &tracer_flags->opts[i]; if (strcmp(cmp, opts->name) == 0) return __set_tracer_option(tr, trace->flags, opts, neg); } return -EINVAL; } /* Some tracers require overwrite to stay enabled */ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) { if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set) return -1; return 0; } int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { if ((mask == TRACE_ITER_RECORD_TGID) || (mask == TRACE_ITER_RECORD_CMD) || (mask == TRACE_ITER_TRACE_PRINTK)) lockdep_assert_held(&event_mutex); /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; /* Give the tracer a chance to approve the change */ if (tr->current_trace->flag_changed) if (tr->current_trace->flag_changed(tr, mask, !!enabled)) return -EINVAL; if (mask == TRACE_ITER_TRACE_PRINTK) { if (enabled) { update_printk_trace(tr); } else { /* * The global_trace cannot clear this. * It's flag only gets cleared if another instance sets it. */ if (printk_trace == &global_trace) return -EINVAL; /* * An instance must always have it set. * by default, that's the global_trace instane. */ if (printk_trace == tr) update_printk_trace(&global_trace); } } if (enabled) tr->trace_flags |= mask; else tr->trace_flags &= ~mask; if (mask == TRACE_ITER_RECORD_CMD) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_RECORD_TGID) { if (trace_alloc_tgid_map() < 0) { tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; return -ENOMEM; } trace_event_enable_tgid_record(enabled); } if (mask == TRACE_ITER_EVENT_FORK) trace_event_follow_fork(tr, enabled); if (mask == TRACE_ITER_FUNC_FORK) ftrace_pid_follow_fork(tr, enabled); if (mask == TRACE_ITER_OVERWRITE) { ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); #endif } if (mask == TRACE_ITER_PRINTK) { trace_printk_start_stop_comm(enabled); trace_printk_control(enabled); } return 0; } int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; int ret; size_t orig_len = strlen(option); int len; cmp = strstrip(option); len = str_has_prefix(cmp, "no"); if (len) neg = 1; cmp += len; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); /* If no option could be set, test the specific tracer options */ if (ret < 0) ret = set_tracer_option(tr, cmp, neg); else ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, * turn it back into a space. */ if (orig_len > strlen(option)) option[strlen(option)] = ' '; return ret; } static void __init apply_trace_boot_options(void) { char *buf = trace_boot_options_buf; char *option; while (true) { option = strsep(&buf, ","); if (!option) break; if (*option) trace_set_options(&global_trace, option); /* Put back the comma to allow this to be called again */ if (buf) *(buf - 1) = ','; } } static ssize_t tracing_trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; char buf[64]; int ret; if (cnt >= sizeof(buf)) return -EINVAL; if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; ret = trace_set_options(tr, buf); if (ret < 0) return ret; *ppos += cnt; return cnt; } static int tracing_trace_options_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = single_open(file, tracing_trace_options_show, inode->i_private); if (ret < 0) trace_array_put(tr); return ret; } static const struct file_operations tracing_iter_fops = { .open = tracing_trace_options_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_single_release_tr, .write = tracing_trace_options_write, }; static const char readme_msg[] = "tracing mini-HOWTO:\n\n" "By default tracefs removes all OTH file permission bits.\n" "When mounting tracefs an optional group id can be specified\n" "which adds the group to every directory and file in tracefs:\n\n" "\t e.g. mount -t tracefs [-o [gid=<gid>]] nodev /sys/kernel/tracing\n\n" "# echo 0 > tracing_on : quick way to disable tracing\n" "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" " Important files:\n" " trace\t\t\t- The static contents of the buffer\n" "\t\t\t To clear the buffer write into this file: echo > trace\n" " trace_pipe\t\t- A consuming read to see the contents of the buffer\n" " current_tracer\t- function and latency tracers\n" " available_tracers\t- list of configured tracers for current_tracer\n" " error_log\t- error log for failed commands (that support it)\n" " buffer_size_kb\t- view and modify size of per cpu buffer\n" " buffer_total_size_kb - view total size of all cpu buffers\n\n" " trace_clock\t\t- change the clock used to order events\n" " local: Per cpu clock but may not be synced across CPUs\n" " global: Synced across CPUs but slows tracing down.\n" " counter: Not a clock, but just an increment\n" " uptime: Jiffy counter from time of boot\n" " perf: Same clock that perf events use\n" #ifdef CONFIG_X86_64 " x86-tsc: TSC cycle counter\n" #endif "\n timestamp_mode\t- view the mode used to timestamp events\n" " delta: Delta difference against a buffer-wide timestamp\n" " absolute: Absolute (standalone) timestamp\n" "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" "\n trace_marker_raw\t\t- Writes into this file writes binary data into the kernel buffer\n" " tracing_cpumask\t- Limit which CPUs to trace\n" " instances\t\t- Make sub-buffers with: mkdir instances/foo\n" "\t\t\t Remove sub-buffer with rmdir\n" " trace_options\t\t- Set format or modify how tracing happens\n" "\t\t\t Disable an option by prefixing 'no' to the\n" "\t\t\t option name\n" " saved_cmdlines_size\t- echo command number in here to store comm-pid list\n" #ifdef CONFIG_DYNAMIC_FTRACE "\n available_filter_functions - list of functions that can be filtered on\n" " set_ftrace_filter\t- echo function name in here to only trace these\n" "\t\t\t functions\n" "\t accepts: func_full_name or glob-matching-pattern\n" "\t modules: Can select a group via module\n" "\t Format: :mod:<module-name>\n" "\t example: echo :mod:ext3 > set_ftrace_filter\n" "\t triggers: a command to perform when function is hit\n" "\t Format: <function>:<trigger>[:count]\n" "\t trigger: traceon, traceoff\n" "\t\t enable_event:<system>:<event>\n" "\t\t disable_event:<system>:<event>\n" #ifdef CONFIG_STACKTRACE "\t\t stacktrace\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT "\t\t snapshot\n" #endif "\t\t dump\n" "\t\t cpudump\n" "\t example: echo do_fault:traceoff > set_ftrace_filter\n" "\t echo do_trap:traceoff:3 > set_ftrace_filter\n" "\t The first one will disable tracing every time do_fault is hit\n" "\t The second will disable tracing at most 3 times when do_trap is hit\n" "\t The first time do trap is hit and it disables tracing, the\n" "\t counter will decrement to 2. If tracing is already disabled,\n" "\t the counter will not decrement. It only decrements when the\n" "\t trigger did work\n" "\t To remove trigger without count:\n" "\t echo '!<function>:<trigger> > set_ftrace_filter\n" "\t To remove trigger with a count:\n" "\t echo '!<function>:<trigger>:0 > set_ftrace_filter\n" " set_ftrace_notrace\t- echo function name in here to never trace.\n" "\t accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" "\t modules: Can select a group via module command :mod:\n" "\t Does not accept triggers\n" #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_TRACER " set_ftrace_pid\t- Write pid(s) to only function trace those pids\n" "\t\t (function)\n" " set_ftrace_notrace_pid\t- Write pid(s) to not function trace those pids\n" "\t\t (function)\n" #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" " set_graph_notrace\t- Do not trace the nested calls of a function (function_graph)\n" " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT "\n snapshot\t\t- Like 'trace' but shows the content of the static\n" "\t\t\t snapshot buffer. Read the contents for more\n" "\t\t\t information\n" #endif #ifdef CONFIG_STACK_TRACER " stack_trace\t\t- Shows the max stack trace when active\n" " stack_max_size\t- Shows current max stack size that was traced\n" "\t\t\t Write into this file to reset the max size (trigger a\n" "\t\t\t new trace)\n" #ifdef CONFIG_DYNAMIC_FTRACE " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace\n" "\t\t\t traces\n" #endif #endif /* CONFIG_STACK_TRACER */ #ifdef CONFIG_DYNAMIC_EVENTS " dynamic_events\t\t- Create/append/remove/show the generic dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_KPROBE_EVENTS " kprobe_events\t\t- Create/append/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_UPROBE_EVENTS " uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) || \ defined(CONFIG_FPROBE_EVENTS) "\t accepts: event-definitions (one definition per line)\n" #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) "\t Format: p[:[<group>/][<event>]] <place> [<args>]\n" "\t r[maxactive][:[<group>/][<event>]] <place> [<args>]\n" #endif #ifdef CONFIG_FPROBE_EVENTS "\t f[:[<group>/][<event>]] <func-name>[%return] [<args>]\n" "\t t[:[<group>/][<event>]] <tracepoint> [<args>]\n" #endif #ifdef CONFIG_HIST_TRIGGERS "\t s:[synthetic/]<event> <field> [<field>]\n" #endif "\t e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>] [if <filter>]\n" "\t -:[<group>/][<event>]\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS " place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n" #endif "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" #ifdef CONFIG_PROBE_EVENTS_BTF_ARGS "\t <argname>[->field[->field|.field...]],\n" #endif #else "\t $stack<index>, $stack, $retval, $comm,\n" #endif "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n" "\t kernel return probes support: $retval, $arg<N>, $comm\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t symstr, %pd/%pD, <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS "\t field: <stype> <name>;\n" "\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n" "\t [unsigned] char/int/long\n" #endif "\t efield: For event probes ('e' types), the field is on of the fields\n" "\t of the <attached-group>/<attached-event>.\n" #endif " set_event\t\t- Enables events by name written into it\n" "\t\t\t Can enable module events via: :mod:<module>\n" " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" " events/<system>/\t- Directory containing all trace events for <system>:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all <system>\n" "\t\t\t events\n" " filter\t\t- If set, only events passing filter are traced\n" " events/<system>/<event>/\t- Directory containing control files for\n" "\t\t\t <event>:\n" " enable\t\t- Write 0/1 to enable/disable tracing of <event>\n" " filter\t\t- If set, only events passing filter are traced\n" " trigger\t\t- If set, a command to perform when event is hit\n" "\t Format: <trigger>[:count][if <filter>]\n" "\t trigger: traceon, traceoff\n" "\t enable_event:<system>:<event>\n" "\t disable_event:<system>:<event>\n" #ifdef CONFIG_HIST_TRIGGERS "\t enable_hist:<system>:<event>\n" "\t disable_hist:<system>:<event>\n" #endif #ifdef CONFIG_STACKTRACE "\t\t stacktrace\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT "\t\t snapshot\n" #endif #ifdef CONFIG_HIST_TRIGGERS "\t\t hist (see below)\n" #endif "\t example: echo traceoff > events/block/block_unplug/trigger\n" "\t echo traceoff:3 > events/block/block_unplug/trigger\n" "\t echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n" "\t events/block/block_unplug/trigger\n" "\t The first disables tracing every time block_unplug is hit.\n" "\t The second disables tracing the first 3 times block_unplug is hit.\n" "\t The third enables the kmalloc event the first 3 times block_unplug\n" "\t is hit and has value of greater than 1 for the 'nr_rq' event field.\n" "\t Like function triggers, the counter is only decremented if it\n" "\t enabled or disabled tracing.\n" "\t To remove a trigger without a count:\n" "\t echo '!<trigger> > <system>/<event>/trigger\n" "\t To remove a trigger with a count:\n" "\t echo '!<trigger>:0 > <system>/<event>/trigger\n" "\t Filters can be ignored when removing a trigger.\n" #ifdef CONFIG_HIST_TRIGGERS " hist trigger\t- If set, event hits are aggregated into a hash table\n" "\t Format: hist:keys=<field1[,field2,...]>\n" "\t [:<var1>=<field|var_ref|numeric_literal>[,<var2>=...]]\n" "\t [:values=<field1[,field2,...]>]\n" "\t [:sort=<field1[,field2,...]>]\n" "\t [:size=#entries]\n" "\t [:pause][:continue][:clear]\n" "\t [:name=histname1]\n" "\t [:nohitcount]\n" "\t [:<handler>.<action>]\n" "\t [if <filter>]\n\n" "\t Note, special fields can be used as well:\n" "\t common_timestamp - to record current timestamp\n" "\t common_cpu - to record the CPU the event happened on\n" "\n" "\t A hist trigger variable can be:\n" "\t - a reference to a field e.g. x=current_timestamp,\n" "\t - a reference to another variable e.g. y=$x,\n" "\t - a numeric literal: e.g. ms_per_sec=1000,\n" "\t - an arithmetic expression: e.g. time_secs=current_timestamp/1000\n" "\n" "\t hist trigger arithmetic expressions support addition(+), subtraction(-),\n" "\t multiplication(*) and division(/) operators. An operand can be either a\n" "\t variable reference, field or numeric literal.\n" "\n" "\t When a matching event is hit, an entry is added to a hash\n" "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" "\t specified using the 'sort' keyword. The sort direction can\n" "\t be modified by appending '.descending' or '.ascending' to a\n" "\t sort field. The 'size' parameter can be used to specify more\n" "\t or fewer than the default 2048 entries for the hashtable size.\n" "\t If a hist trigger is given a name using the 'name' parameter,\n" "\t its histogram data will be shared with other triggers of the\n" "\t same name, and trigger hits will update this common data.\n\n" "\t Reading the 'hist' file for the event will dump the hash\n" "\t table in its entirety to stdout. If there are multiple hist\n" "\t triggers attached to an event, there will be a table for each\n" "\t trigger in the output. The table displayed for a named\n" "\t trigger will be the same as any other instance having the\n" "\t same name. The default format used to display a given field\n" "\t can be modified by appending any of the following modifiers\n" "\t to the field name, as applicable:\n\n" "\t .hex display a number as a hex value\n" "\t .sym display an address as a symbol\n" "\t .sym-offset display an address as a symbol and offset\n" "\t .execname display a common_pid as a program name\n" "\t .syscall display a syscall id as a syscall name\n" "\t .log2 display log2 value rather than raw number\n" "\t .buckets=size display values in groups of size rather than raw number\n" "\t .usecs display a common_timestamp in microseconds\n" "\t .percent display a number of percentage value\n" "\t .graph display a bar-graph of a value\n\n" "\t The 'pause' parameter can be used to pause an existing hist\n" "\t trigger or to start a hist trigger but not log any events\n" "\t until told to do so. 'continue' can be used to start or\n" "\t restart a paused hist trigger.\n\n" "\t The 'clear' parameter will clear the contents of a running\n" "\t hist trigger and leave its current paused/active state\n" "\t unchanged.\n\n" "\t The 'nohitcount' (or NOHC) parameter will suppress display of\n" "\t raw hitcount in the histogram.\n\n" "\t The enable_hist and disable_hist triggers can be used to\n" "\t have one event conditionally start and stop another event's\n" "\t already-attached hist trigger. The syntax is analogous to\n" "\t the enable_event and disable_event triggers.\n\n" "\t Hist trigger handlers and actions are executed whenever a\n" "\t a histogram entry is added or updated. They take the form:\n\n" "\t <handler>.<action>\n\n" "\t The available handlers are:\n\n" "\t onmatch(matching.event) - invoke on addition or update\n" "\t onmax(var) - invoke if var exceeds current max\n" "\t onchange(var) - invoke action if var changes\n\n" "\t The available actions are:\n\n" "\t trace(<synthetic_event>,param list) - generate synthetic event\n" "\t save(field,...) - save current event fields\n" #ifdef CONFIG_TRACER_SNAPSHOT "\t snapshot() - snapshot the trace buffer\n\n" #endif #ifdef CONFIG_SYNTH_EVENTS " events/synthetic_events\t- Create/append/remove/show synthetic events\n" "\t Write into this file to define/undefine new synthetic events.\n" "\t example: echo 'myevent u64 lat; char name[]; long[] stack' >> synthetic_events\n" #endif #endif ; static ssize_t tracing_readme_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { return simple_read_from_buffer(ubuf, cnt, ppos, readme_msg, strlen(readme_msg)); } static const struct file_operations tracing_readme_fops = { .open = tracing_open_generic, .read = tracing_readme_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_TRACE_EVAL_MAP_FILE static union trace_eval_map_item * update_eval_map(union trace_eval_map_item *ptr) { if (!ptr->map.eval_string) { if (ptr->tail.next) { ptr = ptr->tail.next; /* Set ptr to the next real item (skip head) */ ptr++; } else return NULL; } return ptr; } static void *eval_map_next(struct seq_file *m, void *v, loff_t *pos) { union trace_eval_map_item *ptr = v; /* * Paranoid! If ptr points to end, we don't want to increment past it. * This really should never happen. */ (*pos)++; ptr = update_eval_map(ptr); if (WARN_ON_ONCE(!ptr)) return NULL; ptr++; ptr = update_eval_map(ptr); return ptr; } static void *eval_map_start(struct seq_file *m, loff_t *pos) { union trace_eval_map_item *v; loff_t l = 0; mutex_lock(&trace_eval_mutex); v = trace_eval_maps; if (v) v++; while (v && l < *pos) { v = eval_map_next(m, v, &l); } return v; } static void eval_map_stop(struct seq_file *m, void *v) { mutex_unlock(&trace_eval_mutex); } static int eval_map_show(struct seq_file *m, void *v) { union trace_eval_map_item *ptr = v; seq_printf(m, "%s %ld (%s)\n", ptr->map.eval_string, ptr->map.eval_value, ptr->map.system); return 0; } static const struct seq_operations tracing_eval_map_seq_ops = { .start = eval_map_start, .next = eval_map_next, .stop = eval_map_stop, .show = eval_map_show, }; static int tracing_eval_map_open(struct inode *inode, struct file *filp) { int ret; ret = tracing_check_open_get_tr(NULL); if (ret) return ret; return seq_open(filp, &tracing_eval_map_seq_ops); } static const struct file_operations tracing_eval_map_fops = { .open = tracing_eval_map_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static inline union trace_eval_map_item * trace_eval_jmp_to_tail(union trace_eval_map_item *ptr) { /* Return tail of array given the head */ return ptr + ptr->head.length + 1; } static void trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, int len) { struct trace_eval_map **stop; struct trace_eval_map **map; union trace_eval_map_item *map_array; union trace_eval_map_item *ptr; stop = start + len; /* * The trace_eval_maps contains the map plus a head and tail item, * where the head holds the module and length of array, and the * tail holds a pointer to the next list. */ map_array = kmalloc_array(len + 2, sizeof(*map_array), GFP_KERNEL); if (!map_array) { pr_warn("Unable to allocate trace eval mapping\n"); return; } guard(mutex)(&trace_eval_mutex); if (!trace_eval_maps) trace_eval_maps = map_array; else { ptr = trace_eval_maps; for (;;) { ptr = trace_eval_jmp_to_tail(ptr); if (!ptr->tail.next) break; ptr = ptr->tail.next; } ptr->tail.next = map_array; } map_array->head.mod = mod; map_array->head.length = len; map_array++; for (map = start; (unsigned long)map < (unsigned long)stop; map++) { map_array->map = **map; map_array++; } memset(map_array, 0, sizeof(*map_array)); } static void trace_create_eval_file(struct dentry *d_tracer) { trace_create_file("eval_map", TRACE_MODE_READ, d_tracer, NULL, &tracing_eval_map_fops); } #else /* CONFIG_TRACE_EVAL_MAP_FILE */ static inline void trace_create_eval_file(struct dentry *d_tracer) { } static inline void trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, int len) { } #endif /* !CONFIG_TRACE_EVAL_MAP_FILE */ static void trace_insert_eval_map(struct module *mod, struct trace_eval_map **start, int len) { struct trace_eval_map **map; if (len <= 0) return; map = start; trace_event_eval_update(map, len); trace_insert_eval_map_file(mod, start, len); } static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+2]; int r; mutex_lock(&trace_types_lock); r = sprintf(buf, "%s\n", tr->current_trace->name); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } int tracer_init(struct tracer *t, struct trace_array *tr) { tracing_reset_online_cpus(&tr->array_buffer); return t->init(tr); } static void set_buffer_entries(struct array_buffer *buf, unsigned long val) { int cpu; for_each_tracing_cpu(cpu) per_cpu_ptr(buf->data, cpu)->entries = val; } static void update_buffer_entries(struct array_buffer *buf, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0)); } else { per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu); } } #ifdef CONFIG_TRACER_MAX_TRACE /* resize @tr's buffer to the size of @size_tr's entries */ static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, struct array_buffer *size_buf, int cpu_id) { int cpu, ret = 0; if (cpu_id == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { ret = ring_buffer_resize(trace_buf->buffer, per_cpu_ptr(size_buf->data, cpu)->entries, cpu); if (ret < 0) break; per_cpu_ptr(trace_buf->data, cpu)->entries = per_cpu_ptr(size_buf->data, cpu)->entries; } } else { ret = ring_buffer_resize(trace_buf->buffer, per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); if (ret == 0) per_cpu_ptr(trace_buf->data, cpu_id)->entries = per_cpu_ptr(size_buf->data, cpu_id)->entries; } return ret; } #endif /* CONFIG_TRACER_MAX_TRACE */ static int __tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu) { int ret; /* * If kernel or user changes the size of the ring buffer * we use the size that was given, and we can forget about * expanding it later. */ trace_set_ring_buffer_expanded(tr); /* May be called before buffers are initialized */ if (!tr->array_buffer.buffer) return 0; /* Do not allow tracing while resizing ring buffer */ tracing_stop_tr(tr); ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); if (ret < 0) goto out_start; #ifdef CONFIG_TRACER_MAX_TRACE if (!tr->allocated_snapshot) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); if (ret < 0) { int r = resize_buffer_duplicate_size(&tr->array_buffer, &tr->array_buffer, cpu); if (r < 0) { /* * AARGH! We are left with different * size max buffer!!!! * The max buffer is our "snapshot" buffer. * When a tracer needs a snapshot (one of the * latency tracers), it swaps the max buffer * with the saved snap shot. We succeeded to * update the size of the main buffer, but failed to * update the size of the max buffer. But when we tried * to reset the main buffer to the original size, we * failed there too. This is very unlikely to * happen, but if it does, warn and kill all * tracing. */ WARN_ON(1); tracing_disabled = 1; } goto out_start; } update_buffer_entries(&tr->max_buffer, cpu); out: #endif /* CONFIG_TRACER_MAX_TRACE */ update_buffer_entries(&tr->array_buffer, cpu); out_start: tracing_start_tr(tr); return ret; } ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id) { guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { /* make sure, this cpu is enabled in the mask */ if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) return -EINVAL; } return __tracing_resize_ring_buffer(tr, size, cpu_id); } static void update_last_data(struct trace_array *tr) { if (!tr->text_delta && !tr->data_delta) return; /* * Need to clear all CPU buffers as there cannot be events * from the previous boot mixed with events with this boot * as that will cause a confusing trace. Need to clear all * CPU buffers, even for those that may currently be offline. */ tracing_reset_all_cpus(&tr->array_buffer); /* Using current data now */ tr->text_delta = 0; tr->data_delta = 0; } /** * tracing_update_buffers - used by tracing facility to expand ring buffers * @tr: The tracing instance * * To save on memory when the tracing is never used on a system with it * configured in. The ring buffers are set to a minimum size. But once * a user starts to use the tracing facility, then they need to grow * to their default size. * * This function is to be called when a tracer is about to be used. */ int tracing_update_buffers(struct trace_array *tr) { int ret = 0; mutex_lock(&trace_types_lock); update_last_data(tr); if (!tr->ring_buffer_expanded) ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); mutex_unlock(&trace_types_lock); return ret; } struct trace_option_dentry; static void create_trace_option_files(struct trace_array *tr, struct tracer *tracer); /* * Used to clear out the tracer before deletion of an instance. * Must have trace_types_lock held. */ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); tr->current_trace = &nop_trace; } static bool tracer_options_updated; static void add_tracer_options(struct trace_array *tr, struct tracer *t) { /* Only enable if the directory has been created already. */ if (!tr->dir) return; /* Only create trace option files after update_tracer_options finish */ if (!tracer_options_updated) return; create_trace_option_files(tr, t); } int tracing_set_tracer(struct trace_array *tr, const char *buf) { struct tracer *t; #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; #endif int ret; guard(mutex)(&trace_types_lock); update_last_data(tr); if (!tr->ring_buffer_expanded) { ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; ret = 0; } for (t = trace_types; t; t = t->next) { if (strcmp(t->name, buf) == 0) break; } if (!t) return -EINVAL; if (t == tr->current_trace) return 0; #ifdef CONFIG_TRACER_SNAPSHOT if (t->use_max_tr) { local_irq_disable(); arch_spin_lock(&tr->max_lock); ret = tr->cond_snapshot ? -EBUSY : 0; arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) return ret; } #endif /* Some tracers won't work on kernel command line */ if (system_state < SYSTEM_RUNNING && t->noboot) { pr_warn("Tracer '%s' is not allowed on command line, ignored\n", t->name); return -EINVAL; } /* Some tracers are only allowed for the top level buffer */ if (!trace_ok_for_array(t, tr)) return -EINVAL; /* If trace pipe files are being read, we can't change the tracer */ if (tr->trace_ref) return -EBUSY; trace_branch_disable(); tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); #ifdef CONFIG_TRACER_MAX_TRACE had_max_tr = tr->current_trace->use_max_tr; /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; if (had_max_tr && !t->use_max_tr) { /* * We need to make sure that the update_max_tr sees that * current_trace changed to nop_trace to keep it from * swapping the buffers after we resize it. * The update_max_tr is called from interrupts disabled * so a synchronized_sched() is sufficient. */ synchronize_rcu(); free_snapshot(tr); tracing_disarm_snapshot(tr); } if (!had_max_tr && t->use_max_tr) { ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; } #else tr->current_trace = &nop_trace; #endif if (t->init) { ret = tracer_init(t, tr); if (ret) { #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr) tracing_disarm_snapshot(tr); #endif return ret; } } tr->current_trace = t; tr->current_trace->enabled++; trace_branch_enable(tr); return 0; } static ssize_t tracing_set_trace_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+1]; char *name; size_t ret; int err; ret = cnt; if (cnt > MAX_TRACER_SIZE) cnt = MAX_TRACER_SIZE; if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; name = strim(buf); err = tracing_set_tracer(tr, name); if (err) return err; *ppos += ret; return ret; } static ssize_t tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[64]; int r; r = snprintf(buf, sizeof(buf), "%ld\n", *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr)); if (r > sizeof(buf)) r = sizeof(buf); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, size_t cnt, loff_t *ppos) { unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; *ptr = val * 1000; return cnt; } static ssize_t tracing_thresh_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { return tracing_nsecs_read(&tracing_thresh, ubuf, cnt, ppos); } static ssize_t tracing_thresh_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; int ret; guard(mutex)(&trace_types_lock); ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); if (ret < 0) return ret; if (tr->current_trace->update_thresh) { ret = tr->current_trace->update_thresh(tr); if (ret < 0) return ret; } return cnt; } #ifdef CONFIG_TRACER_MAX_TRACE static ssize_t tracing_max_lat_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; return tracing_nsecs_read(&tr->max_latency, ubuf, cnt, ppos); } static ssize_t tracing_max_lat_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; return tracing_nsecs_write(&tr->max_latency, ubuf, cnt, ppos); } #endif static int open_pipe_on_cpu(struct trace_array *tr, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { if (cpumask_empty(tr->pipe_cpumask)) { cpumask_setall(tr->pipe_cpumask); return 0; } } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) { cpumask_set_cpu(cpu, tr->pipe_cpumask); return 0; } return -EBUSY; } static void close_pipe_on_cpu(struct trace_array *tr, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { WARN_ON(!cpumask_full(tr->pipe_cpumask)); cpumask_clear(tr->pipe_cpumask); } else { WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask)); cpumask_clear_cpu(cpu, tr->pipe_cpumask); } } static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int cpu; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; mutex_lock(&trace_types_lock); cpu = tracing_get_cpu(inode); ret = open_pipe_on_cpu(tr, cpu); if (ret) goto fail_pipe_on_cpu; /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; goto fail_alloc_iter; } trace_seq_init(&iter->seq); iter->trace = tr->current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; goto fail; } /* trace pipe does not show start of buffer */ cpumask_setall(iter->started); if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; iter->tr = tr; iter->array_buffer = &tr->array_buffer; iter->cpu_file = cpu; mutex_init(&iter->mutex); filp->private_data = iter; if (iter->trace->pipe_open) iter->trace->pipe_open(iter); nonseekable_open(inode, filp); tr->trace_ref++; mutex_unlock(&trace_types_lock); return ret; fail: kfree(iter); fail_alloc_iter: close_pipe_on_cpu(tr, cpu); fail_pipe_on_cpu: __trace_array_put(tr); mutex_unlock(&trace_types_lock); return ret; } static int tracing_release_pipe(struct inode *inode, struct file *file) { struct trace_iterator *iter = file->private_data; struct trace_array *tr = inode->i_private; mutex_lock(&trace_types_lock); tr->trace_ref--; if (iter->trace->pipe_close) iter->trace->pipe_close(iter); close_pipe_on_cpu(tr, iter->cpu_file); mutex_unlock(&trace_types_lock); free_trace_iter_content(iter); kfree(iter); trace_array_put(tr); return 0; } static __poll_t trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table) { struct trace_array *tr = iter->tr; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return EPOLLIN | EPOLLRDNORM; if (tr->trace_flags & TRACE_ITER_BLOCK) /* * Always select as readable when in blocking mode */ return EPOLLIN | EPOLLRDNORM; else return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file, filp, poll_table, iter->tr->buffer_percent); } static __poll_t tracing_poll_pipe(struct file *filp, poll_table *poll_table) { struct trace_iterator *iter = filp->private_data; return trace_poll(iter, filp, poll_table); } /* Must be called with iter->mutex held. */ static int tracing_wait_pipe(struct file *filp) { struct trace_iterator *iter = filp->private_data; int ret; while (trace_empty(iter)) { if ((filp->f_flags & O_NONBLOCK)) { return -EAGAIN; } /* * We block until we read something and tracing is disabled. * We still block if tracing is disabled, but we have never * read anything. This allows a user to cat this file, and * then enable tracing. But after we have read something, * we give an EOF when tracing is again disabled. * * iter->pos will be 0 if we haven't read anything. */ if (!tracer_tracing_is_on(iter->tr) && iter->pos) break; mutex_unlock(&iter->mutex); ret = wait_on_pipe(iter, 0); mutex_lock(&iter->mutex); if (ret) return ret; } return 1; } /* * Consumer reader. */ static ssize_t tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; ssize_t sret; /* * Avoid more than one consumer on a single file descriptor * This is just a matter of traces coherency, the ring buffer itself * is protected. */ guard(mutex)(&iter->mutex); /* return any leftover data */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (sret != -EBUSY) return sret; trace_seq_init(&iter->seq); if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) return sret; } waitagain: sret = tracing_wait_pipe(filp); if (sret <= 0) return sret; /* stop when tracing is finished */ if (trace_empty(iter)) return 0; if (cnt >= TRACE_SEQ_BUFFER_SIZE) cnt = TRACE_SEQ_BUFFER_SIZE - 1; /* reset all but tr, trace, and overruns */ trace_iterator_reset(iter); cpumask_clear(iter->started); trace_seq_init(&iter->seq); trace_event_read_lock(); trace_access_lock(iter->cpu_file); while (trace_find_next_entry_inc(iter) != NULL) { enum print_line_t ret; int save_len = iter->seq.seq.len; ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { /* * If one print_trace_line() fills entire trace_seq in one shot, * trace_seq_to_user() will returns -EBUSY because save_len == 0, * In this case, we need to consume it, otherwise, loop will peek * this event next time, resulting in an infinite loop. */ if (save_len == 0) { iter->seq.full = 0; trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); trace_consume(iter); break; } /* In other cases, don't print partial lines */ iter->seq.seq.len = save_len; break; } if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(iter); if (trace_seq_used(&iter->seq) >= cnt) break; /* * Setting the full flag means we reached the trace_seq buffer * size and we should leave by partial output condition above. * One of the trace_seq_* functions is not used properly. */ WARN_ONCE(iter->seq.full, "full flag set for trace type %d", iter->ent->type); } trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); /* Now copy what we have to the user */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (iter->seq.readpos >= trace_seq_used(&iter->seq)) trace_seq_init(&iter->seq); /* * If there was nothing to send to user, in spite of consuming trace * entries, go back to wait for more entries. */ if (sret == -EBUSY) goto waitagain; return sret; } static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, unsigned int idx) { __free_page(spd->pages[idx]); } static size_t tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) { size_t count; int save_len; int ret; /* Seq buffer is page-sized, exactly what we need. */ for (;;) { save_len = iter->seq.seq.len; ret = print_trace_line(iter); if (trace_seq_has_overflowed(&iter->seq)) { iter->seq.seq.len = save_len; break; } /* * This should not be hit, because it should only * be set if the iter->seq overflowed. But check it * anyway to be safe. */ if (ret == TRACE_TYPE_PARTIAL_LINE) { iter->seq.seq.len = save_len; break; } count = trace_seq_used(&iter->seq) - save_len; if (rem < count) { rem = 0; iter->seq.seq.len = save_len; break; } if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(iter); rem -= count; if (!trace_find_next_entry_inc(iter)) { rem = 0; iter->ent = NULL; break; } } return rem; } static ssize_t tracing_splice_read_pipe(struct file *filp, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct page *pages_def[PIPE_DEF_BUFFERS]; struct partial_page partial_def[PIPE_DEF_BUFFERS]; struct trace_iterator *iter = filp->private_data; struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ .nr_pages_max = PIPE_DEF_BUFFERS, .ops = &default_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; ssize_t ret; size_t rem; unsigned int i; if (splice_grow_spd(pipe, &spd)) return -ENOMEM; mutex_lock(&iter->mutex); if (iter->trace->splice_read) { ret = iter->trace->splice_read(iter, filp, ppos, pipe, len, flags); if (ret) goto out_err; } ret = tracing_wait_pipe(filp); if (ret <= 0) goto out_err; if (!iter->ent && !trace_find_next_entry_inc(iter)) { ret = -EFAULT; goto out_err; } trace_event_read_lock(); trace_access_lock(iter->cpu_file); /* Fill as many pages as possible. */ for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) { spd.pages[i] = alloc_page(GFP_KERNEL); if (!spd.pages[i]) break; rem = tracing_fill_pipe_page(rem, iter); /* Copy the data into the page, so we can start over. */ ret = trace_seq_to_buffer(&iter->seq, page_address(spd.pages[i]), trace_seq_used(&iter->seq)); if (ret < 0) { __free_page(spd.pages[i]); break; } spd.partial[i].offset = 0; spd.partial[i].len = trace_seq_used(&iter->seq); trace_seq_init(&iter->seq); } trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); mutex_unlock(&iter->mutex); spd.nr_pages = i; if (i) ret = splice_to_pipe(pipe, &spd); else ret = 0; out: splice_shrink_spd(&spd); return ret; out_err: mutex_unlock(&iter->mutex); goto out; } static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; int cpu = tracing_get_cpu(inode); char buf[64]; int r = 0; ssize_t ret; mutex_lock(&trace_types_lock); if (cpu == RING_BUFFER_ALL_CPUS) { int cpu, buf_size_same; unsigned long size; size = 0; buf_size_same = 1; /* check if all cpu sizes are same */ for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) size = per_cpu_ptr(tr->array_buffer.data, cpu)->entries; if (size != per_cpu_ptr(tr->array_buffer.data, cpu)->entries) { buf_size_same = 0; break; } } if (buf_size_same) { if (!tr->ring_buffer_expanded) r = sprintf(buf, "%lu (expanded: %lu)\n", size >> 10, trace_buf_size >> 10); else r = sprintf(buf, "%lu\n", size >> 10); } else r = sprintf(buf, "X\n"); } else r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10); mutex_unlock(&trace_types_lock); ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); return ret; } static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; /* must have at least 1 entry */ if (!val) return -EINVAL; /* value is in KB */ val <<= 10; ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode)); if (ret < 0) return ret; *ppos += cnt; return cnt; } static ssize_t tracing_total_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[64]; int r, cpu; unsigned long size = 0, expanded_size = 0; mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10; if (!tr->ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } if (tr->ring_buffer_expanded) r = sprintf(buf, "%lu\n", size); else r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t tracing_last_boot_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; struct seq_buf seq; char buf[64]; seq_buf_init(&seq, buf, 64); seq_buf_printf(&seq, "text delta:\t%ld\n", tr->text_delta); seq_buf_printf(&seq, "data delta:\t%ld\n", tr->data_delta); return simple_read_from_buffer(ubuf, cnt, ppos, buf, seq_buf_used(&seq)); } static int tracing_buffer_meta_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; int cpu = tracing_get_cpu(inode); int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = ring_buffer_meta_seq_init(filp, tr->array_buffer.buffer, cpu); if (ret < 0) __trace_array_put(tr); return ret; } static ssize_t tracing_free_buffer_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { /* * There is no need to read what the user has written, this function * is just to make sure that there is no error when "echo" is used */ *ppos += cnt; return cnt; } static int tracing_free_buffer_release(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; /* disable tracing ? */ if (tr->trace_flags & TRACE_ITER_STOP_ON_FREE) tracer_tracing_off(tr); /* resize the ring buffer to 0 */ tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); trace_array_put(tr); return 0; } #define TRACE_MARKER_MAX_SIZE 4096 static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; enum event_trigger_type tt = ETT_NONE; struct trace_buffer *buffer; struct print_entry *entry; int meta_size; ssize_t written; size_t size; int len; /* Used in tracing_mark_raw_write() as well */ #define FAULTED_STR "<faulted>" #define FAULTED_SIZE (sizeof(FAULTED_STR) - 1) /* '\0' is already accounted for */ if (tracing_disabled) return -EINVAL; if (!(tr->trace_flags & TRACE_ITER_MARKERS)) return -EINVAL; if ((ssize_t)cnt < 0) return -EINVAL; if (cnt > TRACE_MARKER_MAX_SIZE) cnt = TRACE_MARKER_MAX_SIZE; meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ again: size = cnt + meta_size; /* If less than "<faulted>", then make sure we can still add that */ if (cnt < FAULTED_SIZE) size += FAULTED_SIZE - cnt; buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, tracing_gen_ctx()); if (unlikely(!event)) { /* * If the size was greater than what was allowed, then * make it smaller and try again. */ if (size > ring_buffer_max_event_size(buffer)) { /* cnt < FAULTED size should never be bigger than max */ if (WARN_ON_ONCE(cnt < FAULTED_SIZE)) return -EBADF; cnt = ring_buffer_max_event_size(buffer) - meta_size; /* The above should only happen once */ if (WARN_ON_ONCE(cnt + meta_size == size)) return -EBADF; goto again; } /* Ring buffer disabled, return as if not open for write */ return -EBADF; } entry = ring_buffer_event_data(event); entry->ip = _THIS_IP_; len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt); if (len) { memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); cnt = FAULTED_SIZE; written = -EFAULT; } else written = cnt; if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { /* do not add \n before testing triggers, but add \0 */ entry->buf[cnt] = '\0'; tt = event_triggers_call(tr->trace_marker_file, buffer, entry, event); } if (entry->buf[cnt - 1] != '\n') { entry->buf[cnt] = '\n'; entry->buf[cnt + 1] = '\0'; } else entry->buf[cnt] = '\0'; if (static_branch_unlikely(&trace_marker_exports_enabled)) ftrace_exports(event, TRACE_EXPORT_MARKER); __buffer_unlock_commit(buffer, event); if (tt) event_triggers_post_call(tr->trace_marker_file, tt); return written; } static ssize_t tracing_mark_raw_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; struct trace_buffer *buffer; struct raw_data_entry *entry; ssize_t written; int size; int len; #define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int)) if (tracing_disabled) return -EINVAL; if (!(tr->trace_flags & TRACE_ITER_MARKERS)) return -EINVAL; /* The marker must at least have a tag id */ if (cnt < sizeof(unsigned int)) return -EINVAL; size = sizeof(*entry) + cnt; if (cnt < FAULT_SIZE_ID) size += FAULT_SIZE_ID - cnt; buffer = tr->array_buffer.buffer; if (size > ring_buffer_max_event_size(buffer)) return -EINVAL; event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, tracing_gen_ctx()); if (!event) /* Ring buffer disabled, return as if not open for write */ return -EBADF; entry = ring_buffer_event_data(event); len = __copy_from_user_inatomic(&entry->id, ubuf, cnt); if (len) { entry->id = -1; memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); written = -EFAULT; } else written = cnt; __buffer_unlock_commit(buffer, event); return written; } static int tracing_clock_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; int i; for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) seq_printf(m, "%s%s%s%s", i ? " " : "", i == tr->clock_id ? "[" : "", trace_clocks[i].name, i == tr->clock_id ? "]" : ""); seq_putc(m, '\n'); return 0; } int tracing_set_clock(struct trace_array *tr, const char *clockstr) { int i; for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) { if (strcmp(trace_clocks[i].name, clockstr) == 0) break; } if (i == ARRAY_SIZE(trace_clocks)) return -EINVAL; mutex_lock(&trace_types_lock); tr->clock_id = i; ring_buffer_set_clock(tr->array_buffer.buffer, trace_clocks[i].func); /* * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); tracing_reset_online_cpus(&tr->max_buffer); #endif mutex_unlock(&trace_types_lock); return 0; } static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; char buf[64]; const char *clockstr; int ret; if (cnt >= sizeof(buf)) return -EINVAL; if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; clockstr = strstrip(buf); ret = tracing_set_clock(tr, clockstr); if (ret) return ret; *fpos += cnt; return cnt; } static int tracing_clock_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = single_open(file, tracing_clock_show, inode->i_private); if (ret < 0) trace_array_put(tr); return ret; } static int tracing_time_stamp_mode_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; mutex_lock(&trace_types_lock); if (ring_buffer_time_stamp_abs(tr->array_buffer.buffer)) seq_puts(m, "delta [absolute]\n"); else seq_puts(m, "[delta] absolute\n"); mutex_unlock(&trace_types_lock); return 0; } static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private); if (ret < 0) trace_array_put(tr); return ret; } u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe) { if (rbe == this_cpu_read(trace_buffered_event)) return ring_buffer_time_stamp(buffer); return ring_buffer_event_time_stamp(buffer, rbe); } /* * Set or disable using the per CPU trace_buffer_event when possible. */ int tracing_set_filter_buffering(struct trace_array *tr, bool set) { guard(mutex)(&trace_types_lock); if (set && tr->no_filter_buffering_ref++) return 0; if (!set) { if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) return -EINVAL; --tr->no_filter_buffering_ref; } return 0; } struct ftrace_buffer_info { struct trace_iterator iter; void *spare; unsigned int spare_cpu; unsigned int spare_size; unsigned int read; }; #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; struct seq_file *m; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); if (IS_ERR(iter)) ret = PTR_ERR(iter); } else { /* Writes still need the seq_file to hold the private data */ ret = -ENOMEM; m = kzalloc(sizeof(*m), GFP_KERNEL); if (!m) goto out; iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { kfree(m); goto out; } ret = 0; iter->tr = tr; iter->array_buffer = &tr->max_buffer; iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; } out: if (ret < 0) trace_array_put(tr); return ret; } static void tracing_swap_cpu_buffer(void *tr) { update_max_tr_single((struct trace_array *)tr, current, smp_processor_id()); } static ssize_t tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct seq_file *m = filp->private_data; struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; unsigned long val; int ret; ret = tracing_update_buffers(tr); if (ret < 0) return ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; guard(mutex)(&trace_types_lock); if (tr->current_trace->use_max_tr) return -EBUSY; local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) ret = -EBUSY; arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) return ret; switch (val) { case 0: if (iter->cpu_file != RING_BUFFER_ALL_CPUS) return -EINVAL; if (tr->allocated_snapshot) free_snapshot(tr); break; case 1: /* Only allow per-cpu swap if the ring buffer supports it */ #ifndef CONFIG_RING_BUFFER_ALLOW_SWAP if (iter->cpu_file != RING_BUFFER_ALL_CPUS) return -EINVAL; #endif if (tr->allocated_snapshot) ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, iter->cpu_file); ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { local_irq_disable(); update_max_tr(tr, current, smp_processor_id(), NULL); local_irq_enable(); } else { smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer, (void *)tr, 1); } tracing_disarm_snapshot(tr); break; default: if (tr->allocated_snapshot) { if (iter->cpu_file == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&tr->max_buffer); else tracing_reset_cpu(&tr->max_buffer, iter->cpu_file); } break; } if (ret >= 0) { *ppos += cnt; ret = cnt; } return ret; } static int tracing_snapshot_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; int ret; ret = tracing_release(inode, file); if (file->f_mode & FMODE_READ) return ret; /* If write only, the seq_file is just a stub */ if (m) kfree(m->private); kfree(m); return 0; } static int tracing_buffers_open(struct inode *inode, struct file *filp); static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos); static int tracing_buffers_release(struct inode *inode, struct file *file); static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); static int snapshot_raw_open(struct inode *inode, struct file *filp) { struct ftrace_buffer_info *info; int ret; /* The following checks for tracefs lockdown */ ret = tracing_buffers_open(inode, filp); if (ret < 0) return ret; info = filp->private_data; if (info->iter.trace->use_max_tr) { tracing_buffers_release(inode, filp); return -EBUSY; } info->iter.snapshot = true; info->iter.array_buffer = &info->iter.tr->max_buffer; return ret; } #endif /* CONFIG_TRACER_SNAPSHOT */ static const struct file_operations tracing_thresh_fops = { .open = tracing_open_generic, .read = tracing_thresh_read, .write = tracing_thresh_write, .llseek = generic_file_llseek, }; #ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic_tr, .read = tracing_max_lat_read, .write = tracing_max_lat_write, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; #endif static const struct file_operations set_tracer_fops = { .open = tracing_open_generic_tr, .read = tracing_set_trace_read, .write = tracing_set_trace_write, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_pipe_fops = { .open = tracing_open_pipe, .poll = tracing_poll_pipe, .read = tracing_read_pipe, .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, }; static const struct file_operations tracing_entries_fops = { .open = tracing_open_generic_tr, .read = tracing_entries_read, .write = tracing_entries_write, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_buffer_meta_fops = { .open = tracing_buffer_meta_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_seq_release, }; static const struct file_operations tracing_total_entries_fops = { .open = tracing_open_generic_tr, .read = tracing_total_entries_read, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_free_buffer_fops = { .open = tracing_open_generic_tr, .write = tracing_free_buffer_write, .release = tracing_free_buffer_release, }; static const struct file_operations tracing_mark_fops = { .open = tracing_mark_open, .write = tracing_mark_write, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_mark_raw_fops = { .open = tracing_mark_open, .write = tracing_mark_raw_write, .release = tracing_release_generic_tr, }; static const struct file_operations trace_clock_fops = { .open = tracing_clock_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_single_release_tr, .write = tracing_clock_write, }; static const struct file_operations trace_time_stamp_mode_fops = { .open = tracing_time_stamp_mode_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_single_release_tr, }; static const struct file_operations last_boot_fops = { .open = tracing_open_generic_tr, .read = tracing_last_boot_read, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; #ifdef CONFIG_TRACER_SNAPSHOT static const struct file_operations snapshot_fops = { .open = tracing_snapshot_open, .read = seq_read, .write = tracing_snapshot_write, .llseek = tracing_lseek, .release = tracing_snapshot_release, }; static const struct file_operations snapshot_raw_fops = { .open = snapshot_raw_open, .read = tracing_buffers_read, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, }; #endif /* CONFIG_TRACER_SNAPSHOT */ /* * trace_min_max_write - Write a u64 value to a trace_min_max_param struct * @filp: The active open file structure * @ubuf: The userspace provided buffer to read value into * @cnt: The maximum number of bytes to read * @ppos: The current "file" position * * This function implements the write interface for a struct trace_min_max_param. * The filp->private_data must point to a trace_min_max_param structure that * defines where to write the value, the min and the max acceptable values, * and a lock to protect the write. */ static ssize_t trace_min_max_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_min_max_param *param = filp->private_data; u64 val; int err; if (!param) return -EFAULT; err = kstrtoull_from_user(ubuf, cnt, 10, &val); if (err) return err; if (param->lock) mutex_lock(param->lock); if (param->min && val < *param->min) err = -EINVAL; if (param->max && val > *param->max) err = -EINVAL; if (!err) *param->val = val; if (param->lock) mutex_unlock(param->lock); if (err) return err; return cnt; } /* * trace_min_max_read - Read a u64 value from a trace_min_max_param struct * @filp: The active open file structure * @ubuf: The userspace provided buffer to read value into * @cnt: The maximum number of bytes to read * @ppos: The current "file" position * * This function implements the read interface for a struct trace_min_max_param. * The filp->private_data must point to a trace_min_max_param struct with valid * data. */ static ssize_t trace_min_max_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_min_max_param *param = filp->private_data; char buf[U64_STR_SIZE]; int len; u64 val; if (!param) return -EFAULT; val = *param->val; if (cnt > sizeof(buf)) cnt = sizeof(buf); len = snprintf(buf, sizeof(buf), "%llu\n", val); return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } const struct file_operations trace_min_max_fops = { .open = tracing_open_generic, .read = trace_min_max_read, .write = trace_min_max_write, }; #define TRACING_LOG_ERRS_MAX 8 #define TRACING_LOG_LOC_MAX 128 #define CMD_PREFIX " Command: " struct err_info { const char **errs; /* ptr to loc-specific array of err strings */ u8 type; /* index into errs -> specific err string */ u16 pos; /* caret position */ u64 ts; }; struct tracing_log_err { struct list_head list; struct err_info info; char loc[TRACING_LOG_LOC_MAX]; /* err location */ char *cmd; /* what caused err */ }; static DEFINE_MUTEX(tracing_err_log_lock); static struct tracing_log_err *alloc_tracing_log_err(int len) { struct tracing_log_err *err; err = kzalloc(sizeof(*err), GFP_KERNEL); if (!err) return ERR_PTR(-ENOMEM); err->cmd = kzalloc(len, GFP_KERNEL); if (!err->cmd) { kfree(err); return ERR_PTR(-ENOMEM); } return err; } static void free_tracing_log_err(struct tracing_log_err *err) { kfree(err->cmd); kfree(err); } static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, int len) { struct tracing_log_err *err; char *cmd; if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) { err = alloc_tracing_log_err(len); if (PTR_ERR(err) != -ENOMEM) tr->n_err_log_entries++; return err; } cmd = kzalloc(len, GFP_KERNEL); if (!cmd) return ERR_PTR(-ENOMEM); err = list_first_entry(&tr->err_log, struct tracing_log_err, list); kfree(err->cmd); err->cmd = cmd; list_del(&err->list); return err; } /** * err_pos - find the position of a string within a command for error careting * @cmd: The tracing command that caused the error * @str: The string to position the caret at within @cmd * * Finds the position of the first occurrence of @str within @cmd. The * return value can be passed to tracing_log_err() for caret placement * within @cmd. * * Returns the index within @cmd of the first occurrence of @str or 0 * if @str was not found. */ unsigned int err_pos(char *cmd, const char *str) { char *found; if (WARN_ON(!strlen(cmd))) return 0; found = strstr(cmd, str); if (found) return found - cmd; return 0; } /** * tracing_log_err - write an error to the tracing error log * @tr: The associated trace array for the error (NULL for top level array) * @loc: A string describing where the error occurred * @cmd: The tracing command that caused the error * @errs: The array of loc-specific static error strings * @type: The index into errs[], which produces the specific static err string * @pos: The position the caret should be placed in the cmd * * Writes an error into tracing/error_log of the form: * * <loc>: error: <text> * Command: <cmd> * ^ * * tracing/error_log is a small log file containing the last * TRACING_LOG_ERRS_MAX errors (8). Memory for errors isn't allocated * unless there has been a tracing error, and the error log can be * cleared and have its memory freed by writing the empty string in * truncation mode to it i.e. echo > tracing/error_log. * * NOTE: the @errs array along with the @type param are used to * produce a static error string - this string is not copied and saved * when the error is logged - only a pointer to it is saved. See * existing callers for examples of how static strings are typically * defined for use with tracing_log_err(). */ void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, const char **errs, u8 type, u16 pos) { struct tracing_log_err *err; int len = 0; if (!tr) tr = &global_trace; len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; guard(mutex)(&tracing_err_log_lock); err = get_tracing_log_err(tr, len); if (PTR_ERR(err) == -ENOMEM) return; snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); err->info.errs = errs; err->info.type = type; err->info.pos = pos; err->info.ts = local_clock(); list_add_tail(&err->list, &tr->err_log); } static void clear_tracing_err_log(struct trace_array *tr) { struct tracing_log_err *err, *next; mutex_lock(&tracing_err_log_lock); list_for_each_entry_safe(err, next, &tr->err_log, list) { list_del(&err->list); free_tracing_log_err(err); } tr->n_err_log_entries = 0; mutex_unlock(&tracing_err_log_lock); } static void *tracing_err_log_seq_start(struct seq_file *m, loff_t *pos) { struct trace_array *tr = m->private; mutex_lock(&tracing_err_log_lock); return seq_list_start(&tr->err_log, *pos); } static void *tracing_err_log_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; return seq_list_next(v, &tr->err_log, pos); } static void tracing_err_log_seq_stop(struct seq_file *m, void *v) { mutex_unlock(&tracing_err_log_lock); } static void tracing_err_log_show_pos(struct seq_file *m, u16 pos) { u16 i; for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++) seq_putc(m, ' '); for (i = 0; i < pos; i++) seq_putc(m, ' '); seq_puts(m, "^\n"); } static int tracing_err_log_seq_show(struct seq_file *m, void *v) { struct tracing_log_err *err = v; if (err) { const char *err_text = err->info.errs[err->info.type]; u64 sec = err->info.ts; u32 nsec; nsec = do_div(sec, NSEC_PER_SEC); seq_printf(m, "[%5llu.%06u] %s%s", sec, nsec / 1000, err->loc, err_text); seq_printf(m, "%s", err->cmd); tracing_err_log_show_pos(m, err->info.pos); } return 0; } static const struct seq_operations tracing_err_log_seq_ops = { .start = tracing_err_log_seq_start, .next = tracing_err_log_seq_next, .stop = tracing_err_log_seq_stop, .show = tracing_err_log_seq_show }; static int tracing_err_log_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret = 0; ret = tracing_check_open_get_tr(tr); if (ret) return ret; /* If this file was opened for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) clear_tracing_err_log(tr); if (file->f_mode & FMODE_READ) { ret = seq_open(file, &tracing_err_log_seq_ops); if (!ret) { struct seq_file *m = file->private_data; m->private = tr; } else { trace_array_put(tr); } } return ret; } static ssize_t tracing_err_log_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { return count; } static int tracing_err_log_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); if (file->f_mode & FMODE_READ) seq_release(inode, file); return 0; } static const struct file_operations tracing_err_log_fops = { .open = tracing_err_log_open, .write = tracing_err_log_write, .read = seq_read, .llseek = tracing_lseek, .release = tracing_err_log_release, }; static int tracing_buffers_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct ftrace_buffer_info *info; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; info = kvzalloc(sizeof(*info), GFP_KERNEL); if (!info) { trace_array_put(tr); return -ENOMEM; } mutex_lock(&trace_types_lock); info->iter.tr = tr; info->iter.cpu_file = tracing_get_cpu(inode); info->iter.trace = tr->current_trace; info->iter.array_buffer = &tr->array_buffer; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; filp->private_data = info; tr->trace_ref++; mutex_unlock(&trace_types_lock); ret = nonseekable_open(inode, filp); if (ret < 0) trace_array_put(tr); return ret; } static __poll_t tracing_buffers_poll(struct file *filp, poll_table *poll_table) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; return trace_poll(iter, filp, poll_table); } static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; void *trace_data; int page_size; ssize_t ret = 0; ssize_t size; if (!count) return 0; #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->tr->current_trace->use_max_tr) return -EBUSY; #endif page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); /* Make sure the spare matches the current sub buffer size */ if (info->spare) { if (page_size != info->spare_size) { ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); info->spare = NULL; } } if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file); if (IS_ERR(info->spare)) { ret = PTR_ERR(info->spare); info->spare = NULL; } else { info->spare_cpu = iter->cpu_file; info->spare_size = page_size; } } if (!info->spare) return ret; /* Do we have previous read data to read? */ if (info->read < page_size) goto read; again: trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->array_buffer->buffer, info->spare, count, iter->cpu_file, 0); trace_access_unlock(iter->cpu_file); if (ret < 0) { if (trace_empty(iter) && !iter->closed) { if ((filp->f_flags & O_NONBLOCK)) return -EAGAIN; ret = wait_on_pipe(iter, 0); if (ret) return ret; goto again; } return 0; } info->read = 0; read: size = page_size - info->read; if (size > count) size = count; trace_data = ring_buffer_read_page_data(info->spare); ret = copy_to_user(ubuf, trace_data + info->read, size); if (ret == size) return -EFAULT; size -= ret; *ppos += size; info->read += size; return size; } static int tracing_buffers_flush(struct file *file, fl_owner_t id) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; iter->closed = true; /* Make sure the waiters see the new wait_index */ (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); return 0; } static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; mutex_lock(&trace_types_lock); iter->tr->trace_ref--; __trace_array_put(iter->tr); if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); kvfree(info); mutex_unlock(&trace_types_lock); return 0; } struct buffer_ref { struct trace_buffer *buffer; void *page; int cpu; refcount_t refcount; }; static void buffer_ref_release(struct buffer_ref *ref) { if (!refcount_dec_and_test(&ref->refcount)) return; ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); kfree(ref); } static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; buffer_ref_release(ref); buf->private = 0; } static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; if (refcount_read(&ref->refcount) > INT_MAX/2) return false; refcount_inc(&ref->refcount); return true; } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .release = buffer_pipe_buf_release, .get = buffer_pipe_buf_get, }; /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) { struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; buffer_ref_release(ref); spd->partial[i].private = 0; } static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; struct partial_page partial_def[PIPE_DEF_BUFFERS]; struct page *pages_def[PIPE_DEF_BUFFERS]; struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, .nr_pages_max = PIPE_DEF_BUFFERS, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; bool woken = false; int page_size; int entries, i; ssize_t ret = 0; #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->tr->current_trace->use_max_tr) return -EBUSY; #endif page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); if (*ppos & (page_size - 1)) return -EINVAL; if (len & (page_size - 1)) { if (len < page_size) return -EINVAL; len &= (~(page_size - 1)); } if (splice_grow_spd(pipe, &spd)) return -ENOMEM; again: trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) { struct page *page; int r; ref = kzalloc(sizeof(*ref), GFP_KERNEL); if (!ref) { ret = -ENOMEM; break; } refcount_set(&ref->refcount, 1); ref->buffer = iter->array_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { ret = PTR_ERR(ref->page); ref->page = NULL; kfree(ref); break; } ref->cpu = iter->cpu_file; r = ring_buffer_read_page(ref->buffer, ref->page, len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); kfree(ref); break; } page = virt_to_page(ring_buffer_read_page_data(ref->page)); spd.pages[i] = page; spd.partial[i].len = page_size; spd.partial[i].offset = 0; spd.partial[i].private = (unsigned long)ref; spd.nr_pages++; *ppos += page_size; entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); } trace_access_unlock(iter->cpu_file); spd.nr_pages = i; /* did we read anything? */ if (!spd.nr_pages) { if (ret) goto out; if (woken) goto out; ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; /* No need to wait after waking up when tracing is off */ if (!tracer_tracing_is_on(iter->tr)) goto out; /* Iterate one more time to collect any new data then exit */ woken = true; goto again; } ret = splice_to_pipe(pipe, &spd); out: splice_shrink_spd(&spd); return ret; } static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; int err; if (cmd == TRACE_MMAP_IOCTL_GET_READER) { if (!(file->f_flags & O_NONBLOCK)) { err = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, iter->tr->buffer_percent, NULL, NULL); if (err) return err; } return ring_buffer_map_get_reader(iter->array_buffer->buffer, iter->cpu_file); } else if (cmd) { return -ENOTTY; } /* * An ioctl call with cmd 0 to the ring buffer file will wake up all * waiters */ mutex_lock(&trace_types_lock); /* Make sure the waiters see the new wait_index */ (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); mutex_unlock(&trace_types_lock); return 0; } #ifdef CONFIG_TRACER_MAX_TRACE static int get_snapshot_map(struct trace_array *tr) { int err = 0; /* * Called with mmap_lock held. lockdep would be unhappy if we would now * take trace_types_lock. Instead use the specific * snapshot_trigger_lock. */ spin_lock(&tr->snapshot_trigger_lock); if (tr->snapshot || tr->mapped == UINT_MAX) err = -EBUSY; else tr->mapped++; spin_unlock(&tr->snapshot_trigger_lock); /* Wait for update_max_tr() to observe iter->tr->mapped */ if (tr->mapped == 1) synchronize_rcu(); return err; } static void put_snapshot_map(struct trace_array *tr) { spin_lock(&tr->snapshot_trigger_lock); if (!WARN_ON(!tr->mapped)) tr->mapped--; spin_unlock(&tr->snapshot_trigger_lock); } #else static inline int get_snapshot_map(struct trace_array *tr) { return 0; } static inline void put_snapshot_map(struct trace_array *tr) { } #endif static void tracing_buffers_mmap_close(struct vm_area_struct *vma) { struct ftrace_buffer_info *info = vma->vm_file->private_data; struct trace_iterator *iter = &info->iter; WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file)); put_snapshot_map(iter->tr); } static const struct vm_operations_struct tracing_buffers_vmops = { .close = tracing_buffers_mmap_close, }; static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; int ret = 0; /* Currently the boot mapped buffer is not supported for mmap */ if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) return -ENODEV; ret = get_snapshot_map(iter->tr); if (ret) return ret; ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma); if (ret) put_snapshot_map(iter->tr); vma->vm_ops = &tracing_buffers_vmops; return ret; } static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .mmap = tracing_buffers_mmap, }; static ssize_t tracing_stats_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; struct array_buffer *trace_buf = &tr->array_buffer; int cpu = tracing_get_cpu(inode); struct trace_seq *s; unsigned long cnt; unsigned long long t; unsigned long usec_rem; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; trace_seq_init(s); cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "entries: %ld\n", cnt); cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "overrun: %ld\n", cnt); cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "commit overrun: %ld\n", cnt); cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); if (trace_clocks[tr->clock_id].in_ns) { /* local or global for trace_clock */ t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); } else { /* counter or tsc mode for trace_clock */ trace_seq_printf(s, "oldest event ts: %llu\n", ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); trace_seq_printf(s, "now ts: %llu\n", ring_buffer_time_stamp(trace_buf->buffer)); } cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "dropped events: %ld\n", cnt); cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "read events: %ld\n", cnt); count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, trace_seq_used(s)); kfree(s); return count; } static const struct file_operations tracing_stats_fops = { .open = tracing_open_generic_tr, .read = tracing_stats_read, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; #ifdef CONFIG_DYNAMIC_FTRACE static ssize_t tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { ssize_t ret; char *buf; int r; /* 512 should be plenty to hold the amount needed */ #define DYN_INFO_BUF_SIZE 512 buf = kmalloc(DYN_INFO_BUF_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; r = scnprintf(buf, DYN_INFO_BUF_SIZE, "%ld pages:%ld groups: %ld\n" "ftrace boot update time = %llu (ns)\n" "ftrace module total update time = %llu (ns)\n", ftrace_update_tot_cnt, ftrace_number_of_pages, ftrace_number_of_groups, ftrace_update_time, ftrace_total_mod_time); ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); kfree(buf); return ret; } static const struct file_operations tracing_dyn_info_fops = { .open = tracing_open_generic, .read = tracing_read_dyn_info, .llseek = generic_file_llseek, }; #endif /* CONFIG_DYNAMIC_FTRACE */ #if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) static void ftrace_snapshot(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data) { tracing_snapshot_instance(tr); } static void ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; long *count = NULL; if (mapper) count = (long *)ftrace_func_mapper_find_ip(mapper, ip); if (count) { if (*count <= 0) return; (*count)--; } tracing_snapshot_instance(tr); } static int ftrace_snapshot_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; long *count = NULL; seq_printf(m, "%ps:", (void *)ip); seq_puts(m, "snapshot"); if (mapper) count = (long *)ftrace_func_mapper_find_ip(mapper, ip); if (count) seq_printf(m, ":count=%ld\n", *count); else seq_puts(m, ":unlimited\n"); return 0; } static int ftrace_snapshot_init(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *init_data, void **data) { struct ftrace_func_mapper *mapper = *data; if (!mapper) { mapper = allocate_ftrace_func_mapper(); if (!mapper) return -ENOMEM; *data = mapper; } return ftrace_func_mapper_add_ip(mapper, ip, init_data); } static void ftrace_snapshot_free(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *data) { struct ftrace_func_mapper *mapper = data; if (!ip) { if (!mapper) return; free_ftrace_func_mapper(mapper, NULL); return; } ftrace_func_mapper_remove_ip(mapper, ip); } static struct ftrace_probe_ops snapshot_probe_ops = { .func = ftrace_snapshot, .print = ftrace_snapshot_print, }; static struct ftrace_probe_ops snapshot_count_probe_ops = { .func = ftrace_count_snapshot, .print = ftrace_snapshot_print, .init = ftrace_snapshot_init, .free = ftrace_snapshot_free, }; static int ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; void *count = (void *)-1; char *number; int ret; if (!tr) return -ENODEV; /* hash funcs only work with set_ftrace_filter */ if (!enable) return -EINVAL; ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; if (glob[0] == '!') { ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); if (!ret) tracing_disarm_snapshot(tr); return ret; } if (!param) goto out_reg; number = strsep(¶m, ":"); if (!strlen(number)) goto out_reg; /* * We use the callback data field (which is a pointer) * as our counter. */ ret = kstrtoul(number, 0, (unsigned long *)&count); if (ret) return ret; out_reg: ret = tracing_arm_snapshot(tr); if (ret < 0) goto out; ret = register_ftrace_function_probe(glob, tr, ops, count); if (ret < 0) tracing_disarm_snapshot(tr); out: return ret < 0 ? ret : 0; } static struct ftrace_func_command ftrace_snapshot_cmd = { .name = "snapshot", .func = ftrace_trace_snapshot_callback, }; static __init int register_snapshot_cmd(void) { return register_ftrace_command(&ftrace_snapshot_cmd); } #else static inline __init int register_snapshot_cmd(void) { return 0; } #endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ static struct dentry *tracing_get_dentry(struct trace_array *tr) { if (WARN_ON(!tr->dir)) return ERR_PTR(-ENODEV); /* Top directory uses NULL as the parent */ if (tr->flags & TRACE_ARRAY_FL_GLOBAL) return NULL; /* All sub buffers have a descriptor */ return tr->dir; } static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) { struct dentry *d_tracer; if (tr->percpu_dir) return tr->percpu_dir; d_tracer = tracing_get_dentry(tr); if (IS_ERR(d_tracer)) return NULL; tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer); MEM_FAIL(!tr->percpu_dir, "Could not create tracefs directory 'per_cpu/%d'\n", cpu); return tr->percpu_dir; } static struct dentry * trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent, void *data, long cpu, const struct file_operations *fops) { struct dentry *ret = trace_create_file(name, mode, parent, data, fops); if (ret) /* See tracing_get_cpu() */ d_inode(ret)->i_cdev = (void *)(cpu + 1); return ret; } static void tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) { struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ if (!d_percpu) return; snprintf(cpu_dir, 30, "cpu%ld", cpu); d_cpu = tracefs_create_dir(cpu_dir, d_percpu); if (!d_cpu) { pr_warn("Could not create tracefs '%s' entry\n", cpu_dir); return; } /* per cpu trace_pipe */ trace_create_cpu_file("trace_pipe", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_pipe_fops); /* per cpu trace */ trace_create_cpu_file("trace", TRACE_MODE_WRITE, d_cpu, tr, cpu, &tracing_fops); trace_create_cpu_file("trace_pipe_raw", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_buffers_fops); trace_create_cpu_file("stats", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_stats_fops); trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_entries_fops); if (tr->range_addr_start) trace_create_cpu_file("buffer_meta", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_buffer_meta_fops); #ifdef CONFIG_TRACER_SNAPSHOT if (!tr->range_addr_start) { trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu, tr, cpu, &snapshot_fops); trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu, tr, cpu, &snapshot_raw_fops); } #endif } #ifdef CONFIG_FTRACE_SELFTEST /* Let selftest have access to static functions in this file */ #include "trace_selftest.c" #endif static ssize_t trace_options_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_option_dentry *topt = filp->private_data; char *buf; if (topt->flags->val & topt->opt->bit) buf = "1\n"; else buf = "0\n"; return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); } static ssize_t trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_option_dentry *topt = filp->private_data; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (val != 0 && val != 1) return -EINVAL; if (!!(topt->flags->val & topt->opt->bit) != val) { mutex_lock(&trace_types_lock); ret = __set_tracer_option(topt->tr, topt->flags, topt->opt, !val); mutex_unlock(&trace_types_lock); if (ret) return ret; } *ppos += cnt; return cnt; } static int tracing_open_options(struct inode *inode, struct file *filp) { struct trace_option_dentry *topt = inode->i_private; int ret; ret = tracing_check_open_get_tr(topt->tr); if (ret) return ret; filp->private_data = inode->i_private; return 0; } static int tracing_release_options(struct inode *inode, struct file *file) { struct trace_option_dentry *topt = file->private_data; trace_array_put(topt->tr); return 0; } static const struct file_operations trace_options_fops = { .open = tracing_open_options, .read = trace_options_read, .write = trace_options_write, .llseek = generic_file_llseek, .release = tracing_release_options, }; /* * In order to pass in both the trace_array descriptor as well as the index * to the flag that the trace option file represents, the trace_array * has a character array of trace_flags_index[], which holds the index * of the bit for the flag it represents. index[0] == 0, index[1] == 1, etc. * The address of this character array is passed to the flag option file * read/write callbacks. * * In order to extract both the index and the trace_array descriptor, * get_tr_index() uses the following algorithm. * * idx = *ptr; * * As the pointer itself contains the address of the index (remember * index[1] == 1). * * Then to get the trace_array descriptor, by subtracting that index * from the ptr, we get to the start of the index itself. * * ptr - idx == &index[0] * * Then a simple container_of() from that pointer gets us to the * trace_array descriptor. */ static void get_tr_index(void *data, struct trace_array **ptr, unsigned int *pindex) { *pindex = *(unsigned char *)data; *ptr = container_of(data - *pindex, struct trace_array, trace_flags_index); } static ssize_t trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { void *tr_index = filp->private_data; struct trace_array *tr; unsigned int index; char *buf; get_tr_index(tr_index, &tr, &index); if (tr->trace_flags & (1 << index)) buf = "1\n"; else buf = "0\n"; return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); } static ssize_t trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { void *tr_index = filp->private_data; struct trace_array *tr; unsigned int index; unsigned long val; int ret; get_tr_index(tr_index, &tr, &index); ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (val != 0 && val != 1) return -EINVAL; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); if (ret < 0) return ret; *ppos += cnt; return cnt; } static const struct file_operations trace_options_core_fops = { .open = tracing_open_generic, .read = trace_options_core_read, .write = trace_options_core_write, .llseek = generic_file_llseek, }; struct dentry *trace_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { struct dentry *ret; ret = tracefs_create_file(name, mode, parent, data, fops); if (!ret) pr_warn("Could not create tracefs '%s' entry\n", name); return ret; } static struct dentry *trace_options_init_dentry(struct trace_array *tr) { struct dentry *d_tracer; if (tr->options) return tr->options; d_tracer = tracing_get_dentry(tr); if (IS_ERR(d_tracer)) return NULL; tr->options = tracefs_create_dir("options", d_tracer); if (!tr->options) { pr_warn("Could not create tracefs directory 'options'\n"); return NULL; } return tr->options; } static void create_trace_option_file(struct trace_array *tr, struct trace_option_dentry *topt, struct tracer_flags *flags, struct tracer_opt *opt) { struct dentry *t_options; t_options = trace_options_init_dentry(tr); if (!t_options) return; topt->flags = flags; topt->opt = opt; topt->tr = tr; topt->entry = trace_create_file(opt->name, TRACE_MODE_WRITE, t_options, topt, &trace_options_fops); } static void create_trace_option_files(struct trace_array *tr, struct tracer *tracer) { struct trace_option_dentry *topts; struct trace_options *tr_topts; struct tracer_flags *flags; struct tracer_opt *opts; int cnt; int i; if (!tracer) return; flags = tracer->flags; if (!flags || !flags->opts) return; /* * If this is an instance, only create flags for tracers * the instance may have. */ if (!trace_ok_for_array(tracer, tr)) return; for (i = 0; i < tr->nr_topts; i++) { /* Make sure there's no duplicate flags. */ if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags)) return; } opts = flags->opts; for (cnt = 0; opts[cnt].name; cnt++) ; topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL); if (!topts) return; tr_topts = krealloc(tr->topts, sizeof(*tr->topts) * (tr->nr_topts + 1), GFP_KERNEL); if (!tr_topts) { kfree(topts); return; } tr->topts = tr_topts; tr->topts[tr->nr_topts].tracer = tracer; tr->topts[tr->nr_topts].topts = topts; tr->nr_topts++; for (cnt = 0; opts[cnt].name; cnt++) { create_trace_option_file(tr, &topts[cnt], flags, &opts[cnt]); MEM_FAIL(topts[cnt].entry == NULL, "Failed to create trace option: %s", opts[cnt].name); } } static struct dentry * create_trace_option_core_file(struct trace_array *tr, const char *option, long index) { struct dentry *t_options; t_options = trace_options_init_dentry(tr); if (!t_options) return NULL; return trace_create_file(option, TRACE_MODE_WRITE, t_options, (void *)&tr->trace_flags_index[index], &trace_options_core_fops); } static void create_trace_options_dir(struct trace_array *tr) { struct dentry *t_options; bool top_level = tr == &global_trace; int i; t_options = trace_options_init_dentry(tr); if (!t_options) return; for (i = 0; trace_options[i]; i++) { if (top_level || !((1 << i) & TOP_LEVEL_TRACE_FLAGS)) create_trace_option_core_file(tr, trace_options[i], i); } } static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[64]; int r; r = tracer_tracing_is_on(tr); r = sprintf(buf, "%d\n", r); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; struct trace_buffer *buffer = tr->array_buffer.buffer; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (buffer) { mutex_lock(&trace_types_lock); if (!!val == tracer_tracing_is_on(tr)) { val = 0; /* do nothing */ } else if (val) { tracer_tracing_on(tr); if (tr->current_trace->start) tr->current_trace->start(tr); } else { tracer_tracing_off(tr); if (tr->current_trace->stop) tr->current_trace->stop(tr); /* Wake up any waiters */ ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS); } mutex_unlock(&trace_types_lock); } (*ppos)++; return cnt; } static const struct file_operations rb_simple_fops = { .open = tracing_open_generic_tr, .read = rb_simple_read, .write = rb_simple_write, .release = tracing_release_generic_tr, .llseek = default_llseek, }; static ssize_t buffer_percent_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[64]; int r; r = tr->buffer_percent; r = sprintf(buf, "%d\n", r); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t buffer_percent_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (val > 100) return -EINVAL; tr->buffer_percent = val; (*ppos)++; return cnt; } static const struct file_operations buffer_percent_fops = { .open = tracing_open_generic_tr, .read = buffer_percent_read, .write = buffer_percent_write, .release = tracing_release_generic_tr, .llseek = default_llseek, }; static ssize_t buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; size_t size; char buf[64]; int order; int r; order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); size = (PAGE_SIZE << order) / 1024; r = sprintf(buf, "%zd\n", size); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; unsigned long val; int old_order; int order; int pages; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; val *= 1024; /* value passed in is in KB */ pages = DIV_ROUND_UP(val, PAGE_SIZE); order = fls(pages - 1); /* limit between 1 and 128 system pages */ if (order < 0 || order > 7) return -EINVAL; /* Do not allow tracing while changing the order of the ring buffer */ tracing_stop_tr(tr); old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); if (old_order == order) goto out; ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order); if (ret) goto out; #ifdef CONFIG_TRACER_MAX_TRACE if (!tr->allocated_snapshot) goto out_max; ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); if (ret) { /* Put back the old order */ cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order); if (WARN_ON_ONCE(cnt)) { /* * AARGH! We are left with different orders! * The max buffer is our "snapshot" buffer. * When a tracer needs a snapshot (one of the * latency tracers), it swaps the max buffer * with the saved snap shot. We succeeded to * update the order of the main buffer, but failed to * update the order of the max buffer. But when we tried * to reset the main buffer to the original size, we * failed there too. This is very unlikely to * happen, but if it does, warn and kill all * tracing. */ tracing_disabled = 1; } goto out; } out_max: #endif (*ppos)++; out: if (ret) cnt = ret; tracing_start_tr(tr); return cnt; } static const struct file_operations buffer_subbuf_size_fops = { .open = tracing_open_generic_tr, .read = buffer_subbuf_size_read, .write = buffer_subbuf_size_write, .release = tracing_release_generic_tr, .llseek = default_llseek, }; static struct dentry *trace_instance_dir; static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); static int allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) { enum ring_buffer_flags rb_flags; rb_flags = tr->trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; buf->tr = tr; if (tr->range_addr_start && tr->range_addr_size) { buf->buffer = ring_buffer_alloc_range(size, rb_flags, 0, tr->range_addr_start, tr->range_addr_size); ring_buffer_last_boot_delta(buf->buffer, &tr->text_delta, &tr->data_delta); /* * This is basically the same as a mapped buffer, * with the same restrictions. */ tr->mapped++; } else { buf->buffer = ring_buffer_alloc(size, rb_flags); } if (!buf->buffer) return -ENOMEM; buf->data = alloc_percpu(struct trace_array_cpu); if (!buf->data) { ring_buffer_free(buf->buffer); buf->buffer = NULL; return -ENOMEM; } /* Allocate the first page for all buffers */ set_buffer_entries(&tr->array_buffer, ring_buffer_size(tr->array_buffer.buffer, 0)); return 0; } static void free_trace_buffer(struct array_buffer *buf) { if (buf->buffer) { ring_buffer_free(buf->buffer); buf->buffer = NULL; free_percpu(buf->data); buf->data = NULL; } } static int allocate_trace_buffers(struct trace_array *tr, int size) { int ret; ret = allocate_trace_buffer(tr, &tr->array_buffer, size); if (ret) return ret; #ifdef CONFIG_TRACER_MAX_TRACE /* Fix mapped buffer trace arrays do not have snapshot buffers */ if (tr->range_addr_start) return 0; ret = allocate_trace_buffer(tr, &tr->max_buffer, allocate_snapshot ? size : 1); if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) { free_trace_buffer(&tr->array_buffer); return -ENOMEM; } tr->allocated_snapshot = allocate_snapshot; allocate_snapshot = false; #endif return 0; } static void free_trace_buffers(struct trace_array *tr) { if (!tr) return; free_trace_buffer(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE free_trace_buffer(&tr->max_buffer); #endif } static void init_trace_flags_index(struct trace_array *tr) { int i; /* Used by the trace options files */ for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) tr->trace_flags_index[i] = i; } static void __update_tracer_options(struct trace_array *tr) { struct tracer *t; for (t = trace_types; t; t = t->next) add_tracer_options(tr, t); } static void update_tracer_options(struct trace_array *tr) { mutex_lock(&trace_types_lock); tracer_options_updated = true; __update_tracer_options(tr); mutex_unlock(&trace_types_lock); } /* Must have trace_types_lock held */ struct trace_array *trace_array_find(const char *instance) { struct trace_array *tr, *found = NULL; list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr->name && strcmp(tr->name, instance) == 0) { found = tr; break; } } return found; } struct trace_array *trace_array_find_get(const char *instance) { struct trace_array *tr; mutex_lock(&trace_types_lock); tr = trace_array_find(instance); if (tr) tr->ref++; mutex_unlock(&trace_types_lock); return tr; } static int trace_array_create_dir(struct trace_array *tr) { int ret; tr->dir = tracefs_create_dir(tr->name, trace_instance_dir); if (!tr->dir) return -EINVAL; ret = event_trace_add_tracer(tr->dir, tr); if (ret) { tracefs_remove(tr->dir); return ret; } init_tracer_tracefs(tr, tr->dir); __update_tracer_options(tr); return ret; } static struct trace_array * trace_array_create_systems(const char *name, const char *systems, unsigned long range_addr_start, unsigned long range_addr_size) { struct trace_array *tr; int ret; ret = -ENOMEM; tr = kzalloc(sizeof(*tr), GFP_KERNEL); if (!tr) return ERR_PTR(ret); tr->name = kstrdup(name, GFP_KERNEL); if (!tr->name) goto out_free_tr; if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) goto out_free_tr; if (systems) { tr->system_names = kstrdup_const(systems, GFP_KERNEL); if (!tr->system_names) goto out_free_tr; } /* Only for boot up memory mapped ring buffers */ tr->range_addr_start = range_addr_start; tr->range_addr_size = range_addr_size; tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); raw_spin_lock_init(&tr->start_lock); tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; #ifdef CONFIG_TRACER_MAX_TRACE spin_lock_init(&tr->snapshot_trigger_lock); #endif tr->current_trace = &nop_trace; INIT_LIST_HEAD(&tr->systems); INIT_LIST_HEAD(&tr->events); INIT_LIST_HEAD(&tr->hist_vars); INIT_LIST_HEAD(&tr->err_log); #ifdef CONFIG_MODULES INIT_LIST_HEAD(&tr->mod_events); #endif if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; /* The ring buffer is defaultly expanded */ trace_set_ring_buffer_expanded(tr); if (ftrace_allocate_ftrace_ops(tr) < 0) goto out_free_tr; ftrace_init_trace_array(tr); init_trace_flags_index(tr); if (trace_instance_dir) { ret = trace_array_create_dir(tr); if (ret) goto out_free_tr; } else __trace_early_add_events(tr); list_add(&tr->list, &ftrace_trace_arrays); tr->ref++; return tr; out_free_tr: ftrace_free_ftrace_ops(tr); free_trace_buffers(tr); free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree_const(tr->system_names); kfree(tr->name); kfree(tr); return ERR_PTR(ret); } static struct trace_array *trace_array_create(const char *name) { return trace_array_create_systems(name, NULL, 0, 0); } static int instance_mkdir(const char *name) { struct trace_array *tr; int ret; guard(mutex)(&event_mutex); guard(mutex)(&trace_types_lock); ret = -EEXIST; if (trace_array_find(name)) return -EEXIST; tr = trace_array_create(name); ret = PTR_ERR_OR_ZERO(tr); return ret; } static u64 map_pages(u64 start, u64 size) { struct page **pages; phys_addr_t page_start; unsigned int page_count; unsigned int i; void *vaddr; page_count = DIV_ROUND_UP(size, PAGE_SIZE); page_start = start; pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL); if (!pages) return 0; for (i = 0; i < page_count; i++) { phys_addr_t addr = page_start + i * PAGE_SIZE; pages[i] = pfn_to_page(addr >> PAGE_SHIFT); } vaddr = vmap(pages, page_count, VM_MAP, PAGE_KERNEL); kfree(pages); |