| 15808 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 #define DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE 29 #define DSA_TAG_PROTO_YT921X_VALUE 30 #define DSA_TAG_PROTO_MXL_GSW1XX_VALUE 31 #define DSA_TAG_PROTO_MXL862_VALUE 32 #define DSA_TAG_PROTO_NETC_VALUE 33 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_LEGACY_FCS = DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, DSA_TAG_PROTO_YT921X = DSA_TAG_PROTO_YT921X_VALUE, DSA_TAG_PROTO_MXL_GSW1XX = DSA_TAG_PROTO_MXL_GSW1XX_VALUE, DSA_TAG_PROTO_MXL862 = DSA_TAG_PROTO_MXL862_VALUE, DSA_TAG_PROTO_NETC = DSA_TAG_PROTO_NETC_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct flow_action_police policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; netdevice_tracker conduit_tracker; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } #define dsa_switch_for_each_bridge_member(_dp, _ds, _bdev) \ dsa_switch_for_each_user_port(_dp, _ds) \ if (dsa_port_offloads_bridge_dev(_dp, _bdev)) static inline u32 dsa_bridge_ports(struct dsa_switch *ds, const struct net_device *bdev) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_bridge_member(dp, ds, bdev) mask |= BIT(dp->index); return mask; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_ts_stats)(struct dsa_switch *ds, int port, struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ bool (*support_eee)(struct dsa_switch *ds, int port); int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, const struct flow_action_police *policer, struct netlink_ext_ack *extack); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct kernel_hwtstamp_config *config); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int dsa_port_simple_hsr_validate(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int dsa_port_simple_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int dsa_port_simple_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); bool dsa_supports_eee(struct dsa_switch *ds, int port); #endif |
| 2636 563 40 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2012 Novell Inc. * Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2012-2019 Linux Foundation * * Core driver model functions and structures that should not be * shared outside of the drivers/base/ directory. * */ #include <linux/notifier.h> /** * struct subsys_private - structure to hold the private to the driver core * portions of the bus_type/class structure. * @subsys: the struct kset that defines this subsystem * @devices_kset: the subsystem's 'devices' directory * @interfaces: list of subsystem interfaces associated * @mutex: protect the devices, and interfaces lists. * @drivers_kset: the list of drivers associated * @klist_devices: the klist to iterate over the @devices_kset * @klist_drivers: the klist to iterate over the @drivers_kset * @bus_notifier: the bus notifier list for anything that cares about things * on this bus. * @drivers_autoprobe: gate whether new devices are automatically attached to * registered drivers, or new drivers automatically attach * to existing devices. * @bus: pointer back to the struct bus_type that this structure is associated * with. * @dev_root: Default device to use as the parent. * @glue_dirs: "glue" directory to put in-between the parent device to * avoid namespace conflicts * @class: pointer back to the struct class that this structure is associated * with. * @lock_key: Lock class key for use by the lock validator * * This structure is the one that is the actual kobject allowing struct * bus_type/class to be statically allocated safely. Nothing outside of the * driver core should ever touch these fields. */ struct subsys_private { struct kset subsys; struct kset *devices_kset; struct list_head interfaces; struct mutex mutex; struct kset *drivers_kset; struct klist klist_devices; struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; const struct bus_type *bus; struct device *dev_root; struct kset glue_dirs; const struct class *class; struct lock_class_key lock_key; }; #define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj) static inline struct subsys_private *subsys_get(struct subsys_private *sp) { if (sp) kset_get(&sp->subsys); return sp; } static inline void subsys_put(struct subsys_private *sp) { if (sp) kset_put(&sp->subsys); } struct subsys_private *bus_to_subsys(const struct bus_type *bus); struct subsys_private *class_to_subsys(const struct class *class); struct driver_private { struct kobject kobj; struct klist klist_devices; struct klist_node knode_bus; struct module_kobject *mkobj; struct device_driver *driver; }; #define to_driver(obj) container_of(obj, struct driver_private, kobj) /** * struct device_private - structure to hold the private to the driver core * portions of the device structure. * @klist_children: klist containing all children of this device * @knode_parent: node in sibling list * @knode_driver: node in driver list * @knode_bus: node in bus list * @knode_class: node in class list * @deferred_probe: entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the * resources needed by the device; typically because it depends * on another driver getting probed first. * @async_driver: pointer to device driver awaiting probe via async_probe * @deferred_probe_reason: capture the -EPROBE_DEFER message emitted with * dev_err_probe() for later retrieval via debugfs * @device: pointer back to the struct device that this structure is * associated with. * @dead: This device is currently either in the process of or has been * removed from the system. Any asynchronous events scheduled for this * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ struct device_private { struct klist klist_children; struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; struct klist_node knode_class; struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; struct device *device; u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) #define to_device_private_driver(obj) \ container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) #define to_device_private_class(obj) \ container_of(obj, struct device_private, knode_class) /* initialisation functions */ int devices_init(void); int buses_init(void); int classes_init(void); int firmware_init(void); #ifdef CONFIG_SYS_HYPERVISOR int hypervisor_init(void); #else static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); int faux_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS void auxiliary_bus_init(void); #else static inline void auxiliary_bus_init(void) { } #endif struct kobject *virtual_device_parent(void); int bus_add_device(struct device *dev); void bus_probe_device(struct device *dev); void bus_remove_device(struct device *dev); void bus_notify(struct device *dev, enum bus_notifier_event value); bool bus_is_registered(const struct bus_type *bus); int bus_add_driver(struct device_driver *drv); void bus_remove_driver(struct device_driver *drv); void device_release_driver_internal(struct device *dev, const struct device_driver *drv, struct device *parent); void driver_detach(const struct device_driver *drv); void driver_deferred_probe_del(struct device *dev); void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); static inline int driver_match_device(const struct device_driver *drv, struct device *dev) { return drv->bus->match ? drv->bus->match(dev, drv) : 1; } static inline bool dev_has_sync_state(struct device *dev) { struct device_driver *drv; if (!dev) return false; drv = READ_ONCE(dev->driver); if (drv && drv->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_sync_state(struct device *dev) { if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); } int driver_add_groups(const struct device_driver *drv, const struct attribute_group *const *groups); void driver_remove_groups(const struct device_driver *drv, const struct attribute_group *const *groups); void device_driver_detach(struct device *dev); static inline void device_set_driver(struct device *dev, const struct device_driver *drv) { /* * Majority (all?) read accesses to dev->driver happens either * while holding device lock or in bus/driver code that is only * invoked when the device is bound to a driver and there is no * concern of the pointer being changed while it is being read. * However when reading device's uevent file we read driver pointer * without taking device lock (so we do not block there for * arbitrary amount of time). We use WRITE_ONCE() here to prevent * tearing so that READ_ONCE() can safely be used in uevent code. */ // FIXME - this cast should not be needed "soon" WRITE_ONCE(dev->driver, (struct device_driver *)drv); } struct devres_node; typedef void (*dr_node_release_t)(struct device *dev, struct devres_node *node); typedef void (*dr_node_free_t)(struct devres_node *node); struct devres_node { struct list_head entry; dr_node_release_t release; dr_node_free_t free_node; const char *name; size_t size; }; void devres_node_init(struct devres_node *node, dr_node_release_t release, dr_node_free_t free_node); void devres_node_add(struct device *dev, struct devres_node *node); bool devres_node_remove(struct device *dev, struct devres_node *node); void devres_set_node_dbginfo(struct devres_node *node, const char *name, size_t size); void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); int devres_release_all(struct device *dev); void device_block_probing(void); void device_unblock_probing(void); void deferred_probe_extend_timeout(void); void driver_deferred_probe_trigger(void); const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) int module_add_driver(struct module *mod, const struct device_driver *drv); void module_remove_driver(const struct device_driver *drv); #else static inline int module_add_driver(struct module *mod, struct device_driver *drv) { return 0; } static inline void module_remove_driver(struct device_driver *drv) { } #endif #ifdef CONFIG_DEVTMPFS int devtmpfs_init(void); #else static inline int devtmpfs_init(void) { return 0; } #endif #ifdef CONFIG_BLOCK extern const struct class block_class; static inline bool is_blockdev(struct device *dev) { return dev->class == &block_class; } #else static inline bool is_blockdev(struct device *dev) { return false; } #endif /* Device links support */ int device_links_read_lock(void); void device_links_read_unlock(int idx); int device_links_read_lock_held(void); int device_links_check_suppliers(struct device *dev); void device_links_force_bind(struct device *dev); void device_links_driver_bound(struct device *dev); void device_links_driver_cleanup(struct device *dev); void device_links_no_driver(struct device *dev); bool device_links_busy(struct device *dev); void device_links_unbind_consumers(struct device *dev); bool device_link_flag_is_sync_state_only(u32 flags); void fw_devlink_drivers_done(void); void fw_devlink_probing_done(void); #define dev_for_each_link_to_supplier(__link, __dev) \ list_for_each_entry_srcu(__link, &(__dev)->links.suppliers, c_node, \ device_links_read_lock_held()) #define dev_for_each_link_to_consumer(__link, __dev) \ list_for_each_entry_srcu(__link, &(__dev)->links.consumers, s_node, \ device_links_read_lock_held()) /* device pm support */ void device_pm_move_to_tail(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_create_node(struct device *dev); int devtmpfs_delete_node(struct device *dev); #else static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } #endif void software_node_init(void); void software_node_notify(struct device *dev); void software_node_notify_remove(struct device *dev); #ifdef CONFIG_PINCTRL int pinctrl_bind_pins(struct device *dev); #else static inline int pinctrl_bind_pins(struct device *dev) { return 0; } #endif /* CONFIG_PINCTRL */ |
| 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the ICMP module. * * Version: @(#)icmp.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _ICMP_H #define _ICMP_H #include <linux/icmp.h> #include <net/inet_sock.h> #include <net/snmp.h> #include <net/ip.h> struct icmp_err { int errno; unsigned int fatal:1; }; extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define __ICMP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256) #define ICMPMSGIN_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) struct dst_entry; struct net_proto_family; struct sk_buff; struct net; void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, const struct inet_skb_parm *parm); static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { __icmp_send(skb_in, type, code, info, IPCB(skb_in)); } #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct inet_skb_parm parm; memset(&parm, 0, sizeof(parm)); __icmp_send(skb_in, type, code, info, &parm); } #endif int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr); #endif /* _ICMP_H */ |
| 47968 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 2189 55 2474 195 195 1846 671 461 462 462 17 107 463 16 462 6 6 6 6 6 438 439 440 378 355 440 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 | // SPDX-License-Identifier: GPL-2.0 /* * class.c - basic device class management * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2003-2004 Greg Kroah-Hartman * Copyright (c) 2003-2004 IBM Corp. */ #include <linux/device/class.h> #include <linux/device.h> #include <linux/module.h> #include <linux/init.h> #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mutex.h> #include "base.h" /* /sys/class */ static struct kset *class_kset; #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr) /** * class_to_subsys - Turn a struct class into a struct subsys_private * * @class: pointer to the struct bus_type to look up * * The driver core internals need to work on the subsys_private structure, not * the external struct class pointer. This function walks the list of * registered classes in the system and finds the matching one and returns the * internal struct subsys_private that relates to that class. * * Note, the reference count of the return value is INCREMENTED if it is not * NULL. A call to subsys_put() must be done when finished with the pointer in * order for it to be properly freed. */ struct subsys_private *class_to_subsys(const struct class *class) { struct subsys_private *sp = NULL; struct kobject *kobj; if (!class || !class_kset) return NULL; spin_lock(&class_kset->list_lock); if (list_empty(&class_kset->list)) goto done; list_for_each_entry(kobj, &class_kset->list, entry) { struct kset *kset = container_of(kobj, struct kset, kobj); sp = container_of_const(kset, struct subsys_private, subsys); if (sp->class == class) goto done; } sp = NULL; done: sp = subsys_get(sp); spin_unlock(&class_kset->list_lock); return sp; } static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->show) ret = class_attr->show(cp->class, class_attr, buf); return ret; } static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->store) ret = class_attr->store(cp->class, class_attr, buf, count); return ret; } static void class_release(struct kobject *kobj) { struct subsys_private *cp = to_subsys_private(kobj); const struct class *class = cp->class; pr_debug("class '%s': release.\n", class->name); if (class->class_release) class->class_release(class); else pr_debug("class '%s' does not have a release() function, " "be careful\n", class->name); lockdep_unregister_key(&cp->lock_key); kfree(cp); } static const struct kobj_ns_type_operations *class_child_ns_type(const struct kobject *kobj) { const struct subsys_private *cp = to_subsys_private(kobj); const struct class *class = cp->class; return class->ns_type; } static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; static const struct kobj_type class_ktype = { .sysfs_ops = &class_sysfs_ops, .release = class_release, .child_ns_type = class_child_ns_type, }; int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, const struct ns_common *ns) { struct subsys_private *sp = class_to_subsys(cls); int error; if (!sp) return -EINVAL; error = sysfs_create_file_ns(&sp->subsys.kobj, &attr->attr, ns); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(class_create_file_ns); void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr, const struct ns_common *ns) { struct subsys_private *sp = class_to_subsys(cls); if (!sp) return; sysfs_remove_file_ns(&sp->subsys.kobj, &attr->attr, ns); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_remove_file_ns); static struct device *klist_class_to_dev(struct klist_node *n) { struct device_private *p = to_device_private_class(n); return p->device; } static void klist_class_dev_get(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); get_device(dev); } static void klist_class_dev_put(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); put_device(dev); } int class_register(const struct class *cls) { struct subsys_private *cp; struct lock_class_key *key; int error; pr_debug("device class '%s': registering\n", cls->name); if (cls->ns_type && !cls->namespace) { pr_err("%s: class '%s' does not have namespace\n", __func__, cls->name); return -EINVAL; } if (!cls->ns_type && cls->namespace) { pr_err("%s: class '%s' does not have ns_type\n", __func__, cls->name); return -EINVAL; } cp = kzalloc_obj(*cp); if (!cp) return -ENOMEM; klist_init(&cp->klist_devices, klist_class_dev_get, klist_class_dev_put); INIT_LIST_HEAD(&cp->interfaces); kset_init(&cp->glue_dirs); key = &cp->lock_key; lockdep_register_key(key); __mutex_init(&cp->mutex, "subsys mutex", key); error = kobject_set_name(&cp->subsys.kobj, "%s", cls->name); if (error) goto err_out; cp->subsys.kobj.kset = class_kset; cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; error = kset_register(&cp->subsys); if (error) goto err_out; error = sysfs_create_groups(&cp->subsys.kobj, cls->class_groups); if (error) { kobject_del(&cp->subsys.kobj); kfree_const(cp->subsys.kobj.name); goto err_out; } return 0; err_out: lockdep_unregister_key(key); kfree(cp); return error; } EXPORT_SYMBOL_GPL(class_register); void class_unregister(const struct class *cls) { struct subsys_private *sp = class_to_subsys(cls); if (!sp) return; pr_debug("device class '%s': unregistering\n", cls->name); sysfs_remove_groups(&sp->subsys.kobj, cls->class_groups); kset_unregister(&sp->subsys); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_unregister); static void class_create_release(const struct class *cls) { pr_debug("%s called for %s\n", __func__, cls->name); kfree(cls); } /** * class_create - create a struct class structure * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used * in calls to device_create(). * * Returns &struct class pointer on success, or ERR_PTR() on error. * * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ struct class *class_create(const char *name) { struct class *cls; int retval; cls = kzalloc_obj(*cls); if (!cls) { retval = -ENOMEM; goto error; } cls->name = name; cls->class_release = class_create_release; retval = class_register(cls); if (retval) goto error; return cls; error: kfree(cls); return ERR_PTR(retval); } EXPORT_SYMBOL_GPL(class_create); /** * class_destroy - destroys a struct class structure * @cls: pointer to the struct class that is to be destroyed * * Note, the pointer to be destroyed must have been created with a call * to class_create(). */ void class_destroy(const struct class *cls) { if (IS_ERR_OR_NULL(cls)) return; class_unregister(cls); } EXPORT_SYMBOL_GPL(class_destroy); /** * class_dev_iter_init - initialize class device iterator * @iter: class iterator to initialize * @class: the class we wanna iterate over * @start: the device to start iterating from, if any * @type: device_type of the devices to iterate over, NULL for all * * Initialize class iterator @iter such that it iterates over devices * of @class. If @start is set, the list iteration will start there, * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, const struct device *start, const struct device_type *type) { struct subsys_private *sp = class_to_subsys(class); struct klist_node *start_knode = NULL; memset(iter, 0, sizeof(*iter)); if (!sp) { pr_crit("%s: class %p was not registered yet\n", __func__, class); return; } if (start) start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); /** * class_dev_iter_next - iterate to the next device * @iter: class iterator to proceed * * Proceed @iter to the next device and return it. Returns NULL if * iteration is complete. * * The returned device is referenced and won't be released till * iterator is proceed to the next device or exited. The caller is * free to do whatever it wants to do with the device including * calling back into class code. */ struct device *class_dev_iter_next(struct class_dev_iter *iter) { struct klist_node *knode; struct device *dev; if (!iter->sp) return NULL; while (1) { knode = klist_next(&iter->ki); if (!knode) return NULL; dev = klist_class_to_dev(knode); if (!iter->type || iter->type == dev->type) return dev; } } EXPORT_SYMBOL_GPL(class_dev_iter_next); /** * class_dev_iter_exit - finish iteration * @iter: class iterator to finish * * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); /** * class_for_each_device - device iterator * @class: the class we're iterating * @start: the device to start with in the list, if any. * @data: data for the callback * @fn: function to be called for each device * * Iterate over @class's list of devices, and call @fn for each, * passing it @data. If @start is set, the list iteration will start * there, otherwise if it is NULL, the iteration starts at the * beginning of the list. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. * * @fn is allowed to do anything including calling back into class * code. There's no locking restriction. */ int class_for_each_device(const struct class *class, const struct device *start, void *data, device_iter_t fn) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; int error = 0; if (!class) return -EINVAL; if (!sp) { WARN(1, "%s called for class '%s' before it was registered", __func__, class->name); return -EINVAL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { error = fn(dev, data); if (error) break; } class_dev_iter_exit(&iter); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(class_for_each_device); /** * class_find_device - device iterator for locating a particular device * @class: the class we're iterating * @start: Device to begin with * @data: data for the match function * @match: function to check device * * This is similar to the class_for_each_dev() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. * * Note, you will need to drop the reference with put_device() after use. * * @match is allowed to do anything including calling back into class * code. There's no locking restriction. */ struct device *class_find_device(const struct class *class, const struct device *start, const void *data, device_match_t match) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; if (!class) return NULL; if (!sp) { WARN(1, "%s called for class '%s' before it was registered", __func__, class->name); return NULL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); break; } } class_dev_iter_exit(&iter); subsys_put(sp); return dev; } EXPORT_SYMBOL_GPL(class_find_device); int class_interface_register(struct class_interface *class_intf) { struct subsys_private *sp; const struct class *parent; struct class_dev_iter iter; struct device *dev; if (!class_intf || !class_intf->class) return -ENODEV; parent = class_intf->class; sp = class_to_subsys(parent); if (!sp) return -EINVAL; /* * Reference in sp is now incremented and will be dropped when * the interface is removed in the call to class_interface_unregister() */ mutex_lock(&sp->mutex); list_add_tail(&class_intf->node, &sp->interfaces); if (class_intf->add_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->add_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); return 0; } EXPORT_SYMBOL_GPL(class_interface_register); void class_interface_unregister(struct class_interface *class_intf) { struct subsys_private *sp; const struct class *parent = class_intf->class; struct class_dev_iter iter; struct device *dev; if (!parent) return; sp = class_to_subsys(parent); if (!sp) return; mutex_lock(&sp->mutex); list_del_init(&class_intf->node); if (class_intf->remove_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->remove_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); /* * Decrement the reference count twice, once for the class_to_subsys() * call in the start of this function, and the second one from the * reference increment in class_interface_register() */ subsys_put(sp); subsys_put(sp); } EXPORT_SYMBOL_GPL(class_interface_unregister); ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, char *buf) { struct class_attribute_string *cs; cs = container_of(attr, struct class_attribute_string, attr); return sysfs_emit(buf, "%s\n", cs->str); } EXPORT_SYMBOL_GPL(show_class_attr_string); struct class_compat { struct kobject *kobj; }; /** * class_compat_register - register a compatibility class * @name: the name of the class * * Compatibility class are meant as a temporary user-space compatibility * workaround when converting a family of class devices to a bus devices. */ struct class_compat *class_compat_register(const char *name) { struct class_compat *cls; cls = kmalloc_obj(struct class_compat); if (!cls) return NULL; cls->kobj = kobject_create_and_add(name, &class_kset->kobj); if (!cls->kobj) { kfree(cls); return NULL; } return cls; } EXPORT_SYMBOL_GPL(class_compat_register); /** * class_compat_unregister - unregister a compatibility class * @cls: the class to unregister */ void class_compat_unregister(struct class_compat *cls) { kobject_put(cls->kobj); kfree(cls); } EXPORT_SYMBOL_GPL(class_compat_unregister); /** * class_compat_create_link - create a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device */ int class_compat_create_link(struct class_compat *cls, struct device *dev) { return sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_create_link); /** * class_compat_remove_link - remove a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device */ void class_compat_remove_link(struct class_compat *cls, struct device *dev) { sysfs_remove_link(cls->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_remove_link); /** * class_is_registered - determine if at this moment in time, a class is * registered in the driver core or not. * @class: the class to check * * Returns a boolean to state if the class is registered in the driver core * or not. Note that the value could switch right after this call is made, * so only use this in places where you "know" it is safe to do so (usually * to determine if the specific class has been registered yet or not). * * Be careful in using this. */ bool class_is_registered(const struct class *class) { struct subsys_private *sp = class_to_subsys(class); bool is_initialized = false; if (sp) { is_initialized = true; subsys_put(sp); } return is_initialized; } EXPORT_SYMBOL_GPL(class_is_registered); int __init classes_init(void) { class_kset = kset_create_and_add("class", NULL, NULL); if (!class_kset) return -ENOMEM; return 0; } |
| 5 2 6 3 3 6 1 1 1 1 3 3 3 3 7 7 1 1 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 | // SPDX-License-Identifier: GPL-2.0-or-later /* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv4/xfrm4_protocol.c */ #include <linux/init.h> #include <linux/mutex.h> #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; static DEFINE_MUTEX(xfrm6_protocol_mutex); static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_handlers; case IPPROTO_AH: return &ah6_handlers; case IPPROTO_COMP: return &ipcomp6_handlers; } return NULL; } #define for_each_protocol_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(protocol); if (!head) return 0; for_each_protocol_rcu(*proto_handlers(protocol), handler) if ((ret = handler->cb_handler(skb, err)) <= 0) return ret; return 0; } int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(nexthdr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); if (!head) goto out; if (!skb_dst(skb)) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); int flags = RT6_LOOKUP_F_HAS_SADDR; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowlabel = ip6_flowinfo(ip6h), .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; dst = ip6_route_input_lookup(dev_net(skb->dev), skb->dev, &fl6, skb, flags); if (dst->error) { dst_release(dst); goto drop; } skb_dst_set(skb, dst); } for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; out: icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } EXPORT_SYMBOL(xfrm6_rcv_encap); static int xfrm6_esp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(esp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(esp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ah_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ah6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ah6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ipcomp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ipcomp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ipcomp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol esp6_protocol = { .handler = xfrm6_esp_rcv, .err_handler = xfrm6_esp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ah6_protocol = { .handler = xfrm6_ah_rcv, .err_handler = xfrm6_ah_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ipcomp6_protocol = { .handler = xfrm6_ipcomp_rcv, .err_handler = xfrm6_ipcomp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct xfrm_input_afinfo xfrm6_input_afinfo = { .family = AF_INET6, .callback = xfrm6_rcv_cb, }; static inline const struct inet6_protocol *netproto(unsigned char protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_protocol; case IPPROTO_AH: return &ah6_protocol; case IPPROTO_COMP: return &ipcomp6_protocol; } return NULL; } int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; bool add_netproto = false; int ret = -EEXIST; int priority = handler->priority; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) add_netproto = true; for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_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(&xfrm6_protocol_mutex); if (add_netproto) { if (inet6_add_protocol(netproto(protocol), protocol)) { pr_err("%s: can't add protocol\n", __func__); ret = -EAGAIN; } } return ret; } EXPORT_SYMBOL(xfrm6_protocol_register); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; int ret = -ENOENT; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) { if (inet6_del_protocol(netproto(protocol), protocol) < 0) { pr_err("%s: can't remove protocol\n", __func__); ret = -EAGAIN; } } mutex_unlock(&xfrm6_protocol_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_protocol_deregister); int __init xfrm6_protocol_init(void) { return xfrm_input_register_afinfo(&xfrm6_input_afinfo); } void xfrm6_protocol_fini(void) { xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); } |
| 2669 2669 563 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.h - generic kernel object infrastructure. * * Copyright (c) 2002-2003 Patrick Mochel * Copyright (c) 2002-2003 Open Source Development Labs * Copyright (c) 2006-2008 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2008 Novell Inc. * * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ #ifndef _KOBJECT_H_ #define _KOBJECT_H_ #include <linux/types.h> #include <linux/list.h> #include <linux/sysfs.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> #include <linux/uidgid.h> #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 64 /* number of env pointers */ #define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */ #ifdef CONFIG_UEVENT_HELPER /* path to the userspace helper executed on an event */ extern char uevent_helper[]; #endif /* counter to tag the uevent, read only except for the kobject core */ extern atomic64_t uevent_seqnum; /* * The actions here must match the index to the string array * in lib/kobject_uevent.c * * Do not add new actions here without checking with the driver-core * maintainers. Action strings are not meant to express subsystem * or device specific properties. In most cases you want to send a * kobject_uevent_env(kobj, KOBJ_CHANGE, env) with additional event * specific variables added to the event environment. */ enum kobject_action { KOBJ_ADD, KOBJ_REMOVE, KOBJ_CHANGE, KOBJ_MOVE, KOBJ_ONLINE, KOBJ_OFFLINE, KOBJ_BIND, KOBJ_UNBIND, }; struct kobject { const char *name; struct list_head entry; struct kobject *parent; struct kset *kset; const struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; unsigned int uevent_suppress:1; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; #endif }; __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); __printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); void kobject_del(struct kobject *kobj); struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); int __must_check kobject_rename(struct kobject *, const char *new_name); int __must_check kobject_move(struct kobject *, struct kobject *); struct kobject *kobject_get(struct kobject *kobj); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj); void kobject_put(struct kobject *kobj); const struct ns_common *kobject_namespace(const struct kobject *kobj); void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); char *kobject_get_path(const struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(const struct kobject *kobj); const struct ns_common *(*namespace)(const struct kobject *kobj); void (*get_ownership)(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); }; struct kobj_uevent_env { char *argv[3]; char *envp[UEVENT_NUM_ENVP]; int envp_idx; char buf[UEVENT_BUFFER_SIZE]; int buflen; }; struct kset_uevent_ops { int (* const filter)(const struct kobject *kobj); const char *(* const name)(const struct kobject *kobj); int (* const uevent)(const struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, char *buf); ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count); }; extern const struct sysfs_ops kobj_sysfs_ops; struct sock; /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * * A kset defines a group of kobjects. They can be individually * different "types" but overall these kobjects all want to be grouped * together and operated on in the same manner. ksets are used to * define the attribute callbacks and other common events that happen to * a kobject. * * @list: the list of all kobjects for this kset * @list_lock: a lock for iterating over the kobjects * @kobj: the embedded kobject for this kset (recursion, isn't it fun...) * @uevent_ops: the set of uevent operations for this kset. These are * called whenever a kobject has something happen to it so that the kset * can add new environment variables, or filter out the uevents if so * desired. */ struct kset { struct list_head list; spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; } __randomize_layout; void kset_init(struct kset *kset); int __must_check kset_register(struct kset *kset); void kset_unregister(struct kset *kset); struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { return kobj ? container_of(kobj, struct kset, kobj) : NULL; } static inline struct kset *kset_get(struct kset *k) { return k ? to_kset(kobject_get(&k->kobj)) : NULL; } static inline void kset_put(struct kset *k) { kobject_put(&k->kobj); } static inline const struct kobj_type *get_ktype(const struct kobject *kobj) { return kobj->ktype; } struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; /* The global /sys/kernel/mm/ kobject for people to chain off of */ extern struct kobject *mm_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kobject for people to chain off of */ extern struct kobject *power_kobj; /* The global /sys/firmware/ kobject for people to chain off of */ extern struct kobject *firmware_kobj; int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count); __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); #endif /* _KOBJECT_H_ */ |
| 313 145 207 8 251 308 4 9 569 1178 18 230 310 16 96 55 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); #define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_folio(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_folio(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } /* * Pass journal explicitly as it may not be cached in the sbi->s_journal in some * cases */ static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal) { int err = 0; /* * At this point only two things can be operating on the journal. * JBD2 thread performing transaction commit and s_sb_upd_work * issuing sb update through the journal. Once we set * EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not * queue s_sb_upd_work and ext4_force_commit() makes sure any * ext4_handle_error() calls from the running transaction commit are * finished. Hence no new s_sb_upd_work can be queued after we * flush it here. */ ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY); ext4_force_commit(sbi->s_sb); flush_work(&sbi->s_sb_upd_work); err = jbd2_journal_destroy(journal); sbi->s_journal = NULL; return err; } #endif /* _EXT4_JBD2_H */ |
| 21 21 114 114 114 113 60 60 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * kernel/stop_machine.c * * Copyright (C) 2008, 2005 IBM Corporation. * Copyright (C) 2008, 2005 Rusty Russell rusty@rustcorp.com.au * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> */ #include <linux/compiler.h> #include <linux/completion.h> #include <linux/cpu.h> #include <linux/init.h> #include <linux/kthread.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/sched.h> #include <linux/stop_machine.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/smpboot.h> #include <linux/atomic.h> #include <linux/nmi.h> #include <linux/sched/wake_q.h> /* * Structure to determine completion condition and record errors. May * be shared by works on different cpus. */ struct cpu_stop_done { atomic_t nr_todo; /* nr left to execute */ int ret; /* collected return value */ struct completion completion; /* fired if nr_todo reaches 0 */ }; /* the actual stopper, one per every possible cpu, enabled on online cpus */ struct cpu_stopper { struct task_struct *thread; raw_spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ struct cpu_stop_work stop_work; /* for stop_cpus */ unsigned long caller; cpu_stop_fn_t fn; }; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper); static bool stop_machine_initialized = false; void print_stop_info(const char *log_lvl, struct task_struct *task) { /* * If @task is a stopper task, it cannot migrate and task_cpu() is * stable. */ struct cpu_stopper *stopper = per_cpu_ptr(&cpu_stopper, task_cpu(task)); if (task != stopper->thread) return; printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller); } /* static data for stop_cpus */ static DEFINE_MUTEX(stop_cpus_mutex); static bool stop_cpus_in_progress; static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) { memset(done, 0, sizeof(*done)); atomic_set(&done->nr_todo, nr_todo); init_completion(&done->completion); } /* signal completion unless @done is NULL */ static void cpu_stop_signal_done(struct cpu_stop_done *done) { if (atomic_dec_and_test(&done->nr_todo)) complete(&done->completion); } static void __cpu_stop_queue_work(struct cpu_stopper *stopper, struct cpu_stop_work *work) { list_add_tail(&work->list, &stopper->works); } /* queue @work to @stopper. if offline, @work is completed immediately */ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); unsigned long flags; bool enabled; preempt_disable(); raw_spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) __cpu_stop_queue_work(stopper, work); else if (work->done) cpu_stop_signal_done(work->done); raw_spin_unlock_irqrestore(&stopper->lock, flags); if (enabled) wake_up_process(stopper->thread); preempt_enable(); return enabled; } /** * stop_one_cpu - stop a cpu * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn * * Execute @fn(@arg) on @cpu. @fn is run in a process context with * the highest priority preempting any task on the cpu and * monopolizing it. This function returns after the execution is * complete. * * This function doesn't guarantee @cpu stays online till @fn * completes. If @cpu goes down in the middle, execution may happen * partially or fully on different cpus. @fn should either be ready * for that or the caller should ensure that @cpu stays online until * this function completes. * * CONTEXT: * Might sleep. * * RETURNS: * -ENOENT if @fn(@arg) was not executed because @cpu was offline; * otherwise, the return value of @fn. */ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) { struct cpu_stop_done done; struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done, .caller = _RET_IP_ }; cpu_stop_init_done(&done, 1); if (!cpu_stop_queue_work(cpu, &work)) return -ENOENT; /* * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup * cycle by doing a preemption: */ cond_resched(); wait_for_completion(&done.completion); return done.ret; } /* This controls the threads on each CPU. */ enum multi_stop_state { /* Dummy starting state for thread. */ MULTI_STOP_NONE, /* Awaiting everyone to be scheduled. */ MULTI_STOP_PREPARE, /* Disable interrupts. */ MULTI_STOP_DISABLE_IRQ, /* Run the function */ MULTI_STOP_RUN, /* Exit */ MULTI_STOP_EXIT, }; struct multi_stop_data { cpu_stop_fn_t fn; void *data; /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ unsigned int num_threads; const struct cpumask *active_cpus; enum multi_stop_state state; atomic_t thread_ack; }; static void set_state(struct multi_stop_data *msdata, enum multi_stop_state newstate) { /* Reset ack counter. */ atomic_set(&msdata->thread_ack, msdata->num_threads); smp_wmb(); WRITE_ONCE(msdata->state, newstate); } /* Last one to ack a state moves to the next state. */ static void ack_state(struct multi_stop_data *msdata) { if (atomic_dec_and_test(&msdata->thread_ack)) set_state(msdata, msdata->state + 1); } notrace void __weak stop_machine_yield(const struct cpumask *cpumask) { cpu_relax(); } /* This is the cpu_stop function which stops the CPU. */ static int multi_cpu_stop(void *data) { struct multi_stop_data *msdata = data; enum multi_stop_state newstate, curstate = MULTI_STOP_NONE; int cpu = smp_processor_id(), err = 0; const struct cpumask *cpumask; unsigned long flags; bool is_active; /* * When called from stop_machine_from_inactive_cpu(), irq might * already be disabled. Save the state and restore it on exit. */ local_save_flags(flags); if (!msdata->active_cpus) { cpumask = cpu_online_mask; is_active = cpu == cpumask_first(cpumask); } else { cpumask = msdata->active_cpus; is_active = cpumask_test_cpu(cpu, cpumask); } /* Simple state machine */ do { /* Chill out and ensure we re-read multi_stop_state. */ stop_machine_yield(cpumask); newstate = READ_ONCE(msdata->state); if (newstate != curstate) { curstate = newstate; switch (curstate) { case MULTI_STOP_DISABLE_IRQ: local_irq_disable(); hard_irq_disable(); break; case MULTI_STOP_RUN: if (is_active) err = msdata->fn(msdata->data); break; default: break; } ack_state(msdata); } else if (curstate > MULTI_STOP_PREPARE) { /* * At this stage all other CPUs we depend on must spin * in the same loop. Any reason for hard-lockup should * be detected and reported on their side. */ touch_nmi_watchdog(); /* Also suppress RCU CPU stall warnings. */ rcu_momentary_eqs(); } } while (curstate != MULTI_STOP_EXIT); local_irq_restore(flags); return err; } static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, int cpu2, struct cpu_stop_work *work2) { struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1); struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); int err; retry: /* * The waking up of stopper threads has to happen in the same * scheduling context as the queueing. Otherwise, there is a * possibility of one of the above stoppers being woken up by another * CPU, and preempting us. This will cause us to not wake up the other * stopper forever. */ preempt_disable(); raw_spin_lock_irq(&stopper1->lock); raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); if (!stopper1->enabled || !stopper2->enabled) { err = -ENOENT; goto unlock; } /* * Ensure that if we race with __stop_cpus() the stoppers won't get * queued up in reverse order leading to system deadlock. * * We can't miss stop_cpus_in_progress if queue_stop_cpus_work() has * queued a work on cpu1 but not on cpu2, we hold both locks. * * It can be falsely true but it is safe to spin until it is cleared, * queue_stop_cpus_work() does everything under preempt_disable(). */ if (unlikely(stop_cpus_in_progress)) { err = -EDEADLK; goto unlock; } err = 0; __cpu_stop_queue_work(stopper1, work1); __cpu_stop_queue_work(stopper2, work2); unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); if (unlikely(err == -EDEADLK)) { preempt_enable(); while (stop_cpus_in_progress) cpu_relax(); goto retry; } if (!err) { wake_up_process(stopper1->thread); wake_up_process(stopper2->thread); } preempt_enable(); return err; } /** * stop_two_cpus - stops two cpus * @cpu1: the cpu to stop * @cpu2: the other cpu to stop * @fn: function to execute * @arg: argument to @fn * * Stops both the current and specified CPU and runs @fn on one of them. * * returns when both are completed. */ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg) { struct cpu_stop_done done; struct cpu_stop_work work1, work2; struct multi_stop_data msdata; msdata = (struct multi_stop_data){ .fn = fn, .data = arg, .num_threads = 2, .active_cpus = cpumask_of(cpu1), }; work1 = work2 = (struct cpu_stop_work){ .fn = multi_cpu_stop, .arg = &msdata, .done = &done, .caller = _RET_IP_, }; cpu_stop_init_done(&done, 2); set_state(&msdata, MULTI_STOP_PREPARE); if (cpu1 > cpu2) swap(cpu1, cpu2); if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) return -ENOENT; wait_for_completion(&done.completion); return done.ret; } /** * stop_one_cpu_nowait - stop a cpu but don't wait for completion * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn * @work_buf: pointer to cpu_stop_work structure * * Similar to stop_one_cpu() but doesn't wait for completion. The * caller is responsible for ensuring @work_buf is currently unused * and will remain untouched until stopper starts executing @fn. * * CONTEXT: * Don't care. * * RETURNS: * true if cpu_stop_work was queued successfully and @fn will be called, * false otherwise. */ bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, .caller = _RET_IP_, }; return cpu_stop_queue_work(cpu, work_buf); } static bool queue_stop_cpus_work(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg, struct cpu_stop_done *done) { struct cpu_stop_work *work; unsigned int cpu; bool queued = false; /* * Disable preemption while queueing to avoid getting * preempted by a stopper which might wait for other stoppers * to enter @fn which can lead to deadlock. */ preempt_disable(); stop_cpus_in_progress = true; barrier(); for_each_cpu(cpu, cpumask) { work = &per_cpu(cpu_stopper.stop_work, cpu); work->fn = fn; work->arg = arg; work->done = done; work->caller = _RET_IP_; if (cpu_stop_queue_work(cpu, work)) queued = true; } barrier(); stop_cpus_in_progress = false; preempt_enable(); return queued; } static int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) { struct cpu_stop_done done; cpu_stop_init_done(&done, cpumask_weight(cpumask)); if (!queue_stop_cpus_work(cpumask, fn, arg, &done)) return -ENOENT; wait_for_completion(&done.completion); return done.ret; } /** * stop_cpus - stop multiple cpus * @cpumask: cpus to stop * @fn: function to execute * @arg: argument to @fn * * Execute @fn(@arg) on online cpus in @cpumask. On each target cpu, * @fn is run in a process context with the highest priority * preempting any task on the cpu and monopolizing it. This function * returns after all executions are complete. * * This function doesn't guarantee the cpus in @cpumask stay online * till @fn completes. If some cpus go down in the middle, execution * on the cpu may happen partially or fully on different cpus. @fn * should either be ready for that or the caller should ensure that * the cpus stay online until this function completes. * * All stop_cpus() calls are serialized making it safe for @fn to wait * for all cpus to start executing it. * * CONTEXT: * Might sleep. * * RETURNS: * -ENOENT if @fn(@arg) was not executed at all because all cpus in * @cpumask were offline; otherwise, 0 if all executions of @fn * returned 0, any non zero return value if any returned non zero. */ static int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) { int ret; /* static works are used, process one request at a time */ mutex_lock(&stop_cpus_mutex); ret = __stop_cpus(cpumask, fn, arg); mutex_unlock(&stop_cpus_mutex); return ret; } static int cpu_stop_should_run(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); unsigned long flags; int run; raw_spin_lock_irqsave(&stopper->lock, flags); run = !list_empty(&stopper->works); raw_spin_unlock_irqrestore(&stopper->lock, flags); return run; } static void cpu_stopper_thread(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); struct cpu_stop_work *work; repeat: work = NULL; raw_spin_lock_irq(&stopper->lock); if (!list_empty(&stopper->works)) { work = list_first_entry(&stopper->works, struct cpu_stop_work, list); list_del_init(&work->list); } raw_spin_unlock_irq(&stopper->lock); if (work) { cpu_stop_fn_t fn = work->fn; void *arg = work->arg; struct cpu_stop_done *done = work->done; int ret; /* cpu stop callbacks must not sleep, make in_atomic() == T */ stopper->caller = work->caller; stopper->fn = fn; preempt_count_inc(); ret = fn(arg); if (done) { if (ret) done->ret = ret; cpu_stop_signal_done(done); } preempt_count_dec(); stopper->fn = NULL; stopper->caller = 0; WARN_ONCE(preempt_count(), "cpu_stop: %ps(%p) leaked preempt count\n", fn, arg); goto repeat; } } void stop_machine_park(int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); /* * Lockless. cpu_stopper_thread() will take stopper->lock and flush * the pending works before it parks, until then it is fine to queue * the new works. */ stopper->enabled = false; kthread_park(stopper->thread); } static void cpu_stop_create(unsigned int cpu) { sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu)); } static void cpu_stop_park(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); WARN_ON(!list_empty(&stopper->works)); } void stop_machine_unpark(int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); stopper->enabled = true; kthread_unpark(stopper->thread); } static struct smp_hotplug_thread cpu_stop_threads = { .store = &cpu_stopper.thread, .thread_should_run = cpu_stop_should_run, .thread_fn = cpu_stopper_thread, .thread_comm = "migration/%u", .create = cpu_stop_create, .park = cpu_stop_park, .selfparking = true, }; static int __init cpu_stop_init(void) { unsigned int cpu; for_each_possible_cpu(cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); raw_spin_lock_init(&stopper->lock); INIT_LIST_HEAD(&stopper->works); } BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); stop_machine_unpark(raw_smp_processor_id()); stop_machine_initialized = true; return 0; } early_initcall(cpu_stop_init); int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { .fn = fn, .data = data, .num_threads = num_online_cpus(), .active_cpus = cpus, }; lockdep_assert_cpus_held(); if (!stop_machine_initialized) { /* * Handle the case where stop_machine() is called * early in boot before stop_machine() has been * initialized. */ unsigned long flags; int ret; WARN_ON_ONCE(msdata.num_threads != 1); local_irq_save(flags); hard_irq_disable(); ret = (*fn)(data); local_irq_restore(flags); return ret; } /* Set the initial state and stop all online cpus. */ set_state(&msdata, MULTI_STOP_PREPARE); return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata); } int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { int ret; /* No CPUs can come up or down during this. */ cpus_read_lock(); ret = stop_machine_cpuslocked(fn, data, cpus); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(stop_machine); #ifdef CONFIG_SCHED_SMT /* * INTEL_IFS is the only user of this API. That selftest can * only be compiled if SMP=y. On x86 it selects SCHED_SMT. * Keep the ifdefs for now. */ int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); struct multi_stop_data msdata = { .fn = fn, .data = data, .num_threads = cpumask_weight(smt_mask), .active_cpus = smt_mask, }; lockdep_assert_cpus_held(); /* Set the initial state and stop all online cpus. */ set_state(&msdata, MULTI_STOP_PREPARE); return stop_cpus(smt_mask, multi_cpu_stop, &msdata); } EXPORT_SYMBOL_GPL(stop_core_cpuslocked); #endif /** * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU * @fn: the function to run * @data: the data ptr for the @fn() * @cpus: the cpus to run the @fn() on (NULL = any online cpu) * * This is identical to stop_machine() but can be called from a CPU which * is not active. The local CPU is in the process of hotplug (so no other * CPU hotplug can start) and not marked active and doesn't have enough * context to sleep. * * This function provides stop_machine() functionality for such state by * using busy-wait for synchronization and executing @fn directly for local * CPU. * * CONTEXT: * Local CPU is inactive. Temporarily stops all active CPUs. * * RETURNS: * 0 if all executions of @fn returned 0, any non zero return value if any * returned non zero. */ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { .fn = fn, .data = data, .active_cpus = cpus }; struct cpu_stop_done done; int ret; /* Local CPU must be inactive and CPU hotplug in progress. */ BUG_ON(cpu_active(raw_smp_processor_id())); msdata.num_threads = num_active_cpus() + 1; /* +1 for local */ /* No proper task established and can't sleep - busy wait for lock. */ while (!mutex_trylock(&stop_cpus_mutex)) cpu_relax(); /* Schedule work on other CPUs and execute directly for local CPU */ set_state(&msdata, MULTI_STOP_PREPARE); cpu_stop_init_done(&done, num_active_cpus()); queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, &done); ret = multi_cpu_stop(&msdata); /* Busy wait for completion. */ while (!completion_done(&done.completion)) cpu_relax(); mutex_unlock(&stop_cpus_mutex); return ret ?: done.ret; } |
| 218 8 4 1 2 1 1 1 4 2 5 1 5 1 6 3 6 53 53 53 54 95 1887 87 87 7 4 3 4 6 6 38 38 1884 1885 1888 3 1870 1873 1860 19 44 116 3 114 218 218 75 78 69 75 77 7 78 38 28 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * inode.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org> * * debugfs is for people to use instead of /proc or /sys. * See ./Documentation/core-api/kernel-api.rst for more details. */ #define pr_fmt(fmt) "debugfs: " fmt #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/namei.h> #include <linux/debugfs.h> #include <linux/fsnotify.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/security.h> #include "internal.h" #define DEBUGFS_DEFAULT_MODE 0700 static struct vfsmount *debugfs_mount; static int debugfs_mount_count; static bool debugfs_registered; static bool debugfs_enabled __ro_after_init = IS_ENABLED(CONFIG_DEBUG_FS_ALLOW_ALL); /* * Don't allow access attributes to be changed whilst the kernel is locked down * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ static int debugfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int ret; if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { ret = security_locked_down(LOCKDOWN_DEBUGFS); if (ret) return ret; } return simple_setattr(&nop_mnt_idmap, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_dir_inode_operations = { .lookup = simple_lookup, .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_symlink_inode_operations = { .get_link = simple_get_link, .setattr = debugfs_setattr, }; static struct inode *debugfs_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); } return inode; } struct debugfs_fs_info { kuid_t uid; kgid_t gid; umode_t mode; /* Opt_* bitfield. */ unsigned int opts; }; enum { Opt_uid, Opt_gid, Opt_mode, Opt_source, }; static const struct fs_parameter_spec debugfs_param_specs[] = { fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("mode", Opt_mode), fsparam_uid ("uid", Opt_uid), fsparam_string ("source", Opt_source), {} }; static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct debugfs_fs_info *opts = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, debugfs_param_specs, param, &result); if (opt < 0) { /* * We might like to report bad mount options here; but * traditionally debugfs has ignored all mount options */ if (opt == -ENOPARAM) return 0; return opt; } switch (opt) { case Opt_uid: opts->uid = result.uid; break; case Opt_gid: opts->gid = result.gid; break; case Opt_mode: opts->mode = result.uint_32 & S_IALLUGO; break; case Opt_source: if (fc->source) return invalfc(fc, "Multiple sources specified"); fc->source = param->string; param->string = NULL; break; /* * We might like to report bad mount options here; * but traditionally debugfs has ignored all mount options */ } opts->opts |= BIT(opt); return 0; } static void _debugfs_apply_options(struct super_block *sb, bool remount) { struct debugfs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); /* * On remount, only reset mode/uid/gid if they were provided as mount * options. */ if (!remount || fsi->opts & BIT(Opt_mode)) { inode->i_mode &= ~S_IALLUGO; inode->i_mode |= fsi->mode; } if (!remount || fsi->opts & BIT(Opt_uid)) inode->i_uid = fsi->uid; if (!remount || fsi->opts & BIT(Opt_gid)) inode->i_gid = fsi->gid; } static void debugfs_apply_options(struct super_block *sb) { _debugfs_apply_options(sb, false); } static void debugfs_apply_options_remount(struct super_block *sb) { _debugfs_apply_options(sb, true); } static int debugfs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct debugfs_fs_info *sb_opts = sb->s_fs_info; struct debugfs_fs_info *new_opts = fc->s_fs_info; if (!new_opts) return 0; sync_filesystem(sb); /* structure copy of new mount options to sb */ *sb_opts = *new_opts; debugfs_apply_options_remount(sb); return 0; } static int debugfs_show_options(struct seq_file *m, struct dentry *root) { struct debugfs_fs_info *fsi = root->d_sb->s_fs_info; if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, fsi->uid)); if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, fsi->gid)); if (fsi->mode != DEBUGFS_DEFAULT_MODE) seq_printf(m, ",mode=%o", fsi->mode); return 0; } static struct kmem_cache *debugfs_inode_cachep __ro_after_init; static void init_once(void *foo) { struct debugfs_inode_info *info = foo; inode_init_once(&info->vfs_inode); } static struct inode *debugfs_alloc_inode(struct super_block *sb) { struct debugfs_inode_info *info; info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL); if (!info) return NULL; return &info->vfs_inode; } static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode)); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, .alloc_inode = debugfs_alloc_inode, .free_inode = debugfs_free_inode, }; static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; if (fsd) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { struct inode *inode = path->dentry->d_inode; return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private); } static const struct dentry_operations debugfs_dops = { .d_release = debugfs_release_dentry, .d_automount = debugfs_automount, }; static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr debug_files[] = {{""}}; int err; err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); if (err) return err; sb->s_op = &debugfs_super_operations; set_default_d_op(sb, &debugfs_dops); sb->s_d_flags |= DCACHE_DONTCACHE; debugfs_apply_options(sb); return 0; } static int debugfs_get_tree(struct fs_context *fc) { int err; err = get_tree_single(fc, debugfs_fill_super); if (err) return err; return debugfs_reconfigure(fc); } static void debugfs_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations debugfs_context_ops = { .free = debugfs_free_fc, .parse_param = debugfs_parse_param, .get_tree = debugfs_get_tree, .reconfigure = debugfs_reconfigure, }; static int debugfs_init_fs_context(struct fs_context *fc) { struct debugfs_fs_info *fsi; fsi = kzalloc_obj(struct debugfs_fs_info); if (!fsi) return -ENOMEM; fsi->mode = DEBUGFS_DEFAULT_MODE; fc->s_fs_info = fsi; fc->ops = &debugfs_context_ops; return 0; } static struct file_system_type debug_fs_type = { .owner = THIS_MODULE, .name = "debugfs", .init_fs_context = debugfs_init_fs_context, .parameters = debugfs_param_specs, .kill_sb = kill_anon_super, }; MODULE_ALIAS_FS("debugfs"); /** * debugfs_lookup() - look up an existing debugfs file * @name: a pointer to a string containing the name of the file to look up. * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file * doesn't exist or an error occurs, %NULL will be returned. The returned * dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) { struct dentry *dentry; if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent)) return NULL; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent); if (IS_ERR(dentry)) return NULL; return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); static struct dentry *debugfs_start_creating(const char *name, struct dentry *parent) { struct dentry *dentry; int error; if (!debugfs_enabled) return ERR_PTR(-EPERM); if (!debugfs_initialized()) return ERR_PTR(-ENOENT); pr_debug("creating file '%s'\n", name); if (IS_ERR(parent)) return parent; error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) { pr_err("Unable to pin filesystem for file '%s'\n", name); return ERR_PTR(error); } /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super * block. A pointer to that is in the struct vfsmount that we * have around. */ if (!parent) parent = debugfs_mount->mnt_root; dentry = simple_start_creating(parent, name); if (IS_ERR(dentry)) { if (dentry == ERR_PTR(-EEXIST)) pr_err("'%s' already exists in '%pd'\n", name, parent); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } return dentry; } static struct dentry *debugfs_failed_creating(struct dentry *dentry) { simple_done_creating(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); return ERR_PTR(-ENOMEM); } static struct dentry *debugfs_end_creating(struct dentry *dentry) { simple_done_creating(dentry); return dentry; // borrowed } static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct file_operations *proxy_fops, const void *real_fops) { struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) mode |= S_IFREG; BUG_ON(!S_ISREG(mode)); dentry = debugfs_start_creating(name, parent); if (IS_ERR(dentry)) return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create file '%s'\n", name); return debugfs_failed_creating(dentry); } inode->i_mode = mode; inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; if (!real_fops) proxy_fops = &debugfs_noop_file_operations; inode->i_fop = proxy_fops; DEBUGFS_I(inode)->raw = real_fops; DEBUGFS_I(inode)->aux = (void *)aux; d_make_persistent(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); return debugfs_end_creating(dentry); } struct dentry *debugfs_create_file_full(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, aux, &debugfs_full_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_full); struct dentry *debugfs_create_file_short(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct debugfs_short_fops *fops) { return __debugfs_create_file(name, mode, parent, data, aux, &debugfs_full_short_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); /** * debugfs_create_file_unsafe - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * debugfs_create_file_unsafe() is completely analogous to * debugfs_create_file(), the only difference being that the fops * handed it will not get protected against file removals by the * debugfs core. * * It is your responsibility to protect your struct file_operation * methods against file removals by means of debugfs_file_get() * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and * thus, may be used here. */ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, NULL, &debugfs_open_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); /** * debugfs_create_file_size - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * @file_size: initial file size * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) */ void debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, loff_t file_size) { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); /** * debugfs_create_dir - create a directory in the debugfs filesystem * @name: a pointer to a string containing the name of the directory to * create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * directory will be created in the root of the debugfs filesystem. * * This function creates a directory in debugfs with the given name. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { struct dentry *dentry = debugfs_start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create directory '%s'\n", name); return debugfs_failed_creating(dentry); } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_op = &debugfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_make_persistent(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return debugfs_end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_dir); /** * debugfs_create_automount - create automount point in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @f: function to be called when pathname resolution steps on that one. * @data: opaque argument to pass to f(). * * @f should return what ->d_automount() would. */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, void *data) { struct dentry *dentry = debugfs_start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); return debugfs_failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; DEBUGFS_I(inode)->automount = f; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_make_persistent(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return debugfs_end_creating(dentry); } EXPORT_SYMBOL(debugfs_create_automount); /** * debugfs_create_symlink- create a symbolic link in the debugfs filesystem * @name: a pointer to a string containing the name of the symbolic link to * create. * @parent: a pointer to the parent dentry for this symbolic link. This * should be a directory dentry if set. If this parameter is NULL, * then the symbolic link will be created in the root of the debugfs * filesystem. * @target: a pointer to a string containing the path to the target of the * symbolic link. * * This function creates a symbolic link with the given name in debugfs that * links to the given target path. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target) { struct dentry *dentry; struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); dentry = debugfs_start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); return dentry; } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create symlink '%s'\n", name); kfree(link); return debugfs_failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_make_persistent(dentry, inode); return debugfs_end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_symlink); static void __debugfs_file_removed(struct dentry *dentry) { struct debugfs_fsdata *fsd; /* * Paired with the closing smp_mb() implied by a successful * cmpxchg() in debugfs_file_get(): either * debugfs_file_get() must see a dead dentry or we must see a * debugfs_fsdata instance at ->d_fsdata here (or both). */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); if (!fsd) return; /* if this was the last reference, we're done */ if (refcount_dec_and_test(&fsd->active_users)) return; /* * If there's still a reference, the code that obtained it can * be in different states: * - The common case of not using cancellations, or already * after debugfs_leave_cancellation(), where we just need * to wait for debugfs_file_put() which signals the completion; * - inside a cancellation section, i.e. between * debugfs_enter_cancellation() and debugfs_leave_cancellation(), * in which case we need to trigger the ->cancel() function, * and then wait for debugfs_file_put() just like in the * previous case; * - before debugfs_enter_cancellation() (but obviously after * debugfs_file_get()), in which case we may not see the * cancellation in the list on the first round of the loop, * but debugfs_enter_cancellation() signals the completion * after adding it, so this code gets woken up to call the * ->cancel() function. */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; /* * Lock the cancellations. Note that the cancellations * structs are meant to be on the stack, so we need to * ensure we either use them here or don't touch them, * and debugfs_leave_cancellation() will wait for this * to be finished processing before exiting one. It may * of course win and remove the cancellation, but then * chances are we never even got into this bit, we only * do if the refcount isn't zero already. */ mutex_lock(&fsd->cancellations_mtx); while ((c = list_first_entry_or_null(&fsd->cancellations, typeof(*c), list))) { list_del_init(&c->list); c->cancel(dentry, c->cancel_data); } mutex_unlock(&fsd->cancellations_mtx); wait_for_completion(&fsd->active_users_drained); } } static void remove_one(struct dentry *victim) { if (d_is_reg(victim)) __debugfs_file_removed(victim); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } /** * debugfs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. If this * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function * (like debugfs_create_file() or variants thereof.) * * This function is required to be called in order for the file to be * removed, no automatic cleanup of files will happen when a module is * removed, you are responsible here. */ void debugfs_remove(struct dentry *dentry) { if (IS_ERR_OR_NULL(dentry)) return; simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); simple_recursive_removal(dentry, remove_one); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it * @name: a pointer to a string containing the name of the item to look up. * @parent: a pointer to the parent dentry of the item. * * This is the equlivant of doing something like * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting * handled for the directory being looked up. */ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) { struct dentry *dentry; dentry = debugfs_lookup(name, parent); if (!dentry) return; debugfs_remove(dentry); dput(dentry); } EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** * debugfs_change_name - rename a file/directory in the debugfs filesystem * @dentry: dentry of an object to be renamed. * @fmt: format for new name * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * * This function will return 0 on success and -E... on failure. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...) { int error = 0; const char *new_name; struct name_snapshot old_name; struct dentry *target; struct renamedata rd = {}; struct inode *dir; va_list ap; if (IS_ERR_OR_NULL(dentry)) return 0; va_start(ap, fmt); new_name = kvasprintf_const(GFP_KERNEL, fmt, ap); va_end(ap); if (!new_name) return -ENOMEM; rd.old_parent = dget_parent(dentry); rd.new_parent = rd.old_parent; rd.flags = RENAME_NOREPLACE; target = lookup_noperm_unlocked(&QSTR(new_name), rd.new_parent); if (IS_ERR(target)) { error = PTR_ERR(target); goto out_free; } error = start_renaming_two_dentries(&rd, dentry, target); if (error) { if (error == -EEXIST && target == dentry) /* it isn't an error to rename a thing to itself */ error = 0; goto out; } dir = d_inode(rd.old_parent); take_dentry_name_snapshot(&old_name, dentry); simple_rename_timestamp(dir, dentry, dir, rd.new_dentry); d_move(dentry, rd.new_dentry); fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); release_dentry_name_snapshot(&old_name); end_renaming(&rd); out: dput(rd.old_parent); dput(target); out_free: kfree_const(new_name); return error; } EXPORT_SYMBOL_GPL(debugfs_change_name); /** * debugfs_initialized - Tells whether debugfs has been registered */ bool debugfs_initialized(void) { return debugfs_registered; } EXPORT_SYMBOL_GPL(debugfs_initialized); static int __init debugfs_kernel(char *str) { if (str) { if (!strcmp(str, "on")) debugfs_enabled = true; else if (!strcmp(str, "off")) debugfs_enabled = false; else if (!strcmp(str, "no-mount")) { pr_notice("debugfs=no-mount is a deprecated alias " "for debugfs=off\n"); debugfs_enabled = false; } } return 0; } early_param("debugfs", debugfs_kernel); static int __init debugfs_init(void) { int retval; if (!debugfs_enabled) return -EPERM; retval = sysfs_create_mount_point(kernel_kobj, "debug"); if (retval) return retval; debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache", sizeof(struct debugfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, init_once); if (debugfs_inode_cachep == NULL) { sysfs_remove_mount_point(kernel_kobj, "debug"); return -ENOMEM; } retval = register_filesystem(&debug_fs_type); if (retval) { // Really not going to happen sysfs_remove_mount_point(kernel_kobj, "debug"); kmem_cache_destroy(debugfs_inode_cachep); return retval; } debugfs_registered = true; return 0; } core_initcall(debugfs_init); |
| 9 1 1 6 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* iptables module for the IPv4 and TCP ECN bits, Version 1.5 * * (C) 2002 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <net/ip.h> #include <linux/tcp.h> #include <net/checksum.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_ECN.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag modification"); /* set ECT codepoint from IP header. * return false if there was an error. */ static inline bool set_ect_ip(struct sk_buff *skb, const struct ipt_ECN_info *einfo) { struct iphdr *iph = ip_hdr(skb); if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { __u8 oldtos; if (skb_ensure_writable(skb, sizeof(struct iphdr))) return false; iph = ip_hdr(skb); oldtos = iph->tos; iph->tos &= ~IPT_ECN_IP_MASK; iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK); csum_replace2(&iph->check, htons(oldtos), htons(iph->tos)); } return true; } /* Return false if there was an error. */ static inline bool set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) { struct tcphdr _tcph, *tcph; __be16 oldval; /* Not enough header? */ tcph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); if (!tcph) return false; if ((!(einfo->operation & IPT_ECN_OP_SET_ECE) || tcph->ece == einfo->proto.tcp.ece) && (!(einfo->operation & IPT_ECN_OP_SET_CWR) || tcph->cwr == einfo->proto.tcp.cwr)) return true; if (skb_ensure_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) return false; tcph = (void *)ip_hdr(skb) + ip_hdrlen(skb); oldval = ((__be16 *)tcph)[6]; if (einfo->operation & IPT_ECN_OP_SET_ECE) tcph->ece = einfo->proto.tcp.ece; if (einfo->operation & IPT_ECN_OP_SET_CWR) tcph->cwr = einfo->proto.tcp.cwr; inet_proto_csum_replace2(&tcph->check, skb, oldval, ((__be16 *)tcph)[6], false); return true; } static unsigned int ecn_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_ECN_info *einfo = par->targinfo; if (einfo->operation & IPT_ECN_OP_SET_IP) if (!set_ect_ip(skb, einfo)) return NF_DROP; if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && ip_hdr(skb)->protocol == IPPROTO_TCP) if (!set_ect_tcp(skb, einfo)) return NF_DROP; return XT_CONTINUE; } static int ecn_tg_check(const struct xt_tgchk_param *par) { const struct ipt_ECN_info *einfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; if (einfo->operation & IPT_ECN_OP_MASK) return -EINVAL; if (einfo->ip_ect & ~IPT_ECN_IP_MASK) return -EINVAL; if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { pr_info_ratelimited("cannot use operation on non-tcp rule\n"); return -EINVAL; } return 0; } static struct xt_target ecn_tg_reg __read_mostly = { .name = "ECN", .family = NFPROTO_IPV4, .target = ecn_tg, .targetsize = sizeof(struct ipt_ECN_info), .table = "mangle", .checkentry = ecn_tg_check, .me = THIS_MODULE, }; static int __init ecn_tg_init(void) { return xt_register_target(&ecn_tg_reg); } static void __exit ecn_tg_exit(void) { xt_unregister_target(&ecn_tg_reg); } module_init(ecn_tg_init); module_exit(ecn_tg_exit); |
| 7 15 2 15 15 9 9 9 16 2 15 10 15 15 17 17 15 15 15 9 20 3 17 15 13 2 2 2 4 3 4 4 4 2 14 5 9 9 9 9 9 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 | // SPDX-License-Identifier: GPL-2.0 /* * 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) */ #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 kvzalloc_objs(struct page *, n_pages); } /* * free an array of pointers of struct page */ static void relay_free_page_array(struct page **array) { kvfree(array); } /** * relay_mmap_prepare_buf: - mmap channel buffer to process address space * @buf: the relay channel buffer * @desc: describing what to map * * Returns 0 if ok, negative on error * * Caller should already have grabbed mmap_lock. */ static int relay_mmap_prepare_buf(struct rchan_buf *buf, struct vm_area_desc *desc) { unsigned long length = vma_desc_size(desc); if (!buf) return -EBADF; if (length != (unsigned long)buf->chan->alloc_size) return -EINVAL; desc->vm_ops = &relay_file_mmap_ops; vma_desc_set_flags(desc, VMA_DONTEXPAND_BIT); desc->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 | __GFP_ZERO); 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; 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_obj(struct rchan_buf); if (!buf) return NULL; buf->padding = kmalloc_objs(size_t, chan->n_subbufs); 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) { int full = relay_buf_full(buf); if (full) buf->stats.full_count++; if (!buf->chan->cb->subbuf_start) return !full; return buf->chan->cb->subbuf_start(buf, subbuf, prev_subbuf); } /** * 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; buf->stats.full_count = 0; buf->stats.big_count = 0; for (i = 0; i < buf->chan->n_subbufs; i++) buf->padding[i] = 0; relay_subbuf_start(buf, buf->data, NULL); } /** * 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 = kasprintf(GFP_KERNEL, "%s%d", chan->base_filename, cpu); if (!tmpname) return NULL; /* 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 * @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. */ 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_obj(struct rchan); 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; }; /** * 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) { size_t prev_padding; prev_padding = buf->chan->subbuf_size - buf->offset; old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; buf->padding[old_subbuf] = 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->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->stats.big_count++; 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); 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_stats - get channel buffer statistics * @chan: the channel * @flags: select particular information to get * * Returns the count of certain field that caller specifies. */ size_t relay_stats(struct rchan *chan, int flags) { unsigned int i, count = 0; struct rchan_buf *rbuf; if (!chan || flags > RELAY_STATS_LAST) return 0; if (chan->is_global) { rbuf = *per_cpu_ptr(chan->buf, 0); if (flags & RELAY_STATS_BUF_FULL) count = rbuf->stats.full_count; else if (flags & RELAY_STATS_WRT_BIG) count = rbuf->stats.big_count; } else { for_each_online_cpu(i) { rbuf = *per_cpu_ptr(chan->buf, i); if (rbuf) { if (flags & RELAY_STATS_BUF_FULL) count += rbuf->stats.full_count; else if (flags & RELAY_STATS_WRT_BIG) count += rbuf->stats.big_count; } } } return count; } /** * 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_prepare - mmap file op for relay files * @desc: describing what to map * * Calls upon relay_mmap_prepare_buf() to map the file into user space. */ static int relay_file_mmap_prepare(struct vm_area_desc *desc) { struct rchan_buf *buf = desc->file->private_data; return relay_mmap_prepare_buf(buf, desc); } /** * 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_prepare = relay_file_mmap_prepare, .read = relay_file_read, .release = relay_file_release, }; EXPORT_SYMBOL_GPL(relay_file_operations); |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 | /* SPDX-License-Identifier: GPL-2.0 */ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __HCI_CORE_H #define __HCI_CORE_H #include <linux/idr.h> #include <linux/leds.h> #include <linux/rculist.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <net/bluetooth/hci.h> #include <net/bluetooth/hci_drv.h> #include <net/bluetooth/hci_sync.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/coredump.h> /* HCI priority */ #define HCI_PRIO_MAX 7 /* HCI maximum id value */ #define HCI_MAX_ID 10000 /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; __u8 pscan_rep_mode; __u8 pscan_period_mode; __u8 pscan_mode; __u8 dev_class[3]; __le16 clock_offset; __s8 rssi; __u8 ssp_mode; }; struct inquiry_entry { struct list_head all; /* inq_cache.all */ struct list_head list; /* unknown or resolve */ enum { NAME_NOT_KNOWN, NAME_NEEDED, NAME_PENDING, NAME_KNOWN, } name_state; __u32 timestamp; struct inquiry_data data; }; struct discovery_state { int type; enum { DISCOVERY_STOPPED, DISCOVERY_STARTING, DISCOVERY_FINDING, DISCOVERY_RESOLVING, DISCOVERY_STOPPING, } state; struct list_head all; /* All devices found during inquiry */ struct list_head unknown; /* Name state not known */ struct list_head resolve; /* Name needs to be resolved */ __u32 timestamp; bdaddr_t last_adv_addr; u8 last_adv_addr_type; s8 last_adv_rssi; u32 last_adv_flags; u8 last_adv_data[HCI_MAX_EXT_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; bool result_filtering; bool limited; s8 rssi; u16 uuid_count; u8 (*uuids)[16]; unsigned long name_resolve_timeout; spinlock_t lock; }; #define SUSPEND_NOTIFIER_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ enum suspend_tasks { SUSPEND_PAUSE_DISCOVERY, SUSPEND_UNPAUSE_DISCOVERY, SUSPEND_PAUSE_ADVERTISING, SUSPEND_UNPAUSE_ADVERTISING, SUSPEND_SCAN_DISABLE, SUSPEND_SCAN_ENABLE, SUSPEND_DISCONNECTING, SUSPEND_POWERING_DOWN, SUSPEND_PREPARE_NOTIFIER, SUSPEND_SET_ADV_FILTER, __SUSPEND_NUM_TASKS }; enum suspended_state { BT_RUNNING = 0, BT_SUSPEND_DISCONNECT, BT_SUSPEND_CONFIGURE_WAKE, }; struct hci_conn_hash { struct list_head list; unsigned int acl_num; unsigned int sco_num; unsigned int cis_num; unsigned int bis_num; unsigned int pa_num; unsigned int le_num; unsigned int le_num_peripheral; }; struct bdaddr_list { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; }; struct codec_list { struct list_head list; u8 id; __u16 cid; __u16 vid; u8 transport; u8 num_caps; u32 len; struct hci_codec_caps caps[]; }; struct bdaddr_list_with_irk { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; u8 peer_irk[16]; u8 local_irk[16]; }; /* Bitmask of connection flags */ enum hci_conn_flags { HCI_CONN_FLAG_REMOTE_WAKEUP = BIT(0), HCI_CONN_FLAG_DEVICE_PRIVACY = BIT(1), HCI_CONN_FLAG_ADDRESS_RESOLUTION = BIT(2), HCI_CONN_FLAG_PAST = BIT(3), }; typedef u8 hci_conn_flags_t; struct bdaddr_list_with_flags { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; hci_conn_flags_t flags; }; struct bt_uuid { struct list_head list; u8 uuid[16]; u8 size; u8 svc_hint; }; struct blocked_key { struct list_head list; struct rcu_head rcu; u8 type; u8 val[16]; }; struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; u8 type; u8 val[16]; }; struct smp_ltk { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; u8 authenticated; u8 type; u8 enc_size; __le16 ediv; __le64 rand; u8 val[16]; }; struct smp_irk { struct list_head list; struct rcu_head rcu; bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; u8 val[16]; }; struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; }; struct oob_data { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; u8 present; u8 hash192[16]; u8 rand192[16]; u8 hash256[16]; u8 rand256[16]; }; struct adv_info { struct list_head list; bool enabled; bool pending; bool periodic; bool periodic_enabled; __u8 mesh; __u8 instance; __u8 handle; __u8 sid; __u32 flags; __u16 timeout; __u16 remaining_time; __u16 duration; __u16 adv_data_len; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; bool adv_data_changed; __u16 scan_rsp_len; __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; bool scan_rsp_changed; __u16 per_adv_data_len; __u8 per_adv_data[HCI_MAX_PER_AD_LENGTH]; __s8 tx_power; __u32 min_interval; __u32 max_interval; bdaddr_t random_addr; bool rpa_expired; struct delayed_work rpa_expired_cb; }; struct tx_queue { struct sk_buff_head queue; unsigned int extra; unsigned int tracked; }; #define HCI_MAX_ADV_INSTANCES 5 #define HCI_DEFAULT_ADV_DURATION 2 #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F #define DATA_CMP(_d1, _l1, _d2, _l2) \ (_l1 == _l2 ? memcmp(_d1, _d2, _l1) : _l1 - _l2) #define ADV_DATA_CMP(_adv, _data, _len) \ DATA_CMP((_adv)->adv_data, (_adv)->adv_data_len, _data, _len) #define SCAN_RSP_CMP(_adv, _data, _len) \ DATA_CMP((_adv)->scan_rsp_data, (_adv)->scan_rsp_len, _data, _len) struct monitored_device { struct list_head list; bdaddr_t bdaddr; __u8 addr_type; __u16 handle; bool notified; }; struct adv_pattern { struct list_head list; __u8 ad_type; __u8 offset; __u8 length; __u8 value[HCI_MAX_EXT_AD_LENGTH]; }; struct adv_rssi_thresholds { __s8 low_threshold; __s8 high_threshold; __u16 low_threshold_timeout; __u16 high_threshold_timeout; __u8 sampling_period; }; struct adv_monitor { struct list_head patterns; struct adv_rssi_thresholds rssi; __u16 handle; enum { ADV_MONITOR_STATE_NOT_REGISTERED, ADV_MONITOR_STATE_REGISTERED, ADV_MONITOR_STATE_OFFLOADED } state; }; #define HCI_MIN_ADV_MONITOR_HANDLE 1 #define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32 #define HCI_MAX_ADV_MONITOR_NUM_PATTERNS 16 #define HCI_ADV_MONITOR_EXT_NONE 1 #define HCI_ADV_MONITOR_EXT_MSFT 2 #define HCI_MAX_SHORT_NAME_LENGTH 10 #define HCI_CONN_HANDLE_MAX 0x0eff #define HCI_CONN_HANDLE_UNSET(_handle) (_handle > HCI_CONN_HANDLE_MAX) /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 /* Default LE RPA expiry time, 15 minutes */ #define HCI_DEFAULT_RPA_TIMEOUT (15 * 60) /* Default min/max age of connection information (1s/3s) */ #define DEFAULT_CONN_INFO_MIN_AGE 1000 #define DEFAULT_CONN_INFO_MAX_AGE 3000 /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 #define HCI_MAX_PAGES 3 struct hci_dev { struct list_head list; struct srcu_struct srcu; struct mutex lock; struct ida unset_handle_ida; const char *name; unsigned long flags; __u16 id; __u8 bus; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; bdaddr_t random_addr; bdaddr_t static_addr; __u8 adv_addr_type; __u8 dev_name[HCI_MAX_NAME_LENGTH]; __u8 short_name[HCI_MAX_SHORT_NAME_LENGTH]; __u8 eir[HCI_MAX_EIR_LENGTH]; __u16 appearance; __u8 dev_class[3]; __u8 major_class; __u8 minor_class; __u8 max_page; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[248]; __u8 le_accept_list_size; __u8 le_resolv_list_size; __u8 le_num_of_adv_sets; __u8 le_states[8]; __u8 mesh_ad_types[16]; __u8 mesh_send_ref; __u8 commands[64]; __u8 hci_ver; __u16 hci_rev; __u8 lmp_ver; __u16 manufacturer; __u16 lmp_subver; __u16 voice_setting; __u8 num_iac; __u16 stored_max_keys; __u16 stored_num_keys; __u8 io_capability; __s8 inq_tx_power; __u8 err_data_reporting; __u16 page_scan_interval; __u16 page_scan_window; __u8 page_scan_type; __u8 le_adv_channel_map; __u16 le_adv_min_interval; __u16 le_adv_max_interval; __u8 le_scan_type; __u16 le_scan_interval; __u16 le_scan_window; __u16 le_scan_int_suspend; __u16 le_scan_window_suspend; __u16 le_scan_int_discovery; __u16 le_scan_window_discovery; __u16 le_scan_int_adv_monitor; __u16 le_scan_window_adv_monitor; __u16 le_scan_int_connect; __u16 le_scan_window_connect; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_latency; __u16 le_supv_timeout; __u16 le_def_tx_len; __u16 le_def_tx_time; __u16 le_max_tx_len; __u16 le_max_tx_time; __u16 le_max_rx_len; __u16 le_max_rx_time; __u8 le_max_key_size; __u8 le_min_key_size; __u16 discov_interleaved_timeout; __u16 conn_info_min_age; __u16 conn_info_max_age; __u16 auth_payload_timeout; __u8 min_enc_key_size; __u8 max_enc_key_size; __u8 pairing_opts; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; __u16 advmon_allowlist_duration; __u16 advmon_no_filter_duration; __u8 enable_advmon_interleave_scan; __u16 devid_source; __u16 devid_vendor; __u16 devid_product; __u16 devid_version; __u8 def_page_scan_type; __u16 def_page_scan_int; __u16 def_page_scan_window; __u8 def_inq_scan_type; __u16 def_inq_scan_int; __u16 def_inq_scan_window; __u16 def_br_lsto; __u16 def_page_timeout; __u16 def_multi_adv_rotation_duration; __u16 def_le_autoconnect_timeout; __s8 min_le_tx_power; __s8 max_le_tx_power; __u16 pkt_type; __u16 esco_type; __u16 link_policy; __u16 link_mode; __u32 idle_timeout; __u16 sniff_min_interval; __u16 sniff_max_interval; unsigned int auto_accept_delay; DECLARE_BITMAP(quirk_flags, __HCI_NUM_QUIRKS); atomic_t cmd_cnt; unsigned int acl_cnt; unsigned int sco_cnt; unsigned int le_cnt; unsigned int iso_cnt; unsigned int acl_mtu; unsigned int sco_mtu; unsigned int le_mtu; unsigned int iso_mtu; unsigned int acl_pkts; unsigned int sco_pkts; unsigned int le_pkts; unsigned int iso_pkts; unsigned long acl_last_tx; unsigned long le_last_tx; unsigned long iso_last_tx; __u8 le_tx_def_phys; __u8 le_rx_def_phys; struct workqueue_struct *workqueue; struct workqueue_struct *req_workqueue; struct work_struct power_on; struct delayed_work power_off; struct work_struct error_reset; struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; __u16 discov_timeout; struct delayed_work discov_off; struct delayed_work service_cache; struct delayed_work cmd_timer; struct delayed_work ncmd_timer; struct work_struct rx_work; struct work_struct cmd_work; struct work_struct tx_work; struct delayed_work le_scan_disable; struct sk_buff_head rx_q; struct sk_buff_head raw_q; struct sk_buff_head cmd_q; struct sk_buff *sent_cmd; struct sk_buff *recv_event; struct mutex req_lock; wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; struct sk_buff *req_skb; struct sk_buff *req_rsp; void *smp_data; void *smp_bredr_data; struct discovery_state discovery; bool discovery_paused; int advertising_old_state; bool advertising_paused; struct notifier_block suspend_notifier; enum suspended_state suspend_state_next; enum suspended_state suspend_state; bool scanning_paused; bool suspended; u8 wake_reason; bdaddr_t wake_addr; u8 wake_addr_type; struct hci_conn_hash conn_hash; struct list_head mesh_pending; struct mutex mgmt_pending_lock; struct list_head mgmt_pending; struct list_head reject_list; struct list_head accept_list; struct list_head uuids; struct list_head link_keys; struct list_head long_term_keys; struct list_head identity_resolving_keys; struct list_head remote_oob_data; struct list_head le_accept_list; struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; struct list_head pend_le_reports; struct list_head blocked_keys; struct list_head local_codecs; struct hci_dev_stats stat; atomic_t promisc; const char *hw_info; const char *fw_info; struct dentry *debugfs; struct hci_devcoredump dump; struct device dev; struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); hci_conn_flags_t conn_flags; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 adv_data_len; __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __u8 scan_rsp_data_len; __u8 per_adv_data[HCI_MAX_PER_AD_LENGTH]; __u8 per_adv_data_len; struct list_head adv_instances; unsigned int adv_instance_cnt; __u8 cur_adv_instance; __u16 adv_instance_timeout; struct delayed_work adv_instance_expire; struct idr adv_monitors_idr; unsigned int adv_monitors_cnt; __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; bdaddr_t rpa; struct delayed_work mesh_send_done; enum { INTERLEAVE_SCAN_NONE, INTERLEAVE_SCAN_NO_FILTER, INTERLEAVE_SCAN_ALLOWLIST } interleave_scan_state; struct delayed_work interleave_scan; struct list_head monitored_devices; bool advmon_pend_notify; struct hci_drv *hci_drv; #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif #if IS_ENABLED(CONFIG_BT_MSFTEXT) __u16 msft_opcode; void *msft_data; bool msft_curve_validity; #endif #if IS_ENABLED(CONFIG_BT_AOSPEXT) bool aosp_capable; bool aosp_quality_report; #endif int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); int (*setup)(struct hci_dev *hdev); int (*shutdown)(struct hci_dev *hdev); int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); void (*reset)(struct hci_dev *hdev); bool (*wakeup)(struct hci_dev *hdev); int (*set_quality_report)(struct hci_dev *hdev, bool enable); int (*get_data_path_id)(struct hci_dev *hdev, __u8 *data_path); int (*get_codec_config_data)(struct hci_dev *hdev, __u8 type, struct bt_codec *codec, __u8 *vnd_len, __u8 **vnd_data); u8 (*classify_pkt_type)(struct hci_dev *hdev, struct sk_buff *skb); }; #define hci_set_quirk(hdev, nr) set_bit((nr), (hdev)->quirk_flags) #define hci_clear_quirk(hdev, nr) clear_bit((nr), (hdev)->quirk_flags) #define hci_test_quirk(hdev, nr) test_bit((nr), (hdev)->quirk_flags) #define HCI_PHY_HANDLE(handle) (handle & 0xff) enum conn_reasons { CONN_REASON_PAIR_DEVICE, CONN_REASON_L2CAP_CHAN, CONN_REASON_SCO_CONNECT, CONN_REASON_ISO_CONNECT, }; struct hci_conn { struct list_head list; atomic_t refcnt; bdaddr_t dst; __u8 dst_type; bdaddr_t src; __u8 src_type; bdaddr_t init_addr; __u8 init_addr_type; bdaddr_t resp_addr; __u8 resp_addr_type; __u8 adv_instance; __u16 handle; __u16 sync_handle; __u8 sid; __u16 state; __u16 mtu; __u8 mode; __u8 type; __u8 role; bool out; __u8 attempt; __u8 dev_class[3]; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[248]; __u16 pkt_type; __u16 link_policy; __u8 key_type; __u8 auth_type; __u8 sec_level; __u8 pending_sec_level; __u8 pin_length; __u8 enc_key_size; __u8 io_capability; __u32 passkey_notify; __u8 passkey_entered; __u16 disc_timeout; __u16 conn_timeout; __u16 setting; __u16 auth_payload_timeout; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_interval; __u16 le_conn_latency; __u16 le_supv_timeout; __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; __u16 le_per_adv_data_len; __u16 le_per_adv_data_offset; __u8 le_adv_phy; __u8 le_adv_sec_phy; __u8 le_tx_def_phys; __u8 le_rx_def_phys; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; __s8 tx_power; __s8 max_tx_power; struct bt_iso_qos iso_qos; __u8 num_bis; __u8 bis[HCI_MAX_ISO_BIS]; unsigned long flags; enum conn_reasons conn_reason; __u8 abort_reason; __u32 clock; __u16 clock_accuracy; unsigned long conn_info_timestamp; __u8 remote_cap; __u8 remote_auth; unsigned int sent; struct sk_buff_head data_q; struct list_head chan_list; struct tx_queue tx_q; struct delayed_work disc_work; struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; struct device dev; struct dentry *debugfs; struct hci_dev *hdev; void *l2cap_data; void *sco_data; void *iso_data; struct list_head link_list; struct hci_conn *parent; struct hci_link *link; struct bt_codec codec; void (*connect_cfm_cb) (struct hci_conn *conn, u8 status); void (*security_cfm_cb) (struct hci_conn *conn, u8 status); void (*disconn_cfm_cb) (struct hci_conn *conn, u8 reason); void (*cleanup)(struct hci_conn *conn); }; struct hci_link { struct list_head list; struct hci_conn *conn; }; struct hci_chan { struct list_head list; __u16 handle; struct hci_conn *conn; struct sk_buff_head data_q; unsigned int sent; __u8 state; }; struct hci_conn_params { struct list_head list; struct list_head action; bdaddr_t addr; u8 addr_type; u16 conn_min_interval; u16 conn_max_interval; u16 conn_latency; u16 supervision_timeout; enum { HCI_AUTO_CONN_DISABLED, HCI_AUTO_CONN_REPORT, HCI_AUTO_CONN_DIRECT, HCI_AUTO_CONN_ALWAYS, HCI_AUTO_CONN_LINK_LOSS, HCI_AUTO_CONN_EXPLICIT, } auto_connect; struct hci_conn *conn; bool explicit_connect; /* Accessed without hdev->lock: */ hci_conn_flags_t flags; u8 privacy_mode; }; extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) #define hci_dev_change_flag(hdev, nr) change_bit((nr), (hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_volatile_flags(hdev) \ do { \ hci_dev_clear_flag((hdev), HCI_LE_SCAN); \ hci_dev_clear_flag((hdev), HCI_LE_ADV); \ hci_dev_clear_flag((hdev), HCI_LL_RPA_RESOLUTION); \ hci_dev_clear_flag((hdev), HCI_PERIODIC_INQ); \ hci_dev_clear_flag((hdev), HCI_QUALITY_REPORT); \ } while (0) #define hci_dev_le_state_simultaneous(hdev) \ (!hci_test_quirk((hdev), HCI_QUIRK_BROKEN_LE_STATES) && \ ((hdev)->le_states[4] & 0x08) && /* Central */ \ ((hdev)->le_states[4] & 0x40) && /* Peripheral */ \ ((hdev)->le_states[3] & 0x10)) /* Simultaneous */ /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb); #else static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } static inline int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb) { kfree_skb(skb); return -ENOENT; } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags); #else static inline int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } static inline int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) { kfree_skb(skb); return -ENOENT; } #endif /* ----- Inquiry cache ----- */ #define INQUIRY_CACHE_AGE_MAX (HZ*30) /* 30 seconds */ #define INQUIRY_ENTRY_AGE_MAX (HZ*60) /* 60 seconds */ static inline void discovery_init(struct hci_dev *hdev) { spin_lock_init(&hdev->discovery.lock); hdev->discovery.state = DISCOVERY_STOPPED; INIT_LIST_HEAD(&hdev->discovery.all); INIT_LIST_HEAD(&hdev->discovery.unknown); INIT_LIST_HEAD(&hdev->discovery.resolve); hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; } static inline void hci_discovery_filter_clear(struct hci_dev *hdev) { hdev->discovery.result_filtering = false; hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; spin_lock(&hdev->discovery.lock); kfree(hdev->discovery.uuids); hdev->discovery.uuids = NULL; spin_unlock(&hdev->discovery.lock); } bool hci_discovery_active(struct hci_dev *hdev); void hci_discovery_set_state(struct hci_dev *hdev, int state); static inline int inquiry_cache_empty(struct hci_dev *hdev) { return list_empty(&hdev->discovery.all); } static inline long inquiry_cache_age(struct hci_dev *hdev) { struct discovery_state *c = &hdev->discovery; return jiffies - c->timestamp; } static inline long inquiry_entry_age(struct inquiry_entry *e) { return jiffies - e->timestamp; } struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr); struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, bdaddr_t *bdaddr); struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, bdaddr_t *bdaddr, int state); void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, struct inquiry_entry *ie); u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, bool name_known); void hci_inquiry_cache_flush(struct hci_dev *hdev); /* ----- HCI Connections ----- */ enum { HCI_CONN_AUTH_PEND, HCI_CONN_ENCRYPT_PEND, HCI_CONN_RSWITCH_PEND, HCI_CONN_MODE_CHANGE_PEND, HCI_CONN_SCO_SETUP_PEND, HCI_CONN_MGMT_CONNECTED, HCI_CONN_SSP_ENABLED, HCI_CONN_SC_ENABLED, HCI_CONN_AES_CCM, HCI_CONN_POWER_SAVE, HCI_CONN_FLUSH_KEY, HCI_CONN_ENCRYPT, HCI_CONN_AUTH, HCI_CONN_SECURE, HCI_CONN_FIPS, HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, HCI_CONN_CREATE, HCI_CONN_CREATE_CIS, HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, HCI_CONN_BIG_SYNC_FAILED, HCI_CONN_CREATE_PA_SYNC, HCI_CONN_PA_SYNC, HCI_CONN_PA_SYNC_FAILED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; return hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && test_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } static inline bool hci_conn_sc_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; return hci_dev_test_flag(hdev, HCI_SC_ENABLED) && test_bit(HCI_CONN_SC_ENABLED, &conn->flags); } static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_add_tail_rcu(&c->list, &h->list); switch (c->type) { case ACL_LINK: h->acl_num++; break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) h->le_num_peripheral++; break; case SCO_LINK: case ESCO_LINK: h->sco_num++; break; case CIS_LINK: h->cis_num++; break; case BIS_LINK: h->bis_num++; break; case PA_LINK: h->pa_num++; break; } } static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_del_rcu(&c->list); synchronize_rcu(); switch (c->type) { case ACL_LINK: h->acl_num--; break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) h->le_num_peripheral--; break; case SCO_LINK: case ESCO_LINK: h->sco_num--; break; case CIS_LINK: h->cis_num--; break; case BIS_LINK: h->bis_num--; break; case PA_LINK: h->pa_num--; break; } } static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; switch (type) { case ACL_LINK: return h->acl_num; case LE_LINK: return h->le_num; case SCO_LINK: case ESCO_LINK: return h->sco_num; case CIS_LINK: return h->cis_num; case BIS_LINK: return h->bis_num; case PA_LINK: return h->pa_num; default: return 0; } } static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num + c->pa_num; } static inline unsigned int hci_iso_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; return c->cis_num + c->bis_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c == conn) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; __u8 type = INVALID_LINK; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->handle == handle) { type = c->type; break; } } rcu_read_unlock(); return type; } static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, ba) || c->type != BIS_LINK) continue; if (c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_create_pa_sync(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != PA_LINK) continue; if (!test_bit(HCI_CONN_CREATE_PA_SYNC, &c->flags)) continue; rcu_read_unlock(); return c; } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 big, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, ba) || c->type != BIS_LINK || !test_bit(HCI_CONN_PER_ADV, &c->flags)) continue; if (c->iso_qos.bcast.big == big && c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->handle == handle) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, __u8 type, bdaddr_t *ba) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_role(struct hci_dev *hdev, __u8 type, __u8 role, bdaddr_t *ba) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->role == role && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_le(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != LE_LINK) continue; if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type, __u8 cig, __u8 id) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != CIS_LINK) continue; /* Match CIG ID if set */ if (cig != c->iso_qos.ucast.cig) continue; /* Match CIS ID if set */ if (id != c->iso_qos.ucast.cis) continue; /* Match destination address if set */ if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev, __u8 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != CIS_LINK) continue; if (handle == c->iso_qos.ucast.cig) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, __u8 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != BIS_LINK) continue; if (handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_big_sync_pend(struct hci_dev *hdev, __u8 handle, __u8 num_bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != PA_LINK) continue; if (handle == c->iso_qos.bcast.big && num_bis == c->num_bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state, __u8 role) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != BIS_LINK || c->state != state || c->role != role) continue; if (handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != BIS_LINK || !test_bit(HCI_CONN_PA_SYNC, &c->flags)) continue; if (c->iso_qos.bcast.big == big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != PA_LINK) continue; /* Ignore the listen hcon, we are looking * for the child hcon that was created as * a result of the PA sync established event. */ if (c->state == BT_LISTEN) continue; if (c->sync_handle == sync_handle) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } typedef void (*hci_conn_func_t)(struct hci_conn *conn, void *data); static inline void hci_conn_hash_list_state(struct hci_dev *hdev, hci_conn_func_t func, __u8 type, __u16 state, void *data) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; if (!func) return; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->state == state) func(c, data); } rcu_read_unlock(); } static inline void hci_conn_hash_list_flag(struct hci_dev *hdev, hci_conn_func_t func, __u8 type, __u8 flag, void *data) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; if (!func) return; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && test_bit(flag, &c->flags)) func(c, data); } rcu_read_unlock(); } static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == LE_LINK && c->state == BT_CONNECT && !test_bit(HCI_CONN_SCANNING, &c->flags)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } /* Returns true if an le connection is in the scanning state */ static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == LE_LINK && c->state == BT_CONNECT && test_bit(HCI_CONN_SCANNING, &c->flags)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); bool hci_iso_setup_path(struct hci_conn *conn); int hci_le_create_cis_pending(struct hci_dev *hdev); int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role, u16 handle); struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); void hci_chan_list_flush(struct hci_conn *conn); struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle); struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason, u16 timeout); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec, u16 timeout); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, u16 timeout); struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid, struct bt_iso_qos *qos, __u8 base_len, __u8 *base, u16 timeout); int hci_past_bis(struct hci_conn *conn, bdaddr_t *dst, __u8 dst_type); struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, u16 timeout); struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos, __u8 data_len, __u8 *data, u16 timeout); struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]); int hci_conn_check_link_mode(struct hci_conn *conn); int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level); int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, bool initiator); int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); void hci_conn_failed(struct hci_conn *conn, u8 status); u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle); void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb); void hci_conn_tx_dequeue(struct hci_conn *conn); void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset, const struct sockcm_cookie *sockc); static inline void hci_sockcm_init(struct sockcm_cookie *sockc, struct sock *sk) { *sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags), }; } /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an * "hci_conn" object. They do not guarantee that the hci_conn object is running, * working or anything else. They just guarantee that the object is available * and can be dereferenced. So you can use its locks, local variables and any * other constant data. * Before accessing runtime data, you _must_ lock the object and then check that * it is still running. As soon as you release the locks, the connection might * get dropped, though. * * On the other hand, hci_conn_hold() and hci_conn_drop() are used to control * how long the underlying connection is held. So every channel that runs on the * hci_conn object calls this to prevent the connection from disappearing. As * long as you hold a device, you must also guarantee that you have a valid * reference to the device via hci_conn_get() (or the initial reference from * hci_conn_add()). * The hold()/drop() ref-count is known to drop below 0 sometimes, which doesn't * break because nobody cares for that. But this means, we cannot use * _get()/_drop() in it, but require the caller to have a valid ref (FIXME). */ static inline struct hci_conn *hci_conn_get(struct hci_conn *conn) { get_device(&conn->dev); return conn; } static inline void hci_conn_put(struct hci_conn *conn) { put_device(&conn->dev); } static inline struct hci_conn *hci_conn_hold(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); atomic_inc(&conn->refcnt); cancel_delayed_work(&conn->disc_work); return conn; } static inline void hci_conn_drop(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); if (atomic_dec_and_test(&conn->refcnt)) { unsigned long timeo; switch (conn->type) { case ACL_LINK: case LE_LINK: cancel_delayed_work(&conn->idle_work); if (conn->state == BT_CONNECTED) { timeo = conn->disc_timeout; if (!conn->out) timeo *= 2; } else { timeo = 0; } break; default: timeo = 0; break; } cancel_delayed_work(&conn->disc_work); queue_delayed_work(conn->hdev->workqueue, &conn->disc_work, timeo); } } /* ----- HCI Devices ----- */ static inline void hci_dev_put(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, kref_read(&d->dev.kobj.kref)); put_device(&d->dev); } static inline struct hci_dev *hci_dev_hold(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, kref_read(&d->dev.kobj.kref)); get_device(&d->dev); return d; } #define hci_dev_lock(d) mutex_lock(&d->lock) #define hci_dev_unlock(d) mutex_unlock(&d->lock) #define to_hci_dev(d) container_of(d, struct hci_dev, dev) #define to_hci_conn(c) container_of(c, struct hci_conn, dev) static inline void *hci_get_drvdata(struct hci_dev *hdev) { return dev_get_drvdata(&hdev->dev); } static inline void hci_set_drvdata(struct hci_dev *hdev, void *data) { dev_set_drvdata(&hdev->dev, data); } static inline void *hci_get_priv(struct hci_dev *hdev) { return (char *)hdev + sizeof(*hdev); } struct hci_dev *hci_dev_get(int index); struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, u8 src_type); struct hci_dev *hci_alloc_dev_priv(int sizeof_priv); static inline struct hci_dev *hci_alloc_dev(void) { return hci_alloc_dev_priv(0); } void hci_free_dev(struct hci_dev *hdev); int hci_register_dev(struct hci_dev *hdev); void hci_unregister_dev(struct hci_dev *hdev); void hci_release_dev(struct hci_dev *hdev); int hci_register_suspend_notifier(struct hci_dev *hdev); int hci_unregister_suspend_notifier(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); __printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); __printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); static inline void hci_set_msft_opcode(struct hci_dev *hdev, __u16 opcode) { #if IS_ENABLED(CONFIG_BT_MSFTEXT) hdev->msft_opcode = opcode; #endif } static inline void hci_set_aosp_capable(struct hci_dev *hdev) { #if IS_ENABLED(CONFIG_BT_AOSPEXT) hdev->aosp_capable = true; #endif } static inline void hci_devcd_setup(struct hci_dev *hdev) { #ifdef CONFIG_DEV_COREDUMP INIT_WORK(&hdev->dump.dump_rx, hci_devcd_rx); INIT_DELAYED_WORK(&hdev->dump.dump_timeout, hci_devcd_timeout); skb_queue_head_init(&hdev->dump.dump_q); #endif } int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); int hci_dev_reset(__u16 dev); int hci_dev_reset_stat(__u16 dev); int hci_dev_cmd(unsigned int cmd, void __user *arg); int hci_get_dev_list(void __user *arg); int hci_get_dev_info(void __user *arg); int hci_get_conn_list(void __user *arg); int hci_get_conn_info(struct hci_dev *hdev, void __user *arg); int hci_get_auth_info(struct hci_dev *hdev, void __user *arg); int hci_inquiry(void __user *arg); struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *list, bdaddr_t *bdaddr, u8 type); struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *list, bdaddr_t *bdaddr, u8 type); struct bdaddr_list_with_flags * hci_bdaddr_list_lookup_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type, u8 *peer_irk, u8 *local_irk); int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type, u32 flags); int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_clear_disabled(struct hci_dev *hdev); void hci_conn_params_free(struct hci_conn_params *param); void hci_pend_le_list_del_init(struct hci_conn_params *param); void hci_pend_le_list_add(struct hci_conn_params *param, struct list_head *list); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); void hci_uuids_clear(struct hci_dev *hdev); void hci_link_keys_clear(struct hci_dev *hdev); u8 *hci_conn_key_enc_size(struct hci_conn *conn); struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len, bool *persistent); struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, u8 authenticated, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand); struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 role); int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); void hci_smp_ltks_clear(struct hci_dev *hdev); int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa); struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 val[16], bdaddr_t *rpa); void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]); void hci_blocked_keys_clear(struct hci_dev *hdev); void hci_smp_irks_clear(struct hci_dev *hdev); bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type); void hci_remote_oob_data_clear(struct hci_dev *hdev); struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 *hash192, u8 *rand192, u8 *hash256, u8 *rand256); int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); void hci_adv_instances_clear(struct hci_dev *hdev); struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance); struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid); struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance); struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, u32 min_interval, u32 max_interval, u8 mesh_handle); struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval); int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data); int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance); bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance); void hci_adv_monitors_clear(struct hci_dev *hdev); void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle); int hci_remove_all_adv_monitor(struct hci_dev *hdev); bool hci_is_adv_monitoring(struct hci_dev *hdev); int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); void hci_conn_add_sysfs(struct hci_conn *conn); void hci_conn_del_sysfs(struct hci_conn *conn); #define SET_HCIDEV_DEV(hdev, pdev) ((hdev)->dev.parent = (pdev)) #define GET_HCIDEV_DEV(hdev) ((hdev)->dev.parent) /* ----- LMP capabilities ----- */ #define lmp_encrypt_capable(dev) ((dev)->features[0][0] & LMP_ENCRYPT) #define lmp_rswitch_capable(dev) ((dev)->features[0][0] & LMP_RSWITCH) #define lmp_hold_capable(dev) ((dev)->features[0][0] & LMP_HOLD) #define lmp_sniff_capable(dev) ((dev)->features[0][0] & LMP_SNIFF) #define lmp_park_capable(dev) ((dev)->features[0][1] & LMP_PARK) #define lmp_sco_capable(dev) ((dev)->features[0][1] & LMP_SCO) #define lmp_inq_rssi_capable(dev) ((dev)->features[0][3] & LMP_RSSI_INQ) #define lmp_esco_capable(dev) ((dev)->features[0][3] & LMP_ESCO) #define lmp_bredr_capable(dev) (!((dev)->features[0][4] & LMP_NO_BREDR)) #define lmp_le_capable(dev) ((dev)->features[0][4] & LMP_LE) #define lmp_sniffsubr_capable(dev) ((dev)->features[0][5] & LMP_SNIFF_SUBR) #define lmp_pause_enc_capable(dev) ((dev)->features[0][5] & LMP_PAUSE_ENC) #define lmp_esco_2m_capable(dev) ((dev)->features[0][5] & LMP_EDR_ESCO_2M) #define lmp_ext_inq_capable(dev) ((dev)->features[0][6] & LMP_EXT_INQ) #define lmp_le_br_capable(dev) (!!((dev)->features[0][6] & LMP_SIMUL_LE_BR)) #define lmp_ssp_capable(dev) ((dev)->features[0][6] & LMP_SIMPLE_PAIR) #define lmp_no_flush_capable(dev) ((dev)->features[0][6] & LMP_NO_FLUSH) #define lmp_lsto_capable(dev) ((dev)->features[0][7] & LMP_LSTO) #define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR) #define lmp_ext_feat_capable(dev) ((dev)->features[0][7] & LMP_EXTFEATURES) #define lmp_transp_capable(dev) ((dev)->features[0][2] & LMP_TRANSPARENT) #define lmp_edr_2m_capable(dev) ((dev)->features[0][3] & LMP_EDR_2M) #define lmp_edr_3m_capable(dev) ((dev)->features[0][3] & LMP_EDR_3M) #define lmp_edr_3slot_capable(dev) ((dev)->features[0][4] & LMP_EDR_3SLOT) #define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ #define lmp_cpb_central_capable(dev) ((dev)->features[2][0] & LMP_CPB_CENTRAL) #define lmp_cpb_peripheral_capable(dev) ((dev)->features[2][0] & LMP_CPB_PERIPHERAL) #define lmp_sync_train_capable(dev) ((dev)->features[2][0] & LMP_SYNC_TRAIN) #define lmp_sync_scan_capable(dev) ((dev)->features[2][0] & LMP_SYNC_SCAN) #define lmp_sc_capable(dev) ((dev)->features[2][1] & LMP_SC) #define lmp_ping_capable(dev) ((dev)->features[2][1] & LMP_PING) /* ----- Host capabilities ----- */ #define lmp_host_ssp_capable(dev) ((dev)->features[1][0] & LMP_HOST_SSP) #define lmp_host_sc_capable(dev) ((dev)->features[1][0] & LMP_HOST_SC) #define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) #define hdev_is_powered(dev) (test_bit(HCI_UP, &(dev)->flags) && \ !hci_dev_test_flag(dev, HCI_AUTO_OFF)) #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) #define rpa_valid(dev) (bacmp(&dev->rpa, BDADDR_ANY) && \ !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) #define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ !adv->rpa_expired) #define le_enabled(dev) (lmp_le_capable(dev) && \ hci_dev_test_flag(dev, HCI_LE_ENABLED)) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) #define le_2m_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_2M)) #define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) #define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \ !hci_test_quirk((dev), \ HCI_QUIRK_BROKEN_LE_CODED)) #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) #define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev)) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ ((dev)->commands[39] & 0x04)) #define read_key_size_capable(dev) \ ((dev)->commands[20] & 0x10 && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE)) #define read_voice_setting_capable(dev) \ ((dev)->commands[9] & 0x04 && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_VOICE_SETTING)) /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ #define enhanced_sync_conn_capable(dev) \ (((dev)->commands[29] & 0x08) && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40) && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_SCAN)) /* Use ext create connection if command is supported */ #define use_ext_conn(dev) (((dev)->commands[37] & 0x80) && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) /* Maximum advertising length */ #define max_adv_len(dev) \ (ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH) /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: * * C24: Mandatory if the LE Controller supports Connection State and either * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported */ #define use_enhanced_conn_complete(dev) ((ll_privacy_capable(dev) || \ ext_adv_capable(dev)) && \ !hci_test_quirk((dev), \ HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) /* CIS Master/Slave and BIS support */ #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev)) #define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev)) #define cis_capable(dev) \ (cis_central_capable(dev) || cis_peripheral_capable(dev)) #define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev)) #define cis_central_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_CENTRAL) #define cis_central_enabled(dev) \ (le_enabled(dev) && cis_central_capable(dev)) #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) #define cis_peripheral_enabled(dev) \ (le_enabled(dev) && cis_peripheral_capable(dev)) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) #define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev)) #define sync_recv_capable(dev) \ ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev)) #define past_sender_capable(dev) \ ((dev)->le_features[3] & HCI_LE_PAST_SENDER) #define past_receiver_capable(dev) \ ((dev)->le_features[3] & HCI_LE_PAST_RECEIVER) #define past_capable(dev) \ (past_sender_capable(dev) || past_receiver_capable(dev)) #define past_sender_enabled(dev) \ (le_enabled(dev) && past_sender_capable(dev)) #define past_receiver_enabled(dev) \ (le_enabled(dev) && past_receiver_capable(dev)) #define past_enabled(dev) \ (past_sender_enabled(dev) || past_receiver_enabled(dev)) #define ll_ext_feature_capable(dev) \ ((dev)->le_features[7] & HCI_LE_LL_EXT_FEATURE) /* Channel sounding support */ #define le_cs_capable(dev) \ ((dev)->le_features[5] & HCI_LE_CS) #define le_cs_host_capable(dev) \ ((dev)->le_features[5] & HCI_LE_CS_HOST) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 type, __u8 *flags) { switch (type) { case ACL_LINK: return l2cap_connect_ind(hdev, bdaddr); case SCO_LINK: case ESCO_LINK: return sco_connect_ind(hdev, bdaddr, flags); case CIS_LINK: case BIS_LINK: case PA_LINK: return iso_connect_ind(hdev, bdaddr, flags); default: BT_ERR("unknown link type %d", type); return -EINVAL; } } static inline int hci_proto_disconn_ind(struct hci_conn *conn) { if (conn->type != ACL_LINK && conn->type != LE_LINK) return HCI_ERROR_REMOTE_USER_TERM; return l2cap_disconn_ind(conn); } /* ----- HCI callbacks ----- */ struct hci_cb { struct list_head list; char *name; void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->connect_cfm) cb->connect_cfm(conn, status); } mutex_unlock(&hci_cb_list_lock); if (conn->connect_cfm_cb) conn->connect_cfm_cb(conn, status); } static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->disconn_cfm) cb->disconn_cfm(conn, reason); } mutex_unlock(&hci_cb_list_lock); if (conn->disconn_cfm_cb) conn->disconn_cfm_cb(conn, reason); } static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return; encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; if (conn->state == BT_CONFIG) { if (!status) conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); hci_conn_drop(conn); return; } if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) encrypt = 0x00; else if (test_bit(HCI_CONN_AES_CCM, &conn->flags)) encrypt = 0x02; else encrypt = 0x01; if (!status) { if (conn->sec_level == BT_SECURITY_SDP) conn->sec_level = BT_SECURITY_LOW; if (conn->pending_sec_level > conn->sec_level) conn->sec_level = conn->pending_sec_level; } mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); } mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, __u8 role) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); } mutex_unlock(&hci_cb_list_lock); } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) { if (addr_type != ADDR_LE_DEV_RANDOM) return false; if ((bdaddr->b[5] & 0xc0) == 0x40) return true; return false; } static inline bool hci_is_identity_address(bdaddr_t *addr, u8 addr_type) { if (addr_type == ADDR_LE_DEV_PUBLIC) return true; /* Check for Random Static address type */ if ((addr->b[5] & 0xc0) == 0xc0) return true; return false; } static inline struct smp_irk *hci_get_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { if (!hci_bdaddr_is_rpa(bdaddr, addr_type)) return NULL; return hci_find_irk_by_rpa(hdev, bdaddr); } static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, u16 to_multiplier) { u16 max_latency; if (min > max) { BT_WARN("min %d > max %d", min, max); return -EINVAL; } if (min < 6) { BT_WARN("min %d < 6", min); return -EINVAL; } if (max > 3200) { BT_WARN("max %d > 3200", max); return -EINVAL; } if (to_multiplier < 10) { BT_WARN("to_multiplier %d < 10", to_multiplier); return -EINVAL; } if (to_multiplier > 3200) { BT_WARN("to_multiplier %d > 3200", to_multiplier); return -EINVAL; } if (max >= to_multiplier * 8) { BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier); return -EINVAL; } max_latency = (to_multiplier * 4 / max) - 1; if (latency > 499) { BT_WARN("latency %d > 499", latency); return -EINVAL; } if (latency > max_latency) { BT_WARN("latency %d > max_latency %d", latency, max_latency); return -EINVAL; } return 0; } int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void hci_send_iso(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); void *hci_recv_event_data(struct hci_dev *hdev, __u8 event); u32 hci_conn_get_phy(struct hci_conn *conn); int hci_conn_set_phy(struct hci_conn *conn, u32 phys); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, void *data, u16 data_len, ktime_t tstamp, int flag, struct sock *skip_sk); void hci_sock_dev_event(struct hci_dev *hdev, int event); #define HCI_MGMT_VAR_LEN BIT(0) #define HCI_MGMT_NO_HDEV BIT(1) #define HCI_MGMT_UNTRUSTED BIT(2) #define HCI_MGMT_UNCONFIGURED BIT(3) #define HCI_MGMT_HDEV_OPTIONAL BIT(4) struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len); size_t data_len; unsigned long flags; }; struct hci_mgmt_chan { struct list_head list; unsigned short channel; size_t handler_count; const struct hci_mgmt_handler *handlers; void (*hdev_init) (struct sock *sk, struct hci_dev *hdev); }; int hci_mgmt_chan_register(struct hci_mgmt_chan *c); void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); /* Management interface */ #define DISCOV_TYPE_BREDR (BIT(BDADDR_BREDR)) #define DISCOV_TYPE_LE (BIT(BDADDR_LE_PUBLIC) | \ BIT(BDADDR_LE_RANDOM)) #define DISCOV_TYPE_INTERLEAVED (BIT(BDADDR_BREDR) | \ BIT(BDADDR_LE_PUBLIC) | \ BIT(BDADDR_LE_RANDOM)) /* These LE scan and inquiry parameters were chosen according to LE General * Discovery Procedure specification. */ #define DISCOV_LE_SCAN_WIN 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT_FAST 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_WIN_FAST 0x0030 /* 30 msec */ #define DISCOV_LE_SCAN_INT_CONN 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_WIN_CONN 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_INT_SLOW1 0x0800 /* 1.28 sec */ #define DISCOV_LE_SCAN_WIN_SLOW1 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT_SLOW2 0x1000 /* 2.56 sec */ #define DISCOV_LE_SCAN_WIN_SLOW2 0x0024 /* 22.5 msec */ #define DISCOV_CODED_SCAN_INT_FAST 0x0120 /* 180 msec */ #define DISCOV_CODED_SCAN_WIN_FAST 0x0090 /* 90 msec */ #define DISCOV_CODED_SCAN_INT_SLOW1 0x1800 /* 3.84 sec */ #define DISCOV_CODED_SCAN_WIN_SLOW1 0x0036 /* 33.75 msec */ #define DISCOV_CODED_SCAN_INT_SLOW2 0x3000 /* 7.68 sec */ #define DISCOV_CODED_SCAN_WIN_SLOW2 0x006c /* 67.5 msec */ #define DISCOV_LE_TIMEOUT 10240 /* msec */ #define DISCOV_INTERLEAVED_TIMEOUT 5120 /* msec */ #define DISCOV_INTERLEAVED_INQUIRY_LEN 0x04 #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ #define DISCOV_LE_FAST_ADV_INT_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_FAST_ADV_INT_MAX 0x00F0 /* 150 msec */ #define DISCOV_LE_PER_ADV_INT_MIN 0x00A0 /* 200 msec */ #define DISCOV_LE_PER_ADV_INT_MAX 0x00A0 /* 200 msec */ #define DISCOV_LE_ADV_MESH_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_ADV_MESH_MAX 0x00A0 /* 100 msec */ #define INTERVAL_TO_MS(x) (((x) * 10) / 0x10) #define NAME_RESOLVE_DURATION msecs_to_jiffies(10240) /* 10.24 sec */ void mgmt_fill_version_info(void *ver); int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); void mgmt_set_powered_failed(struct hci_dev *hdev, int err); void mgmt_power_on(struct hci_dev *hdev, int err); void __mgmt_power_off(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u8 *name, u8 name_len); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, u8 status); void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure); void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 value, u8 confirm_hint); int mgmt_user_confirm_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_confirm_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type); int mgmt_user_passkey_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 passkey, u8 entered); void mgmt_auth_failed(struct hci_conn *conn, u8 status); void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len, u64 instant); void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); void mgmt_suspending(struct hci_dev *hdev, u8 state); void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr, u8 addr_type); bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent); void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, bool persistent); void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 store_hint, u16 min_interval, u16 max_interval, u16 latency, u16 timeout); void mgmt_smp_complete(struct hci_conn *conn, bool complete); bool mgmt_get_connectable(struct hci_dev *hdev); u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev); void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, bdaddr_t *bdaddr, u8 addr_type); int hci_abort_conn(struct hci_conn *conn, u8 reason); void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size); void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type); #define SCO_AIRMODE_MASK 0x0003 #define SCO_AIRMODE_CVSD 0x0000 #define SCO_AIRMODE_TRANSP 0x0003 #define LOCAL_CODEC_ACL_MASK BIT(0) #define LOCAL_CODEC_SCO_MASK BIT(1) #define TRANSPORT_TYPE_MAX 0x04 #endif /* __HCI_CORE_H */ |
| 2 22 22 22 22 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ip.h> #include <linux/skbuff.h> #include <net/ip6_checksum.h> #include <net/psp.h> #include <net/sock.h> #include "netdevsim.h" void nsim_psp_handle_ext(struct sk_buff *skb, struct skb_ext *psp_ext) { if (psp_ext) __skb_ext_set(skb, SKB_EXT_PSP, psp_ext); } enum skb_drop_reason nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns, struct netdevsim *peer_ns, struct skb_ext **psp_ext) { enum skb_drop_reason rc = 0; struct psp_dev *peer_psd; struct psp_assoc *pas; struct net *net; int psp_len; void **ptr; rcu_read_lock(); pas = psp_skb_get_assoc_rcu(skb); if (!pas) { rc = SKB_NOT_DROPPED_YET; goto out_unlock; } if (!skb_transport_header_was_set(skb)) { rc = SKB_DROP_REASON_PSP_OUTPUT; goto out_unlock; } ptr = psp_assoc_drv_data(pas); if (*ptr != ns) { rc = SKB_DROP_REASON_PSP_OUTPUT; goto out_unlock; } net = sock_net(skb->sk); if (!psp_dev_encapsulate(net, skb, pas->tx.spi, pas->version, 0)) { rc = SKB_DROP_REASON_PSP_OUTPUT; goto out_unlock; } psp_len = skb->len - skb_inner_transport_offset(skb); atomic64_inc(&ns->psp.tx_packets); atomic64_add(psp_len, &ns->psp.tx_bytes); /* Now pretend we just received this frame */ peer_psd = rcu_dereference(peer_ns->psp.dev); if (peer_psd && peer_psd->config.versions & (1 << pas->version)) { bool strip_icv = false; u8 generation; /* We cheat a bit and put the generation in the key. * In real life if generation was too old, then decryption would * fail. Here, we just make it so a bad key causes a bad * generation too, and psp_sk_rx_policy_check() will fail. */ generation = pas->tx.key[0]; skb_ext_reset(skb); skb->mac_len = ETH_HLEN; if (psp_dev_rcv(skb, peer_psd->id, generation, strip_icv)) { rc = SKB_DROP_REASON_PSP_OUTPUT; goto out_unlock; } *psp_ext = skb->extensions; refcount_inc(&(*psp_ext)->refcnt); skb->decrypted = 1; atomic64_inc(&peer_ns->psp.rx_packets); atomic64_add(psp_len, &peer_ns->psp.rx_bytes); } else { struct ipv6hdr *ip6h __maybe_unused; struct iphdr *iph; struct udphdr *uh; __wsum csum; /* Do not decapsulate. Receive the skb with the udp and psp * headers still there as if this is a normal udp packet. * psp_dev_encapsulate() sets udp checksum to 0, so we need to * provide a valid checksum here, so the skb isn't dropped. */ uh = udp_hdr(skb); csum = skb_checksum(skb, skb_transport_offset(skb), ntohs(uh->len), 0); switch (skb->protocol) { case htons(ETH_P_IP): iph = ip_hdr(skb); uh->check = udp_v4_check(ntohs(uh->len), iph->saddr, iph->daddr, csum); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip6h = ipv6_hdr(skb); uh->check = udp_v6_check(ntohs(uh->len), &ip6h->saddr, &ip6h->daddr, csum); break; #endif } uh->check = uh->check ?: CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_NONE; } out_unlock: rcu_read_unlock(); return rc; } static int nsim_psp_set_config(struct psp_dev *psd, struct psp_dev_config *conf, struct netlink_ext_ack *extack) { return 0; } static int nsim_rx_spi_alloc(struct psp_dev *psd, u32 version, struct psp_key_parsed *assoc, struct netlink_ext_ack *extack) { struct netdevsim *ns = psd->drv_priv; int i; /* Check if incrementing the spi would change the phase bit */ if ((ns->psp.spi & PSP_SPI_KEY_ID) == PSP_SPI_KEY_ID) { NL_SET_ERR_MSG(extack, "SPI space exhausted"); return -ENOSPC; } assoc->spi = cpu_to_be32(++ns->psp.spi); assoc->key[0] = psd->generation; for (i = 1; i < PSP_MAX_KEY; i++) assoc->key[i] = ns->psp.spi + i; return 0; } static int nsim_assoc_add(struct psp_dev *psd, struct psp_assoc *pas, struct netlink_ext_ack *extack) { struct netdevsim *ns = psd->drv_priv; void **ptr = psp_assoc_drv_data(pas); /* Copy drv_priv from psd to assoc */ *ptr = psd->drv_priv; ns->psp.assoc_cnt++; return 0; } static int nsim_key_rotate(struct psp_dev *psd, struct netlink_ext_ack *extack) { struct netdevsim *ns = psd->drv_priv; /* Flip key phase and reset SPI to 0 within that space * (will be pre-incremented, as 0 is an invalid SPI). */ if (ns->psp.spi & PSP_SPI_KEY_PHASE) ns->psp.spi = 0; else ns->psp.spi = PSP_SPI_KEY_PHASE; return 0; } static void nsim_assoc_del(struct psp_dev *psd, struct psp_assoc *pas) { struct netdevsim *ns = psd->drv_priv; void **ptr = psp_assoc_drv_data(pas); *ptr = NULL; ns->psp.assoc_cnt--; } static void nsim_get_stats(struct psp_dev *psd, struct psp_dev_stats *stats) { struct netdevsim *ns = psd->drv_priv; /* WARNING: do *not* blindly zero stats in real drivers! * All required stats must be reported by the device! */ memset(stats, 0, sizeof(struct psp_dev_stats)); stats->rx_bytes = atomic64_read(&ns->psp.rx_bytes); stats->rx_packets = atomic64_read(&ns->psp.rx_packets); stats->tx_bytes = atomic64_read(&ns->psp.tx_bytes); stats->tx_packets = atomic64_read(&ns->psp.tx_packets); } static struct psp_dev_ops nsim_psp_ops = { .set_config = nsim_psp_set_config, .rx_spi_alloc = nsim_rx_spi_alloc, .tx_key_add = nsim_assoc_add, .tx_key_del = nsim_assoc_del, .key_rotate = nsim_key_rotate, .get_stats = nsim_get_stats, }; static struct psp_dev_caps nsim_psp_caps = { .versions = 1 << PSP_VERSION_HDR0_AES_GCM_128 | 1 << PSP_VERSION_HDR0_AES_GMAC_128 | 1 << PSP_VERSION_HDR0_AES_GCM_256 | 1 << PSP_VERSION_HDR0_AES_GMAC_256, .assoc_drv_spc = sizeof(void *), }; static void __nsim_psp_uninit(struct netdevsim *ns, bool teardown) { struct psp_dev *psd; psd = rcu_dereference_protected(ns->psp.dev, teardown || lockdep_is_held(&ns->psp.rereg_lock)); if (psd) { rcu_assign_pointer(ns->psp.dev, NULL); synchronize_rcu(); psp_dev_unregister(psd); } WARN_ON(ns->psp.assoc_cnt); } void nsim_psp_uninit(struct netdevsim *ns) { debugfs_remove(ns->psp.rereg); mutex_destroy(&ns->psp.rereg_lock); __nsim_psp_uninit(ns, true); } static ssize_t nsim_psp_rereg_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct netdevsim *ns = file->private_data; struct psp_dev *psd; ssize_t ret; mutex_lock(&ns->psp.rereg_lock); __nsim_psp_uninit(ns, false); psd = psp_dev_create(ns->netdev, &nsim_psp_ops, &nsim_psp_caps, ns); if (IS_ERR(psd)) { ret = PTR_ERR(psd); goto out; } rcu_assign_pointer(ns->psp.dev, psd); ret = count; out: mutex_unlock(&ns->psp.rereg_lock); return ret; } static const struct file_operations nsim_psp_rereg_fops = { .open = simple_open, .write = nsim_psp_rereg_write, .llseek = generic_file_llseek, .owner = THIS_MODULE, }; int nsim_psp_init(struct netdevsim *ns) { struct dentry *ddir = ns->nsim_dev_port->ddir; struct psp_dev *psd; psd = psp_dev_create(ns->netdev, &nsim_psp_ops, &nsim_psp_caps, ns); if (IS_ERR(psd)) return PTR_ERR(psd); rcu_assign_pointer(ns->psp.dev, psd); mutex_init(&ns->psp.rereg_lock); ns->psp.rereg = debugfs_create_file("psp_rereg", 0200, ddir, ns, &nsim_psp_rereg_fops); return 0; } |
| 1266 809 1917 54 1 37 5 28 2080 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } static inline bool timespec64_is_epoch(const struct timespec64 *ts) { return ts->tv_sec == 0 && ts->tv_nsec == 0; } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 5 26 18 63 63 3 26 37 57 25 30 42 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | /* * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. 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. */ #ifndef _TLS_INT_H #define _TLS_INT_H #include <asm/byteorder.h> #include <linux/types.h> #include <linux/skmsg.h> #include <net/tls.h> #include <net/tls_prot.h> #define TLS_PAGE_ORDER (min_t(unsigned int, PAGE_ALLOC_COSTLY_ORDER, \ TLS_MAX_PAYLOAD_SIZE >> PAGE_SHIFT)) #define __TLS_INC_STATS(net, field) \ __SNMP_INC_STATS((net)->mib.tls_statistics, field) #define TLS_INC_STATS(net, field) \ SNMP_INC_STATS((net)->mib.tls_statistics, field) #define TLS_DEC_STATS(net, field) \ SNMP_DEC_STATS((net)->mib.tls_statistics, field) struct tls_cipher_desc { unsigned int nonce; unsigned int iv; unsigned int key; unsigned int salt; unsigned int tag; unsigned int rec_seq; unsigned int iv_offset; unsigned int key_offset; unsigned int salt_offset; unsigned int rec_seq_offset; char *cipher_name; bool offloadable; size_t crypto_info; }; #define TLS_CIPHER_MIN TLS_CIPHER_AES_GCM_128 #define TLS_CIPHER_MAX TLS_CIPHER_ARIA_GCM_256 extern const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN]; static inline const struct tls_cipher_desc *get_cipher_desc(u16 cipher_type) { if (cipher_type < TLS_CIPHER_MIN || cipher_type > TLS_CIPHER_MAX) return NULL; return &tls_cipher_desc[cipher_type - TLS_CIPHER_MIN]; } static inline char *crypto_info_iv(struct tls_crypto_info *crypto_info, const struct tls_cipher_desc *cipher_desc) { return (char *)crypto_info + cipher_desc->iv_offset; } static inline char *crypto_info_key(struct tls_crypto_info *crypto_info, const struct tls_cipher_desc *cipher_desc) { return (char *)crypto_info + cipher_desc->key_offset; } static inline char *crypto_info_salt(struct tls_crypto_info *crypto_info, const struct tls_cipher_desc *cipher_desc) { return (char *)crypto_info + cipher_desc->salt_offset; } static inline char *crypto_info_rec_seq(struct tls_crypto_info *crypto_info, const struct tls_cipher_desc *cipher_desc) { return (char *)crypto_info + cipher_desc->rec_seq_offset; } /* TLS records are maintained in 'struct tls_rec'. It stores the memory pages * allocated or mapped for each TLS record. After encryption, the records are * stores in a linked list. */ struct tls_rec { struct list_head list; int tx_ready; int tx_flags; struct sk_msg msg_plaintext; struct sk_msg msg_encrypted; /* AAD | msg_plaintext.sg.data | sg_tag */ struct scatterlist sg_aead_in[2]; /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ struct scatterlist sg_aead_out[2]; char content_type; struct scatterlist sg_content_type; struct sock *sk; char aad_space[TLS_AAD_SPACE_SIZE]; u8 iv_data[TLS_MAX_IV_SIZE]; /* Must be last --ends in a flexible-array member. */ struct aead_request aead_req; }; int __net_init tls_proc_init(struct net *net); void __net_exit tls_proc_fini(struct net *net); struct tls_context *tls_ctx_create(struct sock *sk); void tls_ctx_free(struct sock *sk, struct tls_context *ctx); void update_sk_prot(struct sock *sk, struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); void tls_err_abort(struct sock *sk, int err); void tls_strp_abort_strp(struct tls_strparser *strp, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, const struct tls_cipher_desc *cipher_desc); int tls_set_sw_offload(struct sock *sk, int tx, struct tls_crypto_info *new_crypto_info); void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); void tls_sw_splice_eof(struct socket *sock); void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); void tls_sw_release_resources_tx(struct sock *sk); void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags); bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t read_actor); int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); void tls_device_splice_eof(struct socket *sock); int tls_tx_records(struct sock *sk, int flags); void tls_sw_write_space(struct sock *sk, struct tls_context *ctx); void tls_device_write_space(struct sock *sk, struct tls_context *ctx); int tls_process_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); int decrypt_skb(struct sock *sk, struct scatterlist *sgout); int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info); int tls_strp_dev_init(void); void tls_strp_dev_exit(void); void tls_strp_done(struct tls_strparser *strp); void __tls_strp_done(struct tls_strparser *strp); void tls_strp_stop(struct tls_strparser *strp); int tls_strp_init(struct tls_strparser *strp, struct sock *sk); void tls_strp_data_ready(struct tls_strparser *strp); void tls_strp_check_rcv(struct tls_strparser *strp, bool announce); void tls_strp_msg_consume(struct tls_strparser *strp); int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb); void tls_rx_msg_maybe_announce(struct tls_strparser *strp); bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); int tls_strp_msg_cow(struct tls_sw_context_rx *ctx); struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx); int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb; return &scb->tls; } static inline struct sk_buff *tls_strp_msg(struct tls_sw_context_rx *ctx) { DEBUG_NET_WARN_ON_ONCE(!ctx->strp.msg_ready || !ctx->strp.anchor->len); return ctx->strp.anchor; } static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) { return READ_ONCE(ctx->strp.msg_ready); } static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) { return ctx->strp.mixed_decrypted; } #ifdef CONFIG_TLS_DEVICE int tls_device_init(void); void tls_device_cleanup(void); int tls_set_device_offload(struct sock *sk); void tls_device_free_resources_tx(struct sock *sk); int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); void tls_device_offload_cleanup_rx(struct sock *sk); void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx); #else static inline int tls_device_init(void) { return 0; } static inline void tls_device_cleanup(void) {} static inline int tls_set_device_offload(struct sock *sk) { return -EOPNOTSUPP; } static inline void tls_device_free_resources_tx(struct sock *sk) {} static inline int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) { return -EOPNOTSUPP; } static inline void tls_device_offload_cleanup_rx(struct sock *sk) {} static inline void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {} static inline int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) { return 0; } #endif int tls_push_sg(struct sock *sk, struct tls_context *ctx, struct scatterlist *sg, u16 first_offset, int flags); int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags); void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline bool tls_is_partially_sent_record(struct tls_context *ctx) { return !!ctx->partially_sent_record; } static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) { return tls_ctx->pending_open_record_frags; } static inline bool tls_bigint_increment(unsigned char *seq, int len) { int i; for (i = len - 1; i >= 0; i--) { ++seq[i]; if (seq[i] != 0) break; } return (i == -1); } static inline void tls_bigint_subtract(unsigned char *seq, int n) { u64 rcd_sn; __be64 *p; BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); p = (__be64 *)seq; rcd_sn = be64_to_cpu(*p); *p = cpu_to_be64(rcd_sn - n); } static inline void tls_advance_record_sn(struct sock *sk, struct tls_prot_info *prot, struct cipher_context *ctx) { if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) tls_err_abort(sk, -EBADMSG); if (prot->version != TLS_1_3_VERSION && prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) tls_bigint_increment(ctx->iv + prot->salt_size, prot->iv_size); } static inline void tls_xor_iv_with_seq(struct tls_prot_info *prot, char *iv, char *seq) { int i; if (prot->version == TLS_1_3_VERSION || prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) { for (i = 0; i < 8; i++) iv[i + 4] ^= seq[i]; } } static inline void tls_fill_prepend(struct tls_context *ctx, char *buf, size_t plaintext_len, unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; size_t pkt_len, iv_size = prot->iv_size; pkt_len = plaintext_len + prot->tag_size; if (prot->version != TLS_1_3_VERSION && prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) { pkt_len += iv_size; memcpy(buf + TLS_NONCE_OFFSET, ctx->tx.iv + prot->salt_size, iv_size); } /* we cover nonce explicit here as well, so buf should be of * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ buf[0] = prot->version == TLS_1_3_VERSION ? TLS_RECORD_TYPE_DATA : record_type; /* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */ buf[1] = TLS_1_2_VERSION_MINOR; buf[2] = TLS_1_2_VERSION_MAJOR; /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; } static inline void tls_make_aad(char *buf, size_t size, char *record_sequence, unsigned char record_type, struct tls_prot_info *prot) { if (prot->version != TLS_1_3_VERSION) { memcpy(buf, record_sequence, prot->rec_seq_size); buf += 8; } else { size += prot->tag_size; } buf[0] = prot->version == TLS_1_3_VERSION ? TLS_RECORD_TYPE_DATA : record_type; buf[1] = TLS_1_2_VERSION_MAJOR; buf[2] = TLS_1_2_VERSION_MINOR; buf[3] = size >> 8; buf[4] = size & 0xFF; } #endif |
| 34 35 839 845 5355 16642 625 626 625 2106 1810 1806 1396 1408 311 311 311 20 20 20 20 18 15 2 18264 13057 23703 23697 947 23373 895 895 3 17454 21722 17453 22099 23713 23372 948 11 94 64 1 8 24 892 894 892 2 1 28 28 20 1 20 20 20 20 17 17 97 81 21 360 359 1330 359 101 100 4 18502 19798 1661 18502 21017 21061 19758 35 19781 710 19769 429 20688 771 484 543 21000 21009 17517 16452 14745 2619 20983 20995 1 20989 20974 20955 20975 1185 6787 311 6783 7377 7400 18 436 434 48 512 147 470 453 39 433 18 18 18 17742 7936 17320 63 2 63 63 14757 14761 14760 14760 14580 14595 12 12 71 62 1 10 6 6 1 54 6 75 3 72 4 72 75 75 2 15 8 7 75 1 5 59 27 9 26 35 5 58 74 35 59 28 3 25 18 1 17 6 17 5 17 173 170 2 2 16 16 8 13 13 13 8 13 13 13 3 13 8 13 13 3 13 16 14591 14588 14263 650 14249 129 3216 2889 479 39 179 179 179 136 136 124 28 3264 3259 3262 6 3024 1044 10 1042 69 1044 3269 3261 10 4 5 11 25 31 31 4 1 5 26 16 16 4 4 4 1 1 1 24166 24201 2669 3 2661 14219 14266 2959 79 2910 141 127 61 16 15 141 123 140 1 3 2 1 2 1 88 61 87 61 140 35 2 359 329 2 356 285 286 67 273 10 10 10 10 69 118 7 190 118 193 119 1383 425 455 687 141 176 396 37 1 399 29 82 19 82 20 1 3 3 23 33 17 27 23 33 2 33 33 3 12 34 20 34 34 34 12 34 3 34 54 8 47 2 1 10 1 10 1128 51 1015 79 91 82 82 3 39 220 10 199 15 4 23 3 23 2 192 191 3 1 3 3 926 73 869 12 918 6897 6914 1226 1206 50 50 426 424 2 8 8 1 1 8 24 17814 86 78 111 82 120 120 120 120 123 123 128 128 124 124 123 103 53 120 108 3 53 41 103 111 53 119 50 50 9 8 49 49 393 394 394 89 89 41 49 89 89 29 2 60 89 3 85 85 3 3 3 3 84 89 89 89 89 3 8 8 7 71 64 64 64 64 63 63 64 11 11 89 88 2 2 40 48 43 28 42 27 18 30 31 31 31 4 4 25 26 26 3 1 43 1 42 1 1 1 1 86 79 24 78 79 79 100 69 56 54 1 84 64 64 38 24 2 63 23 43 36 64 1 64 64 43 10 6 5 43 21 64 36 242 2 2 239 13 39 39 13 26 38 37 38 8 105 8 101 192 191 160 4 30 28 143 58 8 8 8 45 97 101 8 97 101 4 101 82 382 385 384 382 380 9 173 176 2 174 171 4 182 2 181 180 175 176 173 102 94 174 296 307 299 7 7 7 6 6 6 6 12 3 12 7 6 1 3 3 3 3 3 3 2221 6 2216 1 303 410 228 492 70 45 50 25 10 24 179 2 23 24 24 155 24 25 155 40 34 32 227 188 69 147 40 53 64 107 108 106 106 47 47 46 47 47 3 50 20 8 38 12 49 223 223 212 18 148 126 25 149 48 32 110 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. * Dave Platt : Interrupt stacking fix. * Richard Kooijman : Timestamp fixes. * Alan Cox : Changed buffer format. * Alan Cox : destructor hook for AF_UNIX etc. * Linus Torvalds : Better skb_clone. * Alan Cox : Added skb_copy. * Alan Cox : Added all the changed routines Linus * only put in the headers * Ray VanTassle : Fixed --skb->lock in free * Alan Cox : skb_copy copy arp field * Andi Kleen : slabified it. * Robert Olsson : Removed skb_head_pool * * NOTE: * The __skb_ routines should be called with interrupts * disabled, or you better be *real* sure that the operation is atomic * with respect to whatever list is being frobbed (e.g. via lock_sock() * or via disabling bottom half handlers, etc). */ /* * The functions in this file will not compile correctly with gcc 2.4.x */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/bitfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> #include <linux/iov_iter.h> #include <linux/crc32.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> #include <net/mctp.h> #include <net/tcp.h> #include <net/can.h> #include <net/page_pool/helpers.h> #include <net/psp/types.h> #include <net/dropreason.h> #include <net/xdp_sock.h> #include <linux/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> #include <linux/indirect_call_wrapper.h> #include <linux/textsearch.h> #include "dev.h" #include "devmem.h" #include "net-sysfs.h" #include "netmem_priv.h" #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif #define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ GRO_MAX_HEAD_PAD)) /* SKB_SMALL_HEAD_CACHE_SIZE is the size used for the skbuff_small_head * kmem_cache. The non-power-of-2 padding is kept for historical reasons and * to avoid potential collisions with generic kmalloc bucket sizes. */ #define SKB_SMALL_HEAD_CACHE_SIZE \ (is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \ (SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \ SKB_SMALL_HEAD_SIZE) #define SKB_SMALL_HEAD_HEADROOM \ SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) /* kcm_write_msgs() relies on casting paged frags to bio_vec to use * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the * netmem is a page. */ static_assert(offsetof(struct bio_vec, bv_page) == offsetof(skb_frag_t, netmem)); static_assert(sizeof_field(struct bio_vec, bv_page) == sizeof_field(skb_frag_t, netmem)); static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len)); static_assert(sizeof_field(struct bio_vec, bv_len) == sizeof_field(skb_frag_t, len)); static_assert(offsetof(struct bio_vec, bv_offset) == offsetof(skb_frag_t, offset)); static_assert(sizeof_field(struct bio_vec, bv_offset) == sizeof_field(skb_frag_t, offset)); #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, static const char * const drop_reasons[] = { [SKB_CONSUMED] = "CONSUMED", DEFINE_DROP_REASON(FN, FN) }; static const struct drop_reason_list drop_reasons_core = { .reasons = drop_reasons, .n_reasons = ARRAY_SIZE(drop_reasons), }; const struct drop_reason_list __rcu * drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM] = { [SKB_DROP_REASON_SUBSYS_CORE] = RCU_INITIALIZER(&drop_reasons_core), }; EXPORT_SYMBOL(drop_reasons_by_subsys); /** * drop_reasons_register_subsys - register another drop reason subsystem * @subsys: the subsystem to register, must not be the core * @list: the list of drop reasons within the subsystem, must point to * a statically initialized list */ void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys, const struct drop_reason_list *list) { if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE || subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return; /* must point to statically allocated memory, so INIT is OK */ RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], list); } EXPORT_SYMBOL_GPL(drop_reasons_register_subsys); /** * drop_reasons_unregister_subsys - unregister a drop reason subsystem * @subsys: the subsystem to remove, must not be the core * * Note: This will synchronize_rcu() to ensure no users when it returns. */ void drop_reasons_unregister_subsys(enum skb_drop_reason_subsys subsys) { if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE || subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return; RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], NULL); synchronize_rcu(); } EXPORT_SYMBOL_GPL(drop_reasons_unregister_subsys); /** * skb_panic - private function for out-of-line support * @skb: buffer * @sz: size * @addr: address * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). * Keep out of line to prevent kernel bloat. * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, const char msg[]) { pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n", msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : "<NULL>"); BUG(); } static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } #define NAPI_SKB_CACHE_SIZE 128 #define NAPI_SKB_CACHE_BULK 32 #define NAPI_SKB_CACHE_FREE 32 struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); void *data; fragsz = SKB_DATA_ALIGN(fragsz); local_lock_nested_bh(&napi_alloc_cache.bh_lock); data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC | __GFP_NOWARN, align_mask); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return data; } EXPORT_SYMBOL(__napi_alloc_frag_align); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { void *data; if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); fragsz = SKB_DATA_ALIGN(fragsz); data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC | __GFP_NOWARN, align_mask); } else { local_bh_disable(); data = __napi_alloc_frag_align(fragsz, align_mask); local_bh_enable(); } return data; } EXPORT_SYMBOL(__netdev_alloc_frag_align); /* Cache kmem_cache_size(net_hotdata.skbuff_cache) to help the compiler * remove dead code (and skbuff_cache_size) when CONFIG_KASAN is unset. */ static u32 skbuff_cache_size __read_mostly; static inline struct sk_buff *napi_skb_cache_get(bool alloc) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { if (alloc && kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN, NAPI_SKB_CACHE_BULK, nc->skb_cache)) nc->skb_count = NAPI_SKB_CACHE_BULK; if (unlikely(!nc->skb_count)) { local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return NULL; } } skb = nc->skb_cache[--nc->skb_count]; if (nc->skb_count) prefetch(nc->skb_cache[nc->skb_count - 1]); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); kasan_mempool_unpoison_object(skb, skbuff_cache_size); return skb; } /* * Only clear those fields we need to clear, not those that we will * actually initialise later. Hence, don't put any more fields after * the tail pointer in struct sk_buff! */ static inline void skbuff_clear(struct sk_buff *skb) { /* Replace memset(skb, 0, offsetof(struct sk_buff, tail)) * with two smaller memset(), with a barrier() between them. * This forces the compiler to inline both calls. */ BUILD_BUG_ON(offsetof(struct sk_buff, tail) <= 128); memset(skb, 0, 128); barrier(); memset((void *)skb + 128, 0, offsetof(struct sk_buff, tail) - 128); } /** * napi_skb_cache_get_bulk - obtain a number of zeroed skb heads from the cache * @skbs: pointer to an at least @n-sized array to fill with skb pointers * @n: number of entries to provide * * Tries to obtain @n &sk_buff entries from the NAPI percpu cache and writes * the pointers into the provided array @skbs. If there are less entries * available, tries to replenish the cache and bulk-allocates the diff from * the MM layer if needed. * The heads are being zeroed with either memset() or %__GFP_ZERO, so they are * ready for {,__}build_skb_around() and don't have any data buffers attached. * Must be called *only* from the BH context. * * Return: number of successfully allocated skbs (@n if no actual allocation * needed or kmem_cache_alloc_bulk() didn't fail). */ u32 napi_skb_cache_get_bulk(void **skbs, u32 n) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 bulk, total = n; local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (nc->skb_count >= n) goto get; /* No enough cached skbs. Try refilling the cache first */ bulk = min(NAPI_SKB_CACHE_SIZE - nc->skb_count, NAPI_SKB_CACHE_BULK); if (kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN, bulk, &nc->skb_cache[nc->skb_count])) nc->skb_count += bulk; if (likely(nc->skb_count >= n)) goto get; /* Still not enough. Bulk-allocate the missing part directly, zeroed */ if (kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_ZERO | __GFP_NOWARN, n - nc->skb_count, &skbs[nc->skb_count])) n = nc->skb_count; if (likely(nc->skb_count >= n)) goto get; /* kmem_cache didn't allocate the number we need, limit the output */ total -= n - nc->skb_count; n = nc->skb_count; get: for (u32 base = nc->skb_count - n, i = 0; i < n; i++) { skbs[i] = nc->skb_cache[base + i]; kasan_mempool_unpoison_object(skbs[i], skbuff_cache_size); skbuff_clear(skbs[i]); } nc->skb_count -= n; local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return total; } EXPORT_SYMBOL_GPL(napi_skb_cache_get_bulk); static inline void __finalize_skb_around(struct sk_buff *skb, void *data, unsigned int size) { struct skb_shared_info *shinfo; size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /* Assumes caller memset cleared SKB */ skb->truesize = SKB_TRUESIZE(size); refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb_set_end_offset(skb, size); skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; skb->alloc_cpu = raw_smp_processor_id(); /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); skb_set_kcov_handle(skb, kcov_common_handle()); } static inline void *__slab_build_skb(void *data, unsigned int *size) { void *resized; /* Must find the allocation size (and grow it to match). */ *size = ksize(data); /* krealloc() will immediately return "data" when * "ksize(data)" is requested: it is the existing upper * bounds. As a result, GFP_ATOMIC will be ignored. Note * that this "new" pointer needs to be passed back to the * caller for use so the __alloc_size hinting will be * tracked correctly. */ resized = krealloc(data, *size, GFP_ATOMIC); WARN_ON_ONCE(resized != data); return resized; } /* build_skb() variant which can operate on slab buffers. * Note that this should be used sparingly as slab buffers * cannot be combined efficiently by GRO! */ struct sk_buff *slab_build_skb(void *data) { struct sk_buff *skb; unsigned int size; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; skbuff_clear(skb); data = __slab_build_skb(data, &size); __finalize_skb_around(skb, data, size); return skb; } EXPORT_SYMBOL(slab_build_skb); /* Caller must provide SKB that is memset cleared */ static void __build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { unsigned int size = frag_size; /* frag_size == 0 is considered deprecated now. Callers * using slab buffer should use slab_build_skb() instead. */ if (WARN_ONCE(size == 0, "Use slab_build_skb() instead")) data = __slab_build_skb(data, &size); __finalize_skb_around(skb, data, size); } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data (must not be 0) * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated from the page * allocator or vmalloc(). (A @frag_size of 0 to indicate a kmalloc() * allocation is deprecated, and callers should use slab_build_skb() * instead.) * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : * Before IO, driver allocates only data buffer where NIC put incoming frame * Driver should add room at head (NET_SKB_PAD) and * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) * After IO, driver calls build_skb(), to allocate sk_buff and populate it * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; skbuff_clear(skb); __build_skb_around(skb, data, frag_size); return skb; } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __build_skb(data, frag_size); if (likely(skb && frag_size)) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(build_skb); /** * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller * @frag_size: size of data */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { if (unlikely(!skb)) return NULL; __build_skb_around(skb, data, frag_size); if (frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(build_skb_around); /** * __napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __build_skb() that uses NAPI percpu caches to obtain * skbuff_head instead of inplace allocation. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = napi_skb_cache_get(true); if (unlikely(!skb)) return NULL; skbuff_clear(skb); __build_skb_around(skb, data, frag_size); return skb; } /** * napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __napi_build_skb() that takes care of skb->head_frag * and skb->pfmemalloc when the data is a page or page fragment. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ struct sk_buff *napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __napi_build_skb(data, frag_size); if (likely(skb) && frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(napi_build_skb); static void *kmalloc_pfmemalloc(size_t obj_size, gfp_t flags, int node) { if (!gfp_pfmemalloc_allowed(flags)) return NULL; if (!obj_size) return kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); return kmalloc_node_track_caller(obj_size, flags, node); } /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells * the caller if emergency pfmemalloc reserves are being used. If it is and * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, struct sk_buff *skb) { size_t obj_size; void *obj; obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; if (likely(obj)) goto out; /* Try again but now we are using pfmemalloc reserves */ if (skb) skb->pfmemalloc = true; return kmalloc_pfmemalloc(0, flags, node); } obj_size = kmalloc_size_roundup(obj_size); /* The following cast might truncate high-order bits of obj_size, this * is harmless because kmalloc(obj_size >= 2^32) will fail anyway. */ *size = (unsigned int)obj_size; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (likely(obj)) goto out; /* Try again but now we are using pfmemalloc reserves */ if (skb) skb->pfmemalloc = true; obj = kmalloc_pfmemalloc(obj_size, flags, node); out: return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. * */ /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache * instead of head cache and allocate a cloned (child) skb. * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of at least size bytes. The object has a reference count * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { struct sk_buff *skb = NULL; struct kmem_cache *cache; u8 *data; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; if (flags & SKB_ALLOC_FCLONE) { cache = net_hotdata.skbuff_fclone_cache; goto fallback; } cache = net_hotdata.skbuff_cache; if (unlikely(node != NUMA_NO_NODE && node != numa_mem_id())) goto fallback; if (flags & SKB_ALLOC_NAPI) { skb = napi_skb_cache_get(true); if (unlikely(!skb)) return NULL; } else if (!in_hardirq() && !irqs_disabled()) { local_bh_disable(); skb = napi_skb_cache_get(false); local_bh_enable(); } if (!skb) { fallback: skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); if (unlikely(!skb)) return NULL; } skbuff_clear(skb); /* We do our best to align skb_shared_info on a separate cache * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ data = kmalloc_reserve(&size, gfp_mask, node, skb); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ __finalize_skb_around(skb, data, size); if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); /* skb->fclone is a 2bits field. * Replace expensive RMW (skb->fclone = SKB_FCLONE_ORIG) * with a single OR. */ BUILD_BUG_ON(SKB_FCLONE_UNAVAILABLE != 0); DEBUG_NET_WARN_ON_ONCE(skb->fclone != SKB_FCLONE_UNAVAILABLE); skb->fclone |= SKB_FCLONE_ORIG; refcount_set(&fclones->fclone_ref, 1); } return skb; nodata: kmem_cache_free(cache, skb); return NULL; } EXPORT_SYMBOL(__alloc_skb); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has NET_SKB_PAD headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, gfp_t gfp_mask) { struct page_frag_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; len += NET_SKB_PAD; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = page_frag_cache_is_pfmemalloc(nc); } else { local_bh_disable(); local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = page_frag_cache_is_pfmemalloc(nc); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); } if (unlikely(!data)) return NULL; skb = __build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); /** * napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used * only for NAPI Rx allocation. By doing this we can save several * CPU cycles by avoiding having to disable and re-enable IRQs. * * %NULL is returned if there is no free memory. */ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) { gfp_t gfp_mask = GFP_ATOMIC | __GFP_NOWARN; struct napi_alloc_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; DEBUG_NET_WARN_ON_ONCE(!in_softirq()); len += NET_SKB_PAD + NET_IP_ALIGN; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) return NULL; skb = __napi_build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); skb->dev = napi->dev; skb_fail: return skb; } EXPORT_SYMBOL(napi_alloc_skb); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; DEBUG_NET_WARN_ON_ONCE(size > truesize); skb_frag_size_add(frag, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_coalesce_rx_frag); static void skb_drop_list(struct sk_buff **listp) { kfree_skb_list(*listp); *listp = NULL; } static inline void skb_drop_fraglist(struct sk_buff *skb) { skb_drop_list(&skb_shinfo(skb)->frag_list); } static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; skb_walk_frags(skb, list) skb_get(list); } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom) { #if IS_ENABLED(CONFIG_PAGE_POOL) u32 size, truesize, len, max_head_size, off; struct sk_buff *skb = *pskb, *nskb; int err, i, head_off; void *data; /* XDP does not support fraglist so we need to linearize * the skb. */ if (skb_has_frag_list(skb)) return -EOPNOTSUPP; max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) return -ENOMEM; size = min_t(u32, skb->len, max_head_size); truesize = SKB_HEAD_ALIGN(size) + headroom; data = page_pool_dev_alloc_va(pool, &truesize); if (!data) return -ENOMEM; nskb = napi_build_skb(data, truesize); if (!nskb) { page_pool_free_va(pool, data, true); return -ENOMEM; } skb_reserve(nskb, headroom); skb_copy_header(nskb, skb); skb_mark_for_recycle(nskb); err = skb_copy_bits(skb, 0, nskb->data, size); if (err) { consume_skb(nskb); return err; } skb_put(nskb, size); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); off = size; len = skb->len - off; for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { struct page *page; u32 page_off; size = min_t(u32, len, PAGE_SIZE); truesize = size; page = page_pool_dev_alloc(pool, &page_off, &truesize); if (!page) { consume_skb(nskb); return -ENOMEM; } skb_add_rx_frag(nskb, i, page, page_off, size, truesize); err = skb_copy_bits(skb, off, page_address(page) + page_off, size); if (err) { consume_skb(nskb); return err; } len -= size; off += size; } consume_skb(skb); *pskb = nskb; return 0; #else return -EOPNOTSUPP; #endif } EXPORT_SYMBOL(skb_pp_cow_data); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, const struct bpf_prog *prog) { if (!prog->aux->xdp_has_frags) return -EINVAL; return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM); } EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(netmem_ref netmem) { netmem = netmem_compound_head(netmem); if (unlikely(!netmem_is_pp(netmem))) return false; page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false); return true; } EXPORT_SYMBOL(napi_pp_put_page); #endif static bool skb_pp_recycle(struct sk_buff *skb, void *data) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; return napi_pp_put_page(page_to_netmem(virt_to_page(data))); } /** * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb * @skb: page pool aware skb * * Increase the fragment reference count (pp_ref_count) of a skb. This is * intended to gain fragment references only for page pool aware skbs, * i.e. when skb->pp_recycle is true, and not for fragments in a * non-pp-recycling skb. It has a fallback to increase references on normal * pages, as page pool aware skbs may also have normal page fragments. */ static int skb_pp_frag_ref(struct sk_buff *skb) { struct skb_shared_info *shinfo; netmem_ref head_netmem; int i; if (!skb->pp_recycle) return -EINVAL; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { head_netmem = netmem_compound_head(shinfo->frags[i].netmem); if (likely(netmem_is_pp(head_netmem))) page_pool_ref_netmem(head_netmem); else page_ref_inc(netmem_to_page(head_netmem)); } return 0; } static void skb_kfree_head(void *head) { kfree(head); } static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; if (skb->head_frag) { if (skb_pp_recycle(skb, head)) return; skb_free_frag(head); } else { skb_kfree_head(head); } } static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; if (!skb_data_unref(skb, shinfo)) goto exit; if (skb_zcopy(skb)) { bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS; skb_zcopy_clear(skb, true); if (skip_unref) goto free_head; } for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); free_head: if (shinfo->frag_list) kfree_skb_list_reason(shinfo->frag_list, reason); skb_free_head(skb); exit: /* When we clone an SKB we copy the reycling bit. The pp_recycle * bit is only set on the head though, so in order to avoid races * while trying to recycle fragments on __skb_frag_unref() we need * to make one SKB responsible for triggering the recycle path. * So disable the recycling bit if an SKB is cloned and we have * additional references to the fragmented part of the SKB. * Eventually the last SKB will have the recycling bit set and it's * dataref set to 0, which will trigger the recycling */ skb->pp_recycle = 0; } /* * Free an skbuff by memory without cleaning the state. */ static void kfree_skbmem(struct sk_buff *skb) { struct sk_buff_fclones *fclones; switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: fclones = container_of(skb, struct sk_buff_fclones, skb1); /* We usually free the clone (TX completion) before original skb * This test would have no chance to be true for the clone, * while here, branch prediction will be good. */ if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break; default: /* SKB_FCLONE_CLONE */ fclones = container_of(skb, struct sk_buff_fclones, skb2); break; } if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { DEBUG_NET_WARN_ON_ONCE(in_hardirq()); #ifdef CONFIG_INET INDIRECT_CALL_4(skb->destructor, tcp_wfree, __sock_wfree, sock_wfree, xsk_destruct_skb, skb); #else INDIRECT_CALL_2(skb->destructor, sock_wfree, xsk_destruct_skb, skb); #endif skb->destructor = NULL; skb->sk = NULL; } nf_reset_ct(skb); skb_ext_reset(skb); } /* Free everything but the sk_buff shell. */ static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_head_state(skb); if (likely(skb->head)) skb_release_data(skb, reason); } /** * __kfree_skb - private function * @skb: buffer * * Free an sk_buff. Release anything attached to the buffer. * Clean the state. This is an internal helper function. Users should * always call kfree_skb */ void __kfree_skb(struct sk_buff *skb) { skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); static __always_inline bool __sk_skb_reason_drop(const struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { if (unlikely(!skb_unref(skb))) return false; DEBUG_NET_WARN_ON_ONCE(reason == SKB_NOT_DROPPED_YET || u32_get_bits(reason, SKB_DROP_REASON_SUBSYS_MASK) >= SKB_DROP_REASON_SUBSYS_NUM); if (reason == SKB_CONSUMED) trace_consume_skb(skb, __builtin_return_address(0)); else trace_kfree_skb(skb, __builtin_return_address(0), reason, sk); return true; } /** * sk_skb_reason_drop - free an sk_buff with special reason * @sk: the socket to receive @skb, or NULL if not applicable * @skb: buffer to free * @reason: reason why this skb is dropped * * Drop a reference to the buffer and free it if the usage count has hit * zero. Meanwhile, pass the receiving socket and drop reason to * 'kfree_skb' tracepoint. */ void __fix_address sk_skb_reason_drop(const struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { if (__sk_skb_reason_drop(sk, skb, reason)) __kfree_skb(skb); } EXPORT_SYMBOL(sk_skb_reason_drop); #define KFREE_SKB_BULK_SIZE 16 struct skb_free_array { unsigned int skb_count; void *skb_array[KFREE_SKB_BULK_SIZE]; }; static void kfree_skb_add_bulk(struct sk_buff *skb, struct skb_free_array *sa, enum skb_drop_reason reason) { /* if SKB is a clone, don't handle this case */ if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { __kfree_skb(skb); return; } skb_release_all(skb, reason); sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } } void __fix_address kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) { struct skb_free_array sa; sa.skb_count = 0; while (segs) { struct sk_buff *next = segs->next; if (__sk_skb_reason_drop(NULL, segs, reason)) { skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); } segs = next; } if (sa.skb_count) kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); /* Dump skb information and contents. * * Must only be called from net_ratelimit()-ed paths. * * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; struct sk_buff *list_skb; bool has_mac, has_trans; int headroom, tailroom; int i, len, seg_len; if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); headroom = skb_headroom(skb); tailroom = skb_tailroom(skb); has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); printk("%sskb len=%u data_len=%u headroom=%u headlen=%u tailroom=%u\n" "end-tail=%u mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n" "priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n" "encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n", level, skb->len, skb->data_len, headroom, skb_headlen(skb), tailroom, skb->end - skb->tail, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->mac_len, skb->network_header, has_trans ? skb_network_header_len(skb) : -1, has_trans ? skb->transport_header : -1, sh->tx_flags, sh->nr_frags, sh->gso_size, sh->gso_type, sh->gso_segs, skb->csum, skb->csum_start, skb->csum_offset, skb->ip_summed, skb->csum_complete_sw, skb->csum_valid, skb->csum_level, skb->hash, skb->sw_hash, skb->l4_hash, ntohs(skb->protocol), skb->pkt_type, skb->skb_iif, skb->priority, skb->mark, skb->alloc_cpu, skb->vlan_all, skb->encapsulation, skb->inner_protocol, skb->inner_mac_header, skb->inner_network_header, skb->inner_transport_header); if (dev) printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", level, sk->sk_family, sk->sk_type, sk->sk_protocol); if (full_pkt && headroom) print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb->head, headroom, false); seg_len = min_t(int, skb_headlen(skb), len); if (seg_len) print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, seg_len, false); len -= seg_len; if (full_pkt && tailroom) print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb_tail_pointer(skb), tailroom, false); for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (skb_frag_is_net_iov(frag)) { printk("%sskb frag %d: not readable\n", level, i); len -= skb_frag_size(frag); if (!len) break; continue; } skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); vaddr = kmap_atomic(p); print_hex_dump(level, "skb frag: ", DUMP_PREFIX_OFFSET, 16, 1, vaddr + p_off, seg_len, false); kunmap_atomic(vaddr); len -= seg_len; if (!len) break; } } if (full_pkt && skb_has_frag_list(skb)) { printk("skb fraglist:\n"); skb_walk_frags(skb, list_skb) skb_dump(level, list_skb, true); } } EXPORT_SYMBOL(skb_dump); /** * skb_tx_error - report an sk_buff xmit error * @skb: buffer that triggered an error * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. */ void skb_tx_error(struct sk_buff *skb) { if (skb) { skb_zcopy_downgrade_managed(skb); skb_zcopy_clear(skb, true); } } EXPORT_SYMBOL(skb_tx_error); #ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free * * Drop a ref to the buffer and free it if the usage count has hit zero * Functions identically to kfree_skb, but kfree_skb assumes that the frame * is being dropped after a failure and notes that */ void consume_skb(struct sk_buff *skb) { if (!skb_unref(skb)) return; trace_consume_skb(skb, __builtin_return_address(0)); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); #endif /** * __consume_stateless_skb - free an skbuff, assuming it is stateless * @skb: buffer to free * * Alike consume_skb(), but this variant assumes that this is the last * skb reference and all the head states have been already dropped */ void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb, __builtin_return_address(0)); skb_release_data(skb, SKB_CONSUMED); kfree_skbmem(skb); } static void napi_skb_cache_put(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); if (!kasan_mempool_poison_object(skb)) return; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { u32 i, remaining = NAPI_SKB_CACHE_SIZE - NAPI_SKB_CACHE_FREE; for (i = remaining; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], skbuff_cache_size); kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_FREE, nc->skb_cache + remaining); nc->skb_count = remaining; } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); } void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_all(skb, reason); napi_skb_cache_put(skb); } void napi_skb_free_stolen_head(struct sk_buff *skb) { if (unlikely(skb->slow_gro)) { nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); skb_orphan(skb); skb->slow_gro = 0; } napi_skb_cache_put(skb); } /** * napi_consume_skb() - consume skb in NAPI context, try to feed skb cache * @skb: buffer to free * @budget: NAPI budget * * Non-zero @budget must come from the @budget argument passed by the core * to a NAPI poll function. Note that core may pass budget of 0 to NAPI poll * for example when polling for netpoll / netconsole. * * Passing @budget of 0 is safe from any context, it turns this function * into dev_consume_skb_any(). */ void napi_consume_skb(struct sk_buff *skb, int budget) { if (unlikely(!budget || !skb)) { dev_consume_skb_any(skb); return; } DEBUG_NET_WARN_ON_ONCE(!in_softirq()); if (!static_branch_unlikely(&skb_defer_disable_key) && skb->alloc_cpu != smp_processor_id() && !skb_shared(skb)) { skb_release_head_state(skb); return skb_attempt_defer_free(skb); } if (!skb_unref(skb)) return; /* if reaching here SKB is ready to free */ trace_consume_skb(skb, __builtin_return_address(0)); /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } skb_release_all(skb, SKB_CONSUMED); napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); /* Make sure a field is contained by headers group */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) != \ offsetof(struct sk_buff, headers.field)); \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; /* We do not copy old->sk */ new->dev = old->dev; memcpy(new->cb, old->cb, sizeof(old->cb)); skb_dst_copy(new, old); __skb_ext_copy(new, old); __nf_copy(new, old, false); /* Note : this field could be in the headers group. * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; memcpy(&new->headers, &old->headers, sizeof(new->headers)); CHECK_SKB_FIELD(protocol); CHECK_SKB_FIELD(csum); CHECK_SKB_FIELD(hash); CHECK_SKB_FIELD(priority); CHECK_SKB_FIELD(skb_iif); CHECK_SKB_FIELD(vlan_proto); CHECK_SKB_FIELD(vlan_tci); CHECK_SKB_FIELD(transport_header); CHECK_SKB_FIELD(network_header); CHECK_SKB_FIELD(mac_header); CHECK_SKB_FIELD(inner_protocol); CHECK_SKB_FIELD(inner_transport_header); CHECK_SKB_FIELD(inner_network_header); CHECK_SKB_FIELD(inner_mac_header); CHECK_SKB_FIELD(mark); #ifdef CONFIG_NETWORK_SECMARK CHECK_SKB_FIELD(secmark); #endif #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif CHECK_SKB_FIELD(alloc_cpu); #ifdef CONFIG_XPS CHECK_SKB_FIELD(sender_cpu); #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #endif } /* * You should not add any new code to this function. Add it to * __copy_skb_header above instead. */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { #define C(x) n->x = skb->x n->next = n->prev = NULL; n->sk = NULL; __copy_skb_header(n, skb); C(len); C(data_len); C(mac_len); n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; n->peeked = 0; C(pfmemalloc); C(pp_recycle); n->destructor = NULL; C(tail); C(end); C(head); C(head_frag); C(data); C(truesize); refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); skb->cloned = 1; return n; #undef C } /** * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg * @first: first sk_buff of the msg */ struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) { struct sk_buff *n; n = alloc_skb(0, GFP_ATOMIC); if (!n) return NULL; n->len = first->len; n->data_len = first->len; n->truesize = first->truesize; skb_shinfo(n)->frag_list = first; __copy_skb_header(n, first); n->destructor = NULL; return n; } EXPORT_SYMBOL_GPL(alloc_skb_for_msg); /** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents * * This is identical to skb_clone except that the target skb is * supplied by the user. * * The target skb is returned upon exit. */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { skb_release_all(dst, SKB_CONSUMED); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg, rlim; struct user_struct *user; if (capable(CAP_IPC_LOCK) || !size) return 0; rlim = rlimit(RLIMIT_MEMLOCK); if (rlim == RLIM_INFINITY) return 0; num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ max_pg = rlim >> PAGE_SHIFT; user = mmp->user ? : current_user(); old_pg = atomic_long_read(&user->locked_vm); do { new_pg = old_pg + num_pg; if (new_pg > max_pg) return -ENOBUFS; } while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg)); if (!mmp->user) { mmp->user = get_uid(user); mmp->num_pg = num_pg; } else { mmp->num_pg += num_pg; } return 0; } EXPORT_SYMBOL_GPL(mm_account_pinned_pages); void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size, bool devmem) { struct ubuf_info_msgzc *uarg; struct sk_buff *skb; WARN_ON_ONCE(!in_task()); skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); uarg = (void *)skb->cb; uarg->mmp.user = NULL; if (likely(!devmem) && mm_account_pinned_pages(&uarg->mmp, size)) { kfree_skb(skb); return NULL; } uarg->ubuf.ops = &msg_zerocopy_ubuf_ops; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; uarg->ubuf.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; refcount_set(&uarg->ubuf.refcnt, 1); sock_hold(sk); return &uarg->ubuf; } static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg, bool devmem) { if (uarg) { struct ubuf_info_msgzc *uarg_zc; const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; /* there might be non MSG_ZEROCOPY users */ if (uarg->ops != &msg_zerocopy_ubuf_ops) return NULL; /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ if (!sock_owned_by_user(sk)) { WARN_ON_ONCE(1); return NULL; } uarg_zc = uarg_to_msgzc(uarg); bytelen = uarg_zc->bytelen + size; if (uarg_zc->len == USHRT_MAX - 1 || bytelen > byte_limit) { /* TCP can create new skb to attach new uarg */ if (sk->sk_type == SOCK_STREAM) goto new_alloc; return NULL; } next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg_zc->id + uarg_zc->len) == next) { if (likely(!devmem) && mm_account_pinned_pages(&uarg_zc->mmp, size)) return NULL; uarg_zc->len++; uarg_zc->bytelen = bytelen; atomic_set(&sk->sk_zckey, ++next); /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) net_zcopy_get(uarg); return uarg; } } new_alloc: return msg_zerocopy_alloc(sk, size, devmem); } EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 old_lo, old_hi; u64 sum_len; old_lo = serr->ee.ee_info; old_hi = serr->ee.ee_data; sum_len = old_hi - old_lo + 1ULL + len; if (sum_len >= (1ULL << 32)) return false; if (lo != old_hi + 1) return false; serr->ee.ee_data += len; return true; } static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; bool is_zerocopy; u32 lo, hi; u16 len; mm_unaccount_pinned_pages(&uarg->mmp); /* if !len, there was only 1 call, and it was aborted * so do not queue a completion notification */ if (!uarg->len || sock_flag(sk, SOCK_DEAD)) goto release; len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = 0; serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; spin_lock_irqsave(&q->lock, flags); tail = skb_peek_tail(q); if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY || !skb_zerocopy_notify_extend(tail, lo, len)) { __skb_queue_tail(q, skb); skb = NULL; } spin_unlock_irqrestore(&q->lock, flags); sk_error_report(sk); release: consume_skb(skb); sock_put(sk); } static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg, bool success) { struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg); uarg_zc->zerocopy = uarg_zc->zerocopy & success; if (refcount_dec_and_test(&uarg->refcnt)) __msg_zerocopy_callback(uarg_zc); } void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { struct sock *sk = skb_from_uarg(uarg_to_msgzc(uarg))->sk; atomic_dec(&sk->sk_zckey); uarg_to_msgzc(uarg)->len--; if (have_uref) msg_zerocopy_complete(NULL, uarg, true); } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); const struct ubuf_info_ops msg_zerocopy_ubuf_ops = { .complete = msg_zerocopy_complete, }; EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg, struct net_devmem_dmabuf_binding *binding) { int err, orig_len = skb->len; if (uarg->ops->link_skb) { err = uarg->ops->link_skb(skb, uarg); if (err) return err; } else { struct ubuf_info *orig_uarg = skb_zcopy(skb); /* An skb can only point to one uarg. This edge case happens * when TCP appends to an skb, but zerocopy_realloc triggered * a new alloc. */ if (orig_uarg && uarg != orig_uarg) return -EEXIST; } err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len, binding); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; /* Streams do not free skb on error. Reset to prev state. */ iov_iter_revert(&msg->msg_iter, skb->len - orig_len); skb->sk = sk; ___pskb_trim(skb, orig_len); skb->sk = save_sk; return err; } skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); void __skb_zcopy_downgrade_managed(struct sk_buff *skb) { int i; skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); } EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed); static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { if (skb_zcopy(orig)) { if (skb_zcopy(nskb)) { /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ if (!gfp_mask) { WARN_ON_ONCE(1); return -ENOMEM; } if (skb_uarg(nskb) == skb_uarg(orig)) return 0; if (skb_copy_ubufs(nskb, GFP_ATOMIC)) return -EIO; } skb_zcopy_set(nskb, skb_uarg(orig), NULL); } return 0; } /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. * * Returns 0 on success or a negative error code on failure * to allocate kernel memory to copy to. */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, order, psize, new_frags; u32 d_off; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; if (!skb_frags_readable(skb)) return -EFAULT; if (!num_frags) goto release; /* We might have to allocate high order pages, so compute what minimum * page order is needed. */ order = 0; while ((PAGE_SIZE << order) * MAX_SKB_FRAGS < __skb_pagelen(skb)) order++; psize = (PAGE_SIZE << order); new_frags = (__skb_pagelen(skb) + psize - 1) >> (PAGE_SHIFT + order); for (i = 0; i < new_frags; i++) { page = alloc_pages(gfp_mask | __GFP_COMP, order); if (!page) { while (head) { struct page *next = (struct page *)page_private(head); put_page(head); head = next; } return -ENOMEM; } set_page_private(page, (unsigned long)head); head = page; } page = head; d_off = 0; for (i = 0; i < num_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); while (done < p_len) { if (d_off == psize) { d_off = 0; page = (struct page *)page_private(page); } copy = min_t(u32, psize - d_off, p_len - done); memcpy(page_address(page) + d_off, vaddr + p_off + done, copy); done += copy; d_off += copy; } kunmap_atomic(vaddr); } } /* skb frags release userspace buffers */ for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { __skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize); head = (struct page *)page_private(head); } __skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; release: skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority * * Duplicate an &sk_buff. The new one is not owned by a socket. Both * copies share the same packet data but not structure. The new * buffer has a reference count of 1. If the allocation fails the * function returns %NULL otherwise the new buffer is returned. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. */ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff_fclones *fclones = container_of(skb, struct sk_buff_fclones, skb1); struct sk_buff *n; if (skb_orphan_frags(skb, gfp_mask)) return NULL; if (skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) == 1) { n = &fclones->skb2; refcount_set(&fclones->fclone_ref, 2); n->fclone = SKB_FCLONE_CLONE; } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; n->fclone = SKB_FCLONE_UNAVAILABLE; } return __skb_clone(n, skb); } EXPORT_SYMBOL(skb_clone); void skb_headers_offset_update(struct sk_buff *skb, int off) { /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += off; /* {transport,network,mac}_header and tail are relative to skb->head */ skb->transport_header += off; skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; skb->inner_transport_header += off; skb->inner_network_header += off; skb->inner_mac_header += off; } EXPORT_SYMBOL(skb_headers_offset_update); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { if (skb_pfmemalloc(skb)) return SKB_ALLOC_RX; return 0; } /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data. This is used when the * caller wishes to modify the data and needs a private copy of the * data to alter. Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * As by-product this function converts non-linear &sk_buff to linear * one, so that &sk_buff becomes completely private and caller is allowed * to modify all the data of returned buffer. This means that this * function is not recommended for use in circumstances when only * header is going to be modified. Use pskb_copy() instead. */ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; unsigned int size; int headerlen; if (!skb_frags_readable(skb)) return NULL; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; headerlen = skb_headroom(skb); size = skb_end_offset(skb) + skb->data_len; n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; /* Set the data pointer */ skb_reserve(n, headerlen); /* Set the tail pointer and length */ skb_put(n, skb->len); BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); /** * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy * @headroom: headroom of new skb * @gfp_mask: allocation priority * @fclone: if true allocate the copy of the skb from the fclone * cache instead of the head cache; it is recommended to set this * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when * the caller wishes to modify only header of &sk_buff and needs * private copy of the header to alter. Returns %NULL on failure * or the pointer to the buffer on success. * The returned buffer has a reference count of 1. */ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone) { unsigned int size = skb_headlen(skb) + headroom; int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ skb_copy_from_linear_data(skb, n->data, n->len); n->truesize += skb->data_len; n->data_len = skb->data_len; n->len = skb->len; if (skb_shinfo(skb)->nr_frags) { int i; if (skb_orphan_frags(skb, gfp_mask) || skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; skb_shinfo(n)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } skb_copy_header(n, skb); out: return n; } EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @nhead: room to add at head * @ntail: room to add at tail * @gfp_mask: allocation priority * * Expands (or creates identical copy, if @nhead and @ntail are zero) * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. * * Note: If you skb_push() the start of the buffer after reallocating the * header, call skb_postpush_data_move() first to move the metadata out of * the way before writing to &sk_buff->data. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { unsigned int osize = skb_end_offset(skb); unsigned int size = osize + nhead + ntail; long off; u8 *data; int i; BUG_ON(nhead < 0); BUG_ON(skb_shared(skb)); skb_zcopy_downgrade_managed(skb); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. */ memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); /* * if shinfo is shared we must drop the old head gracefully, but if it * is not we can just drop the old head and let the existing refcount * be since all we did is relocate the values */ if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; if (skb_zcopy(skb)) refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb, SKB_CONSUMED); } else { skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; skb->head_frag = 0; skb->data += off; skb_set_end_offset(skb, size); #ifdef NET_SKBUFF_DATA_USES_OFFSET off = nhead; #endif skb->tail += off; skb_headers_offset_update(skb, nhead); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). */ if (!skb->sk || skb->destructor == sock_edemux) skb->truesize += size - osize; return 0; nofrags: skb_kfree_head(data); nodata: return -ENOMEM; } EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) { struct sk_buff *skb2; int delta = headroom - skb_headroom(skb); if (delta <= 0) skb2 = pskb_copy(skb, GFP_ATOMIC); else { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { kfree_skb(skb2); skb2 = NULL; } } return skb2; } EXPORT_SYMBOL(skb_realloc_headroom); /* Note: We plan to rework this in linux-6.4 */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { unsigned int saved_end_offset, saved_truesize; struct skb_shared_info *shinfo; int res; saved_end_offset = skb_end_offset(skb); saved_truesize = skb->truesize; res = pskb_expand_head(skb, 0, 0, pri); if (res) return res; skb->truesize = saved_truesize; if (likely(skb_end_offset(skb) == saved_end_offset)) return 0; shinfo = skb_shinfo(skb); /* We are about to change back skb->end, * we need to move skb_shinfo() to its new location. */ memmove(skb->head + saved_end_offset, shinfo, offsetof(struct skb_shared_info, frags[shinfo->nr_frags])); skb_set_end_offset(skb, saved_end_offset); return 0; } /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @headroom: needed headroom * * Unlike skb_realloc_headroom, this one does not allocate a new skb * if possible; copies skb->sk to new skb as needed * and frees original skb in case of failures. * * It expect increased headroom and generates warning otherwise. */ struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); int osize = skb_end_offset(skb); struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; delta = SKB_DATA_ALIGN(delta); /* pskb_expand_head() might crash, if skb is shared. */ if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) goto fail; if (sk) skb_set_owner_w(nskb, sk); consume_skb(skb); skb = nskb; } if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) goto fail; if (sk && is_skb_wmem(skb)) { delta = skb_end_offset(skb) - osize; refcount_add(delta, &sk->sk_wmem_alloc); skb->truesize += delta; } return skb; fail: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_expand_head); /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head * @newtailroom: new free bytes at tail * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data and while doing so * allocate additional space. * * This is used when the caller wishes to modify the data and needs a * private copy of the data to alter as well as more space for new fields. * Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask) { /* * Allocate the copy buffer */ int head_copy_len, head_copy_off; struct sk_buff *n; int oldheadroom; if (!skb_frags_readable(skb)) return NULL; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; oldheadroom = skb_headroom(skb); n = __alloc_skb(newheadroom + skb->len + newtailroom, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; skb_reserve(n, newheadroom); /* Set the tail pointer and length */ skb_put(n, skb->len); head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; else head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); return n; } EXPORT_SYMBOL(skb_copy_expand); /** * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error * if @free_on_error is true. */ int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { int err; int ntail; /* If the skbuff is non linear tailroom is always zero.. */ if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); return 0; } ntail = skb->data_len + pad - (skb->end - skb->tail); if (likely(skb_cloned(skb) || ntail > 0)) { err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); if (unlikely(err)) goto free_skb; } /* FIXME: The use of this function with non-linear skb's really needs * to be audited. */ err = skb_linearize(skb); if (unlikely(err)) goto free_skb; memset(skb->data + skb->len, 0, pad); return 0; free_skb: if (free_on_error) kfree_skb(skb); return err; } EXPORT_SYMBOL(__skb_pad); /** * pskb_put - add data to the tail of a potentially fragmented buffer * @skb: start of the buffer to use * @tail: tail fragment of the buffer to use * @len: amount of data to add * * This function extends the used data area of the potentially * fragmented buffer. @tail must be the last fragment of @skb -- or * @skb itself. If this would exceed the total buffer size the kernel * will panic. A pointer to the first byte of the extra data is * returned. */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { if (tail != skb) { skb->data_len += len; skb->len += len; } return skb_put(tail, len); } EXPORT_SYMBOL_GPL(pskb_put); /** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer. If this would * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ void *skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; if (unlikely(skb->tail > skb->end)) skb_over_panic(skb, len, __builtin_return_address(0)); return tmp; } EXPORT_SYMBOL(skb_put); /** * skb_push - add data to the start of a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer at the buffer * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; if (unlikely(skb->data < skb->head)) skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data; } EXPORT_SYMBOL(skb_push); /** * skb_pull - remove data from the start of a buffer * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the next data in the buffer * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ void *skb_pull(struct sk_buff *skb, unsigned int len) { return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); /** * skb_pull_data - remove data from the start of a buffer returning its * original position. * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the original data in the buffer * is returned after checking if there is enough data to pull. Once the * data has been pulled future pushes will overwrite the old data. */ void *skb_pull_data(struct sk_buff *skb, size_t len) { void *data = skb->data; if (skb->len < len) return NULL; skb_pull(skb, len); return data; } EXPORT_SYMBOL(skb_pull_data); /** * skb_trim - remove end from a buffer * @skb: buffer to alter * @len: new length * * Cut the length of a buffer down by removing data from the tail. If * the buffer is already under the length specified it is not modified. * The skb must be linear. */ void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) __skb_trim(skb, len); } EXPORT_SYMBOL(skb_trim); /* Trims skb to length len. It can change skb pointers. */ int ___pskb_trim(struct sk_buff *skb, unsigned int len) { struct sk_buff **fragp; struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; int err; if (skb_cloned(skb) && unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) return err; i = 0; if (offset >= len) goto drop_pages; for (; i < nfrags; i++) { int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); goto done; } for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); fragp = &frag->next) { int end = offset + frag->len; if (skb_shared(frag)) { struct sk_buff *nfrag; nfrag = skb_clone(frag, GFP_ATOMIC); if (unlikely(!nfrag)) return -ENOMEM; nfrag->next = frag->next; consume_skb(frag); frag = nfrag; *fragp = frag; } if (end < len) { offset = end; continue; } if (end > len && unlikely((err = pskb_trim(frag, len - offset)))) return err; if (frag->next) skb_drop_list(&frag->next); break; } done: if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { skb->len = len; skb->data_len = 0; skb_set_tail_pointer(skb, len); } if (!skb_shinfo(skb)->nr_frags && !skb_has_frag_list(skb)) skb->unreadable = 0; if (!skb->sk || skb->destructor == sock_edemux) skb_condense(skb); return 0; } EXPORT_SYMBOL(___pskb_trim); static int pskb_trim_rcsum_complete(struct sk_buff *skb, unsigned int len) { int delta = skb->len - len; if (skb_frags_readable(skb)) { skb->csum = csum_block_sub(skb->csum, skb_checksum(skb, len, delta, 0), len); return 0; } if (len > skb_headlen(skb)) return -EFAULT; /* The trimmed bytes are unreadable, but the remaining packet can be * checksummed by software after trimming. */ skb->ip_summed = CHECKSUM_NONE; return 0; } /* Note : use pskb_trim_rcsum() instead of calling this directly */ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) { int err; err = pskb_trim_rcsum_complete(skb, len); if (err) return err; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len; int offset = skb_checksum_start_offset(skb) + skb->csum_offset; if (offset + sizeof(__sum16) > hdlen) return -EINVAL; } return __pskb_trim(skb, len); } EXPORT_SYMBOL(pskb_trim_rcsum_slow); /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate * @delta: number of bytes to advance tail * * The function makes a sense only on a fragmented &sk_buff, * it expands header moving its tail forward and copying necessary * data from fragmented part. * * &sk_buff MUST have reference count of 1. * * Returns %NULL (and &sk_buff does not change) if pull failed * or value of new tail of skb in the case of success. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ /* Moves tail of skb head forward, copying data from fragmented part, * when it is necessary. * 1. It may fail due to malloc failure. * 2. It may change skb pointers. * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ void *__pskb_pull_tail(struct sk_buff *skb, int delta) { /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough * room at tail, reallocate without expansion only if skb is cloned. */ int i, k, eat = (skb->tail + delta) - skb->end; if (!skb_frags_readable(skb)) return NULL; if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) return NULL; } BUG_ON(skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size >= eat) goto pull_pages; eat -= size; } /* If we need update frag list, we are in troubles. * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. * Pure masohism, indeed. 8)8) */ if (eat) { struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_is_gso(skb) && !list->head_frag && skb_headlen(list)) skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ clone = skb_clone(list, GFP_ATOMIC); if (!clone) return NULL; insp = list->next; list = clone; } else { /* This may be pulled without * problems. */ insp = list; } if (!pskb_pull(list, eat)) { kfree_skb(clone); return NULL; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; skb_shinfo(skb)->frag_list = clone; } } /* Success! Now we may commit changes to skb data. */ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; *frag = skb_shinfo(skb)->frags[i]; if (eat) { skb_frag_off_add(frag, eat); skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; } k++; } } skb_shinfo(skb)->nr_frags = k; end: skb->tail += delta; skb->data_len -= delta; if (!skb->data_len) skb_zcopy_clear(skb, false); return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); /** * skb_copy_bits - copy bits from skb to kernel buffer * @skb: source skb * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source skb to the * destination buffer. * * CAUTION ! : * If its prototype is ever changed, * check arch/{*}/net/{*}.S files, * since it is called from BPF assembly code. */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; /* Copy header. */ if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; to += copy; } if (!skb_frags_readable(skb)) goto fault; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(f, skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_copy_bits(frag_iter, offset - start, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_copy_bits); /* * 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 sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { put_page(spd->pages[i]); } static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) return NULL; *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); memcpy(page_address(pfrag->page) + pfrag->offset, page_address(page) + *offset, *len); *offset = pfrag->offset; pfrag->offset += *len; return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, struct page *page, unsigned int offset) { return spd->nr_pages && spd->pages[spd->nr_pages - 1] == page && (spd->partial[spd->nr_pages - 1].offset + spd->partial[spd->nr_pages - 1].len == offset); } /* * Fill page/offset/length into spd, if it can hold more pages. */ static bool spd_fill_page(struct splice_pipe_desc *spd, struct page *page, unsigned int *len, unsigned int offset, bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { page = linear_to_page(page, len, &offset, sk); if (!page) return true; } if (spd_can_coalesce(spd, page, offset)) { spd->partial[spd->nr_pages - 1].len += *len; return false; } get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; return false; } static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk) { if (!*len) return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; return false; } /* ignore any bits we already processed */ poff += *off; plen -= *off; *off = 0; do { unsigned int flen = min(*len, plen); if (spd_fill_page(spd, page, &flen, poff, linear, sk)) return true; poff += flen; plen -= flen; *len -= flen; if (!*len) return true; } while (plen); return false; } /* * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsigned int *offset, unsigned int *len, struct splice_pipe_desc *spd, struct sock *sk) { struct sk_buff *iter; int seg; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a * fragment, and if the head is not shared with any clones then * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), offset, len, spd, skb_head_is_locked(skb), sk)) return true; /* * then map the fragments */ if (!skb_frags_readable(skb)) return false; for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (WARN_ON_ONCE(!skb_frag_page(f))) return false; if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk)) return true; } skb_walk_frags(skb, iter) { if (*offset >= iter->len) { *offset -= iter->len; continue; } /* __skb_splice_bits() only fails if the output has no room * left, so no point in going over the frag_list for the error * case. */ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) return true; } return false; } /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; int ret = 0; __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); if (spd.nr_pages) ret = splice_to_pipe(pipe, &spd); return ret; } EXPORT_SYMBOL_GPL(skb_splice_bits); static int sendmsg_locked(struct sock *sk, struct msghdr *msg) { struct socket *sock = sk->sk_socket; size_t size = msg_data_left(msg); if (!sock) return -EINVAL; if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); return sock->ops->sendmsg_locked(sk, msg, size); } static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg) { struct socket *sock = sk->sk_socket; if (!sock) return -EINVAL; return sock_sendmsg(sock, msg); } typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg); static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len, sendmsg_func sendmsg, int flags) { int more_hint = sk_is_tcp(sk) ? MSG_MORE : 0; unsigned int orig_len = len; struct sk_buff *head = skb; unsigned short fragidx; int slen, ret; do_frag_list: /* Deal with head data */ while (offset < skb_headlen(skb) && len) { struct kvec kv; struct msghdr msg; slen = min_t(int, len, skb_headlen(skb) - offset); kv.iov_base = skb->data + offset; kv.iov_len = slen; memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT | flags; if (slen < len) msg.msg_flags |= more_hint; iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen); ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked, sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error; offset += ret; len -= ret; } /* All the data was skb head? */ if (!len) goto out; /* Make offset relative to start of frags */ offset -= skb_headlen(skb); /* Find where we are in frag list */ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; if (offset < skb_frag_size(frag)) break; offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { struct bio_vec bvec; struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | flags, }; if (slen < len) msg.msg_flags |= more_hint; bvec_set_page(&bvec, skb_frag_page(frag), slen, skb_frag_off(frag) + offset); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, slen); ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked, sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error; len -= ret; offset += ret; slen -= ret; } offset = 0; } if (len) { /* Process any frag lists */ if (skb == head) { if (skb_has_frag_list(skb)) { skb = skb_shinfo(skb)->frag_list; goto do_frag_list; } } else if (skb->next) { skb = skb->next; goto do_frag_list; } } out: return orig_len - len; error: return orig_len == len ? ret : orig_len - len; } /* Send skb data on a socket. Socket must be locked. */ int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, 0); } EXPORT_SYMBOL_GPL(skb_send_sock_locked); int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, int offset, int len, int flags) { return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, flags); } EXPORT_SYMBOL_GPL(skb_send_sock_locked_with_flags); /* Send skb data on a socket. Socket must be unlocked. */ int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, 0); } /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer * @offset: offset in destination * @from: source buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source buffer to the * destination skb. This function handles all the messy bits of * traversing fragment lists and such. */ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; from += copy; } if (!skb_frags_readable(skb)) goto fault; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_store_bits(frag_iter, offset - start, from, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial(skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; pos = copy; } if (WARN_ON_ONCE(!skb_frags_readable(skb))) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial(vaddr + p_off, p_len, 0); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { __wsum csum2; if (copy > len) copy = len; csum2 = skb_checksum(frag_iter, offset - start, copy, 0); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; __wsum csum = 0; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial_copy_nocheck(skb->data + offset, to, copy); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos = copy; } if (!skb_frags_readable(skb)) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, to + copied, p_len); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { __wsum csum2; int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; csum2 = skb_copy_and_csum_bits(frag_iter, offset - start, to, copy); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_copy_and_csum_bits); #ifdef CONFIG_NET_CRC32C u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; if (copy > 0) { copy = min(copy, len); crc = crc32c(crc, skb->data + offset, copy); len -= copy; if (len == 0) return crc; offset += copy; } if (WARN_ON_ONCE(!skb_frags_readable(skb))) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; copy = min(copy, len); skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); crc = crc32c(crc, vaddr + p_off, p_len); kunmap_atomic(vaddr); } len -= copy; if (len == 0) return crc; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; copy = end - offset; if (copy > 0) { copy = min(copy, len); crc = skb_crc32c(frag_iter, offset - start, copy, crc); len -= copy; if (len == 0) return crc; offset += copy; } start = end; } BUG_ON(len); return crc; } EXPORT_SYMBOL(skb_crc32c); #endif /* CONFIG_NET_CRC32C */ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { __sum16 sum; sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) skb->csum_valid = !sum; return sum; } EXPORT_SYMBOL(__skb_checksum_complete_head); /* This function assumes skb->csum already holds pseudo header's checksum, * which has been changed from the hardware checksum, for example, by * __skb_checksum_validate_complete(). And, the original skb->csum must * have been validated unsuccessfully for CHECKSUM_COMPLETE case. * * It returns non-zero if the recomputed checksum is still invalid, otherwise * zero. The new checksum is stored back into skb->csum unless the skb is * shared. */ __sum16 __skb_checksum_complete(struct sk_buff *skb) { __wsum csum; __sum16 sum; csum = skb_checksum(skb, 0, skb->len, 0); sum = csum_fold(csum_add(skb->csum, csum)); /* This check is inverted, because we already knew the hardware * checksum is invalid before calling this function. So, if the * re-computed checksum is valid instead, then we have a mismatch * between the original skb->csum and skb_checksum(). This means either * the original hardware checksum is incorrect or we screw up skb->csum * when moving skb->data around. */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) { /* Save full packet checksum */ skb->csum = csum; skb->ip_summed = CHECKSUM_COMPLETE; skb->csum_complete_sw = 1; skb->csum_valid = !sum; } return sum; } EXPORT_SYMBOL(__skb_checksum_complete); /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer * * Calculates the amount of linear headroom needed in the 'to' skb passed * into skb_zerocopy(). */ unsigned int skb_zerocopy_headlen(const struct sk_buff *from) { unsigned int hlen = 0; if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); if (!hlen) hlen = from->len; } if (skb_has_frag_list(from)) hlen = from->len; return hlen; } EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); /** * skb_zerocopy - Zero copy skb to skb * @to: destination buffer * @from: source buffer * @len: number of bytes to copy from source buffer * @hlen: size of linear headroom in destination buffer * * Copies up to `len` bytes from `from` to `to` by creating references * to the frags in the source buffer. * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. * * Return value: * 0: everything is OK * -ENOMEM: couldn't orphan frags of @from due to lack of memory * -EFAULT: skb_copy_bits() found some problem with skb geometry */ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); /* dont bother with small payloads */ if (len <= skb_tailroom(to)) return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); if (unlikely(ret)) return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); __skb_fill_netmem_desc(to, 0, page_to_netmem(page), offset, plen); get_page(page); j = 1; len -= plen; } } skb_len_add(to, len + plen); if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { skb_tx_error(from); return -ENOMEM; } skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { int size; if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), len); skb_frag_size_set(&skb_shinfo(to)->frags[j], size); len -= size; skb_frag_ref(to, j); j++; } skb_shinfo(to)->nr_frags = j; return 0; } EXPORT_SYMBOL_GPL(skb_zerocopy); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart); if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum_offset; *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The head item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. The list lock is taken so the function * may be used safely with other locking list functions. The tail item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue_tail(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff_head tmp; unsigned long flags; if (skb_queue_empty_lockless(list)) return; __skb_queue_head_init(&tmp); spin_lock_irqsave(&list->lock, flags); skb_queue_splice_init(list, &tmp); spin_unlock_irqrestore(&list->lock, flags); __skb_queue_purge_reason(&tmp, reason); } EXPORT_SYMBOL(skb_queue_purge_reason); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); sum += skb->truesize; kfree_skb(skb); } return sum; } void skb_errqueue_purge(struct sk_buff_head *list) { struct sk_buff *skb, *next; struct sk_buff_head kill; unsigned long flags; __skb_queue_head_init(&kill); spin_lock_irqsave(&list->lock, flags); skb_queue_walk_safe(list, skb, next) { if (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) continue; __skb_unlink(skb, list); __skb_queue_tail(&kill, skb); } spin_unlock_irqrestore(&list->lock, flags); __skb_queue_purge(&kill); } EXPORT_SYMBOL(skb_errqueue_purge); /** * skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the tail of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * @list: list to use * * Remove a packet from a list. The list locks are taken and this * function is atomic with respect to other list locked calls * * You must know what list the SKB is on. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * @list: list to use * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls. * A buffer cannot be placed on two lists at the same time. */ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_append); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { int i; skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; skb1->unreadable = skb->unreadable; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, int pos) { int i, k = 0; const int nfrags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->len = skb1->data_len = skb->len - len; skb->len = len; skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < len) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; } else skb_shinfo(skb)->nr_frags++; pos += size; } skb_shinfo(skb1)->nr_frags = k; skb1->unreadable = skb->unreadable; } /** * skb_split - Split fragmented skb to two parts at length len. * @skb: the buffer to split * @skb1: the buffer to receive the second part * @len: new length for skb */ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; skb_zcopy_downgrade_managed(skb); skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } EXPORT_SYMBOL(skb_split); /* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here! */ static int skb_prepare_for_shift(struct sk_buff *skb) { return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** * skb_shift - Shifts paged data partially from skb to another * @tgt: buffer into which tail data gets added * @skb: buffer from which the paged data comes from * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. * * Skb cannot include anything else but paged data while tgt is allowed * to have non-paged data as well. * * TODO: full sized shift could be optimized but that would need * specialized skb free'er to handle frags without up-to-date nr_frags. */ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); if (skb_headlen(skb)) return 0; if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0; DEBUG_NET_WARN_ON_ONCE(tgt->pp_recycle != skb->pp_recycle); DEBUG_NET_WARN_ON_ONCE(skb_cmp_decrypted(tgt, skb)); todo = shiftlen; from = 0; to = skb_shinfo(tgt)->nr_frags; fragfrom = &skb_shinfo(skb)->frags[from]; /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; /* All previous frag pointers might be stale! */ fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } from++; } /* Skip full, not-fitting skb to avoid expensive operations */ if ((shiftlen == skb->len) && (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) return 0; if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { if (to == MAX_SKB_FRAGS) return 0; fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; todo -= skb_frag_size(fragfrom); from++; to++; } else { __skb_frag_ref(fragfrom); skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; to++; break; } } /* Ready to "commit" this state change to tgt */ skb_shinfo(tgt)->nr_frags = to; if (merge >= 0) { fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ to = 0; while (from < skb_shinfo(skb)->nr_frags) skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; skb_shinfo(skb)->nr_frags = to; BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); onlymerged: /* Most likely the tgt won't ever need its checksum anymore, skb on * the other hand might need it if it needs to be resent */ tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(tgt)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; skb_len_add(skb, -shiftlen); skb_len_add(tgt, shiftlen); return shiftlen; } /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read * @from: lower offset of data to be read * @to: upper offset of data to be read * @st: state variable * * Initializes the specified state variable. Must be called before * invoking skb_seq_read() for the first time. */ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st) { st->lower_offset = from; st->upper_offset = to; st->root_skb = st->cur_skb = skb; st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; st->frag_off = 0; } EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data * @consumed: number of bytes consumed by the caller so far * @data: destination pointer for data to be returned * @st: state variable * * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st) { unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; if (unlikely(abs_offset >= st->upper_offset)) { if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } return 0; } next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; if (abs_offset < block_limit && !st->frag_data) { *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (!skb_frags_readable(st->cur_skb)) return 0; if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { unsigned int pg_idx, pg_off, pg_sz; frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; pg_idx = 0; pg_off = skb_frag_off(frag); pg_sz = skb_frag_size(frag); if (skb_frag_must_loop(skb_frag_page(frag))) { pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT; pg_off = offset_in_page(pg_off + st->frag_off); pg_sz = min_t(unsigned int, pg_sz - st->frag_off, PAGE_SIZE - pg_off); } block_limit = pg_sz + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx); *data = (u8 *)st->frag_data + pg_off + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->stepped_offset += pg_sz; st->frag_off += pg_sz; if (st->frag_off == skb_frag_size(frag)) { st->frag_off = 0; st->frag_idx++; } } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; } else if (st->cur_skb->next) { st->cur_skb = st->cur_skb->next; st->frag_idx = 0; goto next_skb; } return 0; } EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data * @st: state variable * * Must be called if skb_seq_read() was not called until it * returned 0. */ void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); /** * skb_copy_seq_read() - copy from a skb_seq_state to a buffer * @st: source skb_seq_state * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy @len bytes from @offset bytes into the source @st to the destination * buffer @to. `offset` should increase (or be unchanged) with each subsequent * call to this function. If offset needs to decrease from the previous use `st` * should be reset first. * * Return: 0 on success or -EINVAL if the copy ended early */ int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len) { const u8 *data; u32 sqlen; for (;;) { sqlen = skb_seq_read(offset, &data, st); if (sqlen == 0) return -EINVAL; if (sqlen >= len) { memcpy(to, data, len); return 0; } memcpy(to, data, sqlen); to += sqlen; offset += sqlen; len -= sqlen; } } EXPORT_SYMBOL(skb_copy_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, struct ts_config *conf, struct ts_state *state) { return skb_seq_read(offset, text, TS_SKB_CB(state)); } static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) { skb_abort_seq_read(TS_SKB_CB(state)); } /** * skb_find_text - Find a text pattern in skb data * @skb: the buffer to look in * @from: search offset * @to: search limit * @config: textsearch configuration * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve * subsequent occurrences of the pattern. Returns the offset * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { unsigned int patlen = config->ops->get_pattern_len(config); struct ts_state state; unsigned int ret; BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb)); config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); return (ret + patlen <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags) { int i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < max_frags) { skb_zcopy_downgrade_managed(skb); get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, size); } else { return -EMSGSIZE; } return 0; } EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_pull on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_pull unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { unsigned char *data = skb->data; BUG_ON(len > skb->len); __skb_pull(skb, len); skb_postpull_rcsum(skb, data, len); return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) { skb_frag_t head_frag; struct page *page; page = virt_to_head_page(frag_skb->head); skb_frag_fill_page_desc(&head_frag, page, frag_skb->data - (unsigned char *)page_address(page), skb_headlen(frag_skb)); return head_frag; } struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset) { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int len_diff, err; /* Only skb_gro_receive_list generated skbs arrive here */ DEBUG_NET_WARN_ON_ONCE(!(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)); skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ err = skb_unclone(skb, GFP_ATOMIC); if (err) goto err_linearize; skb_shinfo(skb)->frag_list = NULL; while (list_skb) { nskb = list_skb; list_skb = list_skb->next; DEBUG_NET_WARN_ON_ONCE(nskb->sk); err = 0; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { consume_skb(nskb); nskb = tmp; err = skb_unclone(nskb, GFP_ATOMIC); } else { err = -ENOMEM; } } if (!tail) skb->next = nskb; else tail->next = nskb; if (unlikely(err)) { nskb->next = list_skb; goto err_linearize; } tail = nskb; delta_len += nskb->len; skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; } skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; skb_gso_reset(skb); skb->prev = tail; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto err_linearize; skb_get(skb); return skb; err_linearize: kfree_skb_list(skb->next); skb->next = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(skb_segment_list); /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ struct sk_buff *skb_segment(struct sk_buff *head_skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; struct sk_buff *frag_skb; skb_frag_t *frag; __be16 proto; bool csum, sg; int err = -ENOMEM; int i = 0; int nfrags, pos; if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { struct sk_buff *check_skb; for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { if (skb_headlen(check_skb) && !check_skb->head_frag) { /* gso_size is untrusted, and we have a frag_list with * a linear non head_frag item. * * If head_skb's headlen does not fit requested gso_size, * it means that the frag_list members do NOT terminate * on exact gso_size boundaries. Hence we cannot perform * skb_frag_t page sharing. Therefore we must fallback to * copying the frag_list skbs; we do so by disabling SG. */ features &= ~NETIF_F_SG; break; } } } __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL); sg = !!(features & NETIF_F_SG); csum = !!can_checksum_protocol(features, proto); if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; /* If we get here then all the required * GSO features except frag_list are supported. * Try to split the SKB to multiple GSO SKBs * with no frag_list. * Currently we can do that only when the buffers don't * have a linear part and all the buffers except * the last are of the same length. */ frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { if (frag_len != iter->len && iter->next) goto normal; if (skb_headlen(iter) && !iter->head_frag) goto normal; len -= iter->len; } if (len != frag_len) goto normal; } /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. * Cap len to not accidentally hit GSO_BY_FRAGS. */ partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1) mss *= partial_segs; else partial_segs = 0; } normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); if (skb_orphan_frags(head_skb, GFP_ATOMIC)) return ERR_PTR(-ENOMEM); nfrags = skb_shinfo(head_skb)->nr_frags; frag = skb_shinfo(head_skb)->frags; frag_skb = head_skb; do { struct sk_buff *nskb; skb_frag_t *nskb_frag; int hsize; int size; if (unlikely(mss == GSO_BY_FRAGS)) { len = list_skb->len; } else { len = head_skb->len - offset; if (len > mss) len = mss; } hsize = skb_headlen(head_skb) - offset; if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); nskb = skb_clone(list_skb, GFP_ATOMIC); if (unlikely(!nskb)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; frag++; } list_skb = list_skb->next; if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; } hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) goto err; skb_reserve(nskb, headroom); __skb_put(nskb, doffset); } if (segs) tail->next = nskb; else segs = nskb; tail = nskb; __copy_skb_header(nskb, head_skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { if (!csum) { if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) goto err; } continue; } nskb_frag = skb_shinfo(nskb)->frags; skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); skb_shinfo(nskb)->flags |= (skb_shinfo(head_skb)->flags | skb_shinfo(frag_skb)->flags) & SKBFL_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { if (skb_orphan_frags(list_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, list_skb, GFP_ATOMIC)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; skb_shinfo(nskb)->flags |= skb_shinfo(frag_skb)->flags & SKBFL_SHARED_FRAG; if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { BUG_ON(!list_skb->head_frag); /* to make room for head_frag. */ i--; frag--; } list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS)) { net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); err = -EINVAL; goto err; } *nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag; __skb_frag_ref(nskb_frag); size = skb_frag_size(nskb_frag); if (pos < offset) { skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; frag++; pos += size; } else { skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } nskb_frag++; } skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; perform_csum_check: if (!csum) { if (skb_has_shared_frag(nskb) && __skb_linearize(nskb)) goto err; if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); /* Some callers want to get the end of the list. * Put it in segs->prev to avoid walking the list. * (see validate_xmit_skb_list() for example) */ segs->prev = tail; if (partial_segs) { struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; unsigned short gso_size = skb_shinfo(head_skb)->gso_size; /* Update type to add partial and then remove dodgy if set */ type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL; type &= ~SKB_GSO_DODGY; /* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols. */ for (iter = segs; iter; iter = iter->next) { skb_shinfo(iter)->gso_size = gso_size; skb_shinfo(iter)->gso_segs = partial_segs; skb_shinfo(iter)->gso_type = type; SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset; } if (tail->len - doffset <= gso_size) skb_shinfo(tail)->gso_size = 0; else if (tail != segs) skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size); } /* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment. */ if (head_skb->destructor == sock_wfree) { swap(tail->truesize, head_skb->truesize); swap(tail->destructor, head_skb->destructor); swap(tail->sk, head_skb->sk); } return segs; err: kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info), #endif #ifdef CONFIG_XFRM [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path), #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) [SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow), #endif #if IS_ENABLED(CONFIG_INET_PSP) [SKB_EXT_PSP] = SKB_EXT_CHUNKSIZEOF(struct psp_skb_ext), #endif #if IS_ENABLED(CONFIG_CAN) [SKB_EXT_CAN] = SKB_EXT_CHUNKSIZEOF(struct can_skb_ext), #endif }; static __always_inline __no_profile unsigned int skb_ext_total_length(void) { unsigned int l = SKB_EXT_CHUNKSIZEOF(struct skb_ext); int i; for (i = 0; i < ARRAY_SIZE(skb_ext_type_len); i++) l += skb_ext_type_len[i]; return l; } static noinline void __init __no_profile skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM > 8); BUILD_BUG_ON(skb_ext_total_length() > 255); skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } #else static void skb_extensions_init(void) {} #endif /* The SKB kmem_cache slab is critical for network performance. Never * merge/alias the slab with similar sized objects. This avoids fragmentation * that hurts performance of kmem_cache_{alloc,free}_bulk APIs. */ #ifndef CONFIG_SLUB_TINY #define FLAG_SKB_NO_MERGE SLAB_NO_MERGE #else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */ #define FLAG_SKB_NO_MERGE 0 #endif void __init skb_init(void) { net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| FLAG_SKB_NO_MERGE, offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); skbuff_cache_size = kmem_cache_size(net_hotdata.skbuff_cache); net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, 0, SKB_SMALL_HEAD_HEADROOM, NULL); skb_extensions_init(); } static int __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsigned int recursion_level) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0; if (unlikely(recursion_level >= 24)) return -EMSGSIZE; if (copy > 0) { if (copy > len) copy = len; sg_set_buf(sg, skb->data + offset, copy); elt++; if ((len -= copy) == 0) return elt; offset += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end, ret; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start, copy, recursion_level + 1); if (unlikely(ret < 0)) return ret; elt += ret; if ((len -= copy) == 0) return elt; offset += copy; } start = end; } BUG_ON(len); return elt; } /** * skb_to_sgvec - Fill a scatter-gather list from a socket buffer * @skb: Socket buffer containing the buffers to be mapped * @sg: The scatter-gather list to map into * @offset: The offset into the buffer's contents to start mapping * @len: Length of buffer space to be mapped * * Fill the specified scatter-gather list with mappings/pointers into a * region of the buffer space attached to a socket buffer. Returns either * the number of scatterlist items used, or -EMSGSIZE if the contents * could not fit. */ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len, 0); if (nsg <= 0) return nsg; sg_mark_end(&sg[nsg - 1]); return nsg; } EXPORT_SYMBOL_GPL(skb_to_sgvec); /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after * the first call without calling sg_unmark_end to expend sg list. * * Scenario to use skb_to_sgvec_nomark: * 1. sg_init_table * 2. skb_to_sgvec_nomark(payload1) * 3. skb_to_sgvec_nomark(payload2) * * This is equivalent to: * 1. sg_init_table * 2. skb_to_sgvec(payload1) * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * * When mapping multiple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { return __skb_to_sgvec(skb, sg, offset, len, 0); } EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); /** * skb_cow_data - Check that a socket buffer's data buffers are writable * @skb: The socket buffer to check. * @tailbits: Amount of trailing space to be added * @trailer: Returned pointer to the skb where the @tailbits space begins * * Make sure that the data buffers attached to a socket buffer are * writable. If they are not, private copies are made of the data buffers * and the socket buffer is set to use these instead. * * If @tailbits is given, make sure that there is space to write @tailbits * bytes of data beyond current end of socket buffer. @trailer will be * set to point to the skb in which this space begins. * * The number of scatterlist elements required to completely map the * COW'd and extended socket buffer will be returned. */ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) { int copyflag; int elt; struct sk_buff *skb1, **skb_p; /* If skb is cloned or its head is paged, reallocate * head pulling out all the pages (pages are considered not writable * at the moment even if they are anonymous). */ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && !__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM; /* Easy case. Most of packets will go this way. */ if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more * space, 128 bytes is fair. */ if (skb_tailroom(skb) < tailbits && pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) return -ENOMEM; /* Voila! */ *trailer = skb; return 1; } /* Misery. We are in troubles, going to mincer fragments... */ elt = 1; skb_p = &skb_shinfo(skb)->frag_list; copyflag = 0; while ((skb1 = *skb_p) != NULL) { int ntail = 0; /* The fragment is partially pulled by someone, * this can happen on input. Copy it and everything * after it. */ if (skb_shared(skb1)) copyflag = 1; /* If the skb is the last, worry about trailer. */ if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } if (copyflag || skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ if (ntail == 0) skb2 = skb_copy(skb1, GFP_ATOMIC); else skb2 = skb_copy_expand(skb1, skb_headroom(skb1), ntail, GFP_ATOMIC); if (unlikely(skb2 == NULL)) return -ENOMEM; if (skb1->sk) skb_set_owner_w(skb2, skb1->sk); /* Looking around. Are we still alive? * OK, link new skb, drop old one */ skb2->next = skb1->next; *skb_p = skb2; kfree_skb(skb1); skb1 = skb2; } elt++; *trailer = skb1; skb_p = &skb1->next; } return elt; } EXPORT_SYMBOL_GPL(skb_cow_data); void sock_rmem_free(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); } static void skb_set_err_queue(struct sk_buff *skb) { /* The error-queue test in skb_is_err_queue() matches this marker * with the sock_rmem_free destructor installed by sock_queue_err_skb(). */ skb->pkt_type = PACKET_OUTGOING; BUILD_BUG_ON(PACKET_OUTGOING == 0); } /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); skb_set_err_queue(skb); /* before exiting rcu section, make sure dst is refcounted */ skb_dst_force(skb); skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); static bool is_icmp_err_skb(const struct sk_buff *skb) { return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6); } struct sk_buff *sock_dequeue_err_skb(struct sock *sk) { struct sk_buff_head *q = &sk->sk_error_queue; struct sk_buff *skb, *skb_next = NULL; bool icmp_next = false; unsigned long flags; if (skb_queue_empty_lockless(q)) return NULL; spin_lock_irqsave(&q->lock, flags); skb = __skb_dequeue(q); if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); if (is_icmp_err_skb(skb) && !icmp_next) sk->sk_err = 0; if (skb_next) sk_error_report(sk); return skb; } EXPORT_SYMBOL(sock_dequeue_err_skb); /** * skb_clone_sk - create clone of skb, and take reference to socket * @skb: the skb to clone * * This function creates a clone of a buffer that holds a reference on * sk_refcnt. Buffers created via this function are meant to be * returned using sock_queue_err_skb, or free via kfree_skb. * * When passing buffers allocated with this function to sock_queue_err_skb * it is necessary to wrap the call with sock_hold/sock_put in order to * prevent the socket from being released prior to being enqueued on * the sk_error_queue. */ struct sk_buff *skb_clone_sk(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sk_buff *clone; if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) { sock_put(sk); return NULL; } clone->sk = sk; clone->destructor = sock_efree; return clone; } EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, int tstype, bool opt_stats) { struct sock_exterr_skb *serr; int err; BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) serr->ee.ee_data -= atomic_read(&sk->sk_tskey); } err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); } static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { struct socket *sock; struct file *file; bool ret = false; if (likely(tsonly || READ_ONCE(sock_net(sk)->core.sysctl_tstamp_allow_data))) return true; /* The sk pointer remains valid as long as the skb is. The sk_socket and * file pointer may become NULL if the socket is closed. Both structures * (including file->cred) are RCU freed which means they can be accessed * within a RCU read section. */ rcu_read_lock(); sock = READ_ONCE(sk->sk_socket); if (!sock) goto out; file = READ_ONCE(sock->file); if (!file) goto out; ret = file_ns_capable(file, &init_user_ns, CAP_NET_RAW); out: rcu_read_unlock(); return ret; } void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); return; } err: kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps, int tstype) { switch (tstype) { case SCM_TSTAMP_SCHED: return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP; case SCM_TSTAMP_SND: return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF : SKBTX_SW_TSTAMP); case SCM_TSTAMP_ACK: return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK; case SCM_TSTAMP_COMPLETION: return skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP; } return false; } static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { int op; switch (tstype) { case SCM_TSTAMP_SCHED: op = BPF_SOCK_OPS_TSTAMP_SCHED_CB; break; case SCM_TSTAMP_SND: if (hwtstamps) { op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB; *skb_hwtstamps(skb) = *hwtstamps; } else { op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB; } break; case SCM_TSTAMP_ACK: op = BPF_SOCK_OPS_TSTAMP_ACK_CB; break; default: return; } bpf_skops_tx_timestamping(sk, skb, op); } void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { struct sk_buff *skb; bool tsonly, opt_stats = false; u32 tsflags; if (!sk) return; if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF) skb_tstamp_tx_report_bpf_timestamping(orig_skb, hwtstamps, sk, tstype); if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype)) return; tsflags = READ_ONCE(sk->sk_tsflags); if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk_is_tcp(sk)) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); opt_stats = true; } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { kfree_skb(skb); return; } } if (!skb) return; if (tsonly) { skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags & SKBTX_ANY_TSTAMP; skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; } if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; else __net_timestamp(skb); __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); #ifdef CONFIG_WIRELESS void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } if (err) kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); #endif /* CONFIG_WIRELESS */ /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set * @start: the number of bytes after skb->data to start checksumming. * @off: the offset from start to place the checksum. * * For untrusted partially-checksummed packets, we need to make sure the values * for skb->csum_start and skb->csum_offset are valid so we don't oops. * * This function checks and sets those values and skb->ip_summed: if this * returns false you should drop the packet. */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); u32 csum_start = skb_headroom(skb) + (u32)start; if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) { net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = csum_start; skb->csum_offset = off; skb->transport_header = csum_start; return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, unsigned int max) { if (skb_headlen(skb) >= len) return 0; /* If we need to pullup then pullup to the max, so we * won't need to do it again. */ if (max > skb->len) max = skb->len; if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) return -ENOMEM; if (skb_headlen(skb) < len) return -EPROTO; return 0; } #define MAX_TCP_HDR_LEN (15 * 4) static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { int err; switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; case IPPROTO_UDP: err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), off + sizeof(struct udphdr)); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct udphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &udp_hdr(skb)->check; } return ERR_PTR(-EPROTO); } /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; __sum16 *csum; int err; fragment = false; err = skb_maybe_pull_tail(skb, sizeof(struct iphdr), MAX_IP_HDR_LEN); if (err < 0) goto out; if (ip_is_fragment(ip_hdr(skb))) fragment = true; off = ip_hdrlen(skb); err = -EPROTO; if (fragment) goto out; csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - off, ip_hdr(skb)->protocol, 0); err = 0; out: return err; } /* This value should be large enough to cover a tagged ethernet header plus * an IPv6 header, all options, and a maximal TCP or UDP header. */ #define MAX_IPV6_HDR_LEN 256 #define OPT_HDR(type, skb, off) \ (type *)(skb_network_header(skb) + (off)) static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) { int err; u8 nexthdr; unsigned int off; unsigned int len; bool fragment; bool done; __sum16 *csum; fragment = false; done = false; off = sizeof(struct ipv6hdr); err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); if (err < 0) goto out; nexthdr = ipv6_hdr(skb)->nexthdr; len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { struct ipv6_opt_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ipv6_opt_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { struct ip_auth_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ip_auth_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ip_auth_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_authlen(hp); break; } case IPPROTO_FRAGMENT: { struct frag_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct frag_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct frag_hdr, skb, off); if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) fragment = true; nexthdr = hp->nexthdr; off += sizeof(struct frag_hdr); break; } default: done = true; break; } } err = -EPROTO; if (!done || fragment) goto out; csum = skb_checksum_setup_ip(skb, nexthdr, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - off, nexthdr, 0); err = 0; out: return err; } /** * skb_checksum_setup - set up partial checksum offset * @skb: the skb to set up * @recalculate: if true the pseudo-header checksum will be recalculated */ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) { int err; switch (skb->protocol) { case htons(ETH_P_IP): err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): err = skb_checksum_setup_ipv6(skb, recalculate); break; default: err = -EPROTO; break; } return err; } EXPORT_SYMBOL(skb_checksum_setup); /** * skb_checksum_maybe_trim - maybe trims the given skb * @skb: the skb to check * @transport_len: the data length beyond the network header * * Checks whether the given skb has data beyond the given transport length. * If so, returns a cloned skb trimmed to this transport length. * Otherwise returns the provided skb. Returns NULL in error cases * (e.g. transport_len exceeds skb length or out-of-memory). * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsigned int transport_len) { struct sk_buff *skb_chk; unsigned int len = skb_transport_offset(skb) + transport_len; int ret; if (skb->len < len) return NULL; else if (skb->len == len) return skb; skb_chk = skb_clone(skb, GFP_ATOMIC); if (!skb_chk) return NULL; ret = pskb_trim_rcsum(skb_chk, len); if (ret) { kfree_skb(skb_chk); return NULL; } return skb_chk; } /** * skb_checksum_trimmed - validate checksum of an skb * @skb: the skb to check * @transport_len: the data length beyond the network header * @skb_chkf: checksum function to use * * Applies the given checksum function skb_chkf to the provided skb. * Returns a checked and maybe trimmed skb. Returns NULL on error. * * If the skb has data beyond the given transport length, then a * trimmed & cloned skb is checked and returned. * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)) { struct sk_buff *skb_chk; unsigned int offset = skb_transport_offset(skb); __sum16 ret; skb_chk = skb_checksum_maybe_trim(skb, transport_len); if (!skb_chk) goto err; if (!pskb_may_pull(skb_chk, offset)) goto err; skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); skb_push_rcsum(skb_chk, offset); if (ret) goto err; return skb_chk; err: if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return NULL; } EXPORT_SYMBOL(skb_checksum_trimmed); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } } EXPORT_SYMBOL(kfree_skb_partial); /** * skb_try_coalesce - try to merge skb to prior one * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; if (skb_cloned(to)) return false; /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. In theory we could take full * references if @from is cloned and !@to->pp_recycle but its * tricky (due to potential race with the clone disappearing) and * rare, so not worth dealing with. */ if (to->pp_recycle != from->pp_recycle) return false; if (skb_frags_readable(from) != skb_frags_readable(to)) return false; if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; return true; } to_shinfo = skb_shinfo(to); from_shinfo = skb_shinfo(from); if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; if (skb_headlen(from) != 0) { struct page *page; unsigned int offset; if (to_shinfo->nr_frags + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) return false; delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { if (to_shinfo->nr_frags + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); } WARN_ON_ONCE(delta < len); memcpy(to_shinfo->frags + to_shinfo->nr_frags, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; if (from_shinfo->nr_frags) to_shinfo->flags |= from_shinfo->flags & SKBFL_SHARED_FRAG; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ if (skb_pp_frag_ref(from)) { for (i = 0; i < from_shinfo->nr_frags; i++) __skb_frag_ref(&from_shinfo->frags[i]); } to->truesize += delta; to->len += len; to->data_len += len; *delta_truesize = delta; return true; } EXPORT_SYMBOL(skb_try_coalesce); /** * skb_scrub_packet - scrub an skb * * @skb: buffer to clean * @xnet: packet is crossing netns * * skb_scrub_packet can be used after encapsulating or decapsulating a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in * another namespace (@xnet == true). We have to clear all information in the * skb that could impact namespace isolation. */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif ipvs_reset(skb); if (!xnet) return; skb->mark = 0; skb_clear_tstamp(skb); } EXPORT_SYMBOL_GPL(skb_scrub_packet); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { int mac_len, meta_len; void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } mac_len = skb->data - skb_mac_header(skb); if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) { memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } meta_len = skb_metadata_len(skb); if (meta_len) { meta = skb_metadata_end(skb) - meta_len; memmove(meta + VLAN_HLEN, meta, meta_len); } skb->mac_header += VLAN_HLEN; return skb; } struct sk_buff *skb_vlan_untag(struct sk_buff *skb) { struct vlan_hdr *vhdr; u16 vlan_tci; if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; vlan_tci = ntohs(vhdr->h_vlan_TCI); __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb = skb_reorder_vlan_header(skb); if (unlikely(!skb)) goto err_free; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); return skb; err_free: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_vlan_untag); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) { if (!pskb_may_pull(skb, write_len)) return -ENOMEM; if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; return pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev) { int needed_headroom = dev->needed_headroom; int needed_tailroom = dev->needed_tailroom; /* For tail taggers, we need to pad short frames ourselves, to ensure * that the tail tag does not fail at its role of being at the end of * the packet, once the conduit interface pads the frame. Account for * that pad length here, and pad later. */ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) needed_tailroom += ETH_ZLEN - skb->len; /* skb_headroom() returns unsigned int... */ needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) /* No reallocation needed, yay! */ return 0; return pskb_expand_head(skb, needed_headroom, needed_tailroom, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable_head_tail); /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = skb_ensure_writable(skb, VLAN_ETH_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); vlan_remove_tag(skb, vlan_tci); skb->mac_header += VLAN_HLEN; if (skb_network_offset(skb) < ETH_HLEN) skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return err; } EXPORT_SYMBOL(__skb_vlan_pop); /* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header. */ int skb_vlan_pop(struct sk_buff *skb) { u16 vlan_tci; __be16 vlan_proto; int err; if (likely(skb_vlan_tag_present(skb))) { __vlan_hwaccel_clear_tag(skb); } else { if (unlikely(!eth_type_vlan(skb->protocol))) return 0; err = __skb_vlan_pop(skb, &vlan_tci); if (err) return err; } /* move next vlan tag to hw accel tag */ if (likely(!eth_type_vlan(skb->protocol))) return 0; vlan_proto = skb->protocol; err = __skb_vlan_pop(skb, &vlan_tci); if (unlikely(err)) return err; __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_pop); /* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present). * Expects skb->data at mac header. */ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { if (skb_vlan_tag_present(skb)) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "skb_vlan_push got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; skb->network_header -= VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_push); /** * skb_eth_pop() - Drop the Ethernet header at the head of a packet * * @skb: Socket buffer to modify * * Drop the Ethernet header of @skb. * * Expects that skb->data points to the mac header and that no VLAN tags are * present. * * Returns 0 on success, -errno otherwise. */ int skb_eth_pop(struct sk_buff *skb) { if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || skb_network_offset(skb) < ETH_HLEN) return -EPROTO; skb_pull_rcsum(skb, ETH_HLEN); skb_reset_mac_header(skb); skb_reset_mac_len(skb); return 0; } EXPORT_SYMBOL(skb_eth_pop); /** * skb_eth_push() - Add a new Ethernet header at the head of a packet * * @skb: Socket buffer to modify * @dst: Destination MAC address of the new header * @src: Source MAC address of the new header * * Prepend @skb with a new Ethernet header. * * Expects that skb->data points to the mac header, which must be empty. * * Returns 0 on success, -errno otherwise. */ int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src) { struct ethhdr *eth; int err; if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) return -EPROTO; err = skb_cow_head(skb, sizeof(*eth)); if (err < 0) return err; skb_push(skb, sizeof(*eth)); skb_reset_mac_header(skb); skb_reset_mac_len(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_dest, dst); ether_addr_copy(eth->h_source, src); eth->h_proto = skb->protocol; skb_postpush_rcsum(skb, eth, sizeof(*eth)); return 0; } EXPORT_SYMBOL(skb_eth_push); /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { if (skb->ip_summed == CHECKSUM_COMPLETE) { __be16 diff[] = { ~hdr->h_proto, ethertype }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } hdr->h_proto = ethertype; } /** * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is * ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; if (unlikely(!eth_p_mpls(mpls_proto))) return -EINVAL; /* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) return -EINVAL; err = skb_cow_head(skb, MPLS_HLEN); if (unlikely(err)) return err; if (!skb->inner_protocol) { skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_push); /** * skb_mpls_pop() - pop the outermost MPLS header * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return 0; err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN); skb_mod_eth_type(skb, hdr, next_proto); } skb->protocol = next_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); /** * skb_mpls_update_lse() - modify outermost MPLS header and update csum * * @skb: buffer * @mpls_lse: new MPLS label stack entry to update to * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } mpls_hdr(skb)->label_stack_entry = mpls_lse; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_update_lse); /** * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header * * @skb: buffer * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_dec_ttl(struct sk_buff *skb) { u32 lse; u8 ttl; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) return -ENOMEM; lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) return -EINVAL; lse &= ~MPLS_LS_TTL_MASK; lse |= ttl << MPLS_LS_TTL_SHIFT; return skb_mpls_update_lse(skb, cpu_to_be32(lse)); } EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl); /** * alloc_skb_with_frags - allocate skb with page frags * * @header_len: size of linear part * @data_len: needed length in frags * @order: max page order desired. * @errcode: pointer to error code if any * @gfp_mask: allocation mask * * This can be used to allocate a paged skb, given a maximal order for frags. */ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int order, int *errcode, gfp_t gfp_mask) { unsigned long chunk; struct sk_buff *skb; struct page *page; int nr_frags = 0; *errcode = -EMSGSIZE; if (unlikely(data_len > MAX_SKB_FRAGS * (PAGE_SIZE << order))) return NULL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; while (data_len) { if (nr_frags == MAX_SKB_FRAGS) goto failure; while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order)) order--; if (order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN, order); if (!page) { order--; continue; } } else { page = alloc_page(gfp_mask); if (!page) goto failure; } chunk = min_t(unsigned long, data_len, PAGE_SIZE << order); skb_fill_page_desc(skb, nr_frags, page, 0, chunk); nr_frags++; skb->truesize += (PAGE_SIZE << order); data_len -= chunk; } return skb; failure: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(alloc_skb_with_frags); /* carve out the first off bytes from skb when off < headlen */ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { int i; unsigned int size = skb_end_offset(skb); int new_hlen = headlen - off; u8 *data; if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); /* Copy real data, and all frags */ skb_copy_from_linear_data_offset(skb, off, data, new_hlen); skb->len -= off; /* Remove SKBFL_MANAGED_FRAG_REFS instead of trying to honour it * while refcounting frags below. */ skb_zcopy_downgrade_managed(skb); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { skb_kfree_head(data); return -ENOMEM; } if (skb_zcopy(skb)) net_zcopy_get(skb_zcopy(skb)); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb, SKB_CONSUMED); } else { /* we can reuse existing recount- all we did was * relocate values */ skb_free_head(skb); } skb->head = data; skb->data = data; skb->head_frag = 0; skb_set_end_offset(skb, size); skb_set_tail_pointer(skb, skb_headlen(skb)); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp); /* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve() */ static int pskb_carve_frag_list(struct skb_shared_info *shinfo, int eat, gfp_t gfp_mask) { struct sk_buff *list = shinfo->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (!list) { pr_err("Not enough bytes to eat. Want %d\n", eat); return -EFAULT; } if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_shared(list)) { clone = skb_clone(list, gfp_mask); if (!clone) return -ENOMEM; insp = list->next; list = clone; } else { /* This may be pulled without problems. */ insp = list; } if (pskb_carve(list, eat, gfp_mask) < 0) { kfree_skb(clone); return -ENOMEM; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; shinfo->frag_list = clone; } return 0; } /* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb */ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { int i, k = 0; unsigned int size = skb_end_offset(skb); u8 *data; const int nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo; if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); /* Remove SKBFL_MANAGED_FRAG_REFS instead of trying to honour it * while refcounting frags below. */ skb_zcopy_downgrade_managed(skb); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { skb_kfree_head(data); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); for (i = 0; i < nfrags; i++) { int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + fsize > off) { shinfo->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < off) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); k++; } pos += fsize; } shinfo->nr_frags = k; if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); /* split line is in frag list */ if (k == 0 && pskb_carve_frag_list(shinfo, off - pos, gfp_mask)) { /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); skb_kfree_head(data); return -ENOMEM; } if (skb_zcopy(skb)) net_zcopy_get(skb_zcopy(skb)); skb_release_data(skb, SKB_CONSUMED); skb->head = data; skb->head_frag = 0; skb->data = data; skb_set_end_offset(skb, size); skb_reset_tail_pointer(skb); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; skb->len -= off; skb->data_len = skb->len; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } /* remove len bytes from the beginning of the skb */ static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp) { int headlen = skb_headlen(skb); if (len < headlen) return pskb_carve_inside_header(skb, len, headlen, gfp); else return pskb_carve_inside_nonlinear(skb, len, headlen, gfp); } /* Extract to_copy bytes starting at off from skb, and return this in * a new skb */ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp) { struct sk_buff *clone = skb_clone(skb, gfp); if (!clone) return NULL; if (pskb_carve(clone, off, gfp) < 0 || pskb_trim(clone, to_copy)) { kfree_skb(clone); return NULL; } return clone; } EXPORT_SYMBOL(pskb_extract); /** * skb_condense - try to get rid of fragments/frag_list if possible * @skb: buffer * * Can be used to save memory before skb is added to a busy queue. * If packet has bytes in frags and enough tail room in skb->head, * pull all of them, so that we can free the frags right now and adjust * truesize. * Notes: * We do not reallocate skb->head thus can not fail. * Caller must re-evaluate skb->truesize if needed. */ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || skb_cloned(skb) || !skb_frags_readable(skb)) return; /* Nice, we can free page frag(s) right now */ __pskb_pull_tail(skb, skb->data_len); } /* At this point, skb->truesize might be over estimated, * because skb had a fragment, and fragments do not tell * their truesize. * When we pulled its content into skb->head, fragment * was freed, but __pskb_pull_tail() could not possibly * adjust skb->truesize, not knowing the frag truesize. */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) { return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } /** * __skb_ext_alloc - allocate a new skb extensions storage * * @flags: See kmalloc(). * * Returns the newly allocated pointer. The pointer can later attached to a * skb via __skb_ext_set(). * Note: caller must handle the skb_ext as an opaque data. */ struct skb_ext *__skb_ext_alloc(gfp_t flags) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags); if (new) { memset(new->offset, 0, sizeof(new->offset)); refcount_set(&new->refcnt, 1); } return new; } static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, unsigned int old_active) { struct skb_ext *new; if (refcount_read(&old->refcnt) == 1) return old; new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); if (!new) return NULL; memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE); refcount_set(&new->refcnt, 1); #ifdef CONFIG_XFRM if (old_active & (1 << SKB_EXT_SEC_PATH)) { struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH); unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } #endif #ifdef CONFIG_MCTP_FLOWS if (old_active & (1 << SKB_EXT_MCTP)) { struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP); if (flow->key) refcount_inc(&flow->key->refs); } #endif __skb_ext_put(old); return new; } /** * __skb_ext_set - attach the specified extension storage to this skb * @skb: buffer * @id: extension id * @ext: extension storage previously allocated via __skb_ext_alloc() * * Existing extensions, if any, are cleared. * * Returns the pointer to the extension. */ void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext) { unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); skb_ext_put(skb); newlen = newoff + skb_ext_type_len[id]; ext->chunks = newlen; ext->offset[id] = newoff; skb->extensions = ext; skb->active_extensions = 1 << id; return skb_ext_get_ptr(ext, id); } EXPORT_SYMBOL_NS_GPL(__skb_ext_set, "NETDEV_INTERNAL"); /** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for * * Allocates enough space for the given extension. * If the extension is already present, a pointer to that extension * is returned. * * If the skb was cloned, COW applies and the returned memory can be * modified without changing the extension space of clones buffers. * * Returns pointer to the extension or NULL on allocation failure. */ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *new, *old = NULL; unsigned int newlen, newoff; if (skb->active_extensions) { old = skb->extensions; new = skb_ext_maybe_cow(old, skb->active_extensions); if (!new) return NULL; if (__skb_ext_exist(new, id)) goto set_active; newoff = new->chunks; } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); new = __skb_ext_alloc(GFP_ATOMIC); if (!new) return NULL; } newlen = newoff + skb_ext_type_len[id]; new->chunks = newlen; new->offset[id] = newoff; set_active: skb->slow_gro = 1; skb->extensions = new; skb->active_extensions |= 1 << id; return skb_ext_get_ptr(new, id); } EXPORT_SYMBOL(skb_ext_add); #ifdef CONFIG_XFRM static void skb_ext_put_sp(struct sec_path *sp) { unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_put(sp->xvec[i]); } #endif #ifdef CONFIG_MCTP_FLOWS static void skb_ext_put_mctp(struct mctp_flow *flow) { if (flow->key) mctp_key_unref(flow->key); } #endif void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *ext = skb->extensions; skb->active_extensions &= ~(1 << id); if (skb->active_extensions == 0) { skb->extensions = NULL; __skb_ext_put(ext); #ifdef CONFIG_XFRM } else if (id == SKB_EXT_SEC_PATH && refcount_read(&ext->refcnt) == 1) { struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH); skb_ext_put_sp(sp); sp->len = 0; #endif } } EXPORT_SYMBOL(__skb_ext_del); void __skb_ext_put(struct skb_ext *ext) { /* If this is last clone, nothing can increment * it after check passes. Avoids one atomic op. */ if (refcount_read(&ext->refcnt) == 1) goto free_now; if (!refcount_dec_and_test(&ext->refcnt)) return; free_now: #ifdef CONFIG_XFRM if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH)) skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif #ifdef CONFIG_MCTP_FLOWS if (__skb_ext_exist(ext, SKB_EXT_MCTP)) skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP)); #endif kmem_cache_free(skbuff_ext_cache, ext); } EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ static void kfree_skb_napi_cache(struct sk_buff *skb) { /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } local_bh_disable(); __napi_kfree_skb(skb, SKB_CONSUMED); local_bh_enable(); } DEFINE_STATIC_KEY_FALSE(skb_defer_disable_key); /** * skb_attempt_defer_free - queue skb for remote freeing * @skb: buffer * * Put @skb in a per-cpu list, using the cpu which * allocated the skb/pages to reduce false sharing * and memory zone spinlock contention. */ void skb_attempt_defer_free(struct sk_buff *skb) { struct skb_defer_node *sdn; unsigned long defer_count; unsigned int defer_max; bool kick; int cpu; if (static_branch_unlikely(&skb_defer_disable_key)) goto nodefer; /* zero copy notifications should not be delayed. */ if (skb_zcopy(skb)) goto nodefer; cpu = skb->alloc_cpu; if (cpu == raw_smp_processor_id() || WARN_ON_ONCE(cpu >= nr_cpu_ids) || !cpu_online(cpu)) { nodefer: kfree_skb_napi_cache(skb); return; } DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); DEBUG_NET_WARN_ON_ONCE(skb->destructor); DEBUG_NET_WARN_ON_ONCE(skb_nfct(skb)); sdn = per_cpu_ptr(net_hotdata.skb_defer_nodes, cpu) + numa_node_id(); defer_max = READ_ONCE(net_hotdata.sysctl_skb_defer_max); defer_count = atomic_long_inc_return(&sdn->defer_count); if (defer_count >= defer_max) goto nodefer; llist_add(&skb->ll_node, &sdn->defer_list); /* Send an IPI every time queue reaches half capacity. */ kick = (defer_count - 1) == (defer_max >> 1); /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU * if we are unlucky enough (this seems very unlikely). */ if (unlikely(kick)) kick_defer_list_purge(cpu); } static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, size_t offset, size_t len) { const char *kaddr; __wsum csum; kaddr = kmap_local_page(page); csum = csum_partial(kaddr + offset, len, 0); kunmap_local(kaddr); skb->csum = csum_block_add(skb->csum, csum, skb->len); } /** * skb_splice_from_iter - Splice (or copy) pages to skbuff * @skb: The buffer to add pages to * @iter: Iterator representing the pages to be added * @maxsize: Maximum amount of pages to be added * * This is a common helper function for supporting MSG_SPLICE_PAGES. It * extracts pages from an iterator and adds them to the socket buffer if * possible, copying them to fragments if not possible (such as if they're slab * pages). * * Returns the amount of data spliced/copied or -EMSGSIZE if there's * insufficient space in the buffer to transfer anything. */ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize) { size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags); struct page *pages[8], **ppages = pages; ssize_t spliced = 0, ret = 0; unsigned int i; while (iter->count > 0) { ssize_t space, nr, len; size_t off; ret = -EMSGSIZE; space = frag_limit - skb_shinfo(skb)->nr_frags; if (space < 0) break; /* We might be able to coalesce without increasing nr_frags */ nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages)); len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off); if (len <= 0) { ret = len ?: -EIO; break; } i = 0; do { struct page *page = pages[i++]; size_t part = min_t(size_t, PAGE_SIZE - off, len); ret = -EIO; if (WARN_ON_ONCE(!sendpage_ok(page))) goto out; ret = skb_append_pagefrags(skb, page, off, part, frag_limit); if (ret < 0) { iov_iter_revert(iter, len); goto out; } if (skb->ip_summed == CHECKSUM_NONE) skb_splice_csum_page(skb, page, off, part); off = 0; spliced += part; maxsize -= part; len -= part; } while (len > 0); if (maxsize <= 0) break; } out: skb_len_add(skb, spliced); return spliced ?: ret; } EXPORT_SYMBOL(skb_splice_from_iter); static __always_inline size_t memcpy_from_iter_csum(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { __wsum *csum = priv2; __wsum next = csum_partial_copy_nocheck(iter_from, to + progress, len); *csum = csum_block_add(*csum, next, progress); return 0; } static __always_inline size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { __wsum next, *csum = priv2; next = csum_and_copy_from_user(iter_from, to + progress, len); *csum = csum_block_add(*csum, next, progress); return next ? 0 : len; } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { size_t copied; if (WARN_ON_ONCE(!i->data_source)) return false; copied = iterate_and_advance2(i, bytes, addr, csum, copy_from_user_iter_csum, memcpy_from_iter_csum); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); void __get_netmem(netmem_ref netmem) { struct net_iov *niov = netmem_to_net_iov(netmem); if (net_is_devmem_iov(niov)) net_devmem_get_net_iov(netmem_to_net_iov(netmem)); } EXPORT_SYMBOL(__get_netmem); void __put_netmem(netmem_ref netmem) { struct net_iov *niov = netmem_to_net_iov(netmem); if (net_is_devmem_iov(niov)) net_devmem_put_net_iov(netmem_to_net_iov(netmem)); } EXPORT_SYMBOL(__put_netmem); struct vlan_type_depth __vlan_get_protocol_offset(const struct sk_buff *skb, __be16 type, int mac_offset) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ if (vlan_depth) { if (WARN_ON_ONCE(vlan_depth < VLAN_HLEN)) return (struct vlan_type_depth) { 0 }; vlan_depth -= VLAN_HLEN; } else { vlan_depth = ETH_HLEN; } do { struct vlan_hdr vhdr, *vh; vh = skb_header_pointer(skb, mac_offset + vlan_depth, sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return (struct vlan_type_depth) { 0 }; type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); return (struct vlan_type_depth) { .type = type, .depth = vlan_depth }; } EXPORT_SYMBOL(__vlan_get_protocol_offset); |
| 11 2 11 4 20 3 23 23 23 23 23 3 25 24 6 4 4 23 23 25 25 25 4 21 25 25 25 23 23 11 11 1 11 10 3 6 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 2001-2006 Ian Kent <raven@themaw.net> */ #include <linux/sched/signal.h> #include "autofs_i.h" /* We make this a static variable rather than a part of the superblock; it * is better if we don't reassign numbers easily even across filesystems */ static autofs_wqt_t autofs_next_wait_queue = 1; void autofs_catatonic_mode(struct autofs_sb_info *sbi) { struct autofs_wait_queue *wq, *nwq; mutex_lock(&sbi->wq_mutex); if (sbi->flags & AUTOFS_SBI_CATATONIC) { mutex_unlock(&sbi->wq_mutex); return; } pr_debug("entering catatonic mode\n"); sbi->flags |= AUTOFS_SBI_CATATONIC; wq = sbi->queues; sbi->queues = NULL; /* Erase all wait queues */ while (wq) { nwq = wq->next; wq->status = -ENOENT; /* Magic is gone - report failure */ kfree(wq->name.name - wq->offset); wq->name.name = NULL; wake_up(&wq->queue); if (!--wq->wait_ctr) kfree(wq); wq = nwq; } fput(sbi->pipe); /* Close the pipe */ sbi->pipe = NULL; sbi->pipefd = -1; mutex_unlock(&sbi->wq_mutex); } static int autofs_write(struct autofs_sb_info *sbi, struct file *file, const void *addr, int bytes) { unsigned long sigpipe, flags; const char *data = (const char *)addr; ssize_t wr = 0; sigpipe = sigismember(¤t->pending.signal, SIGPIPE); mutex_lock(&sbi->pipe_mutex); while (bytes) { wr = __kernel_write(file, data, bytes, NULL); if (wr <= 0) break; data += wr; bytes -= wr; } mutex_unlock(&sbi->pipe_mutex); /* Keep the currently executing process from receiving a * SIGPIPE unless it was already supposed to get one */ if (wr == -EPIPE && !sigpipe) { spin_lock_irqsave(¤t->sighand->siglock, flags); sigdelset(¤t->pending.signal, SIGPIPE); recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, flags); } /* if 'wr' returned 0 (impossible) we assume -EIO (safe) */ return bytes == 0 ? 0 : wr < 0 ? wr : -EIO; } static void autofs_notify_daemon(struct autofs_sb_info *sbi, struct autofs_wait_queue *wq, int type) { union { struct autofs_packet_hdr hdr; union autofs_packet_union v4_pkt; union autofs_v5_packet_union v5_pkt; } pkt; struct file *pipe = NULL; size_t pktsz; int ret; pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n", (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type); memset(&pkt, 0, sizeof(pkt)); /* For security reasons */ pkt.hdr.proto_version = sbi->version; pkt.hdr.type = type; switch (type) { /* Kernel protocol v4 missing and expire packets */ case autofs_ptype_missing: { struct autofs_packet_missing *mp = &pkt.v4_pkt.missing; pktsz = sizeof(*mp); mp->wait_queue_token = wq->wait_queue_token; mp->len = wq->name.len; memcpy(mp->name, wq->name.name, wq->name.len); mp->name[wq->name.len] = '\0'; break; } case autofs_ptype_expire_multi: { struct autofs_packet_expire_multi *ep = &pkt.v4_pkt.expire_multi; pktsz = sizeof(*ep); ep->wait_queue_token = wq->wait_queue_token; ep->len = wq->name.len; memcpy(ep->name, wq->name.name, wq->name.len); ep->name[wq->name.len] = '\0'; break; } /* * Kernel protocol v5 packet for handling indirect and direct * mount missing and expire requests */ case autofs_ptype_missing_indirect: case autofs_ptype_expire_indirect: case autofs_ptype_missing_direct: case autofs_ptype_expire_direct: { struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet; struct user_namespace *user_ns = sbi->pipe->f_cred->user_ns; pktsz = sizeof(*packet); packet->wait_queue_token = wq->wait_queue_token; packet->len = wq->name.len; memcpy(packet->name, wq->name.name, wq->name.len); packet->name[wq->name.len] = '\0'; packet->dev = wq->dev; packet->ino = wq->ino; packet->uid = from_kuid_munged(user_ns, wq->uid); packet->gid = from_kgid_munged(user_ns, wq->gid); packet->pid = wq->pid; packet->tgid = wq->tgid; break; } default: pr_warn("bad type %d!\n", type); mutex_unlock(&sbi->wq_mutex); return; } pipe = get_file(sbi->pipe); mutex_unlock(&sbi->wq_mutex); switch (ret = autofs_write(sbi, pipe, &pkt, pktsz)) { case 0: break; case -ENOMEM: case -ERESTARTSYS: /* Just fail this one */ autofs_wait_release(sbi, wq->wait_queue_token, ret); break; default: autofs_catatonic_mode(sbi); break; } fput(pipe); } static struct autofs_wait_queue * autofs_find_wait(struct autofs_sb_info *sbi, const struct qstr *qstr) { struct autofs_wait_queue *wq; for (wq = sbi->queues; wq; wq = wq->next) { if (wq->name.hash == qstr->hash && wq->name.len == qstr->len && wq->name.name && !memcmp(wq->name.name, qstr->name, qstr->len)) break; } return wq; } /* * Check if we have a valid request. * Returns * 1 if the request should continue. * In this case we can return an autofs_wait_queue entry if one is * found or NULL to idicate a new wait needs to be created. * 0 or a negative errno if the request shouldn't continue. */ static int validate_request(struct autofs_wait_queue **wait, struct autofs_sb_info *sbi, const struct qstr *qstr, const struct path *path, enum autofs_notify notify) { struct dentry *dentry = path->dentry; struct autofs_wait_queue *wq; struct autofs_info *ino; if (sbi->flags & AUTOFS_SBI_CATATONIC) return -ENOENT; /* Wait in progress, continue; */ wq = autofs_find_wait(sbi, qstr); if (wq) { *wait = wq; return 1; } *wait = NULL; /* If we don't yet have any info this is a new request */ ino = autofs_dentry_ino(dentry); if (!ino) return 1; /* * If we've been asked to wait on an existing expire (NFY_NONE) * but there is no wait in the queue ... */ if (notify == NFY_NONE) { /* * Either we've betean the pending expire to post it's * wait or it finished while we waited on the mutex. * So we need to wait till either, the wait appears * or the expire finishes. */ while (ino->flags & AUTOFS_INF_EXPIRING) { mutex_unlock(&sbi->wq_mutex); schedule_timeout_interruptible(HZ/10); if (mutex_lock_interruptible(&sbi->wq_mutex)) return -EINTR; if (sbi->flags & AUTOFS_SBI_CATATONIC) return -ENOENT; wq = autofs_find_wait(sbi, qstr); if (wq) { *wait = wq; return 1; } } /* * Not ideal but the status has already gone. Of the two * cases where we wait on NFY_NONE neither depend on the * return status of the wait. */ return 0; } /* * If we've been asked to trigger a mount and the request * completed while we waited on the mutex ... */ if (notify == NFY_MOUNT) { struct dentry *new = NULL; struct path this; int valid = 1; /* * If the dentry was successfully mounted while we slept * on the wait queue mutex we can return success. If it * isn't mounted (doesn't have submounts for the case of * a multi-mount with no mount at it's base) we can * continue on and create a new request. */ if (!IS_ROOT(dentry)) { if (d_unhashed(dentry) && d_really_is_positive(dentry)) { struct dentry *parent = dentry->d_parent; new = d_lookup(parent, &dentry->d_name); if (new) dentry = new; } } this.mnt = path->mnt; this.dentry = dentry; if (path_has_submounts(&this)) valid = 0; if (new) dput(new); return valid; } return 1; } int autofs_wait(struct autofs_sb_info *sbi, const struct path *path, enum autofs_notify notify) { struct dentry *dentry = path->dentry; struct autofs_wait_queue *wq; struct qstr qstr; char *name; int status, ret, type; unsigned int offset = 0; pid_t pid; pid_t tgid; /* In catatonic mode, we don't wait for nobody */ if (sbi->flags & AUTOFS_SBI_CATATONIC) return -ENOENT; /* * Try translating pids to the namespace of the daemon. * * Zero means failure: we are in an unrelated pid namespace. */ pid = task_pid_nr_ns(current, ns_of_pid(sbi->oz_pgrp)); tgid = task_tgid_nr_ns(current, ns_of_pid(sbi->oz_pgrp)); if (pid == 0 || tgid == 0) return -ENOENT; if (d_really_is_negative(dentry)) { /* * A wait for a negative dentry is invalid for certain * cases. A direct or offset mount "always" has its mount * point directory created and so the request dentry must * be positive or the map key doesn't exist. The situation * is very similar for indirect mounts except only dentrys * in the root of the autofs file system may be negative. */ if (autofs_type_trigger(sbi->type)) return -ENOENT; else if (!IS_ROOT(dentry->d_parent)) return -ENOENT; } name = kmalloc(NAME_MAX + 1, GFP_KERNEL); if (!name) return -ENOMEM; /* If this is a direct mount request create a dummy name */ if (IS_ROOT(dentry) && autofs_type_trigger(sbi->type)) { qstr.name = name; qstr.len = sprintf(name, "%p", dentry); } else { char *p = dentry_path_raw(dentry, name, NAME_MAX); if (IS_ERR(p)) { kfree(name); return -ENOENT; } qstr.name = ++p; // skip the leading slash qstr.len = strlen(p); offset = p - name; } qstr.hash = full_name_hash(dentry, qstr.name, qstr.len); if (mutex_lock_interruptible(&sbi->wq_mutex)) { kfree(name); return -EINTR; } ret = validate_request(&wq, sbi, &qstr, path, notify); if (ret <= 0) { if (ret != -EINTR) mutex_unlock(&sbi->wq_mutex); kfree(name); return ret; } if (!wq) { /* Create a new wait queue */ wq = kmalloc_obj(struct autofs_wait_queue); if (!wq) { kfree(name); mutex_unlock(&sbi->wq_mutex); return -ENOMEM; } wq->wait_queue_token = autofs_next_wait_queue; if (++autofs_next_wait_queue == 0) autofs_next_wait_queue = 1; wq->next = sbi->queues; sbi->queues = wq; init_waitqueue_head(&wq->queue); memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->offset = offset; wq->dev = autofs_get_dev(sbi); wq->ino = autofs_get_ino(sbi); wq->uid = current_uid(); wq->gid = current_gid(); wq->pid = pid; wq->tgid = tgid; wq->status = -EINTR; /* Status return if interrupted */ wq->wait_ctr = 2; if (sbi->version < 5) { if (notify == NFY_MOUNT) type = autofs_ptype_missing; else type = autofs_ptype_expire_multi; } else { if (notify == NFY_MOUNT) type = autofs_type_trigger(sbi->type) ? autofs_ptype_missing_direct : autofs_ptype_missing_indirect; else type = autofs_type_trigger(sbi->type) ? autofs_ptype_expire_direct : autofs_ptype_expire_indirect; } pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n", (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, notify); /* * autofs_notify_daemon() may block; it will unlock ->wq_mutex */ autofs_notify_daemon(sbi, wq, type); } else { wq->wait_ctr++; pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n", (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, notify); mutex_unlock(&sbi->wq_mutex); kfree(name); } /* * wq->name.name is NULL iff the lock is already released * or the mount has been made catatonic. */ wait_event_killable(wq->queue, wq->name.name == NULL); status = wq->status; /* * For direct and offset mounts we need to track the requester's * uid and gid in the dentry info struct. This is so it can be * supplied, on request, by the misc device ioctl interface. * This is needed during daemon resatart when reconnecting * to existing, active, autofs mounts. The uid and gid (and * related string values) may be used for macro substitution * in autofs mount maps. */ if (!status) { struct autofs_info *ino; struct dentry *de = NULL; /* direct mount or browsable map */ ino = autofs_dentry_ino(dentry); if (!ino) { /* If not lookup actual dentry used */ de = d_lookup(dentry->d_parent, &dentry->d_name); if (de) ino = autofs_dentry_ino(de); } /* Set mount requester */ if (ino) { spin_lock(&sbi->fs_lock); ino->uid = wq->uid; ino->gid = wq->gid; spin_unlock(&sbi->fs_lock); } if (de) dput(de); } /* Are we the last process to need status? */ mutex_lock(&sbi->wq_mutex); if (!--wq->wait_ctr) kfree(wq); mutex_unlock(&sbi->wq_mutex); return status; } int autofs_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_token, int status) { struct autofs_wait_queue *wq, **wql; mutex_lock(&sbi->wq_mutex); for (wql = &sbi->queues; (wq = *wql) != NULL; wql = &wq->next) { if (wq->wait_queue_token == wait_queue_token) break; } if (!wq) { mutex_unlock(&sbi->wq_mutex); return -EINVAL; } *wql = wq->next; /* Unlink from chain */ kfree(wq->name.name - wq->offset); wq->name.name = NULL; /* Do not wait on this queue */ wq->status = status; wake_up(&wq->queue); if (!--wq->wait_ctr) kfree(wq); mutex_unlock(&sbi->wq_mutex); return 0; } |
| 1 3 1 1 2 12 4 1 9 2 9 3 19 21 2 19 19 8 12 6 4 3 4 7 1 1 5 1 2 2 2 2 2 2 2 2 2 2 4 1 1 1 2 6 1 4 1 750 10 749 750 750 747 71 1 70 18 80 6 74 3 71 1 2 25 1 1 5 5 5 2 3 3 2 3 6 2 2 2 3 3 5 5 12 12 6 10 2 2 3 3 3 5 1 4 4 11 1 6 5 4 8 6 2 8 7 10 9 9 3 1 6 3 1 2 8 8 2 1 5 5 1 4 12 2 1 4 1 5 4 1 3 2 1 1 3 1 2 3 5 5 1 4 4 2 1 1 2 1 48 49 47 47 1 46 2 2 2 2 828 748 808 14 42 39 42 796 794 186 4 4 375 730 730 1 730 686 78 11 76 76 13 1 7 3 1 18 18 14 1 13 1 1 1 13 29 29 20 20 5 20 16 12 29 8 3 3 2 2 1 5 2 2 2 1 705 153 621 152 621 3 706 707 2 684 685 487 692 705 22 1 7 1 11 7 20 20 10 1 9 6 3 32 1 2 3 1 2 26 8 22 4 4 4 11 5 7 7 7 4 2 2 2 1 1 1 4 9 1 9 9 9 2 2 5 2 2 6 1 5 5 1 5 5 1 2 2 5 2 3 11 16 2 14 692 62 36 36 110 81 30 1 30 30 6 4 5 6 12 1 4 3 5 3 4 6 6 4 2 3 1 2 2 3 139 150 150 145 8 136 1 1 135 136 145 14 4 1 2 16 5 9 10 28 28 17 10 10 11 1 1 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/base.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc base directory handling functions * * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. * Instead of using magical inumbers to determine the kind of object * we allocate and fill in-core inodes upon lookup. They don't even * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. * * * Changelog: * 17-Jan-2005 * Allan Bezerra * Bruna Moreira <bruna.moreira@indt.org.br> * Edjard Mota <edjard.mota@indt.org.br> * Ilias Biris <ilias.biris@indt.org.br> * Mauricio Lin <mauricio.lin@indt.org.br> * * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * * A new process specific entry (smaps) included in /proc. It shows the * size of rss for each memory area. The maps entry lacks information * about physical memory size (rss) for each mapped file, i.e., * rss information for executables and library files. * This additional information is useful for any tools that need to know * about physical memory consumption for a process specific library. * * Changelog: * 21-Feb-2005 * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * Pud inclusion in the page table walking. * * ChangeLog: * 10-Mar-2005 * 10LE Instituto Nokia de Tecnologia - INdT: * A better way to walks through the page table as suggested by Hugh Dickins. * * Simo Piiroinen <simo.piiroinen@nokia.com>: * Smaps information related to shared, private, clean and dirty pages. * * Paul Mundt <paul.mundt@nokia.com>: * Overall revision about smaps. */ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/task_io_accounting_ops.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/generic-radix-tree.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> #include <linux/mnt_namespace.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> #include <linux/resource.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/printk.h> #include <linux/cache.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> #include <linux/nsproxy.h> #include <linux/oom.h> #include <linux/elf.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/fs_parser.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/debug.h> #include <linux/sched/exec_state.h> #include <linux/sched/stat.h> #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> #include <linux/cn_proc.h> #include <linux/ksm.h> #include <uapi/linux/lsm.h> #include <trace/events/oom.h> #include "internal.h" #include "fd.h" #include "../../lib/kstrtox.h" /* NOTE: * Implementing inode permission operations in /proc is almost * certainly an error. Permission checks need to happen during * each system call not at open time. The reason is that most of * what we wish to check for permissions in /proc varies at runtime. * * The classic example of a problem is opening file descriptors * in /proc for a task before it execs a suid executable. */ static u8 nlink_tid __ro_after_init; static u8 nlink_tgid __ro_after_init; enum proc_mem_force { PROC_MEM_FORCE_ALWAYS, PROC_MEM_FORCE_PTRACE, PROC_MEM_FORCE_NEVER }; static enum proc_mem_force proc_mem_force_override __ro_after_init = IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : PROC_MEM_FORCE_ALWAYS; static const struct constant_table proc_mem_force_table[] __initconst = { { "always", PROC_MEM_FORCE_ALWAYS }, { "ptrace", PROC_MEM_FORCE_PTRACE }, { "never", PROC_MEM_FORCE_NEVER }, { } }; static int __init early_proc_mem_force_override(char *buf) { if (!buf) return -EINVAL; /* * lookup_constant() defaults to proc_mem_force_override to preseve * the initial Kconfig choice in case an invalid param gets passed. */ proc_mem_force_override = lookup_constant(proc_mem_force_table, buf, proc_mem_force_override); return 0; } early_param("proc_mem.force_override", early_proc_mem_force_override); struct pid_entry { const char *name; unsigned int len; umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op; }; #define NOD(NAME, MODE, IOP, FOP, OP) { \ .name = (NAME), \ .len = sizeof(NAME) - 1, \ .mode = MODE, \ .iop = IOP, \ .fop = FOP, \ .op = OP, \ } #define DIR(NAME, MODE, iops, fops) \ NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} ) #define LNK(NAME, get_link) \ NOD(NAME, (S_IFLNK|S_IRWXUGO), \ &proc_pid_link_inode_operations, NULL, \ { .proc_get_link = get_link } ) #define REG(NAME, MODE, fops) \ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) #define ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } ) #define ATTR(LSMID, NAME, MODE) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_pid_attr_operations, \ { .lsmid = LSMID }) /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. */ static unsigned int __init pid_entry_nlink(const struct pid_entry *entries, unsigned int n) { unsigned int i; unsigned int count; count = 2; for (i = 0; i < n; ++i) { if (S_ISDIR(entries[i].mode)) ++count; } return count; } static int get_task_root(struct task_struct *task, struct path *root) { int result = -ENOENT; task_lock(task); if (task->fs) { get_fs_root(task->fs, root); result = 0; } task_unlock(task); return result; } static int proc_cwd_link(struct dentry *dentry, struct path *path, struct task_struct *task) { int result = -ENOENT; task_lock(task); if (task->fs) { get_fs_pwd(task->fs, path); result = 0; } task_unlock(task); return result; } static int proc_root_link(struct dentry *dentry, struct path *path, struct task_struct *task) { return get_task_root(task, path); } /* * If the user used setproctitle(), we just get the string from * user space at arg_start, and limit it to a maximum of one page. */ static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf, size_t count, unsigned long pos, unsigned long arg_start) { char *page; int ret, got; if (pos >= PAGE_SIZE) return 0; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON); if (got > 0) { int len = strnlen(page, got); /* Include the NUL character if it was found */ if (len < got) len++; if (len > pos) { len -= pos; if (len > count) len = count; len -= copy_to_user(buf, page+pos, len); if (!len) len = -EFAULT; ret = len; } } kfree(page); return ret; } static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, size_t count, loff_t *ppos) { unsigned long arg_start, arg_end, env_start, env_end; unsigned long pos, len; char *page, c; /* Check if process spawned far enough to have cmdline. */ if (!mm->env_end) return 0; spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); if (arg_start >= arg_end) return 0; /* * We allow setproctitle() to overwrite the argument * strings, and overflow past the original end. But * only when it overflows into the environment area. */ if (env_start != arg_end || env_end < env_start) env_start = env_end = arg_end; len = env_end - arg_start; /* We're not going to care if "*ppos" has high bits set */ pos = *ppos; if (pos >= len) return 0; if (count > len - pos) count = len - pos; if (!count) return 0; /* * Magical special case: if the argv[] end byte is not * zero, the user has overwritten it with setproctitle(3). * * Possible future enhancement: do this only once when * pos is 0, and set a flag in the 'struct file'. */ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c) return get_mm_proctitle(mm, buf, count, pos, arg_start); /* * For the non-setproctitle() case we limit things strictly * to the [arg_start, arg_end[ range. */ pos += arg_start; if (pos < arg_start || pos >= arg_end) return 0; if (count > arg_end - pos) count = arg_end - pos; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; len = 0; while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); got = access_remote_vm(mm, pos, page, size, FOLL_ANON); if (got <= 0) break; got -= copy_to_user(buf, page, got); if (unlikely(!got)) { if (!len) len = -EFAULT; break; } pos += got; buf += got; len += got; count -= got; } kfree(page); return len; } static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, size_t count, loff_t *pos) { struct mm_struct *mm; ssize_t ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); return ret; } static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct task_struct *tsk; ssize_t ret; BUG_ON(*pos < 0); tsk = get_proc_task(file_inode(file)); if (!tsk) return -ESRCH; ret = get_task_cmdline(tsk, buf, count, pos); put_task_struct(tsk); if (ret > 0) *pos += ret; return ret; } static const struct file_operations proc_pid_cmdline_ops = { .read = proc_pid_cmdline_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_KALLSYMS /* * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol to user space. */ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto print0; wchan = get_wchan(task); if (wchan && !lookup_symbol_name(wchan, symname)) { seq_puts(m, symname); up_read(&task->signal->exec_update_lock); return 0; } print0: seq_putc(m, '0'); up_read(&task->signal->exec_update_lock); return 0; } #endif /* CONFIG_KALLSYMS */ static int lock_trace(struct task_struct *task) { int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; } static void unlock_trace(struct task_struct *task) { up_read(&task->signal->exec_update_lock); } #ifdef CONFIG_STACKTRACE #define MAX_STACK_TRACE_DEPTH 64 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long *entries; int err; /* * The ability to racily run the kernel stack unwinder on a running task * and then observe the unwinder output is scary; while it is useful for * debugging kernel issues, it can also allow an attacker to leak kernel * stack contents. * Doing this in a manner that is at least safe from races would require * some work to ensure that the remote task can not be scheduled; and * even then, this would still expose the unwinder as local attack * surface. * Therefore, this interface is restricted to root. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; err = lock_trace(task); if (!err) { unsigned int i, nr_entries; nr_entries = stack_trace_save_tsk(task, entries, MAX_STACK_TRACE_DEPTH, 0); for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } kfree(entries); return err; } #endif #ifdef CONFIG_SCHED_INFO /* * Provides /proc/PID/schedstat */ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); return 0; } #endif #ifdef CONFIG_LATENCYTOP static int lstats_show_proc(struct seq_file *m, void *v) { int i; struct inode *inode = m->private; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; seq_puts(m, "Latency Top version : v0.1\n"); for (i = 0; i < LT_SAVECOUNT; i++) { struct latency_record *lr = &task->latency_record[i]; if (lr->backtrace[0]) { int q; seq_printf(m, "%i %li %li", lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; if (!bt) break; seq_printf(m, " %ps", (void *)bt); } seq_putc(m, '\n'); } } put_task_struct(task); return 0; } static int lstats_open(struct inode *inode, struct file *file) { return single_open(file, lstats_show_proc, inode); } static ssize_t lstats_write(struct file *file, const char __user *buf, size_t count, loff_t *offs) { struct task_struct *task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; clear_tsk_latency_tracing(task); put_task_struct(task); return count; } static const struct file_operations proc_lstats_operations = { .open = lstats_open, .read = seq_read, .write = lstats_write, .llseek = seq_lseek, .release = single_release, }; #endif static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; long badness; badness = oom_badness(task, totalpages); /* * Special case OOM_SCORE_ADJ_MIN for all others scale the * badness value into [0, 2000] range which we have been * exporting for a long time so userspace might depend on it. */ if (badness != LONG_MIN) points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3; seq_printf(m, "%lu\n", points); return 0; } struct limit_names { const char *name; const char *unit; }; static const struct limit_names lnames[RLIM_NLIMITS] = { [RLIMIT_CPU] = {"Max cpu time", "seconds"}, [RLIMIT_FSIZE] = {"Max file size", "bytes"}, [RLIMIT_DATA] = {"Max data size", "bytes"}, [RLIMIT_STACK] = {"Max stack size", "bytes"}, [RLIMIT_CORE] = {"Max core file size", "bytes"}, [RLIMIT_RSS] = {"Max resident set", "bytes"}, [RLIMIT_NPROC] = {"Max processes", "processes"}, [RLIMIT_NOFILE] = {"Max open files", "files"}, [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, [RLIMIT_AS] = {"Max address space", "bytes"}, [RLIMIT_LOCKS] = {"Max file locks", "locks"}, [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, [RLIMIT_NICE] = {"Max nice priority", NULL}, [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, }; /* Display limits for a process */ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned int i; unsigned long flags; struct rlimit rlim[RLIM_NLIMITS]; if (!lock_task_sighand(task, &flags)) return 0; memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); unlock_task_sighand(task, &flags); /* * print the file header */ seq_puts(m, "Limit " "Soft Limit " "Hard Limit " "Units \n"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) seq_printf(m, "%-25s %-20s ", lnames[i].name, "unlimited"); else seq_printf(m, "%-25s %-20lu ", lnames[i].name, rlim[i].rlim_cur); if (rlim[i].rlim_max == RLIM_INFINITY) seq_printf(m, "%-20s ", "unlimited"); else seq_printf(m, "%-20lu ", rlim[i].rlim_max); if (lnames[i].unit) seq_printf(m, "%-10s\n", lnames[i].unit); else seq_putc(m, '\n'); } return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct syscall_info info; u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); else if (info.data.nr < 0) seq_printf(m, "%d 0x%llx 0x%llx\n", info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ /************************************************************************/ /* Here the fs part begins */ /************************************************************************/ int proc_nochmod_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); if (attr->ia_valid & ATTR_MODE) return -EPERM; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, attr); return 0; } /* * May current process learn task's sched/cmdline info (for hide_pid_min=1) * or euid/egid (for hide_pid_min=2)? */ static bool has_pid_permissions(struct proc_fs_info *fs_info, struct task_struct *task, enum proc_hidepid hide_pid_min) { /* * If 'hidpid' mount option is set force a ptrace check, * we indicate that we are using a filesystem syscall * by passing PTRACE_MODE_READ_FSCREDS */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); if (fs_info->hide_pid < hide_pid_min) return true; if (in_group_p(fs_info->pid_gid)) return true; return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } static int proc_pid_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; bool has_perms; task = get_proc_task(inode); if (!task) return -ESRCH; has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { if (fs_info->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process * may not stat() a file, it shouldn't be seen * in procfs at all. */ return -ENOENT; } return -EPERM; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_def_inode_operations = { .setattr = proc_nochmod_setattr, }; static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; ret = PROC_I(inode)->op.proc_show(m, ns, pid, task); put_task_struct(task); return ret; } static int proc_single_open(struct inode *inode, struct file *filp) { return single_open(filp, proc_single_show, inode); } static const struct file_operations proc_single_file_operations = { .open = proc_single_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; /* * proc_mem_open() can return errno, NULL or mm_struct*. * * - Returns NULL if the task has no mm (PF_KTHREAD or PF_EXITING) * - Returns mm_struct* on success * - Returns error code on failure */ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) { struct task_struct *task = get_proc_task(inode); struct mm_struct *mm; if (!task) return ERR_PTR(-ESRCH); mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (IS_ERR(mm)) return mm == ERR_PTR(-ESRCH) ? NULL : mm; /* ensure this mm_struct can't be freed */ mmgrab(mm); /* but do not pin its memory */ mmput(mm); return mm; } static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) { struct mm_struct *mm = proc_mem_open(inode, mode); if (IS_ERR_OR_NULL(mm)) return mm ? PTR_ERR(mm) : -ESRCH; file->private_data = mm; return 0; } static int mem_open(struct inode *inode, struct file *file) { if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) return -EINVAL; return __mem_open(inode, file, PTRACE_MODE_ATTACH); } static bool proc_mem_foll_force(struct file *file, struct mm_struct *mm) { struct task_struct *task; bool ptrace_active = false; switch (proc_mem_force_override) { case PROC_MEM_FORCE_NEVER: return false; case PROC_MEM_FORCE_PTRACE: task = get_proc_task(file_inode(file)); if (task) { ptrace_active = READ_ONCE(task->ptrace) && READ_ONCE(task->mm) == mm && READ_ONCE(task->parent) == current; put_task_struct(task); } return ptrace_active; default: return true; } } static ssize_t mem_rw(struct file *file, char __user *buf, size_t count, loff_t *ppos, int write) { struct mm_struct *mm = file->private_data; unsigned long addr = *ppos; ssize_t copied; char *page; unsigned int flags; if (!mm) return 0; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; copied = 0; if (!mmget_not_zero(mm)) goto free; flags = write ? FOLL_WRITE : 0; if (proc_mem_foll_force(file, mm)) flags |= FOLL_FORCE; while (count > 0) { size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; break; } this_len = access_remote_vm(mm, addr, page, this_len, flags); if (!this_len) { if (!copied) copied = -EIO; break; } if (!write && copy_to_user(buf, page, this_len)) { copied = -EFAULT; break; } buf += this_len; addr += this_len; copied += this_len; count -= this_len; } *ppos = addr; mmput(mm); free: kfree(page); return copied; } static ssize_t mem_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, buf, count, ppos, 0); } static ssize_t mem_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, (char __user*)buf, count, ppos, 1); } loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: file->f_pos = offset; break; case 1: file->f_pos += offset; break; default: return -EINVAL; } force_successful_syscall_return(); return file->f_pos; } static int mem_release(struct inode *inode, struct file *file) { struct mm_struct *mm = file->private_data; if (mm) mmdrop(mm); return 0; } static const struct file_operations proc_mem_operations = { .llseek = mem_lseek, .read = mem_read, .write = mem_write, .open = mem_open, .release = mem_release, .fop_flags = FOP_UNSIGNED_OFFSET, }; static int environ_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ); } static ssize_t environ_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *page; unsigned long src = *ppos; int ret = 0; struct mm_struct *mm = file->private_data; unsigned long env_start, env_end; /* Ensure the process spawned far enough to have an environment. */ if (!mm || !mm->env_end) return 0; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; if (!mmget_not_zero(mm)) goto free; spin_lock(&mm->arg_lock); env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); while (count > 0) { size_t this_len, max_len; int retval; if (src >= (env_end - env_start)) break; this_len = env_end - (env_start + src); max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; break; } if (copy_to_user(buf, page, retval)) { ret = -EFAULT; break; } ret += retval; src += retval; buf += retval; count -= retval; } *ppos = src; mmput(mm); free: kfree(page); return ret; } static const struct file_operations proc_environ_operations = { .open = environ_open, .read = environ_read, .llseek = generic_file_llseek, .release = mem_release, }; static int auxv_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); } static ssize_t auxv_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct mm_struct *mm = file->private_data; unsigned int nwords = 0; if (!mm) return 0; do { nwords += 2; } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0])); } static const struct file_operations proc_auxv_operations = { .open = auxv_open, .read = auxv_read, .llseek = generic_file_llseek, .release = mem_release, }; static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; int oom_adj = OOM_ADJUST_MIN; size_t len; if (!task) return -ESRCH; if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) oom_adj = OOM_ADJUST_MAX; else oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); if (oom_adj > OOM_ADJUST_MAX) oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; mutex_lock(&oom_adj_mutex); if (legacy) { if (oom_adj < task->signal->oom_score_adj && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } /* * /proc/pid/oom_adj is provided for legacy purposes, ask users to use * /proc/pid/oom_score_adj instead. */ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); } else { if ((short)oom_adj < task->signal->oom_score_adj_min && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } } /* * Make sure we will check other processes sharing the mm if this is * not vfrok which wants its own oom_score_adj. * pin the mm so it doesn't go away and get reused after task_unlock */ if (!task->vfork_done) { struct task_struct *p = find_lock_task_mm(task); if (p) { if (mm_flags_test(MMF_MULTIPROCESS, p->mm)) { mm = p->mm; mmgrab(mm); } task_unlock(p); } } task->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = (short)oom_adj; trace_oom_score_adj_update(task); if (mm) { struct task_struct *p; rcu_read_lock(); for_each_process(p) { if (same_thread_group(task, p)) continue; /* do not touch kernel threads or the global init */ if (p->flags & PF_KTHREAD || is_global_init(p)) continue; task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; } task_unlock(p); } rcu_read_unlock(); mmdrop(mm); } err_unlock: mutex_unlock(&oom_adj_mutex); put_task_struct(task); return err; } /* * /proc/pid/oom_adj exists solely for backwards compatibility with previous * kernels. The effective policy is defined by oom_score_adj, which has a * different scale: oom_adj grew exponentially and oom_score_adj grows linearly. * Values written to oom_adj are simply mapped linearly to oom_score_adj. * Processes that become oom disabled via oom_adj will still be oom disabled * with this implementation. * * oom_adj cannot be removed since existing userspace binaries use it. */ static ssize_t oom_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_adj); if (err) goto out; if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && oom_adj != OOM_DISABLE) { err = -EINVAL; goto out; } /* * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum * value is always attainable. */ if (oom_adj == OOM_ADJUST_MAX) oom_adj = OOM_SCORE_ADJ_MAX; else oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; err = __set_oom_adj(file, oom_adj, true); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_adj_operations = { .read = oom_adj_read, .write = oom_adj_write, .llseek = generic_file_llseek, }; static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; short oom_score_adj = OOM_SCORE_ADJ_MIN; size_t len; if (!task) return -ESRCH; oom_score_adj = task->signal->oom_score_adj; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_score_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); if (err) goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || oom_score_adj > OOM_SCORE_ADJ_MAX) { err = -EINVAL; goto out; } err = __set_oom_adj(file, oom_score_adj, false); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_score_adj_operations = { .read = oom_score_adj_read, .write = oom_score_adj_write, .llseek = default_llseek, }; #ifdef CONFIG_AUDIT #define TMPBUFLEN 11 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", from_kuid(file->f_cred->user_ns, audit_get_loginuid(task))); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); uid_t loginuid; kuid_t kloginuid; int rv; /* Don't let kthreads write their own loginuid */ if (current->flags & PF_KTHREAD) return -EPERM; rcu_read_lock(); if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { rcu_read_unlock(); return -EPERM; } rcu_read_unlock(); if (*ppos != 0) { /* No partial writes. */ return -EINVAL; } rv = kstrtou32_from_user(buf, count, 10, &loginuid); if (rv < 0) return rv; /* is userspace tring to explicitly UNSET the loginuid? */ if (loginuid == AUDIT_UID_UNSET) { kloginuid = INVALID_UID; } else { kloginuid = make_kuid(file->f_cred->user_ns, loginuid); if (!uid_valid(kloginuid)) return -EINVAL; } rv = audit_set_loginuid(kloginuid); if (rv < 0) return rv; return count; } static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, .llseek = generic_file_llseek, }; static ssize_t proc_sessionid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", audit_get_sessionid(task)); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations proc_sessionid_operations = { .read = proc_sessionid_read, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_FAULT_INJECTION static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; size_t len; int make_it_fail; if (!task) return -ESRCH; make_it_fail = task->make_it_fail; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t proc_fault_inject_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task; char buffer[PROC_NUMBUF] = {}; int make_it_fail; int rv; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; rv = kstrtoint(strstrip(buffer), 0, &make_it_fail); if (rv < 0) return rv; if (make_it_fail < 0 || make_it_fail > 1) return -EINVAL; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->make_it_fail = make_it_fail; put_task_struct(task); return count; } static const struct file_operations proc_fault_inject_operations = { .read = proc_fault_inject_read, .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; int err; unsigned int n; err = kstrtouint_from_user(buf, count, 0, &n); if (err) return err; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->fail_nth = n; put_task_struct(task); return count; } static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; char numbuf[PROC_NUMBUF]; ssize_t len; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; len = snprintf(numbuf, sizeof(numbuf), "%u\n", task->fail_nth); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, numbuf, len); } static const struct file_operations proc_fail_nth_operations = { .read = proc_fail_nth_read, .write = proc_fail_nth_write, }; #endif /* * Print out various scheduling related per-task fields: */ static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_show_task(p, ns, m); put_task_struct(p); return 0; } static ssize_t sched_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_set_task(p); put_task_struct(p); return count; } static int sched_open(struct inode *inode, struct file *filp) { return single_open(filp, sched_show, inode); } static const struct file_operations proc_pid_sched_operations = { .open = sched_open, .read = seq_read, .write = sched_write, .llseek = seq_lseek, .release = single_release, }; #ifdef CONFIG_SCHED_AUTOGROUP /* * Print out autogroup related information: */ static int sched_autogroup_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_autogroup_show_task(p, m); put_task_struct(p); return 0; } static ssize_t sched_autogroup_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[PROC_NUMBUF] = {}; int nice; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; err = kstrtoint(strstrip(buffer), 0, &nice); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; put_task_struct(p); return count; } static int sched_autogroup_open(struct inode *inode, struct file *filp) { int ret; ret = single_open(filp, sched_autogroup_show, NULL); if (!ret) { struct seq_file *m = filp->private_data; m->private = inode; } return ret; } static const struct file_operations proc_pid_sched_autogroup_operations = { .open = sched_autogroup_open, .read = seq_read, .write = sched_autogroup_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_SCHED_AUTOGROUP */ #ifdef CONFIG_TIME_NS static int timens_offsets_show(struct seq_file *m, void *v) { struct task_struct *p; p = get_proc_task(file_inode(m->file)); if (!p) return -ESRCH; proc_timens_show_offsets(p, m); put_task_struct(p); return 0; } static ssize_t timens_offsets_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct proc_timens_offset offsets[2]; char *kbuf = NULL, *pos, *next_line; struct task_struct *p; int ret, noffsets; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* Parse the user data */ ret = -EINVAL; noffsets = 0; for (pos = kbuf; pos; pos = next_line) { struct proc_timens_offset *off = &offsets[noffsets]; char clock[10]; int err; /* Find the end of line and ensure we don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } err = sscanf(pos, "%9s %lld %lu", clock, &off->val.tv_sec, &off->val.tv_nsec); if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC) goto out; clock[sizeof(clock) - 1] = 0; if (strcmp(clock, "monotonic") == 0 || strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0) off->clockid = CLOCK_MONOTONIC; else if (strcmp(clock, "boottime") == 0 || strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0) off->clockid = CLOCK_BOOTTIME; else goto out; noffsets++; if (noffsets == ARRAY_SIZE(offsets)) { if (next_line) count = next_line - kbuf; break; } } ret = -ESRCH; p = get_proc_task(inode); if (!p) goto out; ret = proc_timens_set_offset(file, p, offsets, noffsets); put_task_struct(p); if (ret) goto out; ret = count; out: kfree(kbuf); return ret; } static int timens_offsets_open(struct inode *inode, struct file *filp) { return single_open(filp, timens_offsets_show, inode); } static const struct file_operations proc_timens_offsets_operations = { .open = timens_offsets_open, .read = seq_read, .write = timens_offsets_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_TIME_NS */ static ssize_t comm_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[TASK_COMM_LEN] = {}; const size_t maxlen = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) return -EFAULT; p = get_proc_task(inode); if (!p) return -ESRCH; if (same_thread_group(current, p)) { set_task_comm(p, buffer); proc_comm_connector(p); } else count = -EINVAL; put_task_struct(p); return count; } static int comm_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_task_name(m, p, false); seq_putc(m, '\n'); put_task_struct(p); return 0; } static int comm_open(struct inode *inode, struct file *filp) { return single_open(filp, comm_show, inode); } static const struct file_operations proc_pid_set_comm_operations = { .open = comm_open, .read = seq_read, .write = comm_write, .llseek = seq_lseek, .release = single_release, }; static int proc_exe_link(struct dentry *dentry, struct path *exe_path, struct task_struct *task) { struct file *exe_file; exe_file = get_task_exe_file(task); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); fput(exe_file); return 0; } else return -ENOENT; } static int call_proc_get_link(struct dentry *dentry, struct inode *inode, struct path *path_out) { struct task_struct *task; int ret; task = get_proc_task(inode); if (!task) return -ENOENT; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) goto out_put_task; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { ret = -EACCES; goto out; } ret = PROC_I(inode)->op.proc_get_link(dentry, path_out, task); out: up_read(&task->signal->exec_update_lock); out_put_task: put_task_struct(task); return ret; } static const char *proc_pid_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct path path; int error; if (!dentry) return ERR_PTR(-ECHILD); error = call_proc_get_link(dentry, inode, &path); if (!error) error = nd_jump_link(&path); return ERR_PTR(error); } static int do_proc_readlink(const struct path *path, char __user *buffer, int buflen) { char *tmp = kmalloc(PATH_MAX, GFP_KERNEL); char *pathname; int len; if (!tmp) return -ENOMEM; pathname = d_path(path, tmp, PATH_MAX); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; len = tmp + PATH_MAX - 1 - pathname; if (len > buflen) len = buflen; if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: kfree(tmp); return len; } static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen) { int error = -EACCES; struct inode *inode = d_inode(dentry); struct path path; error = call_proc_get_link(dentry, inode, &path); if (!error) { error = do_proc_readlink(&path, buffer, buflen); path_put(&path); } return error; } const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_pid_get_link, .setattr = proc_nochmod_setattr, }; /* building an inode */ void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid) { /* Depending on the state of dumpable compute who should own a * proc file for a task. */ const struct cred *cred; kuid_t uid; kgid_t gid; if (unlikely(task->flags & PF_KTHREAD)) { *ruid = GLOBAL_ROOT_UID; *rgid = GLOBAL_ROOT_GID; return; } /* Default to the tasks effective ownership */ rcu_read_lock(); cred = __task_cred(task); uid = cred->euid; gid = cred->egid; /* * Before the /proc/pid/status file was created the only way to read * the effective uid of a /process was to stat /proc/pid. Reading * /proc/pid/status is slow enough that procps and other packages * kept stating /proc/pid. To keep the rules in /proc simple I have * made this apply to all per process world readable and executable * directories. */ if (mode != (S_IFDIR | S_IRUGO | S_IXUGO)) { struct task_exec_state *exec_state; exec_state = task_exec_state_rcu(task); if (READ_ONCE(exec_state->dumpable) != TASK_DUMPABLE_OWNER) { uid = make_kuid(exec_state->user_ns, 0); if (!uid_valid(uid)) uid = GLOBAL_ROOT_UID; gid = make_kgid(exec_state->user_ns, 0); if (!gid_valid(gid)) gid = GLOBAL_ROOT_GID; } } rcu_read_unlock(); *ruid = uid; *rgid = gid; } void proc_pid_evict_inode(struct proc_inode *ei) { struct pid *pid = ei->pid; if (S_ISDIR(ei->vfs_inode.i_mode)) { spin_lock(&pid->lock); hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(&pid->lock); } } struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; struct pid *pid; /* We need a new inode */ inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); inode->i_mode = mode; inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); inode->i_op = &proc_def_inode_operations; /* * grab the reference to task. */ pid = get_task_pid(task, PIDTYPE_PID); if (!pid) goto out_unlock; /* Let the pid remember us for quick removal */ ei->pid = pid; task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); out: return inode; out_unlock: iput(inode); return NULL; } /* * Generating an inode and adding it into @pid->inodes, so that task will * invalidate inode's dentry before being released. * * This helper is used for creating dir-type entries under '/proc' and * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' * can be released by invalidating '/proc/<tgid>' dentry. * In theory, dentries under '/proc/<tgid>/task' can also be released by * invalidating '/proc/<tgid>' dentry, we reserve it to handle single * thread exiting situation: Any one of threads should invalidate its * '/proc/<tgid>/task/<pid>' dentry before released. */ static struct inode *proc_pid_make_base_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode *inode; struct proc_inode *ei; struct pid *pid; inode = proc_pid_make_inode(sb, task, mode); if (!inode) return NULL; /* Let proc_flush_pid find this directory inode */ ei = PROC_I(inode); pid = ei->pid; spin_lock(&pid->lock); hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); spin_unlock(&pid->lock); return inode; } int pid_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, * it only makes getattr() consistent with readdir(). */ return -ENOENT; } task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid); } rcu_read_unlock(); return 0; } /* dentry stuff */ /* * Set <pid>/... inode ownership (can change due to setuid(), etc.) */ void pid_update_inode(struct task_struct *task, struct inode *inode) { task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); } /* * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * */ static int pid_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; int ret = 0; rcu_read_lock(); inode = d_inode_rcu(dentry); if (!inode) goto out; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { pid_update_inode(task, inode); ret = 1; } out: rcu_read_unlock(); return ret; } static inline bool proc_inode_is_dead(struct inode *inode) { return !proc_pid(inode)->tasks[PIDTYPE_PID].first; } int pid_delete_dentry(const struct dentry *dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ return proc_inode_is_dead(d_inode(dentry)); } const struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; /* Lookups */ /* * Fill a directory entry. * * If possible create the dcache entry and derive our inode number and * file type from dcache entry. * * Since all of the proc inode numbers are dynamically generated, the inode * numbers do not exist until the inode is cache. This means creating * the dcache entry in readdir is necessary to keep the inode numbers * reported by readdir in sync with the inode numbers reported * by stat. */ bool proc_fill_cache(struct file *file, struct dir_context *ctx, const char *name, unsigned int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = file->f_path.dentry; struct qstr qname = QSTR_INIT(name, len); struct inode *inode; unsigned type = DT_UNKNOWN; ino_t ino = 1; child = try_lookup_noperm(&qname, dir); if (IS_ERR(child)) goto end_instantiate; if (!child) { child = d_alloc_parallel(dir, &qname); if (IS_ERR(child)) goto end_instantiate; if (d_in_lookup(child)) { struct dentry *res; res = instantiate(child, task, ptr); d_lookup_done(child); if (unlikely(res)) { dput(child); child = res; if (IS_ERR(child)) goto end_instantiate; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; dput(child); end_instantiate: return dir_emit(ctx, name, len, ino, type); } /* * dname_to_vma_addr - maps a dentry name into two unsigned longs * which represent vma start and end addresses. */ static int dname_to_vma_addr(struct dentry *dentry, unsigned long *start, unsigned long *end) { const char *str = dentry->d_name.name; unsigned long long sval, eval; unsigned int len; if (str[0] == '0' && str[1] != '-') return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (sval != (unsigned long)sval) return -EINVAL; str += len; if (*str != '-') return -EINVAL; str++; if (str[0] == '0' && str[1]) return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (eval != (unsigned long)eval) return -EINVAL; str += len; if (*str != '\0') return -EINVAL; *start = sval; *end = eval; return 0; } static int map_files_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; struct mm_struct *mm = NULL; struct task_struct *task; struct inode *inode; int status = 0; if (flags & LOOKUP_RCU) return -ECHILD; inode = d_inode(dentry); task = get_proc_task(inode); if (!task) goto out_notask; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { status = mmap_read_lock_killable(mm); if (!status) { exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); mmap_read_unlock(mm); } } mmput(mm); if (exact_vma_exists) { task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); status = 1; } out: put_task_struct(task); out_notask: return status; } static const struct dentry_operations tid_map_files_dentry_operations = { .d_revalidate = map_files_d_revalidate, .d_delete = pid_delete_dentry, }; static int map_files_get_link(struct dentry *dentry, struct path *path, struct task_struct *task) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct mm_struct *mm; int rc; rc = -ENOENT; mm = get_task_mm(task); if (!mm) goto out; rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); if (rc) goto out_mmput; rc = mmap_read_lock_killable(mm); if (rc) goto out_mmput; rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { *path = *file_user_path(vma->vm_file); path_get(path); rc = 0; } mmap_read_unlock(mm); out_mmput: mmput(mm); out: return rc; } struct map_files_info { unsigned long start; unsigned long end; fmode_t mode; }; /* * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due * to concerns about how the symlinks may be used to bypass permissions on * ancestor directories in the path to the file in question. */ static const char * proc_map_files_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { if (!checkpoint_restore_ns_capable(&init_user_ns)) return ERR_PTR(-EPERM); return proc_pid_get_link(dentry, inode, done); } /* * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_map_files_get_link, .setattr = proc_nochmod_setattr, }; static struct dentry * proc_map_files_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { fmode_t mode = (fmode_t)(unsigned long)ptr; struct proc_inode *ei; struct inode *inode; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | ((mode & FMODE_READ ) ? S_IRUSR : 0) | ((mode & FMODE_WRITE) ? S_IWUSR : 0)); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; return proc_splice_unmountable(inode, dentry, &tid_map_files_dentry_operations); } static struct dentry *proc_map_files_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct dentry *result; struct mm_struct *mm; result = ERR_PTR(-ENOENT); task = get_proc_task(dir); if (!task) goto out; result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) goto out_put_task; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) { result = ERR_CAST(mm); goto out_put_task; } result = ERR_PTR(-EINTR); if (mmap_read_lock_killable(mm)) goto out_put_mm; result = ERR_PTR(-ENOENT); vma = find_exact_vma(mm, vm_start, vm_end); if (!vma) goto out_no_vma; if (vma->vm_file) result = proc_map_files_instantiate(dentry, task, (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: mmap_read_unlock(mm); out_put_mm: mmput(mm); out_put_task: put_task_struct(task); out: return result; } static const struct inode_operations proc_map_files_inode_operations = { .lookup = proc_map_files_lookup, .permission = proc_fd_permission, .setattr = proc_nochmod_setattr, }; static int proc_map_files_readdir(struct file *file, struct dir_context *ctx) { struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; unsigned long nr_files, pos, i; GENRADIX(struct map_files_info) fa; struct map_files_info *p; int ret; struct vma_iterator vmi; genradix_init(&fa); ret = -ENOENT; task = get_proc_task(file_inode(file)); if (!task) goto out; ret = 0; if (!dir_emit_dots(file, ctx)) goto out_put_task; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) { ret = PTR_ERR(mm); /* if the task has no mm, the directory should just be empty */ if (ret == -ESRCH) ret = 0; goto out_put_task; } ret = mmap_read_lock_killable(mm); if (ret) goto out_put_mm; nr_files = 0; /* * We need two passes here: * * 1) Collect vmas of mapped files with mmap_lock taken * 2) Release mmap_lock and instantiate entries * * otherwise we get lockdep complained, since filldir() * routine might require mmap_lock taken in might_fault(). */ pos = 2; vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (++pos <= ctx->pos) continue; p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL); if (!p) { ret = -ENOMEM; mmap_read_unlock(mm); goto out_put_mm; } p->start = vma->vm_start; p->end = vma->vm_end; p->mode = vma->vm_file->f_mode; } mmap_read_unlock(mm); for (i = 0; i < nr_files; i++) { char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ unsigned int len; p = genradix_ptr(&fa, i); len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end); if (!proc_fill_cache(file, ctx, buf, len, proc_map_files_instantiate, task, (void *)(unsigned long)p->mode)) break; ctx->pos++; } out_put_mm: mmput(mm); out_put_task: put_task_struct(task); out: genradix_free(&fa); return ret; } static const struct file_operations proc_map_files_operations = { .read = generic_read_dir, .iterate_shared = proc_map_files_readdir, .llseek = generic_file_llseek, }; #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; struct pid_namespace *ns; }; static void *timers_start(struct seq_file *m, loff_t *pos) { struct timers_private *tp = m->private; tp->task = get_pid_task(tp->pid, PIDTYPE_PID); if (!tp->task) return ERR_PTR(-ESRCH); rcu_read_lock(); return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; return seq_hlist_next_rcu(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) { struct timers_private *tp = m->private; if (tp->task) { put_task_struct(tp->task); tp->task = NULL; rcu_read_unlock(); } } static int show_timer(struct seq_file *m, void *v) { static const char * const nstr[] = { [SIGEV_SIGNAL] = "signal", [SIGEV_NONE] = "none", [SIGEV_THREAD] = "thread", }; struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); struct timers_private *tp = m->private; int notify = timer->it_sigev_notify; guard(spinlock_irq)(&timer->it_lock); if (!posixtimer_valid(timer)) return 0; seq_printf(m, "ID: %d\n", timer->it_id); seq_printf(m, "signal: %d/%px\n", timer->sigq.info.si_signo, timer->sigq.info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", pid_nr_ns(timer->it_pid, tp->ns)); seq_printf(m, "ClockID: %d\n", timer->it_clock); return 0; } static const struct seq_operations proc_timers_seq_ops = { .start = timers_start, .next = timers_next, .stop = timers_stop, .show = show_timer, }; static int proc_timers_open(struct inode *inode, struct file *file) { struct timers_private *tp; tp = __seq_open_private(file, &proc_timers_seq_ops, sizeof(struct timers_private)); if (!tp) return -ENOMEM; tp->pid = proc_pid(inode); tp->ns = proc_pid_ns(inode->i_sb); return 0; } static const struct file_operations proc_timers_operations = { .open = proc_timers_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; #endif static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; u64 slack_ns; int err; err = kstrtoull_from_user(buf, count, 10, &slack_ns); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); count = -EPERM; goto out; } rcu_read_unlock(); err = security_task_setscheduler(p); if (err) { count = err; goto out; } } task_lock(p); if (rt_or_dl_task_policy(p)) slack_ns = 0; else if (slack_ns == 0) slack_ns = p->default_timer_slack_ns; p->timer_slack_ns = slack_ns; task_unlock(p); out: put_task_struct(p); return count; } static int timerslack_ns_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; int err = 0; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; goto out; } rcu_read_unlock(); err = security_task_getscheduler(p); if (err) goto out; } task_lock(p); seq_printf(m, "%llu\n", p->timer_slack_ns); task_unlock(p); out: put_task_struct(p); return err; } static int timerslack_ns_open(struct inode *inode, struct file *filp) { return single_open(filp, timerslack_ns_show, inode); } static const struct file_operations proc_pid_set_timerslack_ns_operations = { .open = timerslack_ns_open, .read = seq_read, .write = timerslack_ns_write, .llseek = seq_lseek, .release = single_release, }; static struct dentry *proc_pident_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct pid_entry *p = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, p->mode); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); if (S_ISDIR(inode->i_mode)) set_nlink(inode, 2); /* Use getattr to fix if necessary */ if (p->iop) inode->i_op = p->iop; if (p->fop) inode->i_fop = p->fop; ei->op = p->op; pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static struct dentry *proc_pident_lookup(struct inode *dir, struct dentry *dentry, const struct pid_entry *p, const struct pid_entry *end) { struct task_struct *task = get_proc_task(dir); struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; /* * Yes, it does not scale. And it should not. Don't add * new entries into /proc/<tgid>/ without very good reasons. */ for (; p < end; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) { res = proc_pident_instantiate(dentry, task, p); break; } } put_task_struct(task); out_no_task: return res; } static int proc_pident_readdir(struct file *file, struct dir_context *ctx, const struct pid_entry *ents, unsigned int nents) { struct task_struct *task = get_proc_task(file_inode(file)); const struct pid_entry *p; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= nents + 2) goto out; for (p = ents + (ctx->pos - 2); p < ents + nents; p++) { if (!proc_fill_cache(file, ctx, p->name, p->len, proc_pident_instantiate, task, p)) break; ctx->pos++; } out: put_task_struct(task); return 0; } #ifdef CONFIG_SECURITY static int proc_pid_attr_open(struct inode *inode, struct file *file) { file->private_data = NULL; __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); return 0; } static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); char *p = NULL; ssize_t length; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; length = security_getprocattr(task, PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, &p); put_task_struct(task); if (length > 0) length = simple_read_from_buffer(buf, count, ppos, p, length); kfree(p); return length; } static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task; void *page; int rv; /* A task may only write when it was the opener. */ if (file->private_data != current->mm) return -EPERM; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { rcu_read_unlock(); return -ESRCH; } /* A task may only write its own attributes. */ if (current != task) { rcu_read_unlock(); return -EACCES; } /* Prevent changes to overridden credentials. */ if (current_cred() != current_real_cred()) { rcu_read_unlock(); return -EBUSY; } rcu_read_unlock(); if (count > PAGE_SIZE) count = PAGE_SIZE; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user(buf, count); if (IS_ERR(page)) { rv = PTR_ERR(page); goto out; } /* Guard against adverse ptrace interaction */ rv = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); if (rv < 0) goto out_free; rv = security_setprocattr(PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, page, count); mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); out: return rv; } static const struct file_operations proc_pid_attr_operations = { .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, .release = mem_release, }; #define LSM_DIR_OPS(LSM) \ static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ struct dir_context *ctx) \ { \ return proc_pident_readdir(filp, ctx, \ LSM##_attr_dir_stuff, \ ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct file_operations proc_##LSM##_attr_dir_ops = { \ .read = generic_read_dir, \ .iterate_shared = proc_##LSM##_attr_dir_iterate, \ .llseek = default_llseek, \ }; \ \ static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \ struct dentry *dentry, unsigned int flags) \ { \ return proc_pident_lookup(dir, dentry, \ LSM##_attr_dir_stuff, \ LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \ .lookup = proc_##LSM##_attr_dir_lookup, \ .getattr = pid_getattr, \ .setattr = proc_nochmod_setattr, \ } #ifdef CONFIG_SECURITY_SMACK static const struct pid_entry smack_attr_dir_stuff[] = { ATTR(LSM_ID_SMACK, "current", 0666), }; LSM_DIR_OPS(smack); #endif #ifdef CONFIG_SECURITY_APPARMOR static const struct pid_entry apparmor_attr_dir_stuff[] = { ATTR(LSM_ID_APPARMOR, "current", 0666), ATTR(LSM_ID_APPARMOR, "prev", 0444), ATTR(LSM_ID_APPARMOR, "exec", 0666), }; LSM_DIR_OPS(apparmor); #endif static const struct pid_entry attr_dir_stuff[] = { ATTR(LSM_ID_UNDEF, "current", 0666), ATTR(LSM_ID_UNDEF, "prev", 0444), ATTR(LSM_ID_UNDEF, "exec", 0666), ATTR(LSM_ID_UNDEF, "fscreate", 0666), ATTR(LSM_ID_UNDEF, "keycreate", 0666), ATTR(LSM_ID_UNDEF, "sockcreate", 0666), #ifdef CONFIG_SECURITY_SMACK DIR("smack", 0555, proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), #endif #ifdef CONFIG_SECURITY_APPARMOR DIR("apparmor", 0555, proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops), #endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); } static const struct file_operations proc_attr_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_attr_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, attr_dir_stuff, attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff)); } static const struct inode_operations proc_attr_dir_inode_operations = { .lookup = proc_attr_dir_lookup, .getattr = pid_getattr, .setattr = proc_nochmod_setattr, }; #endif #ifdef CONFIG_ELF_CORE static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; char buffer[PROC_NUMBUF]; size_t len; int ret; if (!task) return -ESRCH; ret = 0; mm = get_task_mm(task); if (mm) { unsigned long flags = __mm_flags_get_word(mm); len = snprintf(buffer, sizeof(buffer), "%08lx\n", ((flags & MMF_DUMP_FILTER_MASK) >> MMF_DUMP_FILTER_SHIFT)); mmput(mm); ret = simple_read_from_buffer(buf, count, ppos, buffer, len); } put_task_struct(task); return ret; } static ssize_t proc_coredump_filter_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; struct mm_struct *mm; unsigned int val; int ret; int i; unsigned long mask; ret = kstrtouint_from_user(buf, count, 0, &val); if (ret < 0) return ret; ret = -ESRCH; task = get_proc_task(file_inode(file)); if (!task) goto out_no_task; mm = get_task_mm(task); if (!mm) goto out_no_mm; ret = 0; for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { if (val & mask) mm_flags_set(i + MMF_DUMP_FILTER_SHIFT, mm); else mm_flags_clear(i + MMF_DUMP_FILTER_SHIFT, mm); } mmput(mm); out_no_mm: put_task_struct(task); out_no_task: if (ret < 0) return ret; return count; } static const struct file_operations proc_coredump_filter_operations = { .read = proc_coredump_filter_read, .write = proc_coredump_filter_write, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_TASK_IO_ACCOUNTING static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole) { struct task_io_accounting acct; int result; result = down_read_killable(&task->signal->exec_update_lock); if (result) return result; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } if (whole) { struct signal_struct *sig = task->signal; struct task_struct *t; guard(rcu)(); scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) { acct = sig->ioac; __for_each_thread(sig, t) task_io_accounting_add(&acct, &t->ioac); } } else { acct = task->ioac; } seq_printf(m, "rchar: %llu\n" "wchar: %llu\n" "syscr: %llu\n" "syscw: %llu\n" "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", (unsigned long long)acct.rchar, (unsigned long long)acct.wchar, (unsigned long long)acct.syscr, (unsigned long long)acct.syscw, (unsigned long long)acct.read_bytes, (unsigned long long)acct.write_bytes, (unsigned long long)acct.cancelled_write_bytes); result = 0; out_unlock: up_read(&task->signal->exec_update_lock); return result; } static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 0); } static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 1); } #endif /* CONFIG_TASK_IO_ACCOUNTING */ #ifdef CONFIG_USER_NS static int proc_id_map_open(struct inode *inode, struct file *file, const struct seq_operations *seq_ops) { struct user_namespace *ns = NULL; struct task_struct *task; struct seq_file *seq; int ret = -EINVAL; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; ret = seq_open(file, seq_ops); if (ret) goto err_put_ns; seq = file->private_data; seq->private = ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_id_map_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; put_user_ns(ns); return seq_release(inode, file); } static int proc_uid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_uid_seq_operations); } static int proc_gid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_gid_seq_operations); } static int proc_projid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_projid_seq_operations); } static const struct file_operations proc_uid_map_operations = { .open = proc_uid_map_open, .write = proc_uid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_gid_map_operations = { .open = proc_gid_map_open, .write = proc_gid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_projid_map_operations = { .open = proc_projid_map_open, .write = proc_projid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static int proc_setgroups_open(struct inode *inode, struct file *file) { struct user_namespace *ns = NULL; struct task_struct *task; int ret; ret = -ESRCH; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; if (file->f_mode & FMODE_WRITE) { ret = -EACCES; if (!ns_capable(ns, CAP_SYS_ADMIN)) goto err_put_ns; } ret = single_open(file, &proc_setgroups_show, ns); if (ret) goto err_put_ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_setgroups_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; int ret = single_release(inode, file); put_user_ns(ns); return ret; } static const struct file_operations proc_setgroups_operations = { .open = proc_setgroups_open, .write = proc_setgroups_write, .read = seq_read, .llseek = seq_lseek, .release = proc_setgroups_release, }; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { int err = lock_trace(task); if (!err) { seq_printf(m, "%08x\n", task->personality); unlock_trace(task); } return err; } #ifdef CONFIG_LIVEPATCH static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { seq_printf(m, "%d\n", task->patch_state); return 0; } #endif /* CONFIG_LIVEPATCH */ #ifdef CONFIG_KSM static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; mm = get_task_mm(task); if (mm) { seq_printf(m, "%lu\n", mm->ksm_merging_pages); mmput(mm); } return 0; } static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; int ret = 0; mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); seq_printf(m, "ksm_merge_any: %s\n", mm_flags_test(MMF_VM_MERGE_ANY, mm) ? "yes" : "no"); ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); return ret; } seq_printf(m, "ksm_mergeable: %s\n", ksm_process_mergeable(mm) ? "yes" : "no"); mmap_read_unlock(mm); mmput(mm); } return 0; } #endif /* CONFIG_KSM */ #ifdef CONFIG_KSTACK_ERASE_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long prev_depth = THREAD_SIZE - (task->prev_lowest_stack & (THREAD_SIZE - 1)); unsigned long depth = THREAD_SIZE - (task->lowest_stack & (THREAD_SIZE - 1)); seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", prev_depth, depth); return 0; } #endif /* CONFIG_KSTACK_ERASE_METRICS */ /* * Thread groups */ static const struct file_operations proc_task_operations; static const struct inode_operations proc_task_inode_operations; static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #ifdef CONFIG_SCHED_AUTOGROUP REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), #endif #ifdef CONFIG_TIME_NS REG("timens_offsets", S_IRUGO|S_IWUSR, proc_timens_offsets_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tgid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), REG("mountstats", S_IRUSR, proc_mountstats_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_ELF_CORE REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tgid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_KSTACK_ERASE_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tgid_base_readdir, .llseek = generic_file_llseek, }; struct pid *tgid_pidfd_to_pid(const struct file *file) { if (file->f_op != &proc_tgid_base_operations) return ERR_PTR(-EBADF); return proc_pid(file_inode(file)); } static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tgid_base_stuff, tgid_base_stuff + ARRAY_SIZE(tgid_base_stuff)); } static const struct inode_operations proc_tgid_base_inode_operations = { .lookup = proc_tgid_base_lookup, .getattr = pid_getattr, .setattr = proc_nochmod_setattr, .permission = proc_pid_permission, }; /** * proc_flush_pid - Remove dcache entries for @pid from the /proc dcache. * @pid: pid that should be flushed. * * This function walks a list of inodes (that belong to any proc * filesystem) that are attached to the pid and flushes them from * the dentry cache. * * It is safe and reasonable to cache /proc entries for a task until * that task exits. After that they just clog up the dcache with * useless entries, possibly causing useful dcache entries to be * flushed instead. This routine is provided to flush those useless * dcache entries when a process is reaped. * * NOTE: This routine is just an optimization so it does not guarantee * that no dcache entries will exist after a process is reaped * it just makes it very unlikely that any will persist. */ void proc_flush_pid(struct pid *pid) { proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); } static struct dentry *proc_pid_instantiate(struct dentry * dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tgid_base_inode_operations; inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; set_nlink(inode, nlink_tgid); pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); tgid = name_to_int(&dentry->d_name); if (tgid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; /* Limit procfs to only ptraceable tasks */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) { if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS)) goto out_put_task; } result = proc_pid_instantiate(dentry, task, NULL); out_put_task: put_task_struct(task); out: return result; } /* * Find the first task with tgid >= tgid * */ struct tgid_iter { unsigned int tgid; struct task_struct *task; struct pid_namespace *const pid_ns; }; static struct tgid_iter make_tgid_iter(unsigned int init_tgid, struct pid_namespace *pid_ns) { return (struct tgid_iter){ .tgid = init_tgid - 1, .pid_ns = pid_ns, }; } static bool next_tgid(struct tgid_iter *it) { if (it->task) { put_task_struct(it->task); it->task = NULL; } rcu_read_lock(); while (1) { it->tgid += 1; const auto pid = find_ge_pid(it->tgid, it->pid_ns); if (pid) { it->tgid = pid_nr_ns(pid, it->pid_ns); it->task = pid_task(pid, PIDTYPE_TGID); if (it->task) { get_task_struct(it->task); rcu_read_unlock(); return true; } } else { rcu_read_unlock(); return false; } } } #define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2) /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb); struct pid_namespace *pid_ns = proc_pid_ns(file_inode(file)->i_sb); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; if (pos == TGID_OFFSET - 2) { if (!dir_emit(ctx, "self", 4, self_inum, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } if (pos == TGID_OFFSET - 1) { if (!dir_emit(ctx, "thread-self", 11, thread_self_inum, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } auto iter = make_tgid_iter(pos - TGID_OFFSET, pid_ns); while (next_tgid(&iter)) { char name[10 + 1]; unsigned int len; cond_resched(); if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%u", iter.tgid); ctx->pos = iter.tgid + TGID_OFFSET; if (!proc_fill_cache(file, ctx, name, len, proc_pid_instantiate, iter.task, NULL)) { put_task_struct(iter.task); return 0; } } ctx->pos = PID_MAX_LIMIT + TGID_OFFSET; return 0; } /* * proc_tid_comm_permission is a special permission function exclusively * used for the node /proc/<pid>/task/<tid>/comm. * It bypasses generic permission checks in the case where a task of the same * task group attempts to access the node. * The rationale behind this is that glibc and bionic access this node for * cross thread naming (pthread_set/getname_np(!self)). However, if * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0, * which locks out the cross thread naming implementation. * This function makes sure that the node is always accessible for members of * same thread group. */ static int proc_tid_comm_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { bool is_same_tgroup; struct task_struct *task; task = get_proc_task(inode); if (!task) return -ESRCH; is_same_tgroup = same_thread_group(current, task); put_task_struct(task); if (likely(is_same_tgroup && !(mask & MAY_EXEC))) { /* This file (/proc/<pid>/task/<tid>/comm) can always be * read or written by the members of the corresponding * thread group. */ return 0; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { .setattr = proc_nochmod_setattr, .permission = proc_tid_comm_permission, }; /* * Tasks */ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), NOD("comm", S_IFREG|S_IRUGO|S_IWUSR, &proc_tid_comm_inode_operations, &proc_pid_set_comm_operations, {}), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_PROC_CHILDREN REG("children", S_IRUGO, proc_tid_children_operations), #endif #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tid_base_stuff, tid_base_stuff + ARRAY_SIZE(tid_base_stuff)); } static const struct file_operations proc_tid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tid_base_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations proc_tid_base_inode_operations = { .lookup = proc_tid_base_lookup, .getattr = pid_getattr, .setattr = proc_nochmod_setattr, }; static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tid_base_inode_operations; inode->i_fop = &proc_tid_base_operations; inode->i_flags |= S_IMMUTABLE; set_nlink(inode, nlink_tid); pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); if (!leader) goto out_no_task; tid = name_to_int(&dentry->d_name); if (tid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; if (!same_thread_group(leader, task)) goto out_drop_task; result = proc_task_instantiate(dentry, task, NULL); out_drop_task: put_task_struct(task); out: put_task_struct(leader); out_no_task: return result; } /* * Find the first tid of a thread group to return to user space. * * Usually this is just the thread group leader, but if the users * buffer was too small or there was a seek into the middle of the * directory we have more work todo. * * In the case of a short read we start with find_task_by_pid. * * In the case of a seek we start with the leader and walk nr * threads past it. */ static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, struct pid_namespace *ns) { struct task_struct *pos, *task; unsigned long nr = f_pos; if (nr != f_pos) /* 32bit overflow? */ return NULL; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); if (!task) goto fail; /* Attempt to start with the tid of a thread */ if (tid && nr) { pos = find_task_by_pid_ns(tid, ns); if (pos && same_thread_group(pos, task)) goto found; } /* If nr exceeds the number of threads there is nothing todo */ if (nr >= get_nr_threads(task)) goto fail; /* If we haven't found our starting place yet start * with the leader and walk nr threads forward. */ for_each_thread(task, pos) { if (!nr--) goto found; } fail: pos = NULL; goto out; found: get_task_struct(pos); out: rcu_read_unlock(); return pos; } /* * Find the next thread in the thread list. * Return NULL if there is an error or no next thread. * * The reference to the input task_struct is released. */ static struct task_struct *next_tid(struct task_struct *start) { struct task_struct *pos = NULL; rcu_read_lock(); if (pid_alive(start)) { pos = __next_thread(start); if (pos) get_task_struct(pos); } rcu_read_unlock(); put_task_struct(start); return pos; } /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct task_struct *task; struct pid_namespace *ns; int tid; if (proc_inode_is_dead(inode)) return -ENOENT; if (!dir_emit_dots(file, ctx)) return 0; /* We cache the tgid value that the last readdir call couldn't * return and lseek resets it to 0. */ ns = proc_pid_ns(inode->i_sb); tid = (int)(intptr_t)file->private_data; file->private_data = NULL; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { char name[10 + 1]; unsigned int len; tid = task_pid_nr_ns(task, ns); if (!tid) continue; /* The task has just exited. */ len = snprintf(name, sizeof(name), "%d", tid); if (!proc_fill_cache(file, ctx, name, len, proc_task_instantiate, task, NULL)) { /* returning this tgid failed, save it as the first * pid for the next readir call */ file->private_data = (void *)(intptr_t)tid; put_task_struct(task); break; } } return 0; } static int proc_task_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct task_struct *p = get_proc_task(inode); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (p) { stat->nlink += get_nr_threads(p); put_task_struct(p); } return 0; } /* * proc_task_readdir() set @file->private_data to a positive integer * value, so casting that to u64 is safe. generic_llseek_cookie() will * set @cookie to 0, so casting to an int is safe. The WARN_ON_ONCE() is * here to catch any unexpected change in behavior either in * proc_task_readdir() or generic_llseek_cookie(). */ static loff_t proc_dir_llseek(struct file *file, loff_t offset, int whence) { u64 cookie = (u64)(intptr_t)file->private_data; loff_t off; off = generic_llseek_cookie(file, offset, whence, &cookie); WARN_ON_ONCE(cookie > INT_MAX); file->private_data = (void *)(intptr_t)cookie; /* serialized by f_pos_lock */ return off; } static const struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, .getattr = proc_task_getattr, .setattr = proc_nochmod_setattr, .permission = proc_pid_permission, }; static const struct file_operations proc_task_operations = { .read = generic_read_dir, .iterate_shared = proc_task_readdir, .llseek = proc_dir_llseek, }; void __init set_proc_pid_nlink(void) { nlink_tid = pid_entry_nlink(tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); nlink_tgid = pid_entry_nlink(tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } |
| 62 48 14 25 1 34 2 2 7 24 23 12 40 3 47 10 34 26 44 16 1 1 1 1 1 7 9 1 8 8 8 1 1 1 1 2 2 2 14 2 3 11 18 18 2 6 1 1 1 1 1 1 1 1 1 1 4 4 4 1 1 43 43 1 1 64 63 1 1 5 1 1 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2020, Red Hat, Inc. */ #define pr_fmt(fmt) "MPTCP: " fmt #include "protocol.h" #include "mptcp_pm_gen.h" #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 static const struct genl_multicast_group mptcp_pm_mcgrps[] = { [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, [MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME, .flags = GENL_MCAST_CAP_NET_ADMIN, }, }; static int mptcp_pm_family_to_addr(int family) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (family == AF_INET6) return MPTCP_PM_ADDR_ATTR_ADDR6; #endif return MPTCP_PM_ADDR_ATTR_ADDR4; } static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], const struct nlattr *attr, struct genl_info *info, struct mptcp_addr_info *addr, bool require_family) { int err, addr_addr; if (!attr) { GENL_SET_ERR_MSG(info, "missing address info"); return -EINVAL; } /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, mptcp_pm_address_nl_policy, info->extack); if (err) return err; if (tb[MPTCP_PM_ADDR_ATTR_ID]) addr->id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]); if (!tb[MPTCP_PM_ADDR_ATTR_FAMILY]) { if (!require_family) return 0; NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing family"); return -EINVAL; } addr->family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]); if (addr->family != AF_INET #if IS_ENABLED(CONFIG_MPTCP_IPV6) && addr->family != AF_INET6 #endif ) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "unknown address family"); return -EINVAL; } addr_addr = mptcp_pm_family_to_addr(addr->family); if (!tb[addr_addr]) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing address data"); return -EINVAL; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (addr->family == AF_INET6) addr->addr6 = nla_get_in6_addr(tb[addr_addr]); else #endif addr->addr.s_addr = nla_get_in_addr(tb[addr_addr]); if (tb[MPTCP_PM_ADDR_ATTR_PORT]) addr->port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); return 0; } int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, struct mptcp_addr_info *addr) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; memset(addr, 0, sizeof(*addr)); return mptcp_pm_parse_pm_addr_attr(tb, attr, info, addr, true); } int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, bool require_family, struct mptcp_pm_addr_entry *entry) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; int err; memset(entry, 0, sizeof(*entry)); err = mptcp_pm_parse_pm_addr_attr(tb, attr, info, &entry->addr, require_family); if (err) return err; if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) { s32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]); entry->ifindex = val; } if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]) & MPTCP_PM_ADDR_FLAGS_MASK; if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); return 0; } static int mptcp_nl_fill_addr(struct sk_buff *skb, struct mptcp_pm_addr_entry *entry) { struct mptcp_addr_info *addr = &entry->addr; struct nlattr *attr; attr = nla_nest_start(skb, MPTCP_PM_ATTR_ADDR); if (!attr) return -EMSGSIZE; if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family)) goto nla_put_failure; if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_PORT, ntohs(addr->port))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags)) goto nla_put_failure; if (entry->ifindex && nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex)) goto nla_put_failure; if (addr->family == AF_INET && nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4, addr->addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->family == AF_INET6 && nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6)) goto nla_put_failure; #endif nla_nest_end(skb, attr); return 0; nla_put_failure: nla_nest_cancel(skb, attr); return -EMSGSIZE; } static int mptcp_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr, struct genl_info *info) { if (info->attrs[MPTCP_PM_ATTR_TOKEN]) return mptcp_userspace_pm_get_addr(id, addr, info); return mptcp_pm_nl_get_addr(id, addr, info); } int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry addr; struct nlattr *attr; struct sk_buff *msg; void *reply; int ret; if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR)) return -EINVAL; attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) return ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, info->genlhdr->cmd); if (!reply) { GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); ret = -EMSGSIZE; goto fail; } ret = mptcp_pm_get_addr(addr.addr.id, &addr, info); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found"); goto fail; } ret = mptcp_nl_fill_addr(msg, &addr); if (ret) goto fail; genlmsg_end(msg, reply); ret = genlmsg_reply(msg, info); return ret; fail: nlmsg_free(msg); return ret; } int mptcp_pm_genl_fill_addr(struct sk_buff *msg, struct netlink_callback *cb, struct mptcp_pm_addr_entry *entry) { void *hdr; hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &mptcp_genl_family, NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); if (!hdr) return -EINVAL; if (mptcp_nl_fill_addr(msg, entry) < 0) { genlmsg_cancel(msg, hdr); return -EINVAL; } genlmsg_end(msg, hdr); return 0; } static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); if (info->attrs[MPTCP_PM_ATTR_TOKEN]) return mptcp_userspace_pm_dump_addr(msg, cb); return mptcp_pm_nl_dump_addr(msg, cb); } int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { return mptcp_pm_dump_addr(msg, cb); } static int mptcp_pm_set_flags(struct genl_info *info) { struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; struct nlattr *attr_loc; int ret = -EINVAL; if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR)) return ret; attr_loc = info->attrs[MPTCP_PM_ATTR_ADDR]; ret = mptcp_pm_parse_entry(attr_loc, info, false, &loc); if (ret < 0) return ret; if (info->attrs[MPTCP_PM_ATTR_TOKEN]) return mptcp_userspace_pm_set_flags(&loc, info); return mptcp_pm_nl_set_flags(&loc, info); } int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { return mptcp_pm_set_flags(info); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) { genlmsg_multicast_netns(&mptcp_genl_family, net, nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp); } bool mptcp_userspace_pm_active(const struct mptcp_sock *msk) { return genl_has_listeners(&mptcp_genl_family, sock_net((const struct sock *)msk), MPTCP_PM_EV_GRP_OFFSET); } static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) { const struct inet_sock *issk = inet_sk(ssk); const struct mptcp_subflow_context *sf; if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) return -EMSGSIZE; switch (ssk->sk_family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) return -EMSGSIZE; if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, issk->inet_daddr)) return -EMSGSIZE; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr)) return -EMSGSIZE; if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr)) return -EMSGSIZE; break; } #endif default: WARN_ON_ONCE(1); return -EMSGSIZE; } if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) return -EMSGSIZE; if (nla_put_be16(skb, MPTCP_ATTR_DPORT, issk->inet_dport)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (WARN_ON_ONCE(!sf)) return -EINVAL; if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) return -EMSGSIZE; return 0; } static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { const struct sock *sk = (const struct sock *)msk; const struct mptcp_subflow_context *sf; u8 sk_err; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) return -EMSGSIZE; if (mptcp_event_add_subflow(skb, ssk)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (WARN_ON_ONCE(!sf)) return -EINVAL; if (nla_put_u8(skb, MPTCP_ATTR_BACKUP, sf->backup)) return -EMSGSIZE; if (ssk->sk_bound_dev_if && nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if)) return -EMSGSIZE; sk_err = READ_ONCE(ssk->sk_err); if (sk_err && sk->sk_state == TCP_ESTABLISHED && nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err)) return -EMSGSIZE; return 0; } static int mptcp_event_sub_established(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { return mptcp_event_put_token_and_ssk(skb, msk, ssk); } static int mptcp_event_sub_closed(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { const struct mptcp_subflow_context *sf; if (mptcp_event_put_token_and_ssk(skb, msk, ssk)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (!sf->reset_seen) return 0; if (nla_put_u32(skb, MPTCP_ATTR_RESET_REASON, sf->reset_reason)) return -EMSGSIZE; if (nla_put_u32(skb, MPTCP_ATTR_RESET_FLAGS, sf->reset_transient)) return -EMSGSIZE; return 0; } static int mptcp_event_created(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); u16 flags = 0; if (err) return err; if (READ_ONCE(msk->pm.server_side)) { flags |= MPTCP_PM_EV_FLAG_SERVER_SIDE; /* Deprecated, and only set when it is the server side */ if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, 1)) return -EMSGSIZE; } if (READ_ONCE(msk->pm.remote_deny_join_id0)) flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0; if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags)) return -EMSGSIZE; return mptcp_event_add_subflow(skb, ssk); } void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id) { struct net *net = sock_net((const struct sock *)msk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_REMOVED); if (!nlh) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id)) goto nla_put_failure; genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_info *info) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct net *net = sock_net(ssk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_ANNOUNCED); if (!nlh) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id)) goto nla_put_failure; if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port == 0 ? inet_sk(ssk)->inet_dport : info->port)) goto nla_put_failure; switch (info->family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, info->addr.s_addr)) goto nla_put_failure; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &info->addr6)) goto nla_put_failure; break; #endif default: WARN_ON_ONCE(1); goto nla_put_failure; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event) { const struct inet_sock *issk = inet_sk(ssk); struct net *net = sock_net(ssk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, event); if (!nlh) goto nla_put_failure; if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) goto nla_put_failure; if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) goto nla_put_failure; switch (ssk->sk_family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) goto nla_put_failure; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr)) goto nla_put_failure; break; } #endif default: WARN_ON_ONCE(1); goto nla_put_failure; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_KERNEL); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { struct net *net = sock_net((const struct sock *)msk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, type); if (!nlh) goto nla_put_failure; switch (type) { case MPTCP_EVENT_UNSPEC: WARN_ON_ONCE(1); break; case MPTCP_EVENT_CREATED: case MPTCP_EVENT_ESTABLISHED: if (mptcp_event_created(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_CLOSED: if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)) < 0) goto nla_put_failure; break; case MPTCP_EVENT_ANNOUNCED: case MPTCP_EVENT_REMOVED: /* call mptcp_event_addr_announced()/removed instead */ WARN_ON_ONCE(1); break; case MPTCP_EVENT_SUB_ESTABLISHED: case MPTCP_EVENT_SUB_PRIORITY: if (mptcp_event_sub_established(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_SUB_CLOSED: if (mptcp_event_sub_closed(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_LISTENER_CREATED: case MPTCP_EVENT_LISTENER_CLOSED: break; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, gfp); return; nla_put_failure: nlmsg_free(skb); } struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, .netnsok = true, .module = THIS_MODULE, .ops = mptcp_pm_nl_ops, .n_ops = ARRAY_SIZE(mptcp_pm_nl_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), }; void __init mptcp_pm_nl_init(void) { if (genl_register_family(&mptcp_genl_family)) panic("Failed to register MPTCP PM netlink family\n"); } |
| 1614 77 9 2723 2187 2130 80 2166 2315 4 5011 4544 18 126 97 4 2912 1188 4 4 26 1725 110 22 2669 2021 78 323 11 11 4607 170 92 1 92 1282 74 4500 675 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* 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, #ifdef CONFIG_MIGRATION /* movable_ops page that is isolated for migration */ PG_movable_ops_isolated = PG_reclaim, /* this is a movable_ops page (for selected typed pages only) */ PG_movable_ops = PG_uptodate, #endif /* 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 /* * For tail pages, if the size of struct page is power-of-2 ->compound_info * encodes the mask that converts the address of the tail page address to * the head page address. * * Otherwise, ->compound_info has direct pointer to head pages. */ static __always_inline bool compound_info_has_mask(void) { /* * Limit mask usage to HugeTLB vmemmap optimization (HVO) where it * makes a difference. * * The approach with mask would work in the wider set of conditions, * but it requires validating that struct pages are naturally aligned * for all orders up to the MAX_FOLIO_ORDER, which can be tricky. */ if (!IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)) return false; return is_power_of_2(sizeof(struct page)); } static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long info = READ_ONCE(page->compound_info); unsigned long mask; if (!compound_info_has_mask()) { /* Bit 0 encodes PageTail() */ if (info & 1) return info - 1; return (unsigned long)page; } /* * If compound_info_has_mask() is true the rest of the info encodes * the mask that converts the address of the tail page to the head page. * * No need to clear bit 0 in the mask as 'page' always has it clear. * * Let's do it in a branchless manner. */ /* Non-tail: -1UL, Tail: 0 */ mask = (info & 1) - 1; /* Non-tail: -1UL, Tail: info */ mask |= info; return (unsigned long)page & mask; } #define compound_head(page) ((typeof(page))_compound_head(page)) static __always_inline void set_compound_head(struct page *tail, const struct page *head, unsigned int order) { unsigned int shift; unsigned long mask; if (!compound_info_has_mask()) { WRITE_ONCE(tail->compound_info, (unsigned long)head | 1); return; } /* * If the size of struct page is power-of-2, bits [shift:0] of the * virtual address of compound head are zero. * * Calculate mask that can be applied to the virtual address of * the tail page to get address of the head page. */ shift = order + order_base_2(sizeof(struct page)); mask = GENMASK(BITS_PER_LONG - 1, shift); /* Bit 0 encodes PageTail() */ WRITE_ONCE(tail->compound_info, mask | 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_info, 0); } /** * 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) (&(folio)->page + (n)) static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_info) & 1; } static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags.f) || READ_ONCE(page->compound_info) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return READ_ONCE(page->flags.f) == 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_info & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page); return &page[n].flags.f; } static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_info & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page); return &page[n].flags.f; } /* * 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.f); } #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.f); } #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.f); } #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.f); } #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.f); } #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.f); } #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.f); } #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 #define PhysHighMem(__p) (PageHighMem(phys_to_page(__p))) /* Does kmap_local_folio() only allow access to one page of the folio? */ #ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP #define folio_test_partial_kmap(f) true #else #define folio_test_partial_kmap(f) folio_test_highmem(f) #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 FOLIO_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous folio in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the FOLIO_MAPPING_ANON_KSM bit may be set along with the FOLIO_MAPPING_ANON * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged folio. See ksm.h. * * 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 FOLIO_MAPPING_ANON 0x1 #define FOLIO_MAPPING_ANON_KSM 0x2 #define FOLIO_MAPPING_KSM (FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM) #define FOLIO_MAPPING_FLAGS (FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM) static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & FOLIO_MAPPING_ANON) != 0; } static __always_inline bool folio_test_lazyfree(const struct folio *folio) { return folio_test_anon(folio) && !folio_test_swapbacked(folio); } static __always_inline bool PageAnonNotKsm(const struct page *page) { unsigned long flags = (unsigned long)page_folio(page)->mapping; return (flags & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_ANON; } static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } #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 & FOLIO_MAPPING_FLAGS) == FOLIO_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) 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.f); } __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); } #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 /* * 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(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_large_kmalloc = 0xf8, 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_type_has_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) PAGE_TYPE_OPS(Slab, slab, slab) #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) PAGE_TYPE_OPS(LargeKmalloc, large_kmalloc, large_kmalloc) /** * 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); } static inline bool folio_contain_hwpoisoned_page(struct folio *folio) { return folio_test_hwpoison(folio) || (folio_test_large(folio) && folio_test_has_hwpoisoned(folio)); } bool is_free_buddy_page(const struct page *page); #ifdef CONFIG_MIGRATION /* * This page is migratable through movable_ops (for selected typed pages * only). * * Page migration of such pages might fail, for example, if the page is * already isolated by somebody else, or if the page is about to get freed. * * While a subsystem might set selected typed pages that support page migration * as being movable through movable_ops, it must never clear this flag. * * This flag is only cleared when the page is freed back to the buddy. * * Only selected page types support this flag (see page_movable_ops()) and * the flag might be used in other context for other pages. Always use * page_has_movable_ops() instead. */ TESTPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL); SETPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL); /* * A movable_ops page has this flag set while it is isolated for migration. * This flag primarily protects against concurrent migration attempts. * * Once migration ended (success or failure), the flag is cleared. The * flag is managed by the migration core. */ PAGEFLAG(MovableOpsIsolated, movable_ops_isolated, PF_NO_TAIL); #else /* !CONFIG_MIGRATION */ TESTPAGEFLAG_FALSE(MovableOps, movable_ops); SETPAGEFLAG_NOOP(MovableOps, movable_ops); PAGEFLAG_FALSE(MovableOpsIsolated, movable_ops_isolated); #endif /* CONFIG_MIGRATION */ /** * page_has_movable_ops - test for a movable_ops page * @page: The page to test. * * Test whether this is a movable_ops page. Such pages will stay that * way until freed. * * Returns true if this is a movable_ops page, otherwise false. */ static inline bool page_has_movable_ops(const struct page *page) { return PageMovableOps(page) && (PageOffline(page) || PageZsmalloc(page)); } 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.f); } 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.f); } 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.f); } 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.f); } #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.f & 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 */ |
| 480 28 902 1 660 4054 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_H #define _IPV6_H #include <uapi/linux/ipv6.h> #include <linux/cache.h> #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) #define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ struct ipv6_devconf { /* RX & TX fastpath fields. */ __cacheline_group_begin(ipv6_devconf_read_txrx); __s32 disable_ipv6; __s32 hop_limit; __s32 mtu6; __s32 forwarding; __s32 force_forwarding; __s32 disable_policy; __s32 proxy_ndp; __cacheline_group_end(ipv6_devconf_read_txrx); __s32 accept_ra; __s32 accept_redirects; __s32 autoconf; __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; __s32 mldv2_unsolicited_report_interval; __s32 use_tempaddr; __s32 temp_valid_lft; __s32 temp_prefered_lft; __s32 regen_min_advance; __s32 regen_max_retry; __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif __s32 accept_source_route; __s32 accept_ra_from_local; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD __s32 optimistic_dad; __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE atomic_t mc_forwarding; #endif __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; __s32 keep_addr_on_down; __s32 seg6_enabled; #ifdef CONFIG_IPV6_SEG6_HMAC __s32 seg6_require_hmac; #endif __u32 enhanced_dad; __u32 addr_gen_mode; __s32 ndisc_tclass; __s32 rpl_seg_enabled; __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; struct ipv6_params { __s32 disable_ipv6; __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; #include <linux/tcp.h> #include <linux/udp.h> #include <net/inet_sock.h> static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_network_header(skb); } static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_inner_network_header(skb); } static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_transport_header(skb); } static inline unsigned int ipv6_transport_len(const struct sk_buff *skb) { return ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr) - skb_network_header_len(skb); } static inline unsigned int ipv6_payload_len(const struct sk_buff *skb, const struct ipv6hdr *ip6) { u32 len = ntohs(ip6->payload_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb) - sizeof(struct ipv6hdr); } static inline unsigned int skb_ipv6_payload_len(const struct sk_buff *skb) { return ipv6_payload_len(skb, ipv6_hdr(skb)); } #define IPV6_MAXPLEN 65535 static inline void ipv6_set_payload_len(struct ipv6hdr *ip6, unsigned int len) { ip6->payload_len = len <= IPV6_MAXPLEN ? htons(len) : 0; } /* This structure contains results of exthdrs parsing as offsets from skb->nh. */ struct inet6_skb_parm { int iif; __be16 ra; __u16 dst0; __u16 srcrt; __u16 dst1; __u16 lastopt; __u16 nhoff; __u16 flags; #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dsthao; #endif __u16 frag_max_size; __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 #define IP6SKB_MULTIPATH 1024 #define IP6SKB_MCROUTE 2048 }; #if defined(CONFIG_NET_L3_MASTER_DEV) static inline bool ipv6_l3mdev_skb(__u16 flags) { return flags & IP6SKB_L3SLAVE; } #else static inline bool ipv6_l3mdev_skb(__u16 flags) { return false; } #endif #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) #define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb)) static inline int inet6_iif(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags); return l3_slave ? skb->skb_iif : IP6CB(skb)->iif; } static inline bool inet6_is_jumbogram(const struct sk_buff *skb) { return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); } /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline int inet6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) return IP6CB(skb)->iif; #endif return 0; } struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; /* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { /* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */ struct in6_addr saddr; union { struct in6_addr daddr; struct in6_addr final; }; __be32 flow_label; u32 dst_cookie; struct ipv6_txoptions __rcu *opt; s16 hop_limit; u8 pmtudisc; u8 tclass; #ifdef CONFIG_IPV6_SUBTREES bool saddr_cache; #endif bool daddr_cache; u8 mcast_hops; u32 frag_size; int ucast_oif; int mcast_oif; /* pktoption flags */ union { struct { u16 srcrt:1, osrcrt:1, rxinfo:1, rxoinfo:1, rxhlim:1, rxohlim:1, hopopts:1, ohopopts:1, dstopts:1, odstopts:1, rxflow:1, rxtclass:1, rxpmtu:1, rxorigdstaddr:1, recvfragsize:1; /* 1 bits hole */ } bits; u16 all; } rxopt; /* sockopt flags */ u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ u8 min_hopcount; __be32 rcv_flowinfo; struct in6_pktinfo sticky_pktinfo; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; }; /* We currently use available bits from inet_sk(sk)->inet_flags, * this could change in the future. */ #define inet6_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_set_bit(nr, sk) \ set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_clear_bit(nr, sk) \ clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ struct raw6_sock { /* inet_sock has to be the first member of raw6_sock */ struct inet_sock inet; __u32 checksum; /* perform checksum */ __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; struct numa_drop_counters drop_counters; struct ipv6_pinfo inet6; }; struct udp6_sock { struct udp_sock udp; struct ipv6_pinfo inet6; }; struct tcp6_sock { struct tcp_sock tcp; struct ipv6_pinfo inet6; }; extern int inet6_sk_rebuild_header(struct sock *sk); struct tcp6_timewait_sock { struct tcp_timewait_sock tcp6tw_tcp; }; #if IS_ENABLED(CONFIG_IPV6) extern int disable_ipv6_mod; static inline bool ipv6_mod_enabled(void) { return disable_ipv6_mod == 0; } static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } #define raw6_sk(ptr) container_of_const(ptr, struct raw6_sock, inet.sk) #define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk) { if (sk->sk_family == AF_INET6) return &sk->sk_v6_rcv_saddr; return NULL; } static inline int inet_v6_ipv6only(const struct sock *sk) { /* ipv6only field is at same position for timewait and other sockets */ return ipv6_only_sock(sk); } #else #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 static inline bool ipv6_mod_enabled(void) { return false; } static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { return NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ |
| 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 | // SPDX-License-Identifier: GPL-2.0 /* * Block stat tracking code * * Copyright (C) 2016 Jens Axboe */ #include <linux/kernel.h> #include <linux/rculist.h> #include "blk-stat.h" #include "blk-mq.h" #include "blk.h" struct blk_queue_stats { struct list_head callbacks; spinlock_t lock; int accounting; }; void blk_rq_stat_init(struct blk_rq_stat *stat) { stat->min = -1ULL; stat->max = stat->nr_samples = stat->mean = 0; stat->batch = 0; } /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); dst->max = max(dst->max, src->max); dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples, dst->nr_samples + src->nr_samples); dst->nr_samples += src->nr_samples; } void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value) { stat->min = min(stat->min, value); stat->max = max(stat->max, value); stat->batch += value; stat->nr_samples++; } void blk_stat_add(struct request *rq, u64 now) { struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; int bucket, cpu; u64 value; value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; rcu_read_lock(); cpu = get_cpu(); list_for_each_entry_rcu(cb, &q->stats->callbacks, list) { if (!blk_stat_is_active(cb)) continue; bucket = cb->bucket_fn(rq); if (bucket < 0) continue; stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket]; blk_rq_stat_add(stat, value); } put_cpu(); rcu_read_unlock(); } static void blk_stat_timer_fn(struct timer_list *t) { struct blk_stat_callback *cb = timer_container_of(cb, t, timer); unsigned int bucket; int cpu; for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cb->stat[bucket]); for_each_online_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) { blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]); blk_rq_stat_init(&cpu_stat[bucket]); } } cb->timer_fn(cb); } struct blk_stat_callback * blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *), int (*bucket_fn)(const struct request *), unsigned int buckets, void *data) { struct blk_stat_callback *cb; cb = kmalloc_obj(*cb); if (!cb) return NULL; cb->stat = kmalloc_objs(struct blk_rq_stat, buckets); if (!cb->stat) { kfree(cb); return NULL; } cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat), __alignof__(struct blk_rq_stat)); if (!cb->cpu_stat) { kfree(cb->stat); kfree(cb); return NULL; } cb->timer_fn = timer_fn; cb->bucket_fn = bucket_fn; cb->data = data; cb->buckets = buckets; timer_setup(&cb->timer, blk_stat_timer_fn, 0); return cb; } void blk_stat_add_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned int bucket; unsigned long flags; int cpu; for_each_possible_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cpu_stat[bucket]); } spin_lock_irqsave(&q->stats->lock, flags); list_add_tail_rcu(&cb->list, &q->stats->callbacks); blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } void blk_stat_remove_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); list_del_rcu(&cb->list); if (list_empty(&q->stats->callbacks) && !q->stats->accounting) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); timer_delete_sync(&cb->timer); } static void blk_stat_free_callback_rcu(struct rcu_head *head) { struct blk_stat_callback *cb; cb = container_of(head, struct blk_stat_callback, rcu); free_percpu(cb->cpu_stat); kfree(cb->stat); kfree(cb); } void blk_stat_free_callback(struct blk_stat_callback *cb) { if (cb) call_rcu(&cb->rcu, blk_stat_free_callback_rcu); } void blk_stat_disable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!--q->stats->accounting && list_empty(&q->stats->callbacks)) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_disable_accounting); void blk_stat_enable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!q->stats->accounting++ && list_empty(&q->stats->callbacks)) blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_enable_accounting); struct blk_queue_stats *blk_alloc_queue_stats(void) { struct blk_queue_stats *stats; stats = kmalloc_obj(*stats); if (!stats) return NULL; INIT_LIST_HEAD(&stats->callbacks); spin_lock_init(&stats->lock); stats->accounting = 0; return stats; } void blk_free_queue_stats(struct blk_queue_stats *stats) { if (!stats) return; WARN_ON(!list_empty(&stats->callbacks)); kfree(stats); } |
| 4 3 3 2 1 12 12 6 2 4 1 4 4 4 4 3 4 4 1 2 4 1 5 1 1 1 5 10 10 9 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:ip,port,ip type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ #define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:ip,port,ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:ip,port,ip"); /* Type specific function prefix */ #define HTYPE hash_ipportip /* IPv4 variant */ /* Member elements */ struct hash_ipportip4_elem { __be32 ip; __be32 ip2; __be16 port; u8 proto; u8 padding; }; static bool hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1, const struct hash_ipportip4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->ip2 == ip2->ip2 && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipportip4_data_list(struct sk_buff *skb, const struct hash_ipportip4_elem *data) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip2) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_ipportip4_data_next(struct hash_ipportip4_elem *next, const struct hash_ipportip4_elem *d) { next->ip = d->ip; next->port = d->port; } /* Common functions */ #define MTYPE hash_ipportip4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_ipportip4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &e.ip2); if (ret) return ret; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip = ntohl(e.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip > ip_to) swap(ip, ip_to); } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } port_to = port = ntohs(e.port); if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); } if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to;) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); if (i > IPSET_MAX_RANGE) { hash_ipportip4_data_next(&h->next, &e); return -ERANGE; } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } if (ip == ip_to) break; ip++; } return ret; } /* IPv6 variant */ struct hash_ipportip6_elem { union nf_inet_addr ip; union nf_inet_addr ip2; __be16 port; u8 proto; u8 padding; }; /* Common functions */ static bool hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1, const struct hash_ipportip6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipportip6_data_list(struct sk_buff *skb, const struct hash_ipportip6_elem *data) { if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_ipportip6_data_next(struct hash_ipportip6_elem *next, const struct hash_ipportip6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_ipportip6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2.in6); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_ipportip6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (unlikely(tb[IPSET_ATTR_CIDR])) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (cidr != HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip2); if (ret) return ret; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_ipportip_type __read_mostly = { .name = "hash:ip,port,ip", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_ipportip_init(void) { return ip_set_type_register(&hash_ipportip_type); } static void __exit hash_ipportip_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_ipportip_type); } module_init(hash_ipportip_init); module_exit(hash_ipportip_fini); |
| 76 74 6 73 633 634 126 126 126 126 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <net/gro_cells.h> #include <net/hotdata.h> struct gro_cell { struct sk_buff_head napi_skbs; struct napi_struct napi; local_lock_t bh_lock; }; int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct net_device *dev = skb->dev; bool have_bh_lock = false; struct gro_cell *cell; int res; rcu_read_lock(); if (unlikely(!(dev->flags & IFF_UP))) goto drop; if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { res = netif_rx(skb); goto unlock; } local_lock_nested_bh(&gcells->cells->bh_lock); have_bh_lock = true; cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); res = NET_RX_DROP; goto unlock; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); res = NET_RX_SUCCESS; unlock: if (have_bh_lock) local_unlock_nested_bh(&gcells->cells->bh_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(gro_cells_receive); /* called under BH context */ static int gro_cell_poll(struct napi_struct *napi, int budget) { struct gro_cell *cell = container_of(napi, struct gro_cell, napi); struct sk_buff *skb; int work_done = 0; while (work_done < budget) { __local_lock_nested_bh(&cell->bh_lock); skb = __skb_dequeue(&cell->napi_skbs); __local_unlock_nested_bh(&cell->bh_lock); if (!skb) break; napi_gro_receive(napi, skb); work_done++; } if (work_done < budget) napi_complete_done(napi, work_done); return work_done; } int gro_cells_init(struct gro_cells *gcells, struct net_device *dev) { int i; gcells->cells = alloc_percpu(struct gro_cell); if (!gcells->cells) return -ENOMEM; for_each_possible_cpu(i) { struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); __skb_queue_head_init(&cell->napi_skbs); local_lock_init(&cell->bh_lock); set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state); netif_napi_add(dev, &cell->napi, gro_cell_poll); napi_enable(&cell->napi); } return 0; } EXPORT_SYMBOL(gro_cells_init); struct percpu_free_defer { struct rcu_head rcu; void __percpu *ptr; }; static void percpu_free_defer_callback(struct rcu_head *head) { struct percpu_free_defer *defer; defer = container_of(head, struct percpu_free_defer, rcu); free_percpu(defer->ptr); kfree(defer); } void gro_cells_destroy(struct gro_cells *gcells) { struct percpu_free_defer *defer; int i; if (!gcells->cells) return; for_each_possible_cpu(i) { struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); napi_disable(&cell->napi); __netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } /* We need to observe an rcu grace period before freeing ->cells, * because netpoll could access dev->napi_list under rcu protection. * Try hard using call_rcu() instead of synchronize_rcu(), * because we might be called from cleanup_net(), and we * definitely do not want to block this critical task. */ defer = kmalloc_obj(*defer, GFP_KERNEL | __GFP_NOWARN); if (likely(defer)) { defer->ptr = gcells->cells; call_rcu(&defer->rcu, percpu_free_defer_callback); } else { /* We do not hold RTNL at this point, synchronize_net() * would not be able to expedite this sync. */ synchronize_rcu_expedited(); free_percpu(gcells->cells); } gcells->cells = NULL; } EXPORT_SYMBOL(gro_cells_destroy); |
| 4 224 349 315 754 797 1189 162 71 152 69 268 124 124 87 266 44 327 237 42 158 201 135 105 761 215 633 620 394 151 150 110 54 619 145 181 353 224 54 42 508 508 562 358 38 56 28 38 23 23 562 562 19 6 877 413 878 410 1 965 508 1283 6 11 88 144 822 208 253 1 260 253 2 499 1104 989 389 389 1408 1409 6 9 61 27 27 24 33 33 24 11 706 175 15 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 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ext4 #if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_EXT4_H #include <linux/writeback.h> #include <linux/tracepoint.h> struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_extent; struct ext4_prealloc_space; struct ext4_inode_info; struct mpage_da_data; struct ext4_map_blocks; struct extent_status; struct ext4_fsmap; struct partial_cluster; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) #define show_mballoc_flags(flags) __print_flags(flags, "|", \ { EXT4_MB_HINT_MERGE, "HINT_MERGE" }, \ { EXT4_MB_HINT_FIRST, "HINT_FIRST" }, \ { EXT4_MB_HINT_DATA, "HINT_DATA" }, \ { EXT4_MB_HINT_NOPREALLOC, "HINT_NOPREALLOC" }, \ { EXT4_MB_HINT_GROUP_ALLOC, "HINT_GRP_ALLOC" }, \ { EXT4_MB_HINT_GOAL_ONLY, "HINT_GOAL_ONLY" }, \ { EXT4_MB_HINT_TRY_GOAL, "HINT_TRY_GOAL" }, \ { EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \ { EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \ { EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \ { EXT4_MB_USE_RESERVED, "USE_RESV" }, \ { EXT4_MB_STRICT_CHECK, "STRICT_CHECK" }) #define show_map_flags(flags) __print_flags(flags, "|", \ { EXT4_GET_BLOCKS_CREATE, "CREATE" }, \ { EXT4_GET_BLOCKS_UNWRIT_EXT, "UNWRIT" }, \ { EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \ { EXT4_GET_BLOCKS_SPLIT_NOMERGE, "SPLIT_NOMERGE" }, \ { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ { EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, "CONVERT_UNWRITTEN" }, \ { EXT4_GET_BLOCKS_ZERO, "ZERO" }, \ { EXT4_GET_BLOCKS_IO_SUBMIT, "IO_SUBMIT" }, \ { EXT4_EX_NOCACHE, "EX_NOCACHE" }) /* * __print_flags() requires that all enum values be wrapped in the * TRACE_DEFINE_ENUM macro so that the enum value can be encoded in the ftrace * ring buffer. */ TRACE_DEFINE_ENUM(BH_New); TRACE_DEFINE_ENUM(BH_Mapped); TRACE_DEFINE_ENUM(BH_Unwritten); TRACE_DEFINE_ENUM(BH_Boundary); #define show_mflags(flags) __print_flags(flags, "", \ { EXT4_MAP_NEW, "N" }, \ { EXT4_MAP_MAPPED, "M" }, \ { EXT4_MAP_UNWRITTEN, "U" }, \ { EXT4_MAP_BOUNDARY, "B" }) #define show_free_flags(flags) __print_flags(flags, "|", \ { EXT4_FREE_BLOCKS_METADATA, "METADATA" }, \ { EXT4_FREE_BLOCKS_FORGET, "FORGET" }, \ { EXT4_FREE_BLOCKS_VALIDATED, "VALIDATED" }, \ { EXT4_FREE_BLOCKS_NO_QUOT_UPDATE, "NO_QUOTA" }, \ { EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\ { EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER, "LAST_CLUSTER" }) TRACE_DEFINE_ENUM(ES_WRITTEN_B); TRACE_DEFINE_ENUM(ES_UNWRITTEN_B); TRACE_DEFINE_ENUM(ES_DELAYED_B); TRACE_DEFINE_ENUM(ES_HOLE_B); TRACE_DEFINE_ENUM(ES_REFERENCED_B); #define show_extent_status(status) __print_flags(status, "", \ { EXTENT_STATUS_WRITTEN, "W" }, \ { EXTENT_STATUS_UNWRITTEN, "U" }, \ { EXTENT_STATUS_DELAYED, "D" }, \ { EXTENT_STATUS_HOLE, "H" }, \ { EXTENT_STATUS_REFERENCED, "R" }) #define show_falloc_mode(mode) __print_flags(mode, "|", \ { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}, \ { FALLOC_FL_WRITE_ZEROES, "WRITE_ZEROES"}) TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_NOMEM); TRACE_DEFINE_ENUM(EXT4_FC_REASON_SWAP_BOOT); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RESIZE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RENAME_DIR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_FALLOC_RANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_INODE_JOURNAL_DATA); TRACE_DEFINE_ENUM(EXT4_FC_REASON_ENCRYPTED_FILENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_MIGRATE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_VERITY); TRACE_DEFINE_ENUM(EXT4_FC_REASON_MOVE_EXT); TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX); #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(EXT4_FC_SNAP_ERR_##a); #define EMe(a) TRACE_DEFINE_ENUM(EXT4_FC_SNAP_ERR_##a); #define TRACE_SNAP_ERR \ EM(NONE) \ EM(ES_MISS) \ EM(ES_DELAYED) \ EM(ES_OTHER) \ EM(INODES_CAP) \ EM(RANGES_CAP) \ EM(NOMEM) \ EMe(INODE_LOC) TRACE_SNAP_ERR #undef EM #undef EMe #define show_fc_reason(reason) \ __print_symbolic(reason, \ { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}, \ { EXT4_FC_REASON_ENCRYPTED_FILENAME, "ENCRYPTED_FILENAME"}, \ { EXT4_FC_REASON_MIGRATE, "MIGRATE"}, \ { EXT4_FC_REASON_VERITY, "VERITY"}, \ { EXT4_FC_REASON_MOVE_EXT, "MOVE_EXT"}) TRACE_DEFINE_ENUM(CR_POWER2_ALIGNED); TRACE_DEFINE_ENUM(CR_GOAL_LEN_FAST); TRACE_DEFINE_ENUM(CR_BEST_AVAIL_LEN); TRACE_DEFINE_ENUM(CR_GOAL_LEN_SLOW); TRACE_DEFINE_ENUM(CR_ANY_FREE); #define show_criteria(cr) \ __print_symbolic(cr, \ { CR_POWER2_ALIGNED, "CR_POWER2_ALIGNED" }, \ { CR_GOAL_LEN_FAST, "CR_GOAL_LEN_FAST" }, \ { CR_BEST_AVAIL_LEN, "CR_BEST_AVAIL_LEN" }, \ { CR_GOAL_LEN_SLOW, "CR_GOAL_LEN_SLOW" }, \ { CR_ANY_FREE, "CR_ANY_FREE" }) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, u64 orig_ino), TP_ARGS(inode, orig_ino), TP_STRUCT__entry( __field( u64, ino ) __field( u64, orig_ino ) __field( dev_t, dev ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u16, mode ) ), TP_fast_assign( __entry->orig_ino = orig_ino; __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d orig_ino %llu ino %llu mode 0%o uid %u gid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->orig_ino, __entry->ino, __entry->mode, __entry->uid, __entry->gid) ); TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, blocks ) __field( dev_t, dev ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %llu mode 0%o uid %u gid %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->mode, __entry->uid, __entry->gid, __entry->blocks) ); TRACE_EVENT(ext4_request_inode, TP_PROTO(struct inode *dir, int mode), TP_ARGS(dir, mode), TP_STRUCT__entry( __field( u64, dir ) __field( dev_t, dev ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d dir %llu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_allocate_inode, TP_PROTO(struct inode *inode, struct inode *dir, int mode), TP_ARGS(inode, dir, mode), TP_STRUCT__entry( __field( u64, ino ) __field( u64, dir ) __field( dev_t, dev ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %llu dir %llu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_evict_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( int, nlink ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nlink = inode->i_nlink; ), TP_printk("dev %d,%d ino %llu nlink %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nlink) ); TRACE_EVENT(ext4_drop_inode, TP_PROTO(struct inode *inode, int drop), TP_ARGS(inode, drop), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( int, drop ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->drop = drop; ), TP_printk("dev %d,%d ino %llu drop %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->drop) ); TRACE_EVENT(ext4_nfs_commit_metadata, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino) ); TRACE_EVENT(ext4_mark_inode_dirty, TP_PROTO(struct inode *inode, unsigned long IP), TP_ARGS(inode, IP), TP_STRUCT__entry( __field( u64, ino ) __field(unsigned long, ip ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ip = IP; ), TP_printk("dev %d,%d ino %llu caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_begin_ordered_truncate, TP_PROTO(struct inode *inode, loff_t new_size), TP_ARGS(inode, new_size), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, new_size ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->new_size = new_size; ), TP_printk("dev %d,%d ino %llu new_size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->new_size) ); DECLARE_EVENT_CLASS(ext4__write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, pos ) __field( dev_t, dev ) __field( unsigned int, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; ), TP_printk("dev %d,%d ino %llu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, pos ) __field( dev_t, dev ) __field( unsigned int, len ) __field( unsigned int, copied ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; __entry->copied = copied; ), TP_printk("dev %d,%d ino %llu pos %lld len %u copied %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->len, __entry->copied) ); DEFINE_EVENT(ext4__write_end, ext4_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); TRACE_EVENT(ext4_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, range_start ) __field( loff_t, range_end ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( pgoff_t, writeback_index ) __field( dev_t, dev ) __field( int, sync_mode ) __field( char, for_kupdate ) __field( char, range_cyclic ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->range_cyclic = wbc->range_cyclic; ), TP_printk("dev %d,%d ino %llu nr_to_write %ld pages_skipped %ld " "range_start %lld range_end %lld sync_mode %d " "for_kupdate %d range_cyclic %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_folios_start, TP_PROTO(struct inode *inode, loff_t start_pos, loff_t next_pos, struct writeback_control *wbc), TP_ARGS(inode, start_pos, next_pos, wbc), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, start_pos ) __field( loff_t, next_pos ) __field( long, nr_to_write ) __field( dev_t, dev ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start_pos = start_pos; __entry->next_pos = next_pos; __entry->nr_to_write = wbc->nr_to_write; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %llu start_pos 0x%llx next_pos 0x%llx nr_to_write %ld sync_mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->start_pos, __entry->next_pos, __entry->nr_to_write, __entry->sync_mode) ); TRACE_EVENT(ext4_da_write_folios_end, TP_PROTO(struct inode *inode, loff_t start_pos, loff_t next_pos, struct writeback_control *wbc, int ret), TP_ARGS(inode, start_pos, next_pos, wbc, ret), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, start_pos ) __field( loff_t, next_pos ) __field( long, nr_to_write ) __field( dev_t, dev ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start_pos = start_pos; __entry->next_pos = next_pos; __entry->nr_to_write = wbc->nr_to_write; __entry->ret = ret; ), TP_printk("dev %d,%d ino %llu start_pos 0x%llx next_pos 0x%llx nr_to_write %ld ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->start_pos, __entry->next_pos, __entry->nr_to_write, __entry->ret) ); TRACE_EVENT(ext4_da_write_pages_extent, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map), TP_ARGS(inode, map), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, lblk ) __field( dev_t, dev ) __field( __u32, len ) __field( __u32, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->flags = map->m_flags; ), TP_printk("dev %d,%d ino %llu lblk %llu len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, show_mflags(__entry->flags)) ); TRACE_EVENT(ext4_writepages_result, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int ret, int pages_written), TP_ARGS(inode, wbc, ret, pages_written), TP_STRUCT__entry( __field( u64, ino ) __field( long, pages_skipped ) __field( pgoff_t, writeback_index ) __field( dev_t, dev ) __field( int, ret ) __field( int, pages_written ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %llu ret %d pages_written %d pages_skipped %ld " "sync_mode %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->sync_mode, (unsigned long) __entry->writeback_index) ); DECLARE_EVENT_CLASS(ext4__folio_op, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio), TP_STRUCT__entry( __field( u64, ino ) __field( pgoff_t, index ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->index = folio->index; ), TP_printk("dev %d,%d ino %llu folio_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned long) __entry->index) ); DEFINE_EVENT(ext4__folio_op, ext4_read_folio, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio) ); DEFINE_EVENT(ext4__folio_op, ext4_release_folio, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio) ); DECLARE_EVENT_CLASS(ext4_invalidate_folio_op, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length), TP_STRUCT__entry( __field( u64, ino ) __field( pgoff_t, index ) __field( size_t, offset ) __field( size_t, length ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = folio->mapping->host->i_sb->s_dev; __entry->ino = folio->mapping->host->i_ino; __entry->index = folio->index; __entry->offset = offset; __entry->length = length; ), TP_printk("dev %d,%d ino %llu folio_index %lu offset %zu length %zu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned long) __entry->index, __entry->offset, __entry->length) ); DEFINE_EVENT(ext4_invalidate_folio_op, ext4_invalidate_folio, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length) ); DEFINE_EVENT(ext4_invalidate_folio_op, ext4_journalled_invalidate_folio, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length) ); TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), TP_ARGS(sb, blk, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, blk ) __field( __u64, count ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->blk = blk; __entry->count = count; ), TP_printk("dev %d,%d blk %llu count %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blk, __entry->count) ); DECLARE_EVENT_CLASS(ext4__mb_new_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, pa_pstart ) __field( __u64, pa_lstart ) __field( dev_t, dev ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = ac->ac_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->pa_pstart = pa->pa_pstart; __entry->pa_lstart = pa->pa_lstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d ino %llu pstart %llu len %u lstart %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); TRACE_EVENT(ext4_mb_release_inode_pa, TP_PROTO(struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), TP_ARGS(pa, block, count), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, block ) __field( dev_t, dev ) __field( __u32, count ) ), TP_fast_assign( __entry->dev = pa->pa_inode->i_sb->s_dev; __entry->ino = pa->pa_inode->i_ino; __entry->block = block; __entry->count = count; ), TP_printk("dev %d,%d ino %llu block %llu count %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, TP_PROTO(struct super_block *sb, struct ext4_prealloc_space *pa), TP_ARGS(sb, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d pstart %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->pa_pstart, __entry->pa_len) ); TRACE_EVENT(ext4_discard_preallocations, TP_PROTO(struct inode *inode, unsigned int len), TP_ARGS(inode, len), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( unsigned int, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->len = len; ), TP_printk("dev %d,%d ino %llu len: %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->len) ); TRACE_EVENT(ext4_mb_discard_preallocations, TP_PROTO(struct super_block *sb, int needed), TP_ARGS(sb, needed), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, needed ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->needed = needed; ), TP_printk("dev %d,%d needed %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->needed) ); TRACE_EVENT(ext4_request_blocks, TP_PROTO(struct ext4_allocation_request *ar), TP_ARGS(ar), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( dev_t, dev ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %llu flags %s len %u lblk %u goal %llu " "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_allocate_blocks, TP_PROTO(struct ext4_allocation_request *ar, unsigned long long block), TP_ARGS(ar, block), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, block ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( dev_t, dev ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->block = block; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %llu flags %s len %u block %llu lblk %u " "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->block, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_free_blocks, TP_PROTO(struct inode *inode, __u64 block, unsigned long count, int flags), TP_ARGS(inode, block, count, flags), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, block ) __field( unsigned long, count ) __field( dev_t, dev ) __field( int, flags ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->count = count; __entry->flags = flags; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %llu mode 0%o block %llu count %lu flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->mode, __entry->block, __entry->count, show_free_flags(__entry->flags)) ); TRACE_EVENT(ext4_sync_file_enter, TP_PROTO(struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry( __field( u64, ino ) __field( u64, parent ) __field( dev_t, dev ) __field( int, datasync ) ), TP_fast_assign( struct dentry *dentry = file->f_path.dentry; __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->datasync = datasync; __entry->parent = d_inode(dentry->d_parent)->i_ino; ), TP_printk("dev %d,%d ino %llu parent %llu datasync %d ", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->parent, __entry->datasync) ); TRACE_EVENT(ext4_sync_file_exit, TP_PROTO(struct inode *inode, int ret), TP_ARGS(inode, ret), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %llu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->ret) ); TRACE_EVENT(ext4_sync_fs, TP_PROTO(struct super_block *sb, int wait), TP_ARGS(sb, wait), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, wait ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->wait = wait; ), TP_printk("dev %d,%d wait %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->wait) ); TRACE_EVENT(ext4_alloc_da_blocks, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( unsigned int, data_blocks ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; ), TP_printk("dev %d,%d ino %llu reserved_data_blocks %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->data_blocks) ); TRACE_EVENT(ext4_mballoc_alloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, goal_logical ) __field( int, goal_start ) __field( __u32, goal_group ) __field( int, goal_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) __field( __u16, found ) __field( __u16, groups ) __field( __u16, buddy ) __field( __u16, flags ) __field( __u16, tail ) __field( __u8, cr ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->goal_logical = ac->ac_g_ex.fe_logical; __entry->goal_start = ac->ac_g_ex.fe_start; __entry->goal_group = ac->ac_g_ex.fe_group; __entry->goal_len = ac->ac_g_ex.fe_len; __entry->result_logical = ac->ac_f_ex.fe_logical; __entry->result_start = ac->ac_f_ex.fe_start; __entry->result_group = ac->ac_f_ex.fe_group; __entry->result_len = ac->ac_f_ex.fe_len; __entry->found = ac->ac_found; __entry->flags = ac->ac_flags; __entry->groups = ac->ac_groups_scanned; __entry->buddy = ac->ac_buddy; __entry->tail = ac->ac_tail; __entry->cr = ac->ac_criteria; ), TP_printk("dev %d,%d inode %llu orig %u/%d/%u@%u goal %u/%d/%u@%u " "result %u/%d/%u@%u blks %u grps %u cr %s flags %s " "tail %u broken %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->goal_group, __entry->goal_start, __entry->goal_len, __entry->goal_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical, __entry->found, __entry->groups, show_criteria(__entry->cr), show_mballoc_flags(__entry->flags), __entry->tail, __entry->buddy ? 1 << __entry->buddy : 0) ); TRACE_EVENT(ext4_mballoc_prealloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->result_logical = ac->ac_b_ex.fe_logical; __entry->result_start = ac->ac_b_ex.fe_start; __entry->result_group = ac->ac_b_ex.fe_group; __entry->result_len = ac->ac_b_ex.fe_len; ), TP_printk("dev %d,%d inode %llu orig %u/%d/%u@%u result %u/%d/%u@%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical) ); DECLARE_EVENT_CLASS(ext4__mballoc, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = inode ? inode->i_ino : 0; __entry->result_start = start; __entry->result_group = group; __entry->result_len = len; ), TP_printk("dev %d,%d inode %llu extent %u/%d/%d ", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->result_group, __entry->result_start, __entry->result_len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); TRACE_EVENT(ext4_forget, TP_PROTO(struct inode *inode, int is_metadata, __u64 block), TP_ARGS(inode, is_metadata, block), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, block ) __field( dev_t, dev ) __field( int, is_metadata ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->is_metadata = is_metadata; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %llu mode 0%o is_metadata %d block %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->mode, __entry->is_metadata, __entry->block) ); TRACE_EVENT(ext4_da_update_reserve_space, TP_PROTO(struct inode *inode, int used_blocks, int quota_claim), TP_ARGS(inode, used_blocks, quota_claim), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, i_blocks ) __field( dev_t, dev ) __field( int, used_blocks ) __field( int, reserved_data_blocks ) __field( int, quota_claim ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->used_blocks = used_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->quota_claim = quota_claim; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %llu mode 0%o i_blocks %llu used_blocks %d " "reserved_data_blocks %d quota_claim %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->quota_claim) ); TRACE_EVENT(ext4_da_reserve_space, TP_PROTO(struct inode *inode, int nr_resv), TP_ARGS(inode, nr_resv), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, i_blocks ) __field( dev_t, dev ) __field( int, reserve_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->reserve_blocks = nr_resv; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %llu mode 0%o i_blocks %llu reserve_blocks %d" "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->mode, __entry->i_blocks, __entry->reserve_blocks, __entry->reserved_data_blocks) ); TRACE_EVENT(ext4_da_release_space, TP_PROTO(struct inode *inode, int freed_blocks), TP_ARGS(inode, freed_blocks), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, i_blocks ) __field( dev_t, dev ) __field( int, freed_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->freed_blocks = freed_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %llu mode 0%o i_blocks %llu freed_blocks %d " "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->mode, __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks) ); DECLARE_EVENT_CLASS(ext4__bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); TRACE_EVENT(ext4_read_block_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), TP_ARGS(sb, group, prefetch), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) __field( bool, prefetch ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; __entry->prefetch = prefetch; ), TP_printk("dev %d,%d group %u prefetch %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group, __entry->prefetch) ); DECLARE_EVENT_CLASS(ext4__fallocate_mode, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, offset ) __field( loff_t, len ) __field( dev_t, dev ) __field( int, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; __entry->mode = mode; ), TP_printk("dev %d,%d ino %llu offset %lld len %lld mode %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->offset, __entry->len, show_falloc_mode(__entry->mode)) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); TRACE_EVENT(ext4_fallocate_exit, TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), TP_ARGS(inode, offset, max_blocks, ret), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, pos ) __field( dev_t, dev ) __field( unsigned int, blocks ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = offset; __entry->blocks = max_blocks; __entry->ret = ret; ), TP_printk("dev %d,%d ino %llu pos %lld blocks %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->blocks, __entry->ret) ); TRACE_EVENT(ext4_unlink_enter, TP_PROTO(struct inode *parent, struct dentry *dentry), TP_ARGS(parent, dentry), TP_STRUCT__entry( __field( u64, ino ) __field( u64, parent ) __field( loff_t, size ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->parent = parent->i_ino; __entry->size = d_inode(dentry)->i_size; ), TP_printk("dev %d,%d ino %llu size %lld parent %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->parent) ); TRACE_EVENT(ext4_unlink_exit, TP_PROTO(struct dentry *dentry, int ret), TP_ARGS(dentry, ret), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( int, ret ) ), TP_fast_assign( __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %llu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->ret) ); DECLARE_EVENT_CLASS(ext4__truncate, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( u64, ino ) __field( __u64, blocks ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->blocks = inode->i_blocks; ), TP_printk("dev %d,%d ino %llu blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->blocks) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* 'ux' is the unwritten extent. */ TRACE_EVENT(ext4_ext_convert_to_initialized_enter, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, struct ext4_extent *ux), TP_ARGS(inode, map, ux), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, u_pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, m_lblk ) __field( unsigned, m_len ) __field( ext4_lblk_t, u_lblk ) __field( unsigned, u_len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_len = map->m_len; __entry->u_lblk = le32_to_cpu(ux->ee_block); __entry->u_len = ext4_ext_get_actual_len(ux); __entry->u_pblk = ext4_ext_pblock(ux); ), TP_printk("dev %d,%d ino %llu m_lblk %u m_len %u u_lblk %u u_len %u " "u_pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->m_lblk, __entry->m_len, __entry->u_lblk, __entry->u_len, __entry->u_pblk) ); /* * 'ux' is the unwritten extent. * 'ix' is the initialized extent to which blocks are transferred. */ TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, struct ext4_extent *ux, struct ext4_extent *ix), TP_ARGS(inode, map, ux, ix), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, u_pblk ) __field( ext4_fsblk_t, i_pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, m_lblk ) __field( unsigned, m_len ) __field( ext4_lblk_t, u_lblk ) __field( unsigned, u_len ) __field( ext4_lblk_t, i_lblk ) __field( unsigned, i_len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_len = map->m_len; __entry->u_lblk = le32_to_cpu(ux->ee_block); __entry->u_len = ext4_ext_get_actual_len(ux); __entry->u_pblk = ext4_ext_pblock(ux); __entry->i_lblk = le32_to_cpu(ix->ee_block); __entry->i_len = ext4_ext_get_actual_len(ix); __entry->i_pblk = ext4_ext_pblock(ix); ), TP_printk("dev %d,%d ino %llu m_lblk %u m_len %u " "u_lblk %u u_len %u u_pblk %llu " "i_lblk %u i_len %u i_pblk %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->m_lblk, __entry->m_len, __entry->u_lblk, __entry->u_len, __entry->u_pblk, __entry->i_lblk, __entry->i_len, __entry->i_pblk) ); DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len, unsigned int flags), TP_ARGS(inode, lblk, len, flags), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; __entry->len = len; __entry->flags = flags; ), TP_printk("dev %d,%d ino %llu lblk %u len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, show_map_flags(__entry->flags)) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned len, unsigned flags), TP_ARGS(inode, lblk, len, flags) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned len, unsigned flags), TP_ARGS(inode, lblk, len, flags) ); DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( unsigned int, flags ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, mflags ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->flags = flags; __entry->pblk = map->m_pblk; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->mflags = map->m_flags; __entry->ret = ret; ), TP_printk("dev %d,%d ino %llu flags %s lblk %u pblk %llu len %u " "mflags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, show_map_flags(__entry->flags), __entry->lblk, __entry->pblk, __entry->len, show_mflags(__entry->mflags), __entry->ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret) ); TRACE_EVENT(ext4_ext_load_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk), TP_ARGS(inode, lblk, pblk), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %llu lblk %u pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->pblk) ); TRACE_EVENT(ext4_load_inode, TP_PROTO(struct super_block *sb, unsigned long ino), TP_ARGS(sb, ino), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = ino; ), TP_printk("dev %d,%d ino %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino) ); TRACE_EVENT(ext4_journal_start_sb, TP_PROTO(struct super_block *sb, int blocks, int rsv_blocks, int revoke_creds, int type, unsigned long IP), TP_ARGS(sb, blocks, rsv_blocks, revoke_creds, type, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, ip ) __field( int, blocks ) __field( int, rsv_blocks ) __field( int, revoke_creds ) __field( int, type ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; __entry->rsv_blocks = rsv_blocks; __entry->revoke_creds = revoke_creds; __entry->type = type; ), TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d," " type %d, caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds, __entry->type, (void *)__entry->ip) ); TRACE_EVENT(ext4_journal_start_inode, TP_PROTO(struct inode *inode, int blocks, int rsv_blocks, int revoke_creds, int type, unsigned long IP), TP_ARGS(inode, blocks, rsv_blocks, revoke_creds, type, IP), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( unsigned long, ip ) __field( int, blocks ) __field( int, rsv_blocks ) __field( int, revoke_creds ) __field( int, type ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; __entry->rsv_blocks = rsv_blocks; __entry->revoke_creds = revoke_creds; __entry->type = type; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d," " type %d, ino %llu, caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds, __entry->type, __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_journal_start_reserved, TP_PROTO(struct super_block *sb, int blocks, unsigned long IP), TP_ARGS(sb, blocks, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, ip ) __field( int, blocks ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; ), TP_printk("dev %d,%d blocks, %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, (void *)__entry->ip) ); DECLARE_EVENT_CLASS(ext4__trim, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len), TP_STRUCT__entry( __field( int, dev_major ) __field( int, dev_minor ) __field( __u32, group ) __field( int, start ) __field( int, len ) ), TP_fast_assign( __entry->dev_major = MAJOR(sb->s_dev); __entry->dev_minor = MINOR(sb->s_dev); __entry->group = group; __entry->start = start; __entry->len = len; ), TP_printk("dev %d,%d group %u, start %d, len %d", __entry->dev_major, __entry->dev_minor, __entry->group, __entry->start, __entry->len) ); DEFINE_EVENT(ext4__trim, ext4_trim_extent, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len) ); DEFINE_EVENT(ext4__trim, ext4_trim_all_free, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len) ); TRACE_EVENT(ext4_ext_handle_unwritten_extents, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags, unsigned int allocated, ext4_fsblk_t newblock), TP_ARGS(inode, map, flags, allocated, newblock), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( ext4_fsblk_t, newblk ) __field( dev_t, dev ) __field( int, flags ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, allocated ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->flags = flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; __entry->allocated = allocated; __entry->newblk = newblock; ), TP_printk("dev %d,%d ino %llu m_lblk %u m_pblk %llu m_len %u flags %s " "allocated %d newblock %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, __entry->len, show_map_flags(__entry->flags), (unsigned int) __entry->allocated, (unsigned long long) __entry->newblk) ); TRACE_EVENT(ext4_get_implied_cluster_alloc_exit, TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret), TP_ARGS(sb, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned int, flags ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) __field( unsigned int, len ) __field( int, ret ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->flags = map->m_flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; __entry->ret = ret; ), TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lblk, (unsigned long long) __entry->pblk, __entry->len, show_mflags(__entry->flags), __entry->ret) ); TRACE_EVENT(ext4_ext_show_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, unsigned short len), TP_ARGS(inode, lblk, pblk, len), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( unsigned short, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; __entry->lblk = lblk; __entry->len = len; ), TP_printk("dev %d,%d ino %llu lblk %u pblk %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, (unsigned short) __entry->len) ); TRACE_EVENT(ext4_remove_blocks, TP_PROTO(struct inode *inode, struct ext4_extent *ex, ext4_lblk_t from, ext4_fsblk_t to, struct partial_cluster *pc), TP_ARGS(inode, ex, from, to, pc), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, ee_pblk ) __field( ext4_fsblk_t, pc_pclu ) __field( dev_t, dev ) __field( ext4_lblk_t, from ) __field( ext4_lblk_t, to ) __field( ext4_lblk_t, ee_lblk ) __field( unsigned short, ee_len ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->from = from; __entry->to = to; __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_len = ext4_ext_get_actual_len(ex); __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %llu extent [%u(%llu), %u]" "from %u to %u partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, (unsigned) __entry->from, (unsigned) __entry->to, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_leaf, TP_PROTO(struct inode *inode, ext4_lblk_t start, struct ext4_extent *ex, struct partial_cluster *pc), TP_ARGS(inode, start, ex, pc), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, ee_pblk ) __field( ext4_fsblk_t, pc_pclu ) __field( dev_t, dev ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, ee_lblk ) __field( short, ee_len ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_len = ext4_ext_get_actual_len(ex); __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %llu start_lblk %u last_extent [%u(%llu), %u]" "partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned) __entry->start, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_idx, TP_PROTO(struct inode *inode, ext4_fsblk_t pblk), TP_ARGS(inode, pblk), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; ), TP_printk("dev %d,%d ino %llu index_pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned long long) __entry->pblk) ); TRACE_EVENT(ext4_ext_remove_space, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, int depth), TP_ARGS(inode, start, end, depth), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->end = end; __entry->depth = depth; ), TP_printk("dev %d,%d ino %llu since %u end %u depth %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth) ); TRACE_EVENT(ext4_ext_remove_space_done, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, int depth, struct partial_cluster *pc, __le16 eh_entries), TP_ARGS(inode, start, end, depth, pc, eh_entries), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pc_pclu ) __field( dev_t, dev ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state ) __field( unsigned short, eh_entries ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->end = end; __entry->depth = depth; __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; __entry->eh_entries = le16_to_cpu(eh_entries); ), TP_printk("dev %d,%d ino %llu since %u end %u depth %d " "partial [pclu %lld lblk %u state %d] " "remaining_entries %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state, (unsigned short) __entry->eh_entries) ); DECLARE_EVENT_CLASS(ext4__es_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), TP_STRUCT__entry( __field( u64, ino ) __field( u64, seq ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->seq = EXT4_I(inode)->i_es_seq; ), TP_printk("dev %d,%d ino %llu es [%u/%u) mapped %llu status %s seq %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status), __entry->seq) ); DEFINE_EVENT(ext4__es_extent, ext4_es_insert_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es) ); DEFINE_EVENT(ext4__es_extent, ext4_es_cache_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es) ); TRACE_EVENT(ext4_es_remove_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len), TP_ARGS(inode, lblk, len), TP_STRUCT__entry( __field( u64, ino ) __field( loff_t, lblk ) __field( loff_t, len ) __field( u64, seq ) __field( dev_t, dev ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; __entry->len = len; __entry->seq = EXT4_I(inode)->i_es_seq; ), TP_printk("dev %d,%d ino %llu es [%lld/%lld) seq %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, __entry->seq) ); TRACE_EVENT(ext4_es_find_extent_range_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %llu lblk %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk) ); TRACE_EVENT(ext4_es_find_extent_range_exit, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); ), TP_printk("dev %d,%d ino %llu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status)) ); TRACE_EVENT(ext4_es_lookup_extent_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), TP_STRUCT__entry( __field( u64, ino ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %llu lblk %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk) ); TRACE_EVENT(ext4_es_lookup_extent_exit, TP_PROTO(struct inode *inode, struct extent_status *es, int found), TP_ARGS(inode, es, found), TP_STRUCT__entry( __field( u64, ino ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( int, found ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->found = found; ), TP_printk("dev %d,%d ino %llu found %d [%u/%u) %llu %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->found, __entry->lblk, __entry->len, __entry->found ? __entry->pblk : 0, show_extent_status(__entry->found ? __entry->status : 0)) ); DECLARE_EVENT_CLASS(ext4__es_shrink_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_to_scan ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_to_scan = nr_to_scan; __entry->cache_cnt = cache_cnt; ), TP_printk("dev %d,%d nr_to_scan %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_to_scan, __entry->cache_cnt) ); DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_count, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt) ); DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_scan_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt) ); TRACE_EVENT(ext4_es_shrink_scan_exit, TP_PROTO(struct super_block *sb, int nr_shrunk, int cache_cnt), TP_ARGS(sb, nr_shrunk, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_shrunk ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_shrunk = nr_shrunk; __entry->cache_cnt = cache_cnt; ), TP_printk("dev %d,%d nr_shrunk %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, __entry->cache_cnt) ); TRACE_EVENT(ext4_collapse_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len), TP_ARGS(inode, offset, len), TP_STRUCT__entry( __field(u64, ino) __field(loff_t, offset) __field(loff_t, len) __field(dev_t, dev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; ), TP_printk("dev %d,%d ino %llu offset %lld len %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->offset, __entry->len) ); TRACE_EVENT(ext4_insert_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len), TP_ARGS(inode, offset, len), TP_STRUCT__entry( __field(u64, ino) __field(loff_t, offset) __field(loff_t, len) __field(dev_t, dev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; ), TP_printk("dev %d,%d ino %llu offset %lld len %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->offset, __entry->len) ); TRACE_EVENT(ext4_es_shrink, TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time, int nr_skipped, int retried), TP_ARGS(sb, nr_shrunk, scan_time, nr_skipped, retried), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_shrunk ) __field( unsigned long long, scan_time ) __field( int, nr_skipped ) __field( int, retried ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_shrunk = nr_shrunk; __entry->scan_time = div_u64(scan_time, 1000); __entry->nr_skipped = nr_skipped; __entry->retried = retried; ), TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu " "nr_skipped %d retried %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, __entry->scan_time, __entry->nr_skipped, __entry->retried) ); TRACE_EVENT(ext4_es_insert_delayed_extent, TP_PROTO(struct inode *inode, struct extent_status *es, bool lclu_allocated, bool end_allocated), TP_ARGS(inode, es, lclu_allocated, end_allocated), TP_STRUCT__entry( __field( u64, ino ) __field( u64, seq ) __field( ext4_fsblk_t, pblk ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( char, status ) __field( bool, lclu_allocated ) __field( bool, end_allocated ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->lclu_allocated = lclu_allocated; __entry->end_allocated = end_allocated; __entry->seq = EXT4_I(inode)->i_es_seq; ), TP_printk("dev %d,%d ino %llu es [%u/%u) mapped %llu status %s allocated %d %d seq %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status), __entry->lclu_allocated, __entry->end_allocated, __entry->seq) ); /* fsmap traces */ DECLARE_EVENT_CLASS(ext4_fsmap_class, TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, u64 owner), TP_ARGS(sb, keydev, agno, bno, len, owner), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(u32, agno) __field(u64, bno) __field(u64, len) __field(u64, owner) ), TP_fast_assign( __entry->dev = sb->s_bdev->bd_dev; __entry->keydev = new_decode_dev(keydev); __entry->agno = agno; __entry->bno = bno; __entry->len = len; __entry->owner = owner; ), TP_printk("dev %d:%d keydev %d:%d agno %u bno %llu len %llu owner %lld\n", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, __entry->bno, __entry->len, __entry->owner) ) #define DEFINE_FSMAP_EVENT(name) \ DEFINE_EVENT(ext4_fsmap_class, name, \ TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, \ u64 owner), \ TP_ARGS(sb, keydev, agno, bno, len, owner)) DEFINE_FSMAP_EVENT(ext4_fsmap_low_key); DEFINE_FSMAP_EVENT(ext4_fsmap_high_key); DEFINE_FSMAP_EVENT(ext4_fsmap_mapping); DECLARE_EVENT_CLASS(ext4_getfsmap_class, TP_PROTO(struct super_block *sb, struct ext4_fsmap *fsmap), TP_ARGS(sb, fsmap), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(u64, block) __field(u64, len) __field(u64, owner) __field(u64, flags) ), TP_fast_assign( __entry->dev = sb->s_bdev->bd_dev; __entry->keydev = new_decode_dev(fsmap->fmr_device); __entry->block = fsmap->fmr_physical; __entry->len = fsmap->fmr_length; __entry->owner = fsmap->fmr_owner; __entry->flags = fsmap->fmr_flags; ), TP_printk("dev %d:%d keydev %d:%d block %llu len %llu owner %lld flags 0x%llx\n", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->block, __entry->len, __entry->owner, __entry->flags) ) #define DEFINE_GETFSMAP_EVENT(name) \ DEFINE_EVENT(ext4_getfsmap_class, name, \ TP_PROTO(struct super_block *sb, struct ext4_fsmap *fsmap), \ TP_ARGS(sb, fsmap)) DEFINE_GETFSMAP_EVENT(ext4_getfsmap_low_key); DEFINE_GETFSMAP_EVENT(ext4_getfsmap_high_key); DEFINE_GETFSMAP_EVENT(ext4_getfsmap_mapping); TRACE_EVENT(ext4_shutdown, TP_PROTO(struct super_block *sb, unsigned long flags), TP_ARGS(sb, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned, flags ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->flags = flags; ), TP_printk("dev %d,%d flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->flags) ); TRACE_EVENT(ext4_error, TP_PROTO(struct super_block *sb, const char *function, unsigned int line), TP_ARGS(sb, function, line), TP_STRUCT__entry( __field( dev_t, dev ) __field( const char *, function ) __field( unsigned, line ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->function = function; __entry->line = line; ), TP_printk("dev %d,%d function %s line %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->function, __entry->line) ); TRACE_EVENT(ext4_prefetch_bitmaps, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_group_t next, unsigned int prefetch_ios), TP_ARGS(sb, group, next, prefetch_ios), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) __field( __u32, next ) __field( __u32, ios ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; __entry->next = next; __entry->ios = prefetch_ios; ), TP_printk("dev %d,%d group %u next %u ios %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group, __entry->next, __entry->ios) ); TRACE_EVENT(ext4_lazy_itable_init, TP_PROTO(struct super_block *sb, ext4_group_t group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); TRACE_EVENT(ext4_fc_replay_scan, TP_PROTO(struct super_block *sb, int error, int off), TP_ARGS(sb, error, off), TP_STRUCT__entry( __field(dev_t, dev) __field(int, error) __field(int, off) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->error = error; __entry->off = off; ), TP_printk("dev %d,%d error %d, off %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->error, __entry->off) ); TRACE_EVENT(ext4_fc_replay, TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2), TP_ARGS(sb, tag, ino, priv1, priv2), TP_STRUCT__entry( __field(dev_t, dev) __field(int, tag) __field(int, ino) __field(int, priv1) __field(int, priv2) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->tag = tag; __entry->ino = ino; __entry->priv1 = priv1; __entry->priv2 = priv2; ), TP_printk("dev %d,%d: tag %d, ino %d, data1 %d, data2 %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tag, __entry->ino, __entry->priv1, __entry->priv2) ); TRACE_EVENT(ext4_fc_commit_start, TP_PROTO(struct super_block *sb, tid_t commit_tid), TP_ARGS(sb, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->tid = commit_tid; ), TP_printk("dev %d,%d tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid) ); TRACE_EVENT(ext4_fc_commit_stop, TP_PROTO(struct super_block *sb, int nblks, int reason, tid_t commit_tid), TP_ARGS(sb, nblks, reason, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) __field(int, nblks) __field(int, reason) __field(int, num_fc) __field(int, num_fc_ineligible) __field(int, nblks_agg) __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nblks = nblks; __entry->reason = reason; __entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits; __entry->num_fc_ineligible = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks; __entry->tid = commit_tid; ), TP_printk("dev %d,%d nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nblks, __entry->reason, __entry->num_fc, __entry->num_fc_ineligible, __entry->nblks_agg, __entry->tid) ); #define EM(a) { EXT4_FC_SNAP_ERR_##a, #a }, #define EMe(a) { EXT4_FC_SNAP_ERR_##a, #a } TRACE_EVENT(ext4_fc_lock_updates, TP_PROTO(struct super_block *sb, tid_t commit_tid, u64 locked_ns, unsigned int nr_inodes, unsigned int nr_ranges, int err, int snap_err), TP_ARGS(sb, commit_tid, locked_ns, nr_inodes, nr_ranges, err, snap_err), TP_STRUCT__entry(/* entry */ __field(dev_t, dev) __field(tid_t, tid) __field(u64, locked_ns) __field(unsigned int, nr_inodes) __field(unsigned int, nr_ranges) __field(int, err) __field(int, snap_err) ), TP_fast_assign(/* assign */ __entry->dev = sb->s_dev; __entry->tid = commit_tid; __entry->locked_ns = locked_ns; __entry->nr_inodes = nr_inodes; __entry->nr_ranges = nr_ranges; __entry->err = err; __entry->snap_err = snap_err; ), TP_printk("dev %d,%d tid %u locked_ns %llu nr_inodes %u nr_ranges %u err %d snap_err %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->locked_ns, __entry->nr_inodes, __entry->nr_ranges, __entry->err, __print_symbolic(__entry->snap_err, TRACE_SNAP_ERR)) ); #undef EM #undef EMe #undef TRACE_SNAP_ERR #define FC_REASON_NAME_STAT(reason) \ show_fc_reason(reason), \ __entry->fc_ineligible_rc[reason] TRACE_EVENT(ext4_fc_stats, TP_PROTO(struct super_block *sb), TP_ARGS(sb), TP_STRUCT__entry( __field(dev_t, dev) __array(unsigned int, fc_ineligible_rc, EXT4_FC_REASON_MAX) __field(unsigned long, fc_commits) __field(unsigned long, fc_ineligible_commits) __field(unsigned long, fc_numblks) ), TP_fast_assign( int i; __entry->dev = sb->s_dev; for (i = 0; i < EXT4_FC_REASON_MAX; i++) { __entry->fc_ineligible_rc[i] = EXT4_SB(sb)->s_fc_stats.fc_ineligible_reason_count[i]; } __entry->fc_commits = EXT4_SB(sb)->s_fc_stats.fc_num_commits; __entry->fc_ineligible_commits = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->fc_numblks = EXT4_SB(sb)->s_fc_stats.fc_numblks; ), TP_printk("dev %d,%d fc ineligible reasons:\n" "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u" "num_commits:%lu, ineligible: %lu, numblks: %lu", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), FC_REASON_NAME_STAT(EXT4_FC_REASON_ENCRYPTED_FILENAME), __entry->fc_commits, __entry->fc_ineligible_commits, __entry->fc_numblks) ); DECLARE_EVENT_CLASS(ext4_fc_track_dentry, TP_PROTO(handle_t *handle, struct inode *inode, struct dentry *dentry, int ret), TP_ARGS(handle, inode, dentry, ret), TP_STRUCT__entry( __field(u64, i_ino) __field(dev_t, dev) __field(tid_t, t_tid) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), TP_printk("dev %d,%d, t_tid %u, ino %llu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error ) ); #define DEFINE_EVENT_CLASS_DENTRY(__type) \ DEFINE_EVENT(ext4_fc_track_dentry, ext4_fc_track_##__type, \ TP_PROTO(handle_t *handle, struct inode *inode, \ struct dentry *dentry, int ret), \ TP_ARGS(handle, inode, dentry, ret) \ ) DEFINE_EVENT_CLASS_DENTRY(create); DEFINE_EVENT_CLASS_DENTRY(link); DEFINE_EVENT_CLASS_DENTRY(unlink); TRACE_EVENT(ext4_fc_track_inode, TP_PROTO(handle_t *handle, struct inode *inode, int ret), TP_ARGS(handle, inode, ret), TP_STRUCT__entry( __field(u64, i_ino) __field(dev_t, dev) __field(tid_t, t_tid) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), TP_printk("dev %d:%d, t_tid %u, inode %llu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error) ); TRACE_EVENT(ext4_fc_track_range, TP_PROTO(handle_t *handle, struct inode *inode, long start, long end, int ret), TP_ARGS(handle, inode, start, end, ret), TP_STRUCT__entry( __field(u64, i_ino) __field(long, start) __field(long, end) __field(dev_t, dev) __field(tid_t, t_tid) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->start = start; __entry->end = end; __entry->error = ret; ), TP_printk("dev %d:%d, t_tid %u, inode %llu, i_sync_tid %u, error %d, start %ld, end %ld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error, __entry->start, __entry->end) ); TRACE_EVENT(ext4_fc_cleanup, TP_PROTO(journal_t *journal, int full, tid_t tid), TP_ARGS(journal, full, tid), TP_STRUCT__entry( __field(dev_t, dev) __field(int, j_fc_off) __field(int, full) __field(tid_t, tid) ), TP_fast_assign( struct super_block *sb = journal->j_private; __entry->dev = sb->s_dev; __entry->j_fc_off = journal->j_fc_off; __entry->full = full; __entry->tid = tid; ), TP_printk("dev %d,%d, j_fc_off %d, full %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->j_fc_off, __entry->full, __entry->tid) ); TRACE_EVENT(ext4_update_sb, TP_PROTO(struct super_block *sb, ext4_fsblk_t fsblk, unsigned int flags), TP_ARGS(sb, fsblk, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(ext4_fsblk_t, fsblk) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->fsblk = fsblk; __entry->flags = flags; ), TP_printk("dev %d,%d fsblk %llu flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fsblk, __entry->flags) ); TRACE_EVENT(ext4_move_extent_enter, TP_PROTO(struct inode *orig_inode, struct ext4_map_blocks *orig_map, struct inode *donor_inode, ext4_lblk_t donor_lblk), TP_ARGS(orig_inode, orig_map, donor_inode, donor_lblk), TP_STRUCT__entry( __field(u64, orig_ino) __field(u64, donor_ino) __field(dev_t, dev) __field(ext4_lblk_t, orig_lblk) __field(unsigned int, orig_flags) __field(ext4_lblk_t, donor_lblk) __field(unsigned int, len) ), TP_fast_assign( __entry->dev = orig_inode->i_sb->s_dev; __entry->orig_ino = orig_inode->i_ino; __entry->orig_lblk = orig_map->m_lblk; __entry->orig_flags = orig_map->m_flags; __entry->donor_ino = donor_inode->i_ino; __entry->donor_lblk = donor_lblk; __entry->len = orig_map->m_len; ), TP_printk("dev %d,%d origin ino %llu lblk %u flags %s donor ino %llu lblk %u len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->orig_ino, __entry->orig_lblk, show_mflags(__entry->orig_flags), __entry->donor_ino, __entry->donor_lblk, __entry->len) ); TRACE_EVENT(ext4_move_extent_exit, TP_PROTO(struct inode *orig_inode, ext4_lblk_t orig_lblk, struct inode *donor_inode, ext4_lblk_t donor_lblk, unsigned int m_len, u64 move_len, int move_type, int ret), TP_ARGS(orig_inode, orig_lblk, donor_inode, donor_lblk, m_len, move_len, move_type, ret), TP_STRUCT__entry( __field(u64, orig_ino) __field(u64, donor_ino) __field(u64, move_len) __field(dev_t, dev) __field(ext4_lblk_t, orig_lblk) __field(ext4_lblk_t, donor_lblk) __field(unsigned int, m_len) __field(int, move_type) __field(int, ret) ), TP_fast_assign( __entry->dev = orig_inode->i_sb->s_dev; __entry->orig_ino = orig_inode->i_ino; __entry->orig_lblk = orig_lblk; __entry->donor_ino = donor_inode->i_ino; __entry->donor_lblk = donor_lblk; __entry->m_len = m_len; __entry->move_len = move_len; __entry->move_type = move_type; __entry->ret = ret; ), TP_printk("dev %d,%d origin ino %llu lblk %u donor ino %llu lblk %u m_len %u, move_len %llu type %d ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->orig_ino, __entry->orig_lblk, __entry->donor_ino, __entry->donor_lblk, __entry->m_len, __entry->move_len, __entry->move_type, __entry->ret) ); #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 6 2 1 1 2 1 1 1 1 13 13 8 5 12 24 24 57 70 61 61 61 12 56 2 2 55 56 60 104 63 56 103 103 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "device.h" #include "peer.h" #include "socket.h" #include "queueing.h" #include "messages.h" #include <linux/ctype.h> #include <linux/net.h> #include <linux/if_vlan.h> #include <linux/if_ether.h> #include <linux/inetdevice.h> #include <net/udp_tunnel.h> #include <net/ipv6.h> static int send4(struct wg_device *wg, struct sk_buff *skb, struct endpoint *endpoint, u8 ds, struct dst_cache *cache) { struct flowi4 fl = { .saddr = endpoint->src4.s_addr, .daddr = endpoint->addr4.sin_addr.s_addr, .fl4_dport = endpoint->addr4.sin_port, .flowi4_mark = wg->fwmark, .flowi4_proto = IPPROTO_UDP }; struct rtable *rt = NULL; struct sock *sock; int ret = 0; skb_mark_not_on_list(skb); skb->dev = wg->dev; skb->mark = wg->fwmark; rcu_read_lock_bh(); sock = rcu_dereference_bh(wg->sock4); if (unlikely(!sock)) { ret = -ENONET; goto err; } fl.fl4_sport = inet_sk(sock)->inet_sport; if (cache) rt = dst_cache_get_ip4(cache, &fl.saddr); if (!rt) { security_sk_classify_flow(sock, flowi4_to_flowi_common(&fl)); if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, fl.saddr, RT_SCOPE_HOST))) { endpoint->src4.s_addr = 0; endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); } rt = ip_route_output_flow(sock_net(sock), &fl, sock); if (unlikely(endpoint->src_if4 && ((IS_ERR(rt) && PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && rt->dst.dev->ifindex != endpoint->src_if4)))) { endpoint->src4.s_addr = 0; endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); if (!IS_ERR(rt)) ip_rt_put(rt); rt = ip_route_output_flow(sock_net(sock), &fl, sock); } if (IS_ERR(rt)) { ret = PTR_ERR(rt); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; } if (cache) dst_cache_set_ip4(cache, &rt->dst, fl.saddr); } skb->ignore_df = 1; udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds, ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, fl.fl4_dport, false, false, 0); goto out; err: kfree_skb(skb); out: rcu_read_unlock_bh(); return ret; } static int send6(struct wg_device *wg, struct sk_buff *skb, struct endpoint *endpoint, u8 ds, struct dst_cache *cache) { #if IS_ENABLED(CONFIG_IPV6) struct flowi6 fl = { .saddr = endpoint->src6, .daddr = endpoint->addr6.sin6_addr, .fl6_dport = endpoint->addr6.sin6_port, .flowi6_mark = wg->fwmark, .flowi6_oif = endpoint->addr6.sin6_scope_id, .flowi6_proto = IPPROTO_UDP /* TODO: addr->sin6_flowinfo */ }; struct dst_entry *dst = NULL; struct sock *sock; int ret = 0; skb_mark_not_on_list(skb); skb->dev = wg->dev; skb->mark = wg->fwmark; rcu_read_lock_bh(); sock = rcu_dereference_bh(wg->sock6); if (unlikely(!sock)) { ret = -ENONET; goto err; } fl.fl6_sport = inet_sk(sock)->inet_sport; if (cache) dst = dst_cache_get_ip6(cache, &fl.saddr); if (!dst) { security_sk_classify_flow(sock, flowi6_to_flowi_common(&fl)); if (unlikely(!ipv6_addr_any(&fl.saddr) && !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) { endpoint->src6 = fl.saddr = in6addr_any; if (cache) dst_cache_reset(cache); } dst = ip6_dst_lookup_flow(sock_net(sock), sock, &fl, NULL); if (IS_ERR(dst)) { ret = PTR_ERR(dst); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; } if (cache) dst_cache_set_ip6(cache, dst, &fl.saddr); } skb->ignore_df = 1; udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds, ip6_dst_hoplimit(dst), 0, fl.fl6_sport, fl.fl6_dport, false, 0); goto out; err: kfree_skb(skb); out: rcu_read_unlock_bh(); return ret; #else kfree_skb(skb); return -EAFNOSUPPORT; #endif } int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb, u8 ds) { size_t skb_len = skb->len; int ret = -EAFNOSUPPORT; read_lock_bh(&peer->endpoint_lock); if (peer->endpoint.addr.sa_family == AF_INET) ret = send4(peer->device, skb, &peer->endpoint, ds, &peer->endpoint_cache); else if (peer->endpoint.addr.sa_family == AF_INET6) ret = send6(peer->device, skb, &peer->endpoint, ds, &peer->endpoint_cache); else dev_kfree_skb(skb); if (likely(!ret)) peer->tx_bytes += skb_len; read_unlock_bh(&peer->endpoint_lock); return ret; } int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *buffer, size_t len, u8 ds) { struct sk_buff *skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC); if (unlikely(!skb)) return -ENOMEM; skb_reserve(skb, SKB_HEADER_LEN); skb_set_inner_network_header(skb, 0); skb_put_data(skb, buffer, len); return wg_socket_send_skb_to_peer(peer, skb, ds); } int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg, struct sk_buff *in_skb, void *buffer, size_t len) { int ret = 0; struct sk_buff *skb; struct endpoint endpoint; if (unlikely(!in_skb)) return -EINVAL; ret = wg_socket_endpoint_from_skb(&endpoint, in_skb); if (unlikely(ret < 0)) return ret; skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC); if (unlikely(!skb)) return -ENOMEM; skb_reserve(skb, SKB_HEADER_LEN); skb_set_inner_network_header(skb, 0); skb_put_data(skb, buffer, len); if (endpoint.addr.sa_family == AF_INET) ret = send4(wg, skb, &endpoint, 0, NULL); else if (endpoint.addr.sa_family == AF_INET6) ret = send6(wg, skb, &endpoint, 0, NULL); /* No other possibilities if the endpoint is valid, which it is, * as we checked above. */ return ret; } int wg_socket_endpoint_from_skb(struct endpoint *endpoint, const struct sk_buff *skb) { memset(endpoint, 0, sizeof(*endpoint)); if (skb->protocol == htons(ETH_P_IP)) { endpoint->addr4.sin_family = AF_INET; endpoint->addr4.sin_port = udp_hdr(skb)->source; endpoint->addr4.sin_addr.s_addr = ip_hdr(skb)->saddr; endpoint->src4.s_addr = ip_hdr(skb)->daddr; endpoint->src_if4 = skb->skb_iif; } else if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { endpoint->addr6.sin6_family = AF_INET6; endpoint->addr6.sin6_port = udp_hdr(skb)->source; endpoint->addr6.sin6_addr = ipv6_hdr(skb)->saddr; endpoint->addr6.sin6_scope_id = ipv6_iface_scope_id( &ipv6_hdr(skb)->saddr, skb->skb_iif); endpoint->src6 = ipv6_hdr(skb)->daddr; } else { return -EINVAL; } return 0; } static bool endpoint_eq(const struct endpoint *a, const struct endpoint *b) { return (a->addr.sa_family == AF_INET && b->addr.sa_family == AF_INET && a->addr4.sin_port == b->addr4.sin_port && a->addr4.sin_addr.s_addr == b->addr4.sin_addr.s_addr && a->src4.s_addr == b->src4.s_addr && a->src_if4 == b->src_if4) || (a->addr.sa_family == AF_INET6 && b->addr.sa_family == AF_INET6 && a->addr6.sin6_port == b->addr6.sin6_port && ipv6_addr_equal(&a->addr6.sin6_addr, &b->addr6.sin6_addr) && a->addr6.sin6_scope_id == b->addr6.sin6_scope_id && ipv6_addr_equal(&a->src6, &b->src6)) || unlikely(!a->addr.sa_family && !b->addr.sa_family); } void wg_socket_set_peer_endpoint(struct wg_peer *peer, const struct endpoint *endpoint) { /* First we check unlocked, in order to optimize, since it's pretty rare * that an endpoint will change. If we happen to be mid-write, and two * CPUs wind up writing the same thing or something slightly different, * it doesn't really matter much either. */ if (endpoint_eq(endpoint, &peer->endpoint)) return; write_lock_bh(&peer->endpoint_lock); if (endpoint->addr.sa_family == AF_INET) { peer->endpoint.addr4 = endpoint->addr4; peer->endpoint.src4 = endpoint->src4; peer->endpoint.src_if4 = endpoint->src_if4; } else if (IS_ENABLED(CONFIG_IPV6) && endpoint->addr.sa_family == AF_INET6) { peer->endpoint.addr6 = endpoint->addr6; peer->endpoint.src6 = endpoint->src6; } else { goto out; } dst_cache_reset(&peer->endpoint_cache); out: write_unlock_bh(&peer->endpoint_lock); } void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer, const struct sk_buff *skb) { struct endpoint endpoint; if (!wg_socket_endpoint_from_skb(&endpoint, skb)) wg_socket_set_peer_endpoint(peer, &endpoint); } void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer) { write_lock_bh(&peer->endpoint_lock); memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6)); dst_cache_reset_now(&peer->endpoint_cache); write_unlock_bh(&peer->endpoint_lock); } static int wg_receive(struct sock *sk, struct sk_buff *skb) { struct wg_device *wg; if (unlikely(!sk)) goto err; wg = sk->sk_user_data; if (unlikely(!wg)) goto err; skb_mark_not_on_list(skb); wg_packet_receive(wg, skb); return 0; err: kfree_skb(skb); return 0; } static void sock_free(struct sock *sock) { if (unlikely(!sock)) return; sk_clear_memalloc(sock); udp_tunnel_sock_release(sock); } static void set_sock_opts(struct socket *sock) { sock->sk->sk_allocation = GFP_ATOMIC; sock->sk->sk_sndbuf = INT_MAX; sk_set_memalloc(sock->sk); } int wg_socket_init(struct wg_device *wg, u16 port) { struct net *net; int ret; struct udp_tunnel_sock_cfg cfg = { .sk_user_data = wg, .encap_type = 1, .encap_rcv = wg_receive }; struct socket *new4 = NULL, *new6 = NULL; struct udp_port_cfg port4 = { .family = AF_INET, .local_ip.s_addr = htonl(INADDR_ANY), .local_udp_port = htons(port), .use_udp_checksums = true }; #if IS_ENABLED(CONFIG_IPV6) int retries = 0; struct udp_port_cfg port6 = { .family = AF_INET6, .local_ip6 = IN6ADDR_ANY_INIT, .use_udp6_tx_checksums = true, .use_udp6_rx_checksums = true, .ipv6_v6only = true }; #endif rcu_read_lock(); net = rcu_dereference(wg->creating_net); net = net ? maybe_get_net(net) : NULL; rcu_read_unlock(); if (unlikely(!net)) return -ENONET; #if IS_ENABLED(CONFIG_IPV6) retry: #endif ret = udp_sock_create(net, &port4, &new4); if (ret < 0) { pr_err("%s: Could not create IPv4 socket\n", wg->dev->name); goto out; } set_sock_opts(new4); setup_udp_tunnel_sock(net, new4->sk, &cfg); #if IS_ENABLED(CONFIG_IPV6) if (ipv6_mod_enabled()) { port6.local_udp_port = inet_sk(new4->sk)->inet_sport; ret = udp_sock_create(net, &port6, &new6); if (ret < 0) { udp_tunnel_sock_release(new4->sk); if (ret == -EADDRINUSE && !port && retries++ < 100) goto retry; pr_err("%s: Could not create IPv6 socket\n", wg->dev->name); goto out; } set_sock_opts(new6); setup_udp_tunnel_sock(net, new6->sk, &cfg); } #endif wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL); ret = 0; out: put_net(net); return ret; } void wg_socket_reinit(struct wg_device *wg, struct sock *new4, struct sock *new6) { struct sock *old4, *old6; mutex_lock(&wg->socket_update_lock); old4 = rcu_dereference_protected(wg->sock4, lockdep_is_held(&wg->socket_update_lock)); old6 = rcu_dereference_protected(wg->sock6, lockdep_is_held(&wg->socket_update_lock)); rcu_assign_pointer(wg->sock4, new4); rcu_assign_pointer(wg->sock6, new6); if (new4) wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); synchronize_net(); sock_free(old4); sock_free(old6); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SEGMENT_H #define _ASM_X86_SEGMENT_H #include <linux/const.h> #include <asm/alternative.h> #include <asm/ibt.h> /* * Constructor for a conventional segment GDT (or LDT) entry. * This is a macro so it can be used in initializers. */ #define GDT_ENTRY(flags, base, limit) \ ((((base) & _AC(0xff000000,ULL)) << (56-24)) | \ (((flags) & _AC(0x0000f0ff,ULL)) << 40) | \ (((limit) & _AC(0x000f0000,ULL)) << (48-16)) | \ (((base) & _AC(0x00ffffff,ULL)) << 16) | \ (((limit) & _AC(0x0000ffff,ULL)))) /* Simple and small GDT entries for booting only: */ #define GDT_ENTRY_BOOT_CS 2 #define GDT_ENTRY_BOOT_DS 3 #define GDT_ENTRY_BOOT_TSS 4 #define __BOOT_CS (GDT_ENTRY_BOOT_CS*8) #define __BOOT_DS (GDT_ENTRY_BOOT_DS*8) #define __BOOT_TSS (GDT_ENTRY_BOOT_TSS*8) /* * Bottom two bits of selector give the ring * privilege level */ #define SEGMENT_RPL_MASK 0x3 /* * When running on Xen PV, the actual privilege level of the kernel is 1, * not 0. Testing the Requested Privilege Level in a segment selector to * determine whether the context is user mode or kernel mode with * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level * matches the 0x3 mask. * * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV * kernels because privilege level 2 is never used. */ #define USER_SEGMENT_RPL_MASK 0x2 /* User mode is privilege level 3: */ #define USER_RPL 0x3 /* Bit 2 is Table Indicator (TI): selects between LDT or GDT */ #define SEGMENT_TI_MASK 0x4 /* LDT segment has TI set ... */ #define SEGMENT_LDT 0x4 /* ... GDT has it cleared */ #define SEGMENT_GDT 0x0 #define GDT_ENTRY_INVALID_SEG 0 #if defined(CONFIG_X86_32) && !defined(BUILD_VDSO32_64) /* * The layout of the per-CPU GDT under Linux: * * 0 - null <=== cacheline #1 * 1 - reserved * 2 - reserved * 3 - reserved * * 4 - unused <=== cacheline #2 * 5 - unused * * ------- start of TLS (Thread-Local Storage) segments: * * 6 - TLS segment #1 [ glibc's TLS segment ] * 7 - TLS segment #2 [ Wine's %fs Win32 segment ] * 8 - TLS segment #3 <=== cacheline #3 * 9 - reserved * 10 - reserved * 11 - reserved * * ------- start of kernel segments: * * 12 - kernel code segment <=== cacheline #4 * 13 - kernel data segment * 14 - default user CS * 15 - default user DS * 16 - TSS <=== cacheline #5 * 17 - LDT * 18 - PNPBIOS support (16->32 gate) * 19 - PNPBIOS support * 20 - PNPBIOS support <=== cacheline #6 * 21 - PNPBIOS support * 22 - PNPBIOS support * 23 - APM BIOS support * 24 - APM BIOS support <=== cacheline #7 * 25 - APM BIOS support * * 26 - ESPFIX small SS * 27 - per-cpu [ offset to per-cpu data area ] * 28 - VDSO getcpu * 29 - unused * 30 - unused * 31 - TSS for double fault handler */ #define GDT_ENTRY_TLS_MIN 6 #define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) #define GDT_ENTRY_KERNEL_CS 12 #define GDT_ENTRY_KERNEL_DS 13 #define GDT_ENTRY_DEFAULT_USER_CS 14 #define GDT_ENTRY_DEFAULT_USER_DS 15 #define GDT_ENTRY_TSS 16 #define GDT_ENTRY_LDT 17 #define GDT_ENTRY_PNPBIOS_CS32 18 #define GDT_ENTRY_PNPBIOS_CS16 19 #define GDT_ENTRY_PNPBIOS_DS 20 #define GDT_ENTRY_PNPBIOS_TS1 21 #define GDT_ENTRY_PNPBIOS_TS2 22 #define GDT_ENTRY_APMBIOS_BASE 23 #define GDT_ENTRY_ESPFIX_SS 26 #define GDT_ENTRY_PERCPU 27 #define GDT_ENTRY_CPUNODE 28 #define GDT_ENTRY_DOUBLEFAULT_TSS 31 /* * Number of entries in the GDT table: */ #define GDT_ENTRIES 32 /* * Segment selector values corresponding to the above entries: */ #define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) #define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) #define __USER32_CS __USER_CS #define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS*8) /* segment for calling fn: */ #define PNP_CS32 (GDT_ENTRY_PNPBIOS_CS32*8) /* code segment for BIOS: */ #define PNP_CS16 (GDT_ENTRY_PNPBIOS_CS16*8) /* "Is this PNP code selector (PNP_CS32 or PNP_CS16)?" */ #define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == PNP_CS32) /* data segment for BIOS: */ #define PNP_DS (GDT_ENTRY_PNPBIOS_DS*8) /* transfer data segment: */ #define PNP_TS1 (GDT_ENTRY_PNPBIOS_TS1*8) /* another data segment: */ #define PNP_TS2 (GDT_ENTRY_PNPBIOS_TS2*8) #ifdef CONFIG_SMP # define __KERNEL_PERCPU (GDT_ENTRY_PERCPU*8) #else # define __KERNEL_PERCPU 0 #endif #define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) #else /* 64-bit: */ #include <asm/cache.h> #define GDT_ENTRY_KERNEL32_CS 1 #define GDT_ENTRY_KERNEL_CS 2 #define GDT_ENTRY_KERNEL_DS 3 /* * We cannot use the same code segment descriptor for user and kernel mode, * not even in long flat mode, because of different DPL. * * GDT layout to get 64-bit SYSCALL/SYSRET support right. SYSRET hardcodes * selectors: * * if returning to 32-bit userspace: cs = STAR.SYSRET_CS, * if returning to 64-bit userspace: cs = STAR.SYSRET_CS+16, * * ss = STAR.SYSRET_CS+8 (in either case) * * thus USER_DS should be between 32-bit and 64-bit code selectors: */ #define GDT_ENTRY_DEFAULT_USER32_CS 4 #define GDT_ENTRY_DEFAULT_USER_DS 5 #define GDT_ENTRY_DEFAULT_USER_CS 6 /* Needs two entries */ #define GDT_ENTRY_TSS 8 /* Needs two entries */ #define GDT_ENTRY_LDT 10 #define GDT_ENTRY_TLS_MIN 12 #define GDT_ENTRY_TLS_MAX 14 #define GDT_ENTRY_CPUNODE 15 /* * Number of entries in the GDT table: */ #define GDT_ENTRIES 16 /* * Segment selector values corresponding to the above entries: * * Note, selectors also need to have a correct RPL, * expressed with the +3 value for user-space selectors: */ #define __KERNEL32_CS (GDT_ENTRY_KERNEL32_CS*8) #define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) #define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) #define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8 + 3) #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) #define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) #endif #define IDT_ENTRIES 256 #define NUM_EXCEPTION_VECTORS 32 /* Bitmask of exception vectors which push an error code on the stack: */ #define EXCEPTION_ERRCODE_MASK 0x20027d00 #define GDT_SIZE (GDT_ENTRIES*8) #define GDT_ENTRY_TLS_ENTRIES 3 #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8) /* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */ #define VDSO_CPUNODE_BITS 12 #define VDSO_CPUNODE_MASK 0xfff #ifndef __ASSEMBLER__ /* Helper functions to store/load CPU and node numbers */ static inline unsigned long vdso_encode_cpunode(int cpu, unsigned long node) { return (node << VDSO_CPUNODE_BITS) | cpu; } static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) { unsigned long p; /* * Load CPU and node number from the GDT. LSL is faster than RDTSCP * and works on all CPUs. This is volatile so that it orders * correctly with respect to barrier() and to keep GCC from cleverly * hoisting it out of the calling function. * * If RDPID is available, use it. */ alternative_io ("lsl %[seg],%k[p]", "rdpid %[p]", X86_FEATURE_RDPID, [p] "=r" (p), [seg] "r" (__CPUNODE_SEG)); if (cpu) *cpu = (p & VDSO_CPUNODE_MASK); if (node) *node = (p >> VDSO_CPUNODE_BITS); } #endif /* !__ASSEMBLER__ */ #ifdef __KERNEL__ /* * early_idt_handler_array is an array of entry points referenced in the * early IDT. For simplicity, it's a real array with one entry point * every nine bytes. That leaves room for an optional 'push $0' if the * vector has no error code (two bytes), a 'push $vector_number' (two * bytes), and a jump to the common entry code (up to five bytes). */ #define EARLY_IDT_HANDLER_SIZE (9 + ENDBR_INSN_SIZE) /* * xen_early_idt_handler_array is for Xen pv guests: for each entry in * early_idt_handler_array it contains a prequel in the form of * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to * max 8 bytes. */ #define XEN_EARLY_IDT_HANDLER_SIZE (8 + ENDBR_INSN_SIZE) #ifndef __ASSEMBLER__ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; extern void early_ignore_irq(void); #ifdef CONFIG_XEN_PV extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE]; #endif /* * Load a segment. Fall back on loading the zero segment if something goes * wrong. This variant assumes that loading zero fully clears the segment. * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any * failure to fully clear the cached descriptor is only observable for * FS and GS. */ #define LOAD_SEGMENT(seg) \ static inline void __loadsegment_##seg(u16 value) \ { \ asm volatile("1: movl %k0,%%" #seg "\n" \ _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k0)\ : "+r" (value) : : "memory"); \ } LOAD_SEGMENT(ss) LOAD_SEGMENT(ds) LOAD_SEGMENT(es) #ifdef CONFIG_X86_32 /* * On 32-bit systems, the hidden parts of FS and GS are unobservable if * the selector is NULL, so there's no funny business here. */ LOAD_SEGMENT(fs) LOAD_SEGMENT(gs) #else static inline void __loadsegment_fs(u16 value) { asm volatile("1: movw %0, %%fs\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_CLEAR_FS) : : ASM_INPUT_RM (value) : "memory"); } /* __loadsegment_gs is intentionally undefined. Use load_gs_index instead. */ #endif #undef LOAD_SEGMENT #define loadsegment(seg, val) __loadsegment_##seg(val) /* * Save a segment register away: */ #define SAVE_SEGMENT(seg) \ static inline unsigned long __savesegment_##seg(void) \ { \ unsigned long v; \ asm volatile("movl %%" #seg ",%k0" : "=r" (v)); \ return v; \ } SAVE_SEGMENT(cs) SAVE_SEGMENT(ss) SAVE_SEGMENT(ds) SAVE_SEGMENT(es) SAVE_SEGMENT(fs) SAVE_SEGMENT(gs) #undef SAVE_SEGMENT #define savesegment(seg, var) ((var) = __savesegment_##seg()) #endif /* !__ASSEMBLER__ */ #endif /* __KERNEL__ */ #endif /* _ASM_X86_SEGMENT_H */ |
| 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_H #define _LINUX_CONTEXT_TRACKING_H #include <linux/sched.h> #include <linux/vtime.h> #include <linux/context_tracking_state.h> #include <linux/instrumentation.h> #include <asm/ptrace.h> #ifdef CONFIG_CONTEXT_TRACKING_USER extern void ct_cpu_track_user(int cpu); /* Called with interrupts disabled. */ extern void __ct_user_enter(enum ctx_state state); extern void __ct_user_exit(enum ctx_state state); extern void ct_user_enter(enum ctx_state state); extern void ct_user_exit(enum ctx_state state); extern void user_enter_callable(void); extern void user_exit_callable(void); static inline void user_enter(void) { if (context_tracking_enabled()) ct_user_enter(CT_STATE_USER); } static inline void user_exit(void) { if (context_tracking_enabled()) ct_user_exit(CT_STATE_USER); } /* Called with interrupts disabled. */ static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) __ct_user_enter(CT_STATE_USER); } static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) __ct_user_exit(CT_STATE_USER); } static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) || !context_tracking_enabled()) return 0; prev_ctx = __ct_state(); if (prev_ctx != CT_STATE_KERNEL) ct_user_exit(prev_ctx); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) && context_tracking_enabled()) { if (prev_ctx != CT_STATE_KERNEL) ct_user_enter(prev_ctx); } } static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) __ct_user_enter(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) __ct_user_exit(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline void user_enter_irqoff(void) { } static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ #ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE extern void context_tracking_init(void); #else static inline void context_tracking_init(void) { } #endif /* CONFIG_CONTEXT_TRACKING_USER_FORCE */ #ifdef CONFIG_CONTEXT_TRACKING_IDLE extern void ct_idle_enter(void); extern void ct_idle_exit(void); /* * Is RCU watching the current CPU (IOW, it is not in an extended quiescent state)? * * Note that this returns the actual boolean data (watching / not watching), * whereas ct_rcu_watching() returns the RCU_WATCHING subvariable of * context_tracking.state. * * No ordering, as we are sampling CPU-local information. */ static __always_inline bool rcu_is_watching_curr_cpu(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING; } /* * Increment the current CPU's context_tracking structure's ->state field * with ordering. Return the new value. */ static __always_inline unsigned long ct_state_inc(int incby) { return raw_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state)); } static __always_inline bool warn_rcu_enter(void) { bool ret = false; /* * Horrible hack to shut up recursive RCU isn't watching fail since * lots of the actual reporting also relies on RCU. */ preempt_disable_notrace(); if (!rcu_is_watching_curr_cpu()) { ret = true; ct_state_inc(CT_RCU_WATCHING); } return ret; } static __always_inline void warn_rcu_exit(bool rcu) { if (rcu) ct_state_inc(CT_RCU_WATCHING); preempt_enable_notrace(); } #else static inline void ct_idle_enter(void) { } static inline void ct_idle_exit(void) { } static __always_inline bool warn_rcu_enter(void) { return false; } static __always_inline void warn_rcu_exit(bool rcu) { } #endif /* !CONFIG_CONTEXT_TRACKING_IDLE */ #endif |
| 1 1 1 13 7 3 4 39 35 22 1 22 3 13 7 7 2 2 1 5 19 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Facebook #include <linux/debugfs.h> #include <linux/random.h> #include <net/netdev_queues.h> #include "netdevsim.h" static void nsim_get_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { struct netdevsim *ns = netdev_priv(dev); if (ns->ethtool.pauseparam.report_stats_rx) pause_stats->rx_pause_frames = 1; if (ns->ethtool.pauseparam.report_stats_tx) pause_stats->tx_pause_frames = 2; } static void nsim_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct netdevsim *ns = netdev_priv(dev); pause->autoneg = 0; /* We don't support ksettings, so can't pretend */ pause->rx_pause = ns->ethtool.pauseparam.rx; pause->tx_pause = ns->ethtool.pauseparam.tx; } static int nsim_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct netdevsim *ns = netdev_priv(dev); if (pause->autoneg) return -EINVAL; ns->ethtool.pauseparam.rx = pause->rx_pause; ns->ethtool.pauseparam.tx = pause->tx_pause; return 0; } static int nsim_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); memcpy(coal, &ns->ethtool.coalesce, sizeof(ns->ethtool.coalesce)); return 0; } static int nsim_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); memcpy(&ns->ethtool.coalesce, coal, sizeof(ns->ethtool.coalesce)); return 0; } static void nsim_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring)); kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX; if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; } static int nsim_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); ns->ethtool.ring.rx_pending = ring->rx_pending; ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending; ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending; ns->ethtool.ring.tx_pending = ring->tx_pending; return 0; } static void nsim_get_channels(struct net_device *dev, struct ethtool_channels *ch) { struct netdevsim *ns = netdev_priv(dev); ch->max_combined = ns->nsim_bus_dev->num_queues; ch->combined_count = ns->ethtool.channels; } static void nsim_wake_queues(struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); struct netdevsim *peer; synchronize_net(); netif_tx_wake_all_queues(dev); rcu_read_lock(); peer = rcu_dereference(ns->peer); if (peer) netif_tx_wake_all_queues(peer->netdev); rcu_read_unlock(); } static int nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch) { struct netdevsim *ns = netdev_priv(dev); int err; err = netif_set_real_num_queues(dev, ch->combined_count, ch->combined_count); if (err) return err; ns->ethtool.channels = ch->combined_count; /* Only wake up queues if devices are linked */ if (rcu_access_pointer(ns->peer)) nsim_wake_queues(dev); return 0; } static int nsim_get_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam) { struct netdevsim *ns = netdev_priv(dev); if (ns->ethtool.get_err) return -ns->ethtool.get_err; memcpy(fecparam, &ns->ethtool.fec, sizeof(ns->ethtool.fec)); return 0; } static int nsim_set_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam) { struct netdevsim *ns = netdev_priv(dev); u32 fec; if (ns->ethtool.set_err) return -ns->ethtool.set_err; memcpy(&ns->ethtool.fec, fecparam, sizeof(ns->ethtool.fec)); fec = fecparam->fec; if (fec == ETHTOOL_FEC_AUTO) fec |= ETHTOOL_FEC_OFF; fec |= ETHTOOL_FEC_NONE; ns->ethtool.fec.active_fec = 1 << (fls(fec) - 1); return 0; } static const struct ethtool_fec_hist_range netdevsim_fec_ranges[] = { { 0, 0}, { 1, 3}, { 4, 7}, { 0, 0} }; static void nsim_get_fec_stats(struct net_device *dev, struct ethtool_fec_stats *fec_stats, struct ethtool_fec_hist *hist) { struct ethtool_fec_hist_value *values = hist->values; hist->ranges = netdevsim_fec_ranges; fec_stats->corrected_blocks.total = 123; fec_stats->uncorrectable_blocks.total = 4; values[0].per_lane[0] = 125; values[0].per_lane[1] = 120; values[0].per_lane[2] = 100; values[0].per_lane[3] = 100; values[1].sum = 12; values[2].sum = 2; values[2].per_lane[0] = 2; values[2].per_lane[1] = 0; values[2].per_lane[2] = 0; values[2].per_lane[3] = 0; } static int nsim_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct netdevsim *ns = netdev_priv(dev); info->phc_index = mock_phc_index(ns->phc); return 0; } static const struct ethtool_ops nsim_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_ALL_PARAMS, .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT | ETHTOOL_RING_USE_HDS_THRS, .op_needs_rtnl = ETHTOOL_OP_NEEDS_RTNL_SCHANNELS, .get_pause_stats = nsim_get_pause_stats, .get_pauseparam = nsim_get_pauseparam, .set_pauseparam = nsim_set_pauseparam, .set_coalesce = nsim_set_coalesce, .get_coalesce = nsim_get_coalesce, .get_ringparam = nsim_get_ringparam, .set_ringparam = nsim_set_ringparam, .get_channels = nsim_get_channels, .set_channels = nsim_set_channels, .get_fecparam = nsim_get_fecparam, .set_fecparam = nsim_set_fecparam, .get_fec_stats = nsim_get_fec_stats, .get_ts_info = nsim_get_ts_info, }; static void nsim_ethtool_ring_init(struct netdevsim *ns) { ns->ethtool.ring.rx_pending = 512; ns->ethtool.ring.rx_max_pending = 4096; ns->ethtool.ring.rx_jumbo_max_pending = 4096; ns->ethtool.ring.rx_mini_max_pending = 4096; ns->ethtool.ring.tx_pending = 512; ns->ethtool.ring.tx_max_pending = 4096; } void nsim_ethtool_init(struct netdevsim *ns) { struct dentry *ethtool, *dir; ns->netdev->ethtool_ops = &nsim_ethtool_ops; nsim_ethtool_ring_init(ns); ns->ethtool.pauseparam.report_stats_rx = true; ns->ethtool.pauseparam.report_stats_tx = true; ns->ethtool.fec.fec = ETHTOOL_FEC_NONE; ns->ethtool.fec.active_fec = ETHTOOL_FEC_NONE; ns->ethtool.channels = ns->nsim_bus_dev->num_queues; ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir); ns->ethtool_ddir = ethtool; debugfs_create_u32("get_err", 0600, ethtool, &ns->ethtool.get_err); debugfs_create_u32("set_err", 0600, ethtool, &ns->ethtool.set_err); dir = debugfs_create_dir("pause", ethtool); debugfs_create_bool("report_stats_rx", 0600, dir, &ns->ethtool.pauseparam.report_stats_rx); debugfs_create_bool("report_stats_tx", 0600, dir, &ns->ethtool.pauseparam.report_stats_tx); dir = debugfs_create_dir("ring", ethtool); debugfs_create_u32("rx_max_pending", 0600, dir, &ns->ethtool.ring.rx_max_pending); debugfs_create_u32("rx_jumbo_max_pending", 0600, dir, &ns->ethtool.ring.rx_jumbo_max_pending); debugfs_create_u32("rx_mini_max_pending", 0600, dir, &ns->ethtool.ring.rx_mini_max_pending); debugfs_create_u32("tx_max_pending", 0600, dir, &ns->ethtool.ring.tx_max_pending); } void nsim_ethtool_fini(struct netdevsim *ns) { debugfs_remove(ns->ethtool_ddir); } |
| 85 36 36 35 115 14 100 155 4 151 150 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/fsync.c * * Copyright (C) 1993 Stephen Tweedie (sct@redhat.com) * from * Copyright (C) 1992 Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * from * linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds * * ext4fs fsync primitive * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * * Removed unnecessary code duplication for little endian machines * and excessive __inline__s. * Andi Kleen, 1997 * * Major simplications and cleanup - we only need to do the metadata, because * we can depend on generic_block_fdatasync() to sync the data blocks. */ #include <linux/time.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include "ext4.h" #include "ext4_jbd2.h" #include <trace/events/ext4.h> /* * If we're not journaling and this is a just-created file, we have to * sync our parent directory (if it was freshly created) since * otherwise it will only be written by writeback, leaving a huge * window during which a crash may lose the file. This may apply for * the parent directory's parent as well, and so on recursively, if * they are also freshly created. */ static int ext4_sync_parent(struct inode *inode) { struct dentry *dentry, *next; int ret = 0; if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) return 0; dentry = d_find_any_alias(inode); if (!dentry) return 0; while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); next = dget_parent(dentry); dput(dentry); dentry = next; inode = dentry->d_inode; /* * The directory inode may have gone through rmdir by now. But * the inode itself and its blocks are still allocated (we hold * a reference to the inode via its dentry), so it didn't go * through ext4_evict_inode()) and so we are safe to flush * metadata blocks and the inode. */ ret = mmb_sync(&EXT4_I(inode)->i_metadata_bhs); if (ret) break; ret = sync_inode_metadata(inode, 1); if (ret) break; } dput(dentry); return ret; } static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end, int datasync, bool *needs_barrier) { struct inode *inode = file->f_inode; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 0, }; int ret; ret = mmb_fsync_noflush(file, &EXT4_I(inode)->i_metadata_bhs, start, end, datasync); if (ret) return ret; /* Force writeout of inode table buffer to disk */ ret = ext4_write_inode(inode, &wbc); if (ret) return ret; ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) *needs_barrier = true; return ret; } static int ext4_fsync_journal(struct inode *inode, bool datasync, bool *needs_barrier) { struct ext4_inode_info *ei = EXT4_I(inode); journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; /* * Fastcommit does not really support fsync on directories or other * special files. Force a full commit. */ if (!S_ISREG(inode->i_mode)) return ext4_force_commit(inode->i_sb); if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) *needs_barrier = true; return ext4_fc_commit(journal, commit_tid); } /* * akpm: A new design for ext4_sync_file(). * * This is only called from sys_fsync(), sys_fdatasync() and sys_msync(). * There cannot be a transaction open by this task. * Another task could have dirtied this inode. Its data can be in any * state in the journalling system. * * What we do is just kick off a commit and wait on it. This will snapshot the * inode to disk. */ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { int ret = 0, err; bool needs_barrier = false; struct inode *inode = file->f_mapping->host; ret = ext4_emergency_state(inode->i_sb); if (unlikely(ret)) return ret; ASSERT(ext4_journal_current_handle() == NULL); trace_ext4_sync_file_enter(file, datasync); if (sb_rdonly(inode->i_sb)) goto out; if (!EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fsync_nojournal(file, start, end, datasync, &needs_barrier); if (needs_barrier) goto issue_flush; goto out; } ret = file_write_and_wait_range(file, start, end); if (ret) goto out; /* * The caller's filemap_fdatawrite()/wait will sync the data. * Metadata is in the journal, we wait for proper transaction to * commit here. */ ret = ext4_fsync_journal(inode, datasync, &needs_barrier); issue_flush: if (needs_barrier) { err = blkdev_issue_flush(inode->i_sb->s_bdev); if (!ret) ret = err; } out: err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; trace_ext4_sync_file_exit(inode, ret); return ret; } |
| 6 24 2 1 11 11 7 106 77 31 22 22 22 22 22 19 1 8 2 6 1 29 1 2 26 3 11 22 215 137 92 18 8 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 | // SPDX-License-Identifier: GPL-2.0 /* * Supplementary group IDs */ #include <linux/cred.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sort.h> #include <linux/syscalls.h> #include <linux/user_namespace.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; gi = kvmalloc_flex(*gi, gid, gidsetsize, GFP_KERNEL_ACCOUNT); if (!gi) return NULL; refcount_set(&gi->usage, 1); gi->ngroups = gidsetsize; return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { kvfree(group_info); } EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, const struct group_info *group_info) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } return 0; } /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; kgid_t kgid; if (get_user(gid, grouplist+i)) return -EFAULT; kgid = make_kgid(user_ns, gid); if (!gid_valid(kgid)) return -EINVAL; group_info->gid[i] = kgid; } return 0; } static int gid_cmp(const void *_a, const void *_b) { kgid_t a = *(kgid_t *)_a; kgid_t b = *(kgid_t *)_b; return gid_gt(a, b) - gid_lt(a, b); } void groups_sort(struct group_info *group_info) { sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid), gid_cmp, NULL); } EXPORT_SYMBOL(groups_sort); /* a simple bsearch */ int groups_search(const struct group_info *group_info, kgid_t grp) { unsigned int left, right; if (!group_info) return 0; left = 0; right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; } return 0; } /** * set_groups - Change a group subscription in a set of credentials * @new: The newly prepared set of credentials to alter * @group_info: The group list to install */ void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); get_group_info(group_info); new->group_info = group_info; } EXPORT_SYMBOL(set_groups); /** * set_current_groups - Change current's group subscription * @group_info: The group list to impose * * Validate a group subscription and, if valid, impose it upon current's task * security record. */ int set_current_groups(struct group_info *group_info) { struct cred *new; const struct cred *old; int retval; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); set_groups(new, group_info); retval = security_task_fix_setgroups(new, old); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } EXPORT_SYMBOL(set_current_groups); SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) { const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: return i; } bool may_setgroups(void) { struct user_namespace *user_ns = current_user_ns(); return ns_capable_setid(user_ns, CAP_SETGID) && userns_may_setgroups(user_ns); } /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. */ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) { struct group_info *group_info; int retval; if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; group_info = groups_alloc(gidsetsize); if (!group_info) return -ENOMEM; retval = groups_from_user(group_info, grouplist); if (retval) { put_group_info(group_info); return retval; } groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); return retval; } /* * Check whether we're fsgid/egid or in the supplemental group.. */ int in_group_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->fsgid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_group_p); int in_egroup_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->egid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_egroup_p); |
| 84 181 182 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Client Manager * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_CLIENTMGR_H #define __SND_SEQ_CLIENTMGR_H #include <sound/seq_kernel.h> #include <linux/bitops.h> #include "seq_fifo.h" #include "seq_ports.h" #include "seq_lock.h" /* client manager */ #define SND_SEQ_GROUP_FILTER_MASK GENMASK(SNDRV_UMP_MAX_GROUPS, 0) #define SND_SEQ_GROUP_FILTER_GROUPS GENMASK(SNDRV_UMP_MAX_GROUPS, 1) struct snd_seq_user_client { struct file *file; /* file struct of client */ /* ... */ struct pid *owner; /* fifo */ struct snd_seq_fifo *fifo; /* queue for incoming events */ int fifo_pool_size; }; struct snd_seq_kernel_client { /* ... */ struct snd_card *card; }; struct snd_seq_client { snd_seq_client_type_t type; unsigned int accept_input: 1, accept_output: 1; unsigned int midi_version; unsigned int user_pversion; char name[64]; /* client name */ int number; /* client number */ unsigned int filter; /* filter flags */ DECLARE_BITMAP(event_filter, 256); unsigned int group_filter; snd_use_lock_t use_lock; int event_lost; /* ports */ int num_ports; /* number of ports */ struct list_head ports_list_head; rwlock_t ports_lock; struct mutex ports_mutex; struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ int ump_endpoint_port; /* output pool */ struct snd_seq_pool *pool; /* memory pool for this client */ union { struct snd_seq_user_client user; struct snd_seq_kernel_client kernel; } data; /* for UMP */ void **ump_info; }; /* usage statistics */ struct snd_seq_usage { int cur; int peak; }; int client_init_data(void); int snd_sequencer_device_init(void); void snd_sequencer_device_done(void); /* get locked pointer to client */ struct snd_seq_client *snd_seq_client_use_ptr(int clientid); static inline struct snd_seq_client * snd_seq_client_ref(struct snd_seq_client *client) { snd_use_lock_use(&client->use_lock); return client; } /* unlock pointer to client */ static inline void snd_seq_client_unref(struct snd_seq_client *client) { snd_use_lock_free(&client->use_lock); } DEFINE_FREE(snd_seq_client, struct snd_seq_client *, if (!IS_ERR_OR_NULL(_T)) snd_seq_client_unref(_T)) /* dispatch event to client(s) */ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop); int snd_seq_kernel_client_write_poll(int clientid, struct file *file, poll_table *wait); int snd_seq_client_notify_subscription(int client, int port, struct snd_seq_port_subscribe *info, int evtype); int __snd_seq_deliver_single_event(struct snd_seq_client *dest, struct snd_seq_client_port *dest_port, struct snd_seq_event *event, int atomic, int hop); /* only for OSS sequencer */ int snd_seq_kernel_client_ioctl(int clientid, unsigned int cmd, void *arg); extern int seq_client_load[15]; /* for internal use between kernel sequencer clients */ struct snd_seq_client *snd_seq_kernel_client_get(int client); void snd_seq_kernel_client_put(struct snd_seq_client *cptr); static inline bool snd_seq_client_is_ump(struct snd_seq_client *c) { return c->midi_version != SNDRV_SEQ_CLIENT_LEGACY_MIDI; } static inline bool snd_seq_client_is_midi2(struct snd_seq_client *c) { return c->midi_version == SNDRV_SEQ_CLIENT_UMP_MIDI_2_0; } #endif |
| 6 3 3 6 6 6 6 6 6 6 6 6 6 6 6 6 1 9 3 1 2 3 3 27 1 1 1 1 1 9 1 1 12 9 1 1 1 7 6 6 6 6 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/dma-map-ops.h> #include <linux/mm.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/skbuff_ref.h> #include <linux/anon_inodes.h> #include <net/page_pool/helpers.h> #include <net/page_pool/memory_provider.h> #include <net/netlink.h> #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> #include <net/tcp.h> #include <net/rps.h> #include <trace/events/page_pool.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "kbuf.h" #include "memmap.h" #include "zcrx.h" #include "rsrc.h" #define IO_ZCRX_AREA_SUPPORTED_FLAGS (IORING_ZCRX_AREA_DMABUF) #define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) static inline struct io_zcrx_ifq *io_pp_to_ifq(struct page_pool *pp) { return pp->mp_priv; } static inline struct io_zcrx_area *io_zcrx_iov_to_area(const struct net_iov *niov) { struct net_iov_area *owner = net_iov_owner(niov); return container_of(owner, struct io_zcrx_area, nia); } static bool zcrx_set_ring_ctx(struct io_zcrx_ifq *zcrx, struct io_ring_ctx *ctx) { guard(spinlock_bh)(&zcrx->ctx_lock); if (zcrx->master_ctx) return false; percpu_ref_get(&ctx->refs); zcrx->master_ctx = ctx; return true; } static inline struct page *io_zcrx_iov_page(const struct net_iov *niov) { struct io_zcrx_area *area = io_zcrx_iov_to_area(niov); unsigned niov_pages_shift; lockdep_assert(!area->mem.is_dmabuf); niov_pages_shift = area->ifq->niov_shift - PAGE_SHIFT; return area->mem.pages[net_iov_idx(niov) << niov_pages_shift]; } static int io_area_max_shift(struct io_zcrx_mem *mem) { struct sg_table *sgt = mem->sgt; struct scatterlist *sg; unsigned shift = -1U; unsigned i; for_each_sgtable_dma_sg(sgt, sg, i) shift = min(shift, __ffs(sg_dma_len(sg))); return shift; } static int io_populate_area_dma(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) { unsigned niov_size = 1U << ifq->niov_shift; struct sg_table *sgt = area->mem.sgt; struct scatterlist *sg; unsigned i, niov_idx = 0; for_each_sgtable_dma_sg(sgt, sg, i) { dma_addr_t dma = sg_dma_address(sg); unsigned long sg_len = sg_dma_len(sg); if (WARN_ON_ONCE(sg_len % niov_size)) return -EINVAL; while (sg_len && niov_idx < area->nia.num_niovs) { struct net_iov *niov = &area->nia.niovs[niov_idx]; if (net_mp_niov_set_dma_addr(niov, dma)) return -EFAULT; sg_len -= niov_size; dma += niov_size; niov_idx++; } } if (WARN_ON_ONCE(niov_idx != area->nia.num_niovs)) return -EFAULT; return 0; } static void io_release_dmabuf(struct io_zcrx_mem *mem) { if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) return; if (mem->sgt) dma_buf_unmap_attachment_unlocked(mem->attach, mem->sgt, DMA_FROM_DEVICE); if (mem->attach) dma_buf_detach(mem->dmabuf, mem->attach); if (mem->dmabuf) dma_buf_put(mem->dmabuf); mem->sgt = NULL; mem->attach = NULL; mem->dmabuf = NULL; } static int io_import_dmabuf(struct io_zcrx_ifq *ifq, struct io_zcrx_mem *mem, struct io_uring_zcrx_area_reg *area_reg) { unsigned long off = (unsigned long)area_reg->addr; unsigned long len = (unsigned long)area_reg->len; unsigned long total_size = 0; struct scatterlist *sg; int dmabuf_fd = area_reg->dmabuf_fd; int i, ret; if (!ifq->dev) return -EINVAL; if (off) return -EINVAL; if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) return -EINVAL; mem->is_dmabuf = true; mem->dmabuf = dma_buf_get(dmabuf_fd); if (IS_ERR(mem->dmabuf)) { ret = PTR_ERR(mem->dmabuf); mem->dmabuf = NULL; goto err; } mem->attach = dma_buf_attach(mem->dmabuf, ifq->dev); if (IS_ERR(mem->attach)) { ret = PTR_ERR(mem->attach); mem->attach = NULL; goto err; } mem->sgt = dma_buf_map_attachment_unlocked(mem->attach, DMA_FROM_DEVICE); if (IS_ERR(mem->sgt)) { ret = PTR_ERR(mem->sgt); mem->sgt = NULL; goto err; } for_each_sgtable_dma_sg(mem->sgt, sg, i) total_size += sg_dma_len(sg); if (total_size != len) { ret = -EINVAL; goto err; } mem->size = len; return 0; err: io_release_dmabuf(mem); return ret; } static unsigned long io_count_account_pages(struct page **pages, unsigned nr_pages) { struct folio *last_folio = NULL; unsigned long res = 0; int i; for (i = 0; i < nr_pages; i++) { struct folio *folio = page_folio(pages[i]); if (folio == last_folio) continue; last_folio = folio; res += folio_nr_pages(folio); } return res; } static int io_import_umem(struct io_zcrx_ifq *ifq, struct io_zcrx_mem *mem, struct io_uring_zcrx_area_reg *area_reg) { struct page **pages; int nr_pages, ret; bool mapped = false; if (area_reg->dmabuf_fd) return -EINVAL; if (!area_reg->addr) return -EFAULT; pages = io_pin_pages((unsigned long)area_reg->addr, area_reg->len, &nr_pages); if (IS_ERR(pages)) return PTR_ERR(pages); ret = sg_alloc_table_from_pages(&mem->page_sg_table, pages, nr_pages, 0, (unsigned long)nr_pages << PAGE_SHIFT, GFP_KERNEL_ACCOUNT); if (ret) goto out_err; if (ifq->dev) { ret = dma_map_sgtable(ifq->dev, &mem->page_sg_table, DMA_FROM_DEVICE, IO_DMA_ATTR); if (ret < 0) goto out_err; mapped = true; } mem->account_pages = io_count_account_pages(pages, nr_pages); ret = io_account_mem(ifq->user, ifq->mm_account, mem->account_pages); if (ret < 0) { mem->account_pages = 0; goto out_err; } mem->sgt = &mem->page_sg_table; mem->pages = pages; mem->nr_folios = nr_pages; mem->size = area_reg->len; return ret; out_err: if (mapped) dma_unmap_sgtable(ifq->dev, &mem->page_sg_table, DMA_FROM_DEVICE, IO_DMA_ATTR); sg_free_table(&mem->page_sg_table); unpin_user_pages(pages, nr_pages); kvfree(pages); return ret; } static void io_release_area_mem(struct io_zcrx_mem *mem) { if (mem->is_dmabuf) { io_release_dmabuf(mem); } else if (mem->pages) { unpin_user_pages(mem->pages, mem->nr_folios); sg_free_table(mem->sgt); kvfree(mem->pages); } mem->pages = IO_URING_PTR_POISON; mem->sgt = IO_URING_PTR_POISON; } static int io_import_area(struct io_zcrx_ifq *ifq, struct io_zcrx_mem *mem, struct io_uring_zcrx_area_reg *area_reg) { int ret; if (area_reg->flags & ~IO_ZCRX_AREA_SUPPORTED_FLAGS) return -EINVAL; if (area_reg->rq_area_token) return -EINVAL; if (area_reg->__resv2[0] || area_reg->__resv2[1]) return -EINVAL; ret = io_validate_user_buf_range(area_reg->addr, area_reg->len); if (ret) return ret; if (area_reg->addr & ~PAGE_MASK || area_reg->len & ~PAGE_MASK) return -EINVAL; if (area_reg->flags & IORING_ZCRX_AREA_DMABUF) return io_import_dmabuf(ifq, mem, area_reg); return io_import_umem(ifq, mem, area_reg); } static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) { int i; guard(mutex)(&ifq->pp_lock); if (!area->is_mapped) return; area->is_mapped = false; if (area->nia.niovs) { for (i = 0; i < area->nia.num_niovs; i++) net_mp_niov_set_dma_addr(&area->nia.niovs[i], 0); } if (area->mem.is_dmabuf) { io_release_dmabuf(&area->mem); } else { dma_unmap_sgtable(ifq->dev, &area->mem.page_sg_table, DMA_FROM_DEVICE, IO_DMA_ATTR); } } static void zcrx_sync_for_device(struct page_pool *pp, struct io_zcrx_ifq *zcrx, netmem_ref *netmems, unsigned nr) { #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) struct device *dev = pp->p.dev; unsigned i, niov_size; dma_addr_t dma_addr; if (!dma_dev_need_sync(dev)) return; niov_size = 1U << zcrx->niov_shift; for (i = 0; i < nr; i++) { dma_addr = page_pool_get_dma_addr_netmem(netmems[i]); __dma_sync_single_for_device(dev, dma_addr + pp->p.offset, niov_size, pp->p.dma_dir); } #endif } #define IO_RQ_MAX_ENTRIES 32768 #define IO_SKBS_PER_CALL_LIMIT 20 struct io_zcrx_args { struct io_kiocb *req; struct io_zcrx_ifq *ifq; unsigned nr_skbs; }; static const struct memory_provider_ops io_uring_pp_zc_ops; static inline atomic_t *io_get_user_counter(struct net_iov *niov) { struct io_zcrx_area *area = io_zcrx_iov_to_area(niov); return &area->user_refs[net_iov_idx(niov)]; } static bool io_zcrx_put_niov_uref(struct net_iov *niov) { atomic_t *uref = io_get_user_counter(niov); int old; old = atomic_read(uref); do { if (unlikely(old == 0)) return false; } while (!atomic_try_cmpxchg(uref, &old, old - 1)); return true; } static void io_zcrx_get_niov_uref(struct net_iov *niov) { atomic_inc(io_get_user_counter(niov)); } static void io_fill_zcrx_offsets(struct io_uring_zcrx_offsets *offsets) { offsets->head = offsetof(struct io_uring, head); offsets->tail = offsetof(struct io_uring, tail); offsets->rqes = ALIGN(sizeof(struct io_uring), L1_CACHE_BYTES); } static int io_allocate_rbuf_ring(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq, struct io_uring_zcrx_ifq_reg *reg, struct io_uring_region_desc *rd, u32 id) { u64 mmap_offset; size_t off, size; void *ptr; int ret; io_fill_zcrx_offsets(®->offsets); off = reg->offsets.rqes; size = off + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries; if (size > rd->size) return -EINVAL; mmap_offset = IORING_MAP_OFF_ZCRX_REGION; mmap_offset += (u64)id << IORING_OFF_ZCRX_SHIFT; ret = io_create_region(ctx, &ifq->rq_region, rd, mmap_offset); if (ret < 0) return ret; ptr = io_region_get_ptr(&ifq->rq_region); ifq->rq.ring = (struct io_uring *)ptr; ifq->rq.rqes = (struct io_uring_zcrx_rqe *)(ptr + off); memset(ifq->rq.ring, 0, sizeof(*ifq->rq.ring)); return 0; } static void io_free_rbuf_ring(struct io_zcrx_ifq *ifq) { io_free_region(ifq->user, &ifq->rq_region); ifq->rq.ring = IO_URING_PTR_POISON; ifq->rq.rqes = IO_URING_PTR_POISON; ifq->notif_stats = IO_URING_PTR_POISON; } static void io_zcrx_free_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) { io_zcrx_unmap_area(ifq, area); io_release_area_mem(&area->mem); if (area->mem.account_pages) io_unaccount_mem(ifq->user, ifq->mm_account, area->mem.account_pages); kvfree(area->freelist); kvfree(area->nia.niovs); kvfree(area->user_refs); kfree(area); } static int io_zcrx_append_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area) { bool kern_readable = !area->mem.is_dmabuf; if (WARN_ON_ONCE(ifq->area)) return -EINVAL; if (WARN_ON_ONCE(ifq->kern_readable != kern_readable)) return -EINVAL; ifq->area = area; return 0; } static int io_zcrx_create_area(struct io_zcrx_ifq *ifq, struct io_uring_zcrx_area_reg *area_reg, struct io_uring_zcrx_ifq_reg *reg) { int buf_size_shift = PAGE_SHIFT; struct io_zcrx_area *area; unsigned nr_iovs; int i, ret; if (reg->rx_buf_len) { if (!is_power_of_2(reg->rx_buf_len) || reg->rx_buf_len < PAGE_SIZE) return -EINVAL; buf_size_shift = ilog2(reg->rx_buf_len); } if (!ifq->dev && buf_size_shift != PAGE_SHIFT) return -EOPNOTSUPP; ret = -ENOMEM; area = kzalloc_obj(*area); if (!area) goto err; area->ifq = ifq; ret = io_import_area(ifq, &area->mem, area_reg); if (ret) goto err; if (ifq->dev) area->is_mapped = true; if (ifq->dev && buf_size_shift > io_area_max_shift(&area->mem)) { ret = -ERANGE; goto err; } ifq->niov_shift = buf_size_shift; nr_iovs = area->mem.size >> ifq->niov_shift; area->nia.num_niovs = nr_iovs; ret = -ENOMEM; area->nia.niovs = kvmalloc_objs(area->nia.niovs[0], nr_iovs, GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!area->nia.niovs) goto err; area->freelist = kvmalloc_array(nr_iovs, sizeof(area->freelist[0]), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!area->freelist) goto err; area->user_refs = kvmalloc_objs(area->user_refs[0], nr_iovs, GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!area->user_refs) goto err; for (i = 0; i < nr_iovs; i++) { struct net_iov *niov = &area->nia.niovs[i]; net_iov_init(niov, &area->nia, NET_IOV_IOURING); area->freelist[i] = i; atomic_set(&area->user_refs[i], 0); } if (ifq->dev) { ret = io_populate_area_dma(ifq, area); if (ret) goto err; } area->free_count = nr_iovs; /* we're only supporting one area per ifq for now */ area->area_id = 0; area_reg->rq_area_token = (u64)area->area_id << IORING_ZCRX_AREA_SHIFT; spin_lock_init(&area->freelist_lock); ret = io_zcrx_append_area(ifq, area); if (!ret) return 0; err: if (area) io_zcrx_free_area(ifq, area); return ret; } static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx) { struct io_zcrx_ifq *ifq; ifq = kzalloc_obj(*ifq); if (!ifq) return NULL; ifq->if_rxq = -1; spin_lock_init(&ifq->ctx_lock); spin_lock_init(&ifq->rq.lock); mutex_init(&ifq->pp_lock); refcount_set(&ifq->refs, 1); refcount_set(&ifq->user_refs, 1); return ifq; } static void io_zcrx_drop_netdev(struct io_zcrx_ifq *ifq) { guard(mutex)(&ifq->pp_lock); if (!ifq->netdev) return; netdev_put(ifq->netdev, &ifq->netdev_tracker); ifq->netdev = NULL; } static void io_close_queue(struct io_zcrx_ifq *ifq) { struct net_device *netdev; netdevice_tracker netdev_tracker; struct pp_memory_provider_params p = { .mp_ops = &io_uring_pp_zc_ops, .mp_priv = ifq, }; scoped_guard(mutex, &ifq->pp_lock) { netdev = ifq->netdev; netdev_tracker = ifq->netdev_tracker; ifq->netdev = NULL; } if (netdev) { if (ifq->if_rxq != -1) { netdev_lock(netdev); netif_mp_close_rxq(netdev, ifq->if_rxq, &p); netdev_unlock(netdev); } netdev_put(netdev, &netdev_tracker); } ifq->if_rxq = -1; } static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq) { if (WARN_ON_ONCE(ifq->if_rxq != -1)) return; if (WARN_ON_ONCE(ifq->netdev != NULL)) return; if (WARN_ON_ONCE(ifq->master_ctx)) return; if (ifq->area) io_zcrx_free_area(ifq, ifq->area); if (ifq->mm_account) mmdrop(ifq->mm_account); if (ifq->dev) put_device(ifq->dev); io_free_rbuf_ring(ifq); free_uid(ifq->user); mutex_destroy(&ifq->pp_lock); kfree(ifq); } static void io_put_zcrx_ifq(struct io_zcrx_ifq *ifq) { if (refcount_dec_and_test(&ifq->refs)) io_zcrx_ifq_free(ifq); } static void io_zcrx_return_niov_freelist(struct net_iov *niov) { struct io_zcrx_area *area = io_zcrx_iov_to_area(niov); guard(spinlock_bh)(&area->freelist_lock); if (WARN_ON_ONCE(area->free_count >= area->nia.num_niovs)) return; area->freelist[area->free_count++] = net_iov_idx(niov); } static struct net_iov *zcrx_get_free_niov(struct io_zcrx_area *area) { unsigned niov_idx; lockdep_assert_held(&area->freelist_lock); if (unlikely(!area->free_count)) return NULL; niov_idx = area->freelist[--area->free_count]; return &area->nia.niovs[niov_idx]; } static void io_zcrx_return_niov(struct net_iov *niov) { netmem_ref netmem = net_iov_to_netmem(niov); if (!niov->desc.pp) { /* copy fallback allocated niovs */ io_zcrx_return_niov_freelist(niov); return; } page_pool_put_unrefed_netmem(niov->desc.pp, netmem, -1, false); } static void io_zcrx_scrub(struct io_zcrx_ifq *ifq) { struct io_zcrx_area *area = ifq->area; int i; if (!area) return; /* Reclaim back all buffers given to the user space. */ for (i = 0; i < area->nia.num_niovs; i++) { struct net_iov *niov = &area->nia.niovs[i]; int nr; if (!atomic_read(io_get_user_counter(niov))) continue; nr = atomic_xchg(io_get_user_counter(niov), 0); if (nr && !page_pool_unref_netmem(net_iov_to_netmem(niov), nr)) io_zcrx_return_niov(niov); } } static void zcrx_unregister_user(struct io_zcrx_ifq *ifq, struct io_ring_ctx *ctx) { scoped_guard(spinlock_bh, &ifq->ctx_lock) { if (ctx && ifq->master_ctx == ctx) { ifq->master_ctx = NULL; percpu_ref_put(&ctx->refs); } } if (refcount_dec_and_test(&ifq->user_refs)) { io_close_queue(ifq); io_zcrx_scrub(ifq); } } static void zcrx_unregister(struct io_zcrx_ifq *ifq, struct io_ring_ctx *ctx) { zcrx_unregister_user(ifq, ctx); io_put_zcrx_ifq(ifq); } struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx, unsigned int id) { struct io_zcrx_ifq *ifq = xa_load(&ctx->zcrx_ctxs, id); lockdep_assert_held(&ctx->mmap_lock); return ifq ? &ifq->rq_region : NULL; } static int zcrx_box_release(struct inode *inode, struct file *file) { struct io_zcrx_ifq *ifq = file->private_data; if (WARN_ON_ONCE(!ifq)) return -EFAULT; zcrx_unregister(ifq, NULL); return 0; } static const struct file_operations zcrx_box_fops = { .owner = THIS_MODULE, .release = zcrx_box_release, }; static int zcrx_export(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq, struct zcrx_ctrl *ctrl, void __user *arg) { struct zcrx_ctrl_export *ce = &ctrl->zc_export; struct file *file; int fd; if (!mem_is_zero(ce, sizeof(*ce))) return -EINVAL; refcount_inc(&ifq->refs); refcount_inc(&ifq->user_refs); file = anon_inode_create_getfile("[zcrx]", &zcrx_box_fops, ifq, O_CLOEXEC, NULL); if (IS_ERR(file)) { zcrx_unregister(ifq, NULL); return PTR_ERR(file); } fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { fput(file); return fd; } ce->zcrx_fd = fd; if (copy_to_user(arg, ctrl, sizeof(*ctrl))) { fput(file); put_unused_fd(fd); return -EFAULT; } fd_install(fd, file); return 0; } static int import_zcrx(struct io_ring_ctx *ctx, struct io_uring_zcrx_ifq_reg __user *arg, struct io_uring_zcrx_ifq_reg *reg) { struct io_zcrx_ifq *ifq; struct file *file; int fd, ret; u32 id; if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) return -EINVAL; if (!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED))) return -EINVAL; if (reg->if_rxq || reg->rq_entries || reg->area_ptr || reg->region_ptr) return -EINVAL; if (reg->notif_desc) return -EINVAL; if (reg->flags & ~ZCRX_REG_IMPORT) return -EINVAL; fd = reg->if_idx; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; file = fd_file(f); if (file->f_op != &zcrx_box_fops || !file->private_data) return -EBADF; ifq = file->private_data; refcount_inc(&ifq->refs); refcount_inc(&ifq->user_refs); scoped_guard(mutex, &ctx->mmap_lock) { ret = xa_alloc(&ctx->zcrx_ctxs, &id, NULL, xa_limit_31b, GFP_KERNEL); if (ret) goto err; } reg->zcrx_id = id; io_fill_zcrx_offsets(®->offsets); if (copy_to_user(arg, reg, sizeof(*reg))) { ret = -EFAULT; goto err_xa_erase; } scoped_guard(mutex, &ctx->mmap_lock) { ret = -ENOMEM; if (xa_store(&ctx->zcrx_ctxs, id, ifq, GFP_KERNEL)) goto err_xa_erase; } return 0; err_xa_erase: scoped_guard(mutex, &ctx->mmap_lock) xa_erase(&ctx->zcrx_ctxs, id); err: zcrx_unregister(ifq, ctx); return ret; } static int zcrx_register_netdev(struct io_zcrx_ifq *ifq, struct io_uring_zcrx_ifq_reg *reg, struct io_uring_zcrx_area_reg *area) { struct pp_memory_provider_params mp_param = {}; unsigned if_rxq = reg->if_rxq; int ret; ifq->netdev = netdev_get_by_index_lock(current->nsproxy->net_ns, reg->if_idx); if (!ifq->netdev) return -ENODEV; netdev_hold(ifq->netdev, &ifq->netdev_tracker, GFP_KERNEL); ifq->dev = netdev_queue_get_dma_dev(ifq->netdev, if_rxq, NETDEV_QUEUE_TYPE_RX); if (!ifq->dev) { ret = -EOPNOTSUPP; goto netdev_put_unlock; } get_device(ifq->dev); ret = io_zcrx_create_area(ifq, area, reg); if (ret) goto netdev_put_unlock; if (reg->rx_buf_len) mp_param.rx_page_size = 1U << ifq->niov_shift; mp_param.mp_ops = &io_uring_pp_zc_ops; mp_param.mp_priv = ifq; ret = netif_mp_open_rxq(ifq->netdev, if_rxq, &mp_param, NULL); if (ret) goto netdev_put_unlock; ifq->if_rxq = if_rxq; ret = 0; netdev_put_unlock: netdev_unlock(ifq->netdev); return ret; } static int zcrx_validate_notif_stats(struct io_zcrx_ifq *ifq, const struct io_uring_zcrx_ifq_reg *reg, const struct zcrx_notification_desc *notif) { size_t stats_off = notif->stats_offset; size_t used, end; used = reg->offsets.rqes + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries; if (!IS_ALIGNED(stats_off, __alignof__(struct zcrx_notif_stats))) return -EINVAL; if (stats_off < used) return -ERANGE; if (check_add_overflow(stats_off, sizeof(struct zcrx_notif_stats), &end)) return -ERANGE; if (end > io_region_size(&ifq->rq_region)) return -ERANGE; ifq->notif_stats = io_region_get_ptr(&ifq->rq_region) + stats_off; memset(ifq->notif_stats, 0, sizeof(*ifq->notif_stats)); return 0; } int io_register_zcrx(struct io_ring_ctx *ctx, struct io_uring_zcrx_ifq_reg __user *arg) { struct zcrx_notification_desc notif; struct io_uring_zcrx_area_reg area; struct io_uring_zcrx_ifq_reg reg; struct io_uring_region_desc rd; struct io_zcrx_ifq *ifq; int ret; u32 id; /* * 1. Interface queue allocation. * 2. It can observe data destined for sockets of other tasks. */ if (!capable(CAP_NET_ADMIN)) return -EPERM; /* mandatory io_uring features for zc rx */ if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) return -EINVAL; if (!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED))) return -EINVAL; if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (!mem_is_zero(®.__resv, sizeof(reg.__resv)) || reg.zcrx_id) return -EINVAL; if (reg.flags & ~ZCRX_SUPPORTED_REG_FLAGS) return -EINVAL; if (reg.flags & ZCRX_REG_IMPORT) return import_zcrx(ctx, arg, ®); if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd))) return -EFAULT; if (reg.if_rxq == -1 || !reg.rq_entries) return -EINVAL; if ((reg.if_rxq || reg.if_idx) && (reg.flags & ZCRX_REG_NODEV)) return -EINVAL; if (reg.rq_entries > IO_RQ_MAX_ENTRIES) { if (!(ctx->flags & IORING_SETUP_CLAMP)) return -EINVAL; reg.rq_entries = IO_RQ_MAX_ENTRIES; } reg.rq_entries = roundup_pow_of_two(reg.rq_entries); if (copy_from_user(&area, u64_to_user_ptr(reg.area_ptr), sizeof(area))) return -EFAULT; memset(¬if, 0, sizeof(notif)); if (reg.notif_desc && copy_from_user(¬if, u64_to_user_ptr(reg.notif_desc), sizeof(notif))) return -EFAULT; if (notif.type_mask & ~ZCRX_NOTIF_TYPE_MASK) return -EINVAL; if (notif.flags & ~ZCRX_NOTIF_DESC_FLAG_STATS) return -EINVAL; if (!(notif.flags & ZCRX_NOTIF_DESC_FLAG_STATS)) { if (notif.stats_offset) return -EINVAL; } if (!mem_is_zero(¬if.__resv2, sizeof(notif.__resv2))) return -EINVAL; ifq = io_zcrx_ifq_alloc(ctx); if (!ifq) return -ENOMEM; ifq->notif_data = notif.user_data; ifq->allowed_notif_mask = notif.type_mask; if (ctx->user) { get_uid(ctx->user); ifq->user = ctx->user; } if (ctx->mm_account) { mmgrab(ctx->mm_account); ifq->mm_account = ctx->mm_account; } ifq->rq.nr_entries = reg.rq_entries; scoped_guard(mutex, &ctx->mmap_lock) { /* preallocate id */ ret = xa_alloc(&ctx->zcrx_ctxs, &id, NULL, xa_limit_31b, GFP_KERNEL); if (ret) goto ifq_free; } ret = io_allocate_rbuf_ring(ctx, ifq, ®, &rd, id); if (ret) goto err; if (notif.flags & ZCRX_NOTIF_DESC_FLAG_STATS) { ret = zcrx_validate_notif_stats(ifq, ®, ¬if); if (ret) goto err; } ifq->kern_readable = !(area.flags & IORING_ZCRX_AREA_DMABUF); if (!(reg.flags & ZCRX_REG_NODEV)) { ret = zcrx_register_netdev(ifq, ®, &area); if (ret) goto err; } else { ret = io_zcrx_create_area(ifq, &area, ®); if (ret) goto err; } reg.zcrx_id = id; scoped_guard(mutex, &ctx->mmap_lock) { /* publish ifq */ ret = -ENOMEM; if (xa_store(&ctx->zcrx_ctxs, id, ifq, GFP_KERNEL)) goto err; } reg.rx_buf_len = 1U << ifq->niov_shift; if (copy_to_user(arg, ®, sizeof(reg)) || copy_to_user(u64_to_user_ptr(reg.region_ptr), &rd, sizeof(rd)) || copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) { ret = -EFAULT; goto err; } if (notif.type_mask) zcrx_set_ring_ctx(ifq, ctx); return 0; err: scoped_guard(mutex, &ctx->mmap_lock) xa_erase(&ctx->zcrx_ctxs, id); ifq_free: zcrx_unregister(ifq, ctx); return ret; } static inline bool is_zcrx_entry_marked(struct io_ring_ctx *ctx, unsigned long id) { return xa_get_mark(&ctx->zcrx_ctxs, id, XA_MARK_1); } static inline void set_zcrx_entry_mark(struct io_ring_ctx *ctx, unsigned long id) { xa_set_mark(&ctx->zcrx_ctxs, id, XA_MARK_1); } void io_terminate_zcrx(struct io_ring_ctx *ctx) { struct io_zcrx_ifq *ifq; unsigned long id = 0; lockdep_assert_held(&ctx->uring_lock); while (1) { scoped_guard(mutex, &ctx->mmap_lock) ifq = xa_find(&ctx->zcrx_ctxs, &id, ULONG_MAX, XA_PRESENT); if (!ifq) break; if (WARN_ON_ONCE(is_zcrx_entry_marked(ctx, id))) break; set_zcrx_entry_mark(ctx, id); id++; zcrx_unregister_user(ifq, ctx); } } void io_unregister_zcrx(struct io_ring_ctx *ctx) { struct io_zcrx_ifq *ifq; lockdep_assert_held(&ctx->uring_lock); while (1) { scoped_guard(mutex, &ctx->mmap_lock) { unsigned long id = 0; ifq = xa_find(&ctx->zcrx_ctxs, &id, ULONG_MAX, XA_PRESENT); if (ifq) { if (WARN_ON_ONCE(!is_zcrx_entry_marked(ctx, id))) { ifq = NULL; break; } xa_erase(&ctx->zcrx_ctxs, id); } } if (!ifq) break; /* * io_uring can run requests and return buffers to the user * after termination, scrub it again. */ if (refcount_read(&ifq->user_refs) == 0) io_zcrx_scrub(ifq); io_put_zcrx_ifq(ifq); } xa_destroy(&ctx->zcrx_ctxs); } static inline u32 zcrx_rq_entries(struct zcrx_rq *rq) { u32 entries; entries = smp_load_acquire(&rq->ring->tail) - rq->cached_head; return min(entries, rq->nr_entries); } static struct io_uring_zcrx_rqe *zcrx_next_rqe(struct zcrx_rq *rq, unsigned mask) { unsigned int idx = rq->cached_head++ & mask; return &rq->rqes[idx]; } static inline bool io_parse_rqe(struct io_uring_zcrx_rqe *rqe, struct io_zcrx_ifq *ifq, struct net_iov **ret_niov) { __u64 off = READ_ONCE(rqe->off); unsigned niov_idx, area_idx; struct io_zcrx_area *area; area_idx = off >> IORING_ZCRX_AREA_SHIFT; niov_idx = (off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift; if (unlikely(rqe->__pad || area_idx)) return false; area = ifq->area; if (unlikely(niov_idx >= area->nia.num_niovs)) return false; niov_idx = array_index_nospec(niov_idx, area->nia.num_niovs); *ret_niov = &area->nia.niovs[niov_idx]; return true; } static unsigned io_zcrx_ring_refill(struct page_pool *pp, struct io_zcrx_ifq *ifq, netmem_ref *netmems, unsigned to_alloc) { struct zcrx_rq *rq = &ifq->rq; unsigned int mask = rq->nr_entries - 1; unsigned int entries; unsigned allocated = 0; guard(spinlock_bh)(&rq->lock); entries = zcrx_rq_entries(rq); entries = min_t(unsigned, entries, to_alloc); if (unlikely(!entries)) return 0; do { struct io_uring_zcrx_rqe *rqe = zcrx_next_rqe(rq, mask); struct net_iov *niov; netmem_ref netmem; if (!io_parse_rqe(rqe, ifq, &niov)) continue; if (!io_zcrx_put_niov_uref(niov)) continue; netmem = net_iov_to_netmem(niov); if (!page_pool_unref_and_test(netmem)) continue; if (unlikely(niov->desc.pp != pp)) { io_zcrx_return_niov(niov); continue; } netmems[allocated] = netmem; allocated++; } while (--entries); smp_store_release(&rq->ring->head, rq->cached_head); return allocated; } static unsigned io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq, netmem_ref *netmems, unsigned to_alloc) { struct io_zcrx_area *area = ifq->area; unsigned allocated = 0; guard(spinlock_bh)(&area->freelist_lock); for (allocated = 0; allocated < to_alloc; allocated++) { struct net_iov *niov = zcrx_get_free_niov(area); if (!niov) break; net_mp_niov_set_page_pool(pp, niov); netmems[allocated] = net_iov_to_netmem(niov); } return allocated; } static void zcrx_notif_tw(struct io_tw_req tw_req, io_tw_token_t tw) { struct io_kiocb *req = tw_req.req; struct io_ring_ctx *ctx = req->ctx; io_post_aux_cqe(ctx, req->cqe.user_data, req->cqe.res, 0); percpu_ref_put(&ctx->refs); io_poison_req(req); kmem_cache_free(req_cachep, req); } static void zcrx_stat_add(__u64 *p, s64 v) { WRITE_ONCE(*p, READ_ONCE(*p) + v); } static void zcrx_send_notif(struct io_zcrx_ifq *ifq, unsigned type) { gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN | __GFP_ZERO; u32 type_mask = 1 << type; struct io_kiocb *req; if (!(type_mask & ifq->allowed_notif_mask)) return; guard(spinlock_bh)(&ifq->ctx_lock); if (!ifq->master_ctx) return; if (type_mask & ifq->fired_notifs) return; req = kmem_cache_alloc(req_cachep, gfp); if (unlikely(!req)) return; ifq->fired_notifs |= type_mask; req->opcode = IORING_OP_NOP; req->cqe.user_data = ifq->notif_data; req->cqe.res = type; req->ctx = ifq->master_ctx; percpu_ref_get(&req->ctx->refs); req->tctx = NULL; req->io_task_work.func = zcrx_notif_tw; io_req_task_work_add(req); } static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp) { struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); netmem_ref *netmems = pp->alloc.cache; unsigned to_alloc = PP_ALLOC_CACHE_REFILL; unsigned allocated; /* pp should already be ensuring that */ if (WARN_ON_ONCE(pp->alloc.count)) return 0; allocated = io_zcrx_ring_refill(pp, ifq, netmems, to_alloc); if (likely(allocated)) goto out_return; allocated = io_zcrx_refill_slow(pp, ifq, netmems, to_alloc); if (!allocated) { zcrx_send_notif(ifq, ZCRX_NOTIF_NO_BUFFERS); return 0; } out_return: zcrx_sync_for_device(pp, ifq, netmems, allocated); allocated--; pp->alloc.count += allocated; return netmems[allocated]; } static bool io_pp_zc_release_netmem(struct page_pool *pp, netmem_ref netmem) { struct net_iov *niov; if (WARN_ON_ONCE(!netmem_is_net_iov(netmem))) return false; niov = netmem_to_net_iov(netmem); net_mp_niov_clear_page_pool(niov); io_zcrx_return_niov_freelist(niov); return false; } static int io_pp_zc_init(struct page_pool *pp) { struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); if (WARN_ON_ONCE(!ifq)) return -EINVAL; if (WARN_ON_ONCE(ifq->dev != pp->p.dev)) return -EINVAL; if (WARN_ON_ONCE(!pp->dma_map)) return -EOPNOTSUPP; if (pp->p.order + PAGE_SHIFT != ifq->niov_shift) return -EINVAL; if (pp->p.dma_dir != DMA_FROM_DEVICE) return -EOPNOTSUPP; refcount_inc(&ifq->refs); return 0; } static void io_pp_zc_destroy(struct page_pool *pp) { io_put_zcrx_ifq(io_pp_to_ifq(pp)); } static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp, struct netdev_rx_queue *rxq) { struct io_zcrx_ifq *ifq = mp_priv; struct nlattr *nest; int type; type = rxq ? NETDEV_A_QUEUE_IO_URING : NETDEV_A_PAGE_POOL_IO_URING; nest = nla_nest_start(rsp, type); if (!nest) return -EMSGSIZE; if (nla_put_uint(rsp, NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN, 1ULL << ifq->niov_shift)) { nla_nest_cancel(rsp, nest); return -EMSGSIZE; } nla_nest_end(rsp, nest); return 0; } static void io_pp_uninstall(void *mp_priv, struct netdev_rx_queue *rxq) { struct pp_memory_provider_params *p = &rxq->mp_params; struct io_zcrx_ifq *ifq = mp_priv; io_zcrx_drop_netdev(ifq); if (ifq->area) io_zcrx_unmap_area(ifq, ifq->area); p->mp_ops = NULL; p->mp_priv = NULL; } static const struct memory_provider_ops io_uring_pp_zc_ops = { .alloc_netmems = io_pp_zc_alloc_netmems, .release_netmem = io_pp_zc_release_netmem, .init = io_pp_zc_init, .destroy = io_pp_zc_destroy, .nl_fill = io_pp_nl_fill, .uninstall = io_pp_uninstall, }; static unsigned zcrx_parse_rq(netmem_ref *netmem_array, unsigned nr, struct io_zcrx_ifq *zcrx, struct zcrx_rq *rq) { unsigned int mask = rq->nr_entries - 1; unsigned int i; nr = min(nr, zcrx_rq_entries(rq)); for (i = 0; i < nr; i++) { struct io_uring_zcrx_rqe *rqe = zcrx_next_rqe(rq, mask); struct net_iov *niov; if (!io_parse_rqe(rqe, zcrx, &niov)) break; netmem_array[i] = net_iov_to_netmem(niov); } smp_store_release(&rq->ring->head, rq->cached_head); return i; } #define ZCRX_FLUSH_BATCH 32 static void zcrx_return_buffers(netmem_ref *netmems, unsigned nr) { unsigned i; for (i = 0; i < nr; i++) { netmem_ref netmem = netmems[i]; struct net_iov *niov = netmem_to_net_iov(netmem); if (!io_zcrx_put_niov_uref(niov)) continue; if (!page_pool_unref_and_test(netmem)) continue; io_zcrx_return_niov(niov); } } static int zcrx_flush_rq(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, struct zcrx_ctrl *ctrl) { struct zcrx_ctrl_flush_rq *frq = &ctrl->zc_flush; netmem_ref netmems[ZCRX_FLUSH_BATCH]; unsigned total = 0; unsigned nr; if (!mem_is_zero(&frq->__resv, sizeof(frq->__resv))) return -EINVAL; do { struct zcrx_rq *rq = &zcrx->rq; scoped_guard(spinlock_bh, &rq->lock) { nr = zcrx_parse_rq(netmems, ZCRX_FLUSH_BATCH, zcrx, rq); zcrx_return_buffers(netmems, nr); } total += nr; if (fatal_signal_pending(current)) break; cond_resched(); } while (nr == ZCRX_FLUSH_BATCH && total < zcrx->rq.nr_entries); return 0; } static int zcrx_arm_notif(struct io_ring_ctx *ctx, struct io_zcrx_ifq *zcrx, struct zcrx_ctrl *ctrl) { const struct zcrx_ctrl_arm_notif *an = &ctrl->zc_arm_notif; unsigned type_mask; if (an->notif_type >= __ZCRX_NOTIF_TYPE_LAST) return -EINVAL; if (!mem_is_zero(&an->__resv, sizeof(an->__resv))) return -EINVAL; guard(spinlock_bh)(&zcrx->ctx_lock); type_mask = 1U << an->notif_type; if (type_mask & ~zcrx->fired_notifs) return -EINVAL; zcrx->fired_notifs &= ~type_mask; return 0; } int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { struct zcrx_ctrl ctrl; struct io_zcrx_ifq *zcrx; BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_flush)); BUILD_BUG_ON(sizeof(ctrl.zc_export) != sizeof(ctrl.zc_arm_notif)); if (nr_args) return -EINVAL; if (copy_from_user(&ctrl, arg, sizeof(ctrl))) return -EFAULT; if (!mem_is_zero(&ctrl.__resv, sizeof(ctrl.__resv))) return -EFAULT; zcrx = xa_load(&ctx->zcrx_ctxs, ctrl.zcrx_id); if (!zcrx) return -ENXIO; switch (ctrl.op) { case ZCRX_CTRL_FLUSH_RQ: return zcrx_flush_rq(ctx, zcrx, &ctrl); case ZCRX_CTRL_EXPORT: return zcrx_export(ctx, zcrx, &ctrl, arg); case ZCRX_CTRL_ARM_NOTIFICATION: return zcrx_arm_notif(ctx, zcrx, &ctrl); } return -EOPNOTSUPP; } static bool io_zcrx_queue_cqe(struct io_kiocb *req, struct net_iov *niov, struct io_zcrx_ifq *ifq, int off, int len) { struct io_ring_ctx *ctx = req->ctx; struct io_uring_zcrx_cqe *rcqe; struct io_zcrx_area *area; struct io_uring_cqe *cqe; u64 offset; if (!io_defer_get_uncommited_cqe(ctx, &cqe)) return false; cqe->user_data = req->cqe.user_data; cqe->res = len; cqe->flags = IORING_CQE_F_MORE; if (ctx->flags & IORING_SETUP_CQE_MIXED) cqe->flags |= IORING_CQE_F_32; area = io_zcrx_iov_to_area(niov); offset = off + (net_iov_idx(niov) << ifq->niov_shift); rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1); rcqe->off = offset + ((u64)area->area_id << IORING_ZCRX_AREA_SHIFT); rcqe->__pad = 0; return true; } static struct net_iov *io_alloc_fallback_niov(struct io_zcrx_ifq *ifq) { struct io_zcrx_area *area = ifq->area; struct net_iov *niov = NULL; if (!ifq->kern_readable) return NULL; scoped_guard(spinlock_bh, &area->freelist_lock) niov = zcrx_get_free_niov(area); if (niov) page_pool_fragment_netmem(net_iov_to_netmem(niov), 1); return niov; } struct io_copy_cache { struct page *page; unsigned long offset; size_t size; }; static ssize_t io_copy_page(struct io_copy_cache *cc, struct page *src_page, unsigned int src_offset, size_t len) { size_t copied = 0; len = min(len, cc->size); while (len) { void *src_addr, *dst_addr; struct page *dst_page = cc->page; unsigned dst_offset = cc->offset; size_t n = len; if (folio_test_partial_kmap(page_folio(dst_page)) || folio_test_partial_kmap(page_folio(src_page))) { dst_page += dst_offset / PAGE_SIZE; dst_offset = offset_in_page(dst_offset); src_page += src_offset / PAGE_SIZE; src_offset = offset_in_page(src_offset); n = min(PAGE_SIZE - src_offset, PAGE_SIZE - dst_offset); n = min(n, len); } dst_addr = kmap_local_page(dst_page) + dst_offset; src_addr = kmap_local_page(src_page) + src_offset; memcpy(dst_addr, src_addr, n); kunmap_local(src_addr); kunmap_local(dst_addr); cc->size -= n; cc->offset += n; src_offset += n; len -= n; copied += n; } return copied; } static ssize_t io_zcrx_copy_chunk(struct io_kiocb *req, struct io_zcrx_ifq *ifq, struct page *src_page, unsigned int src_offset, size_t len) { size_t copied = 0; int ret = 0; while (len) { struct io_copy_cache cc; struct net_iov *niov; size_t n; niov = io_alloc_fallback_niov(ifq); if (!niov) { ret = -ENOMEM; break; } cc.page = io_zcrx_iov_page(niov); cc.offset = 0; cc.size = PAGE_SIZE; n = io_copy_page(&cc, src_page, src_offset, len); if (!io_zcrx_queue_cqe(req, niov, ifq, 0, n)) { io_zcrx_return_niov(niov); ret = -ENOSPC; break; } io_zcrx_get_niov_uref(niov); src_offset += n; len -= n; copied += n; } return copied ? copied : ret; } static int io_zcrx_copy_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, const skb_frag_t *frag, int off, int len) { struct page *page = skb_frag_page(frag); int ret; ret = io_zcrx_copy_chunk(req, ifq, page, off + skb_frag_off(frag), len); if (ret > 0) { if (ifq->notif_stats) { zcrx_stat_add(&ifq->notif_stats->copy_count, 1); zcrx_stat_add(&ifq->notif_stats->copy_bytes, ret); } zcrx_send_notif(ifq, ZCRX_NOTIF_COPY); } return ret; } static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, const skb_frag_t *frag, int off, int len) { struct net_iov *niov; struct page_pool *pp; if (unlikely(!skb_frag_is_net_iov(frag))) return io_zcrx_copy_frag(req, ifq, frag, off, len); niov = netmem_to_net_iov(frag->netmem); pp = niov->desc.pp; if (!pp || pp->mp_ops != &io_uring_pp_zc_ops || io_pp_to_ifq(pp) != ifq) return -EFAULT; if (!io_zcrx_queue_cqe(req, niov, ifq, off + skb_frag_off(frag), len)) return -ENOSPC; /* * Prevent it from being recycled while user is accessing it. * It has to be done before grabbing a user reference. */ page_pool_ref_netmem(net_iov_to_netmem(niov)); io_zcrx_get_niov_uref(niov); return len; } static int io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct io_zcrx_args *args = desc->arg.data; struct io_zcrx_ifq *ifq = args->ifq; struct io_kiocb *req = args->req; struct sk_buff *frag_iter; unsigned start, start_off = offset; int i, copy, end, off; int ret = 0; len = min_t(size_t, len, desc->count); /* * __tcp_read_sock() always calls io_zcrx_recv_skb one last time, even * if desc->count is already 0. This is caused by the if (offset + 1 != * skb->len) check. Return early in this case to break out of * __tcp_read_sock(). */ if (!len) return 0; if (unlikely(args->nr_skbs++ > IO_SKBS_PER_CALL_LIMIT)) return -EAGAIN; if (unlikely(offset < skb_headlen(skb))) { ssize_t copied; size_t to_copy; to_copy = min_t(size_t, skb_headlen(skb) - offset, len); copied = io_zcrx_copy_chunk(req, ifq, virt_to_page(skb->data), offset_in_page(skb->data) + offset, to_copy); if (copied < 0) { ret = copied; goto out; } offset += copied; len -= copied; if (!len) goto out; if (offset != skb_headlen(skb)) goto out; } start = skb_headlen(skb); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { const skb_frag_t *frag; if (WARN_ON(start > offset + len)) return -EFAULT; frag = &skb_shinfo(skb)->frags[i]; end = start + skb_frag_size(frag); if (offset < end) { copy = end - offset; if (copy > len) copy = len; off = offset - start; ret = io_zcrx_recv_frag(req, ifq, frag, off, copy); if (ret < 0) goto out; offset += ret; len -= ret; if (len == 0 || ret != copy) goto out; } start = end; } skb_walk_frags(skb, frag_iter) { if (WARN_ON(start > offset + len)) return -EFAULT; end = start + frag_iter->len; if (offset < end) { size_t count; copy = end - offset; if (copy > len) copy = len; off = offset - start; count = desc->count; ret = io_zcrx_recv_skb(desc, frag_iter, off, copy); desc->count = count; if (ret < 0) goto out; offset += ret; len -= ret; if (len == 0 || ret != copy) goto out; } start = end; } out: if (offset == start_off) return ret; desc->count -= (offset - start_off); return offset - start_off; } static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq, struct sock *sk, int flags, unsigned issue_flags, unsigned int *outlen) { unsigned int len = *outlen; struct io_zcrx_args args = { .req = req, .ifq = ifq, }; read_descriptor_t rd_desc = { .count = len ? len : UINT_MAX, .arg.data = &args, }; int ret; lock_sock(sk); ret = tcp_read_sock(sk, &rd_desc, io_zcrx_recv_skb); if (len && ret > 0) *outlen = len - ret; if (ret <= 0) { if (ret < 0 || sock_flag(sk, SOCK_DONE)) goto out; if (sk->sk_err) ret = sock_error(sk); else if (sk->sk_shutdown & RCV_SHUTDOWN) goto out; else if (sk->sk_state == TCP_CLOSE) ret = -ENOTCONN; else ret = -EAGAIN; } else if (unlikely(args.nr_skbs > IO_SKBS_PER_CALL_LIMIT) && (issue_flags & IO_URING_F_MULTISHOT)) { ret = IOU_REQUEUE; } else if (sock_flag(sk, SOCK_DONE)) { /* Make it to retry until it finally gets 0. */ if (issue_flags & IO_URING_F_MULTISHOT) ret = IOU_REQUEUE; else ret = -EAGAIN; } out: release_sock(sk); return ret; } int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq, struct socket *sock, unsigned int flags, unsigned issue_flags, unsigned int *len) { struct sock *sk = sock->sk; const struct proto *prot = READ_ONCE(sk->sk_prot); if (prot->recvmsg != tcp_recvmsg) return -EPROTONOSUPPORT; sock_rps_record_flow(sk); return io_zcrx_tcp_recvmsg(req, ifq, sk, flags, issue_flags, len); } |
| 9 9 2 2 22 19 4 22 22 7 7 6 3 3 3 3 7 2 4 2 1 1 3 5 2 5 5 2 5 5 5 5 3 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 | // 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 <kunit/visibility.h> #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" 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) 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_handle_frame() 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_obj(*sn); 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); } static void hsr_free_node(struct hsr_node *node) { xa_destroy(&node->seq_blocks); kfree(node->block_buf); kfree(node); } static void hsr_free_node_rcu(struct rcu_head *rn) { struct hsr_node *node = container_of(rn, struct hsr_node, rcu_head); hsr_free_node(node); } static void hsr_lock_seq_out_pair(struct hsr_node *node_a, struct hsr_node *node_b) { if (node_a == node_b) { spin_lock_bh(&node_a->seq_out_lock); return; } if (node_a < node_b) { spin_lock_bh(&node_a->seq_out_lock); spin_lock_nested(&node_b->seq_out_lock, SINGLE_DEPTH_NESTING); } else { spin_lock_bh(&node_b->seq_out_lock); spin_lock_nested(&node_a->seq_out_lock, SINGLE_DEPTH_NESTING); } } static void hsr_unlock_seq_out_pair(struct hsr_node *node_a, struct hsr_node *node_b) { if (node_a == node_b) { spin_unlock_bh(&node_a->seq_out_lock); return; } if (node_a < node_b) { spin_unlock(&node_b->seq_out_lock); spin_unlock_bh(&node_a->seq_out_lock); } else { spin_unlock(&node_a->seq_out_lock); spin_unlock_bh(&node_b->seq_out_lock); } } 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) { list_del_rcu(&node->mac_list); call_rcu(&node->rcu_head, hsr_free_node_rcu); } } 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. */ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, struct list_head *node_db, unsigned char addr[], bool san, enum hsr_port_type rx_port) { struct hsr_node *new_node, *node = NULL; unsigned long now; size_t block_sz; int i; new_node = kzalloc_obj(*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); if (hsr->prot_version == PRP_V1) new_node->seq_port_cnt = 1; else new_node->seq_port_cnt = HSR_PT_PORTS - 1; block_sz = hsr_seq_block_size(new_node); new_node->block_buf = kcalloc(HSR_MAX_SEQ_BLOCKS, block_sz, GFP_ATOMIC); if (!new_node->block_buf) goto free; xa_init(&new_node->seq_blocks); /* 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; } 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->block_buf); free: 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; 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; } else { rct = skb_get_PRP_rct(skb); if (!rct && rx_port != HSR_PT_MASTER) san = true; } return hsr_add_node(hsr, node_db, ethhdr->h_source, san, rx_port); } static bool hsr_seq_block_is_old(struct hsr_seq_block *block) { unsigned long expiry = msecs_to_jiffies(HSR_ENTRY_FORGET_TIME); return time_is_before_jiffies(block->time + expiry); } static void hsr_forget_seq_block(struct hsr_node *node, struct hsr_seq_block *block) { if (block->time) xa_erase(&node->seq_blocks, block->block_idx); block->time = 0; } /* Get the currently active sequence number block. If there is no block yet, or * the existing one is expired, a new block is created. The idea is to maintain * a "sparse bitmap" where a bitmap for the whole sequence number space is * split into blocks and not all blocks exist all the time. The blocks can * expire after time (in low traffic situations) or when they are replaced in * the backing fixed size buffer (in high traffic situations). */ VISIBLE_IF_KUNIT struct hsr_seq_block *hsr_get_seq_block(struct hsr_node *node, u16 block_idx) { struct hsr_seq_block *block, *res; size_t block_sz; block = xa_load(&node->seq_blocks, block_idx); if (block && hsr_seq_block_is_old(block)) { hsr_forget_seq_block(node, block); block = NULL; } if (!block) { block_sz = hsr_seq_block_size(node); block = node->block_buf + node->next_block * block_sz; hsr_forget_seq_block(node, block); memset(block, 0, block_sz); block->time = jiffies; block->block_idx = block_idx; res = xa_store(&node->seq_blocks, block_idx, block, GFP_ATOMIC); if (xa_is_err(res)) { block->time = 0; return NULL; } node->next_block = (node->next_block + 1) & (HSR_MAX_SEQ_BLOCKS - 1); } return block; } EXPORT_SYMBOL_IF_KUNIT(hsr_get_seq_block); /* 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_seq_block *src_blk, *merge_blk; struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_tlv *hsr_sup_tlv; struct hsr_sup_payload *hsr_sp; struct hsr_node *node_real; struct sk_buff *skb = NULL; struct list_head *node_db; struct ethhdr *ethhdr; unsigned int total_pull_size = 0; unsigned int pull_size = 0; unsigned long idx; int i; /* 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, 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); hsr_lock_seq_out_pair(node_real, node_curr); 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]; } } xa_for_each(&node_curr->seq_blocks, idx, src_blk) { if (hsr_seq_block_is_old(src_blk)) continue; merge_blk = hsr_get_seq_block(node_real, src_blk->block_idx); if (!merge_blk) continue; merge_blk->time = min(merge_blk->time, src_blk->time); for (i = 0; i < node_real->seq_port_cnt; i++) { bitmap_or(merge_blk->seq_nrs[i], merge_blk->seq_nrs[i], src_blk->seq_nrs[i], HSR_SEQ_BLOCK_SIZE); } } hsr_unlock_seq_out_pair(node_real, node_curr); 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; call_rcu(&node_curr->rcu_head, hsr_free_node_rcu); } 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) { node->time_in[port->type] = jiffies; node->time_in_stale[port->type] = false; } /* Duplicate discard algorithm: we maintain a bitmap where we set a bit for * every seen sequence number. The bitmap is split into blocks and the block * management is detailed in hsr_get_seq_block(). In any case, we err on the * side of accepting a packet, as the specification requires the algorithm to * be "designed such that it never rejects a legitimate frame, while occasional * acceptance of a duplicate can be tolerated." (IEC 62439-3:2021, 4.1.10.3). * While this requirement is explicit for PRP, applying it to HSR does no harm * either. * * 'frame' is the frame to be sent * 'port_type' is the type of the outgoing interface * * Return: * 1 if frame can be shown to have been sent recently on this interface, * 0 otherwise */ static int hsr_check_duplicate(struct hsr_frame_info *frame, unsigned int port_type) { u16 sequence_nr, seq_bit, block_idx; struct hsr_seq_block *block; struct hsr_node *node; node = frame->node_src; sequence_nr = frame->sequence_nr; if (WARN_ON_ONCE(port_type >= node->seq_port_cnt)) return 0; spin_lock_bh(&node->seq_out_lock); block_idx = hsr_seq_block_index(sequence_nr); block = hsr_get_seq_block(node, block_idx); if (!block) goto out_new; seq_bit = hsr_seq_block_bit(sequence_nr); if (__test_and_set_bit(seq_bit, block->seq_nrs[port_type])) goto out_seen; out_new: spin_unlock_bh(&node->seq_out_lock); return 0; out_seen: spin_unlock_bh(&node->seq_out_lock); return 1; } /* HSR duplicate discard: we check if the same frame has already been sent on * this outgoing interface. The check follows the general duplicate discard * algorithm. * * 'port' is the outgoing interface * 'frame' is the frame to be sent * * Return: * 1 if frame can be shown to have been sent recently on this interface, * 0 otherwise */ int hsr_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame) { return hsr_check_duplicate(frame, port->type - 1); } /* PRP duplicate discard: we only consider frames that are received on port A * or port B and should go to the master port. For those, we check if they have * already been received by the host, i.e., master port. The check uses the * general duplicate discard algorithm, but without tracking multiple ports. * * 'port' is the outgoing interface * 'frame' is the frame to be sent * * Return: * 1 if frame can be shown to have been sent recently on this interface, * 0 otherwise */ int prp_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame) { /* out-going frames are always in order */ if (frame->port_rcv->type == HSR_PT_MASTER) return 0; /* for PRP we should only forward frames from the slave ports * to the master port */ if (port->type != HSR_PT_MASTER) return 1; return hsr_check_duplicate(frame, 0); } EXPORT_SYMBOL_IF_KUNIT(prp_register_frame_out); 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 = timer_container_of(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: */ call_rcu(&node->rcu_head, hsr_free_node_rcu); } } } 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 = timer_container_of(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: */ call_rcu(&node->rcu_head, hsr_free_node_rcu); } } } 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; } /* Fill the last sequence number that has been received from node on if1 by * finding the last sequence number sent on port B; accordingly get the last * received sequence number for if2 using sent sequence numbers on port A. */ static void fill_last_seq_nrs(struct hsr_node *node, u16 *if1_seq, u16 *if2_seq) { struct hsr_seq_block *block; unsigned int block_off; size_t block_sz; u16 seq_bit; spin_lock_bh(&node->seq_out_lock); /* Get last inserted block */ block_off = (node->next_block - 1) & (HSR_MAX_SEQ_BLOCKS - 1); block_sz = hsr_seq_block_size(node); block = node->block_buf + block_off * block_sz; seq_bit = find_last_bit(block->seq_nrs[HSR_PT_SLAVE_B - 1], HSR_SEQ_BLOCK_SIZE); if (seq_bit < HSR_SEQ_BLOCK_SIZE) *if1_seq = (block->block_idx << HSR_SEQ_BLOCK_SHIFT) | seq_bit; seq_bit = find_last_bit(block->seq_nrs[HSR_PT_SLAVE_A - 1], HSR_SEQ_BLOCK_SIZE); if (seq_bit < HSR_SEQ_BLOCK_SIZE) *if2_seq = (block->block_idx << HSR_SEQ_BLOCK_SHIFT) | seq_bit; spin_unlock_bh(&node->seq_out_lock); } 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 = 0; *if2_seq = 0; if (hsr->prot_version != PRP_V1) fill_last_seq_nrs(node, if1_seq, if2_seq); if (node->addr_B_port != HSR_PT_NONE) { port = hsr_port_get_hsr(hsr, node->addr_B_port); if (port) *addr_b_ifindex = port->dev->ifindex; else *addr_b_ifindex = -1; } else { *addr_b_ifindex = -1; } return 0; } |
| 70 46 46 46 46 46 46 1 46 46 46 46 46 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * GF(2^128) polynomial hashing: GHASH and POLYVAL * * Copyright 2025 Google LLC */ #include <crypto/gf128hash.h> #include <linux/export.h> #include <linux/module.h> #include <linux/string.h> #include <linux/unaligned.h> /* * GHASH and POLYVAL are almost-XOR-universal hash functions. They interpret * the message as the coefficients of a polynomial in the finite field GF(2^128) * and evaluate that polynomial at a secret point. * * Neither GHASH nor POLYVAL is a cryptographic hash function. They should be * used only by algorithms that are specifically designed to use them. * * GHASH is the older variant, defined as part of GCM in NIST SP 800-38D * (https://nvlpubs.nist.gov/nistpubs/legacy/sp/nistspecialpublication800-38d.pdf). * GHASH is hard to implement directly, due to its backwards mapping between * bits and polynomial coefficients. GHASH implementations typically pre and * post-process the inputs and outputs (mainly by byte-swapping) to convert the * GHASH computation into an equivalent computation over a different, * easier-to-use representation of GF(2^128). * * POLYVAL is a newer GF(2^128) polynomial hash, originally defined as part of * AES-GCM-SIV (https://datatracker.ietf.org/doc/html/rfc8452) and also used by * HCTR2 (https://eprint.iacr.org/2021/1441.pdf). It uses that easier-to-use * field representation directly, eliminating the data conversion steps. * * This file provides library APIs for GHASH and POLYVAL. These APIs can * delegate to either a generic implementation or an architecture-optimized * implementation. Due to the mathematical relationship between GHASH and * POLYVAL, in some cases code for one is reused with the other. * * For the generic implementation, we don't use the traditional table approach * to GF(2^128) multiplication. That approach is not constant-time and requires * a lot of memory. Instead, we use a different approach which emulates * carryless multiplication using standard multiplications by spreading the data * bits apart using "holes". This allows the carries to spill harmlessly. This * approach is borrowed from BoringSSL, which in turn credits BearSSL's * documentation (https://bearssl.org/constanttime.html#ghash-for-gcm) for the * "holes" trick and a presentation by Shay Gueron * (https://crypto.stanford.edu/RealWorldCrypto/slides/gueron.pdf) for the * 256-bit => 128-bit reduction algorithm. */ #ifdef CONFIG_ARCH_SUPPORTS_INT128 /* Do a 64 x 64 => 128 bit carryless multiplication. */ static void clmul64(u64 a, u64 b, u64 *out_lo, u64 *out_hi) { /* * With 64-bit multiplicands and one term every 4 bits, there would be * up to 64 / 4 = 16 one bits per column when each multiplication is * written out as a series of additions in the schoolbook manner. * Unfortunately, that doesn't work since the value 16 is 1 too large to * fit in 4 bits. Carries would sometimes overflow into the next term. * * Using one term every 5 bits would work. However, that would cost * 5 x 5 = 25 multiplications instead of 4 x 4 = 16. * * Instead, mask off 4 bits from one multiplicand, giving a max of 15 * one bits per column. Then handle those 4 bits separately. */ u64 a0 = a & 0x1111111111111110; u64 a1 = a & 0x2222222222222220; u64 a2 = a & 0x4444444444444440; u64 a3 = a & 0x8888888888888880; u64 b0 = b & 0x1111111111111111; u64 b1 = b & 0x2222222222222222; u64 b2 = b & 0x4444444444444444; u64 b3 = b & 0x8888888888888888; /* Multiply the high 60 bits of @a by @b. */ u128 c0 = (a0 * (u128)b0) ^ (a1 * (u128)b3) ^ (a2 * (u128)b2) ^ (a3 * (u128)b1); u128 c1 = (a0 * (u128)b1) ^ (a1 * (u128)b0) ^ (a2 * (u128)b3) ^ (a3 * (u128)b2); u128 c2 = (a0 * (u128)b2) ^ (a1 * (u128)b1) ^ (a2 * (u128)b0) ^ (a3 * (u128)b3); u128 c3 = (a0 * (u128)b3) ^ (a1 * (u128)b2) ^ (a2 * (u128)b1) ^ (a3 * (u128)b0); /* Multiply the low 4 bits of @a by @b. */ u64 e0 = -(a & 1) & b; u64 e1 = -((a >> 1) & 1) & b; u64 e2 = -((a >> 2) & 1) & b; u64 e3 = -((a >> 3) & 1) & b; u64 extra_lo = e0 ^ (e1 << 1) ^ (e2 << 2) ^ (e3 << 3); u64 extra_hi = (e1 >> 63) ^ (e2 >> 62) ^ (e3 >> 61); /* Add all the intermediate products together. */ *out_lo = (((u64)c0) & 0x1111111111111111) ^ (((u64)c1) & 0x2222222222222222) ^ (((u64)c2) & 0x4444444444444444) ^ (((u64)c3) & 0x8888888888888888) ^ extra_lo; *out_hi = (((u64)(c0 >> 64)) & 0x1111111111111111) ^ (((u64)(c1 >> 64)) & 0x2222222222222222) ^ (((u64)(c2 >> 64)) & 0x4444444444444444) ^ (((u64)(c3 >> 64)) & 0x8888888888888888) ^ extra_hi; } #else /* CONFIG_ARCH_SUPPORTS_INT128 */ /* Do a 32 x 32 => 64 bit carryless multiplication. */ static noinline_for_stack u64 clmul32(u32 a, u32 b) { /* * With 32-bit multiplicands and one term every 4 bits, there are up to * 32 / 4 = 8 one bits per column when each multiplication is written * out as a series of additions in the schoolbook manner. The value 8 * fits in 4 bits, so the carries don't overflow into the next term. */ u32 a0 = a & 0x11111111; u32 a1 = a & 0x22222222; u32 a2 = a & 0x44444444; u32 a3 = a & 0x88888888; u32 b0 = b & 0x11111111; u32 b1 = b & 0x22222222; u32 b2 = b & 0x44444444; u32 b3 = b & 0x88888888; u64 c0 = (a0 * (u64)b0) ^ (a1 * (u64)b3) ^ (a2 * (u64)b2) ^ (a3 * (u64)b1); u64 c1 = (a0 * (u64)b1) ^ (a1 * (u64)b0) ^ (a2 * (u64)b3) ^ (a3 * (u64)b2); u64 c2 = (a0 * (u64)b2) ^ (a1 * (u64)b1) ^ (a2 * (u64)b0) ^ (a3 * (u64)b3); u64 c3 = (a0 * (u64)b3) ^ (a1 * (u64)b2) ^ (a2 * (u64)b1) ^ (a3 * (u64)b0); /* Add all the intermediate products together. */ return (c0 & 0x1111111111111111) ^ (c1 & 0x2222222222222222) ^ (c2 & 0x4444444444444444) ^ (c3 & 0x8888888888888888); } /* Do a 64 x 64 => 128 bit carryless multiplication. */ static void clmul64(u64 a, u64 b, u64 *out_lo, u64 *out_hi) { u32 a_lo = (u32)a; u32 a_hi = a >> 32; u32 b_lo = (u32)b; u32 b_hi = b >> 32; /* Karatsuba multiplication */ u64 lo = clmul32(a_lo, b_lo); u64 hi = clmul32(a_hi, b_hi); u64 mi = clmul32(a_lo ^ a_hi, b_lo ^ b_hi) ^ lo ^ hi; *out_lo = lo ^ (mi << 32); *out_hi = hi ^ (mi >> 32); } #endif /* !CONFIG_ARCH_SUPPORTS_INT128 */ /* Compute @a = @a * @b * x^-128 in the POLYVAL field. */ static void __maybe_unused polyval_mul_generic(struct polyval_elem *a, const struct polyval_elem *b) { u64 c0, c1, c2, c3, mi0, mi1; /* * Carryless-multiply @a by @b using Karatsuba multiplication. Store * the 256-bit product in @c0 (low) through @c3 (high). */ clmul64(le64_to_cpu(a->lo), le64_to_cpu(b->lo), &c0, &c1); clmul64(le64_to_cpu(a->hi), le64_to_cpu(b->hi), &c2, &c3); clmul64(le64_to_cpu(a->lo ^ a->hi), le64_to_cpu(b->lo ^ b->hi), &mi0, &mi1); mi0 ^= c0 ^ c2; mi1 ^= c1 ^ c3; c1 ^= mi0; c2 ^= mi1; /* * Cancel out the low 128 bits of the product by adding multiples of * G(x) = x^128 + x^127 + x^126 + x^121 + 1. Do this in two steps, each * of which cancels out 64 bits. Note that we break G(x) into three * parts: 1, x^64 * (x^63 + x^62 + x^57), and x^128 * 1. */ /* * First, add G(x) times c0 as follows: * * (c0, c1, c2) = (0, * c1 + (c0 * (x^63 + x^62 + x^57) mod x^64), * c2 + c0 + floor((c0 * (x^63 + x^62 + x^57)) / x^64)) */ c1 ^= (c0 << 63) ^ (c0 << 62) ^ (c0 << 57); c2 ^= c0 ^ (c0 >> 1) ^ (c0 >> 2) ^ (c0 >> 7); /* * Second, add G(x) times the new c1: * * (c1, c2, c3) = (0, * c2 + (c1 * (x^63 + x^62 + x^57) mod x^64), * c3 + c1 + floor((c1 * (x^63 + x^62 + x^57)) / x^64)) */ c2 ^= (c1 << 63) ^ (c1 << 62) ^ (c1 << 57); c3 ^= c1 ^ (c1 >> 1) ^ (c1 >> 2) ^ (c1 >> 7); /* Return (c2, c3). This implicitly multiplies by x^-128. */ a->lo = cpu_to_le64(c2); a->hi = cpu_to_le64(c3); } static void __maybe_unused ghash_blocks_generic(struct polyval_elem *acc, const struct polyval_elem *key, const u8 *data, size_t nblocks) { do { acc->lo ^= cpu_to_le64(get_unaligned_be64((__be64 *)(data + 8))); acc->hi ^= cpu_to_le64(get_unaligned_be64((__be64 *)data)); polyval_mul_generic(acc, key); data += GHASH_BLOCK_SIZE; } while (--nblocks); } static void __maybe_unused polyval_blocks_generic(struct polyval_elem *acc, const struct polyval_elem *key, const u8 *data, size_t nblocks) { do { acc->lo ^= get_unaligned((__le64 *)data); acc->hi ^= get_unaligned((__le64 *)(data + 8)); polyval_mul_generic(acc, key); data += POLYVAL_BLOCK_SIZE; } while (--nblocks); } /* Convert the key from GHASH format to POLYVAL format. */ static void __maybe_unused ghash_key_to_polyval(const u8 in[GHASH_BLOCK_SIZE], struct polyval_elem *out) { u64 hi = get_unaligned_be64(&in[0]); u64 lo = get_unaligned_be64(&in[8]); u64 mask = (s64)hi >> 63; hi = (hi << 1) ^ (lo >> 63) ^ (mask & ((u64)0xc2 << 56)); lo = (lo << 1) ^ (mask & 1); out->lo = cpu_to_le64(lo); out->hi = cpu_to_le64(hi); } /* Convert the accumulator from POLYVAL format to GHASH format. */ static void polyval_acc_to_ghash(const struct polyval_elem *in, u8 out[GHASH_BLOCK_SIZE]) { put_unaligned_be64(le64_to_cpu(in->hi), &out[0]); put_unaligned_be64(le64_to_cpu(in->lo), &out[8]); } /* Convert the accumulator from GHASH format to POLYVAL format. */ static void __maybe_unused ghash_acc_to_polyval(const u8 in[GHASH_BLOCK_SIZE], struct polyval_elem *out) { out->lo = cpu_to_le64(get_unaligned_be64(&in[8])); out->hi = cpu_to_le64(get_unaligned_be64(&in[0])); } #ifdef CONFIG_CRYPTO_LIB_GF128HASH_ARCH #include "gf128hash.h" /* $(SRCARCH)/gf128hash.h */ #endif void ghash_preparekey(struct ghash_key *key, const u8 raw_key[GHASH_BLOCK_SIZE]) { #ifdef ghash_preparekey_arch ghash_preparekey_arch(key, raw_key); #else ghash_key_to_polyval(raw_key, &key->h); #endif } EXPORT_SYMBOL_GPL(ghash_preparekey); static void ghash_mul(struct ghash_ctx *ctx) { #ifdef ghash_mul_arch ghash_mul_arch(&ctx->acc, ctx->key); #elif defined(ghash_blocks_arch) static const u8 zeroes[GHASH_BLOCK_SIZE]; ghash_blocks_arch(&ctx->acc, ctx->key, zeroes, 1); #else polyval_mul_generic(&ctx->acc, &ctx->key->h); #endif } /* nblocks is always >= 1. */ static void ghash_blocks(struct ghash_ctx *ctx, const u8 *data, size_t nblocks) { #ifdef ghash_blocks_arch ghash_blocks_arch(&ctx->acc, ctx->key, data, nblocks); #else ghash_blocks_generic(&ctx->acc, &ctx->key->h, data, nblocks); #endif } void ghash_update(struct ghash_ctx *ctx, const u8 *data, size_t len) { if (unlikely(ctx->partial)) { size_t n = min(len, GHASH_BLOCK_SIZE - ctx->partial); len -= n; while (n--) ctx->acc.bytes[GHASH_BLOCK_SIZE - 1 - ctx->partial++] ^= *data++; if (ctx->partial < GHASH_BLOCK_SIZE) return; ghash_mul(ctx); } if (len >= GHASH_BLOCK_SIZE) { size_t nblocks = len / GHASH_BLOCK_SIZE; ghash_blocks(ctx, data, nblocks); data += len & ~(GHASH_BLOCK_SIZE - 1); len &= GHASH_BLOCK_SIZE - 1; } for (size_t i = 0; i < len; i++) ctx->acc.bytes[GHASH_BLOCK_SIZE - 1 - i] ^= data[i]; ctx->partial = len; } EXPORT_SYMBOL_GPL(ghash_update); void ghash_final(struct ghash_ctx *ctx, u8 out[GHASH_BLOCK_SIZE]) { if (unlikely(ctx->partial)) ghash_mul(ctx); polyval_acc_to_ghash(&ctx->acc, out); memzero_explicit(ctx, sizeof(*ctx)); } EXPORT_SYMBOL_GPL(ghash_final); void polyval_preparekey(struct polyval_key *key, const u8 raw_key[POLYVAL_BLOCK_SIZE]) { #ifdef polyval_preparekey_arch polyval_preparekey_arch(key, raw_key); #else memcpy(key->h.bytes, raw_key, POLYVAL_BLOCK_SIZE); #endif } EXPORT_SYMBOL_GPL(polyval_preparekey); /* * polyval_mul_generic() and polyval_blocks_generic() take the key as a * polyval_elem rather than a polyval_key, so that arch-optimized * implementations with a different key format can use it as a fallback (if they * have H^1 stored somewhere in their struct). Thus, the following dispatch * code is needed to pass the appropriate key argument. */ static void polyval_mul(struct polyval_ctx *ctx) { #ifdef polyval_mul_arch polyval_mul_arch(&ctx->acc, ctx->key); #elif defined(polyval_blocks_arch) static const u8 zeroes[POLYVAL_BLOCK_SIZE]; polyval_blocks_arch(&ctx->acc, ctx->key, zeroes, 1); #else polyval_mul_generic(&ctx->acc, &ctx->key->h); #endif } /* nblocks is always >= 1. */ static void polyval_blocks(struct polyval_ctx *ctx, const u8 *data, size_t nblocks) { #ifdef polyval_blocks_arch polyval_blocks_arch(&ctx->acc, ctx->key, data, nblocks); #else polyval_blocks_generic(&ctx->acc, &ctx->key->h, data, nblocks); #endif } void polyval_update(struct polyval_ctx *ctx, const u8 *data, size_t len) { if (unlikely(ctx->partial)) { size_t n = min(len, POLYVAL_BLOCK_SIZE - ctx->partial); len -= n; while (n--) ctx->acc.bytes[ctx->partial++] ^= *data++; if (ctx->partial < POLYVAL_BLOCK_SIZE) return; polyval_mul(ctx); } if (len >= POLYVAL_BLOCK_SIZE) { size_t nblocks = len / POLYVAL_BLOCK_SIZE; polyval_blocks(ctx, data, nblocks); data += len & ~(POLYVAL_BLOCK_SIZE - 1); len &= POLYVAL_BLOCK_SIZE - 1; } for (size_t i = 0; i < len; i++) ctx->acc.bytes[i] ^= data[i]; ctx->partial = len; } EXPORT_SYMBOL_GPL(polyval_update); void polyval_final(struct polyval_ctx *ctx, u8 out[POLYVAL_BLOCK_SIZE]) { if (unlikely(ctx->partial)) polyval_mul(ctx); memcpy(out, &ctx->acc, POLYVAL_BLOCK_SIZE); memzero_explicit(ctx, sizeof(*ctx)); } EXPORT_SYMBOL_GPL(polyval_final); #ifdef gf128hash_mod_init_arch static int __init gf128hash_mod_init(void) { gf128hash_mod_init_arch(); return 0; } subsys_initcall(gf128hash_mod_init); static void __exit gf128hash_mod_exit(void) { } module_exit(gf128hash_mod_exit); #endif MODULE_DESCRIPTION("GF(2^128) polynomial hashing: GHASH and POLYVAL"); MODULE_LICENSE("GPL"); |
| 5 5 5 5 5 5 5 5 5 5 5 5 5 5 18 18 18 3 1 1 1 1 18 22 18 18 1 12 3 2 4 6 19 19 19 19 19 19 19 19 22 19 19 18 18 18 18 28 28 29 16 2 18 11 7 18 1 1 1 1 1 1 1 1 1 4 4 4 4 4 2 2 2 1 1 1 1 2 2 2 2 2 2 2 7 7 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include <linux/device.h> #include <net/genetlink.h> #include <net/sock.h> #include "devl_internal.h" struct devlink_info_req { struct sk_buff *msg; void (*version_cb)(const char *version_name, enum devlink_info_version_type version_type, void *version_cb_priv); void *version_cb_priv; }; struct devlink_reload_combination { enum devlink_reload_action action; enum devlink_reload_limit limit; }; static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { { /* can't reinitialize driver with no down time */ .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, }, }; static bool devlink_reload_combination_is_invalid(enum devlink_reload_action action, enum devlink_reload_limit limit) { int i; for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) if (devlink_reload_invalid_combinations[i].action == action && devlink_reload_invalid_combinations[i].limit == limit) return true; return false; } static bool devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) { return test_bit(action, &devlink->ops->reload_actions); } static bool devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) { return test_bit(limit, &devlink->ops->reload_limits); } static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_limit limit, u32 value) { struct nlattr *reload_stats_entry; reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); if (!reload_stats_entry) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) goto nla_put_failure; nla_nest_end(msg, reload_stats_entry); return 0; nla_put_failure: nla_nest_cancel(msg, reload_stats_entry); return -EMSGSIZE; } static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) { struct nlattr *reload_stats_attr, *act_info, *act_stats; int i, j, stat_idx; u32 value; if (!is_remote) reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); else reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); if (!reload_stats_attr) return -EMSGSIZE; for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || i == DEVLINK_RELOAD_ACTION_UNSPEC) continue; act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); if (!act_info) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) goto action_info_nest_cancel; act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); if (!act_stats) goto action_info_nest_cancel; for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { /* Remote stats are shown even if not locally supported. * Stats of actions with unspecified limit are shown * though drivers don't need to register unspecified * limit. */ if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && !devlink_reload_limit_is_supported(devlink, j)) || devlink_reload_combination_is_invalid(i, j)) continue; stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; if (!is_remote) value = devlink->stats.reload_stats[stat_idx]; else value = devlink->stats.remote_reload_stats[stat_idx]; if (devlink_reload_stat_put(msg, j, value)) goto action_stats_nest_cancel; } nla_nest_end(msg, act_stats); nla_nest_end(msg, act_info); } nla_nest_end(msg, reload_stats_attr); return 0; action_stats_nest_cancel: nla_nest_cancel(msg, act_stats); action_info_nest_cancel: nla_nest_cancel(msg, act_info); nla_put_failure: nla_nest_cancel(msg, reload_stats_attr); return -EMSGSIZE; } static int devlink_nl_nested_fill(struct sk_buff *msg, struct devlink *devlink) { unsigned long rel_index; void *unused; int err; xa_for_each(&devlink->nested_rels, rel_index, unused) { err = devlink_rel_devlink_handle_put(msg, devlink, rel_index, DEVLINK_ATTR_NESTED_DEVLINK, NULL); if (err) return err; } return 0; } static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags) { struct nlattr *dev_stats; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) goto nla_put_failure; dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); if (!dev_stats) goto nla_put_failure; if (devlink_reload_stats_put(msg, devlink, false)) goto dev_stats_nest_cancel; if (devlink_reload_stats_put(msg, devlink, true)) goto dev_stats_nest_cancel; nla_nest_end(msg, dev_stats); if (devlink_nl_nested_fill(msg, devlink)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; dev_stats_nest_cancel: nla_nest_cancel(msg, dev_stats); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) { struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); WARN_ON(!devl_is_registered(devlink)); if (!devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } devlink_nl_notify_send(devlink, msg); } int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); } int devlink_nl_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { return devlink_nl_dumpit(msg, cb, devlink_nl_get_dump_one); } static void devlink_rel_notify_cb(struct devlink *devlink, u32 obj_index) { devlink_notify(devlink, DEVLINK_CMD_NEW); } static void devlink_rel_cleanup_cb(struct devlink *devlink, u32 obj_index, u32 rel_index) { xa_erase(&devlink->nested_rels, rel_index); } int devl_nested_devlink_set(struct devlink *devlink, struct devlink *nested_devlink) { u32 rel_index; int err; err = devlink_rel_nested_in_add(&rel_index, devlink->index, 0, devlink_rel_notify_cb, devlink_rel_cleanup_cb, nested_devlink); if (err) return err; return xa_insert(&devlink->nested_rels, rel_index, xa_mk_value(0), GFP_KERNEL); } EXPORT_SYMBOL_GPL(devl_nested_devlink_set); void devlink_notify_register(struct devlink *devlink) { devlink_notify(devlink, DEVLINK_CMD_NEW); devlink_linecards_notify_register(devlink); devlink_ports_notify_register(devlink); devlink_trap_policers_notify_register(devlink); devlink_trap_groups_notify_register(devlink); devlink_traps_notify_register(devlink); devlink_rates_notify_register(devlink); devlink_regions_notify_register(devlink); devlink_params_notify_register(devlink); } void devlink_notify_unregister(struct devlink *devlink) { devlink_params_notify_unregister(devlink); devlink_regions_notify_unregister(devlink); devlink_rates_notify_unregister(devlink); devlink_traps_notify_unregister(devlink); devlink_trap_groups_notify_unregister(devlink); devlink_trap_policers_notify_unregister(devlink); devlink_ports_notify_unregister(devlink); devlink_linecards_notify_unregister(devlink); devlink_notify(devlink, DEVLINK_CMD_DEL); } static void devlink_reload_failed_set(struct devlink *devlink, bool reload_failed) { if (devlink->reload_failed == reload_failed) return; devlink->reload_failed = reload_failed; devlink_notify(devlink, DEVLINK_CMD_NEW); } bool devlink_is_reload_failed(const struct devlink *devlink) { return devlink->reload_failed; } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); static void __devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, enum devlink_reload_limit limit, u32 actions_performed) { unsigned long actions = actions_performed; int stat_idx; int action; for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; reload_stats[stat_idx]++; } devlink_notify(devlink, DEVLINK_CMD_NEW); } static void devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, u32 actions_performed) { __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, actions_performed); } /** * devlink_remote_reload_actions_performed - Update devlink on reload actions * performed which are not a direct result of devlink reload call. * * This should be called by a driver after performing reload actions in case it was not * a result of devlink reload call. For example fw_activate was performed as a result * of devlink reload triggered fw_activate on another host. * The motivation for this function is to keep data on reload actions performed on this * function whether it was done due to direct devlink reload call or not. * * @devlink: devlink * @limit: reload limit * @actions_performed: bitmask of actions performed */ void devlink_remote_reload_actions_performed(struct devlink *devlink, enum devlink_reload_limit limit, u32 actions_performed) { if (WARN_ON(!actions_performed || actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || limit > DEVLINK_RELOAD_LIMIT_MAX)) return; __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, actions_performed); } EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); static struct net *devlink_netns_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; struct net *net; if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified"); return ERR_PTR(-EINVAL); } if (netns_pid_attr) { net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); } else if (netns_fd_attr) { net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); } else if (netns_id_attr) { net = get_net_ns_by_id(sock_net(skb->sk), nla_get_u32(netns_id_attr)); if (!net) net = ERR_PTR(-EINVAL); } else { WARN_ON(1); net = ERR_PTR(-EINVAL); } if (IS_ERR(net)) { NL_SET_ERR_MSG(info->extack, "Unknown network namespace"); return ERR_PTR(-EINVAL); } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { put_net(net); return ERR_PTR(-EPERM); } return net; } static void devlink_reload_netns_change(struct devlink *devlink, struct net *curr_net, struct net *dest_net) { /* Userspace needs to be notified about devlink objects * removed from original and entering new network namespace. * The rest of the devlink objects are re-created during * reload process so the notifications are generated separatelly. */ devlink_notify_unregister(devlink); write_pnet(&devlink->_net, dest_net); devlink_notify_register(devlink); devlink_rel_nested_in_notify(devlink); } static void devlink_reload_reinit_sanity_check(struct devlink *devlink) { WARN_ON(!list_empty(&devlink->trap_policer_list)); WARN_ON(!list_empty(&devlink->trap_group_list)); WARN_ON(!list_empty(&devlink->trap_list)); WARN_ON(!list_empty(&devlink->dpipe_table_list)); WARN_ON(!list_empty(&devlink->sb_list)); WARN_ON(devlink_rates_check(devlink, NULL, NULL)); WARN_ON(!list_empty(&devlink->linecard_list)); WARN_ON(!xa_empty(&devlink->ports)); } int devlink_reload(struct devlink *devlink, struct net *dest_net, enum devlink_reload_action action, enum devlink_reload_limit limit, u32 *actions_performed, struct netlink_ext_ack *extack) { u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; struct net *curr_net; int err; /* Make sure the reload operations are invoked with the device lock * held to allow drivers to trigger functionality that expects it * (e.g., PCI reset) and to close possible races between these * operations and probe/remove. */ if (devlink->dev) device_lock_assert(devlink->dev); memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); if (err) return err; curr_net = devlink_net(devlink); if (dest_net && !net_eq(dest_net, curr_net)) devlink_reload_netns_change(devlink, curr_net, dest_net); if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT) { devlink_params_driverinit_load_new(devlink); devlink_reload_reinit_sanity_check(devlink); } err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); if (err) return err; WARN_ON(!(*actions_performed & BIT(action))); /* Catch driver on updating the remote action within devlink reload */ WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats))); devlink_reload_stats_update(devlink, limit, *actions_performed); return 0; } static int devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, enum devlink_command cmd, struct genl_info *info) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); if (!hdr) goto free_msg; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, actions_performed)) goto nla_put_failure; genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); nla_put_failure: genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; } int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; enum devlink_reload_action action; enum devlink_reload_limit limit; struct net *dest_net = NULL; u32 actions_performed; int err; err = devlink_resources_validate(devlink, NULL, info); if (err) { NL_SET_ERR_MSG(info->extack, "resources size validation failed"); return err; } action = nla_get_u8_default(info->attrs[DEVLINK_ATTR_RELOAD_ACTION], DEVLINK_RELOAD_ACTION_DRIVER_REINIT); if (!devlink_reload_action_is_supported(devlink, action)) { NL_SET_ERR_MSG(info->extack, "Requested reload action is not supported by the driver"); return -EOPNOTSUPP; } limit = DEVLINK_RELOAD_LIMIT_UNSPEC; if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { struct nla_bitfield32 limits; u32 limits_selected; limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); limits_selected = limits.value & limits.selector; if (!limits_selected) { NL_SET_ERR_MSG(info->extack, "Invalid limit selected"); return -EINVAL; } for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) if (limits_selected & BIT(limit)) break; /* UAPI enables multiselection, but currently it is not used */ if (limits_selected != BIT(limit)) { NL_SET_ERR_MSG(info->extack, "Multiselection of limit is not supported"); return -EOPNOTSUPP; } if (!devlink_reload_limit_is_supported(devlink, limit)) { NL_SET_ERR_MSG(info->extack, "Requested limit is not supported by the driver"); return -EOPNOTSUPP; } if (devlink_reload_combination_is_invalid(action, limit)) { NL_SET_ERR_MSG(info->extack, "Requested limit is invalid for this action"); return -EINVAL; } } if (info->attrs[DEVLINK_ATTR_NETNS_PID] || info->attrs[DEVLINK_ATTR_NETNS_FD] || info->attrs[DEVLINK_ATTR_NETNS_ID]) { dest_net = devlink_netns_get(skb, info); if (IS_ERR(dest_net)) return PTR_ERR(dest_net); if (!net_eq(dest_net, devlink_net(devlink)) && action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) { NL_SET_ERR_MSG_MOD(info->extack, "Changing namespace is only supported for reinit action"); return -EOPNOTSUPP; } } err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); if (dest_net) put_net(dest_net); if (err) return err; /* For backward compatibility generate reply only if attributes used by user */ if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) return 0; return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, DEVLINK_CMD_RELOAD, info); } bool devlink_reload_actions_valid(const struct devlink_ops *ops) { const struct devlink_reload_combination *comb; int i; if (!devlink_reload_supported(ops)) { if (WARN_ON(ops->reload_actions)) return false; return true; } if (WARN_ON(!ops->reload_actions || ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) return false; if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) return false; for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { comb = &devlink_reload_invalid_combinations[i]; if (ops->reload_actions == BIT(comb->action) && ops->reload_limits == BIT(comb->limit)) return false; } return true; } static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; enum devlink_eswitch_encap_mode encap_mode; u8 inline_mode; void *hdr; int err = 0; u16 mode; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = devlink_nl_put_handle(msg, devlink); if (err) goto nla_put_failure; if (ops->eswitch_mode_get) { err = ops->eswitch_mode_get(devlink, &mode); if (err) goto nla_put_failure; err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); if (err) goto nla_put_failure; } if (ops->eswitch_inline_mode_get) { err = ops->eswitch_inline_mode_get(devlink, &inline_mode); if (err) goto nla_put_failure; err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, inline_mode); if (err) goto nla_put_failure; } if (ops->eswitch_encap_mode_get) { err = ops->eswitch_encap_mode_get(devlink, &encap_mode); if (err) goto nla_put_failure; err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); if (err) goto nla_put_failure; } genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return err; } int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; enum devlink_eswitch_encap_mode encap_mode; u8 inline_mode; int err = 0; u16 mode; if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { if (!ops->eswitch_mode_set) return -EOPNOTSUPP; err = devlink_rates_check(devlink, devlink_rate_is_node, info->extack); if (err) return err; mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); err = ops->eswitch_mode_set(devlink, mode, info->extack); if (err) return err; } if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { if (!ops->eswitch_inline_mode_set) return -EOPNOTSUPP; inline_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); err = ops->eswitch_inline_mode_set(devlink, inline_mode, info->extack); if (err) return err; } if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { if (!ops->eswitch_encap_mode_set) return -EOPNOTSUPP; encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); err = ops->eswitch_encap_mode_set(devlink, encap_mode, info->extack); if (err) return err; } return 0; } int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) { if (!req->msg) return 0; return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); } EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); int devlink_info_board_serial_number_put(struct devlink_info_req *req, const char *bsn) { if (!req->msg) return 0; return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, bsn); } EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); static int devlink_info_version_put(struct devlink_info_req *req, int attr, const char *version_name, const char *version_value, enum devlink_info_version_type version_type) { struct nlattr *nest; int err; if (req->version_cb) req->version_cb(version_name, version_type, req->version_cb_priv); if (!req->msg || !*version_value) return 0; nest = nla_nest_start_noflag(req->msg, attr); if (!nest) return -EMSGSIZE; err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, version_name); if (err) goto nla_put_failure; err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, version_value); if (err) goto nla_put_failure; nla_nest_end(req->msg, nest); return 0; nla_put_failure: nla_nest_cancel(req->msg, nest); return err; } int devlink_info_version_fixed_put(struct devlink_info_req *req, const char *version_name, const char *version_value) { return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, version_name, version_value, DEVLINK_INFO_VERSION_TYPE_NONE); } EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); int devlink_info_version_stored_put(struct devlink_info_req *req, const char *version_name, const char *version_value) { return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, version_name, version_value, DEVLINK_INFO_VERSION_TYPE_NONE); } EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); int devlink_info_version_stored_put_ext(struct devlink_info_req *req, const char *version_name, const char *version_value, enum devlink_info_version_type version_type) { return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, version_name, version_value, version_type); } EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); int devlink_info_version_running_put(struct devlink_info_req *req, const char *version_name, const char *version_value) { return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, version_name, version_value, DEVLINK_INFO_VERSION_TYPE_NONE); } EXPORT_SYMBOL_GPL(devlink_info_version_running_put); int devlink_info_version_running_put_ext(struct devlink_info_req *req, const char *version_name, const char *version_value, enum devlink_info_version_type version_type) { return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, version_name, version_value, version_type); } EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); static int devlink_nl_driver_info_get(const struct device_driver *drv, struct devlink_info_req *req) { if (!drv) return 0; if (drv->name[0]) return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, drv->name); return 0; } static int devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct devlink_info_req req = {}; void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto err_cancel_msg; req.msg = msg; if (devlink->ops->info_get) { err = devlink->ops->info_get(devlink, &req, extack); if (err) goto err_cancel_msg; } err = devlink_nl_driver_info_get(devlink->dev_driver, &req); if (err) goto err_cancel_msg; genlmsg_end(msg, hdr); return 0; err_cancel_msg: genlmsg_cancel(msg, hdr); return err; } int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { int err; err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); if (err == -EOPNOTSUPP) err = 0; return err; } int devlink_nl_info_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { return devlink_nl_dumpit(msg, cb, devlink_nl_info_get_dump_one); } static int devlink_nl_flash_update_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, struct devlink_flash_notify *params) { void *hdr; hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) goto out; if (params->status_msg && nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, params->status_msg)) goto nla_put_failure; if (params->component && nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, params->component)) goto nla_put_failure; if (devlink_nl_put_u64(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, params->done)) goto nla_put_failure; if (devlink_nl_put_u64(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, params->total)) goto nla_put_failure; if (devlink_nl_put_u64(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, params->timeout)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void __devlink_flash_update_notify(struct devlink *devlink, enum devlink_command cmd, struct devlink_flash_notify *params) { struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && cmd != DEVLINK_CMD_FLASH_UPDATE_END && cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); if (err) goto out_free_msg; devlink_nl_notify_send(devlink, msg); return; out_free_msg: nlmsg_free(msg); } static void devlink_flash_update_begin_notify(struct devlink *devlink) { struct devlink_flash_notify params = {}; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE, ¶ms); } static void devlink_flash_update_end_notify(struct devlink *devlink) { struct devlink_flash_notify params = {}; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_END, ¶ms); } void devlink_flash_update_status_notify(struct devlink *devlink, const char *status_msg, const char *component, unsigned long done, unsigned long total) { struct devlink_flash_notify params = { .status_msg = status_msg, .component = component, .done = done, .total = total, }; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_STATUS, ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); void devlink_flash_update_timeout_notify(struct devlink *devlink, const char *status_msg, const char *component, unsigned long timeout) { struct devlink_flash_notify params = { .status_msg = status_msg, .component = component, .timeout = timeout, }; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_STATUS, ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); struct devlink_flash_component_lookup_ctx { const char *lookup_name; bool lookup_name_found; }; static void devlink_flash_component_lookup_cb(const char *version_name, enum devlink_info_version_type version_type, void *version_cb_priv) { struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || lookup_ctx->lookup_name_found) return; lookup_ctx->lookup_name_found = !strcmp(lookup_ctx->lookup_name, version_name); } static int devlink_flash_component_get(struct devlink *devlink, struct nlattr *nla_component, const char **p_component, struct netlink_ext_ack *extack) { struct devlink_flash_component_lookup_ctx lookup_ctx = {}; struct devlink_info_req req = {}; const char *component; int ret; if (!nla_component) return 0; component = nla_data(nla_component); if (!devlink->ops->info_get) { NL_SET_ERR_MSG_ATTR(extack, nla_component, "component update is not supported by this device"); return -EOPNOTSUPP; } lookup_ctx.lookup_name = component; req.version_cb = devlink_flash_component_lookup_cb; req.version_cb_priv = &lookup_ctx; ret = devlink->ops->info_get(devlink, &req, NULL); if (ret) return ret; if (!lookup_ctx.lookup_name_found) { NL_SET_ERR_MSG_ATTR(extack, nla_component, "selected component is not supported by this device"); return -EINVAL; } *p_component = component; return 0; } int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_overwrite_mask, *nla_file_name; struct devlink_flash_update_params params = {}; struct devlink *devlink = info->user_ptr[0]; const char *file_name; u32 supported_params; int ret; if (!devlink->ops->flash_update) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) return -EINVAL; ret = devlink_flash_component_get(devlink, info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], ¶ms.component, info->extack); if (ret) return ret; supported_params = devlink->ops->supported_flash_update_params; nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; if (nla_overwrite_mask) { struct nla_bitfield32 sections; if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, "overwrite settings are not supported by this device"); return -EOPNOTSUPP; } sections = nla_get_bitfield32(nla_overwrite_mask); params.overwrite_mask = sections.value & sections.selector; } nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; file_name = nla_data(nla_file_name); ret = request_firmware(¶ms.fw, file_name, devlink->dev); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file"); return ret; } devlink_flash_update_begin_notify(devlink); ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); devlink_flash_update_end_notify(devlink); release_firmware(params.fw); return ret; } static void __devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { struct devlink_info_req req = {}; const struct nlattr *nlattr; struct sk_buff *msg; int rem, err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; req.msg = msg; err = devlink->ops->info_get(devlink, &req, NULL); if (err) goto free_msg; nla_for_each_attr_type(nlattr, DEVLINK_ATTR_INFO_VERSION_RUNNING, (void *)msg->data, msg->len, rem) { const struct nlattr *kv; int rem_kv; nla_for_each_nested_type(kv, DEVLINK_ATTR_INFO_VERSION_VALUE, nlattr, rem_kv) { strlcat(buf, nla_data(kv), len); strlcat(buf, " ", len); } } free_msg: nlmsg_consume(msg); } void devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { if (!devlink->ops->info_get) return; devl_lock(devlink); if (devl_is_registered(devlink)) __devlink_compat_running_version(devlink, buf, len); devl_unlock(devlink); } int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) { struct devlink_flash_update_params params = {}; int ret; devl_lock(devlink); if (!devl_is_registered(devlink)) { ret = -ENODEV; goto out_unlock; } if (!devlink->ops->flash_update) { ret = -EOPNOTSUPP; goto out_unlock; } ret = request_firmware(¶ms.fw, file_name, devlink->dev); if (ret) goto out_unlock; devlink_flash_update_begin_notify(devlink); ret = devlink->ops->flash_update(devlink, ¶ms, NULL); devlink_flash_update_end_notify(devlink); release_firmware(params.fw); out_unlock: devl_unlock(devlink); return ret; } static int devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct nlattr *selftests; void *hdr; int err; int i; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, DEVLINK_CMD_SELFTESTS_GET); if (!hdr) return -EMSGSIZE; err = -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto err_cancel_msg; selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); if (!selftests) goto err_cancel_msg; for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { if (devlink->ops->selftest_check(devlink, i, extack)) { err = nla_put_flag(msg, i); if (err) goto err_cancel_msg; } } nla_nest_end(msg, selftests); genlmsg_end(msg, hdr); return 0; err_cancel_msg: genlmsg_cancel(msg, hdr); return err; } int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; int err; if (!devlink->ops->selftest_check) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_selftests_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { if (!devlink->ops->selftest_check) return 0; return devlink_nl_selftests_fill(msg, devlink, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); } int devlink_nl_selftests_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_selftests_get_dump_one); } static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, enum devlink_selftest_status test_status) { struct nlattr *result_attr; result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); if (!result_attr) return -EMSGSIZE; if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, test_status)) goto nla_put_failure; nla_nest_end(skb, result_attr); return 0; nla_put_failure: nla_nest_cancel(skb, result_attr); return -EMSGSIZE; } static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, }; int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; struct devlink *devlink = info->user_ptr[0]; struct nlattr *attrs, *selftests; struct sk_buff *msg; void *hdr; int err; int i; if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) return -EINVAL; attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, devlink_selftest_nl_policy, info->extack); if (err < 0) return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = -EMSGSIZE; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); if (!hdr) goto free_msg; if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); if (!selftests) goto genlmsg_cancel; for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { enum devlink_selftest_status test_status; if (nla_get_flag(tb[i])) { if (!devlink->ops->selftest_check(devlink, i, info->extack)) { if (devlink_selftest_result_put(msg, i, DEVLINK_SELFTEST_STATUS_SKIP)) goto selftests_nest_cancel; continue; } test_status = devlink->ops->selftest_run(devlink, i, info->extack); if (devlink_selftest_result_put(msg, i, test_status)) goto selftests_nest_cancel; } } nla_nest_end(msg, selftests); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); selftests_nest_cancel: nla_nest_cancel(msg, selftests); genlmsg_cancel: genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return err; } |
| 13 1 2 3 5 2 14 27 31 2 3 1 1 1 2 2 1598 4 2251 1 1612 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions Copyright (C) 1992 Drew Eckhardt */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H #include <linux/types.h> #include <linux/blk_types.h> #include <linux/device.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/completion.h> #include <linux/wait.h> #include <linux/bio.h> #include <linux/gfp.h> #include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/blkzoned.h> #include <linux/sched.h> #include <linux/sbitmap.h> #include <linux/uuid.h> #include <linux/xarray.h> #include <linux/file.h> #include <linux/lockdep.h> struct module; struct request_queue; struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; struct blkcg_gq; struct blk_flush_queue; struct kiocb; struct pr_ops; struct rq_qos; struct hd_geometry; struct blk_report_zones_args; struct blk_queue_stats; struct blk_stat_callback; struct blk_crypto_profile; extern const struct device_type disk_type; extern const struct device_type part_type; extern const struct class block_class; /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ #define BLKCG_MAX_POLS 6 #define DISK_MAX_PARTS 256 #define DISK_NAME_LEN 32 #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. * EFI UUID is 36 characters. MSDOS UUID is 11 characters. */ #define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) struct partition_meta_info { char uuid[PARTITION_META_INFO_UUIDLTH]; u8 volname[PARTITION_META_INFO_VOLNAMELTH]; }; /** * DOC: genhd capability flags * * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to * removable media. When set, the device remains present even when media is not * inserted. Shall not be set for devices which are removed entirely when the * media is removed. * * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, * doesn't appear in sysfs, and can't be opened from userspace or using * blkdev_get*. Used for the underlying components of multipath devices. * * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not * scan for partitions from add_disk, and users can't add partitions manually. * */ enum { GENHD_FL_REMOVABLE = 1 << 0, GENHD_FL_HIDDEN = 1 << 1, GENHD_FL_NO_PART = 1 << 2, }; enum { DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ }; enum { /* Poll even if events_poll_msecs is unset */ DISK_EVENT_FLAG_POLL = 1 << 0, /* Forward events to udev */ DISK_EVENT_FLAG_UEVENT = 1 << 1, /* Block event polling when open for exclusive write */ DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, }; struct disk_events; struct badblocks; enum blk_integrity_checksum { BLK_INTEGRITY_CSUM_NONE = 0, BLK_INTEGRITY_CSUM_IP = 1, BLK_INTEGRITY_CSUM_CRC = 2, BLK_INTEGRITY_CSUM_CRC64 = 3, } __packed ; struct blk_integrity { unsigned char flags; enum blk_integrity_checksum csum_type; unsigned char metadata_size; unsigned char pi_offset; unsigned char interval_exp; unsigned char tag_size; unsigned char pi_tuple_size; }; typedef unsigned int __bitwise blk_mode_t; /* open for reading */ #define BLK_OPEN_READ ((__force blk_mode_t)(1 << 0)) /* open for writing */ #define BLK_OPEN_WRITE ((__force blk_mode_t)(1 << 1)) /* open exclusively (vs other exclusive openers */ #define BLK_OPEN_EXCL ((__force blk_mode_t)(1 << 2)) /* opened with O_NDELAY */ #define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) /* open for "writes" only for ioctls (specialy hack for floppy.c) */ #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) /* return partition scanning errors */ #define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* * major/first_minor/minors should not be set by any new driver, the * block core will take care of allocating them automatically. */ int major; int first_minor; int minors; char disk_name[DISK_NAME_LEN]; /* name of major driver */ unsigned short events; /* supported events */ unsigned short event_flags; /* flags related to event processing */ struct xarray part_tbl; struct block_device *part0; const struct block_device_operations *fops; struct request_queue *queue; void *private_data; struct bio_set bio_split; int flags; unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 #define GD_DEAD 2 #define GD_NATIVE_CAPACITY 3 #define GD_ADDED 4 #define GD_SUPPRESS_PART_SCAN 5 #define GD_OWNS_QUEUE 6 #define GD_ZONE_APPEND_USED 7 #define GD_ERROR_INJECT 8 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ struct backing_dev_info *bdi; struct kobject queue_kobj; /* the queue/ directory */ struct kobject *slave_dir; #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED struct list_head slave_bdevs; #endif struct timer_rand_state *random; struct disk_events *ev; #ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information. Reads of this information must be * protected with blk_queue_enter() / blk_queue_exit(). Modifying this * information is only allowed while no requests are being processed. * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue(). */ unsigned int nr_zones; unsigned int zone_capacity; unsigned int last_zone_capacity; u8 __rcu *zones_cond; unsigned int zone_wplugs_hash_bits; atomic_t nr_zone_wplugs; spinlock_t zone_wplugs_hash_lock; struct mempool *zone_wplugs_pool; struct hlist_head *zone_wplugs_hash; struct workqueue_struct *zone_wplugs_wq; spinlock_t zone_wplugs_list_lock; struct list_head zone_wplugs_list; struct task_struct *zone_wplugs_worker; struct completion zone_wplugs_worker_bio_done; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) struct cdrom_device_info *cdi; #endif int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; u64 diskseq; blk_mode_t open_mode; /* * Independent sector access ranges. This is always NULL for * devices that do not have multiple independent access ranges. */ struct blk_independent_access_ranges *ia_ranges; #ifdef CONFIG_BLK_ERROR_INJECTION struct mutex error_injection_lock; struct list_head error_injection_list; #endif struct mutex rqos_state_mutex; /* rqos state change mutex */ }; /** * disk_openers - returns how many openers are there for a disk * @disk: disk to check * * This returns the number of openers for a disk. Note that this value is only * stable if disk->open_mutex is held. * * Note: Due to a quirk in the block layer open code, each open partition is * only counted once even if there are multiple openers. */ static inline unsigned int disk_openers(struct gendisk *disk) { return atomic_read(&disk->part0->bd_openers); } /** * disk_has_partscan - return %true if partition scanning is enabled on a disk * @disk: disk to check * * Returns %true if partitions scanning is enabled for @disk, or %false if * partition scanning is disabled either permanently or temporarily. */ static inline bool disk_has_partscan(struct gendisk *disk) { return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); } /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. */ #define dev_to_disk(device) \ (dev_to_bdev(device)->bd_disk) #define disk_to_dev(disk) \ (&((disk)->part0->bd_device)) #if IS_REACHABLE(CONFIG_CDROM) #define disk_to_cdi(disk) ((disk)->cdi) #else #define disk_to_cdi(disk) NULL #endif static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) * however we constrain this to what we can validate and test. */ #define BLK_MAX_BLOCK_SIZE SZ_64K #else #define BLK_MAX_BLOCK_SIZE PAGE_SIZE #endif /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > BLK_MAX_BLOCK_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; } static inline bool blk_op_is_passthrough(blk_opf_t op) { op &= REQ_OP_MASK; return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } /* flags set by the driver in queue_limits.features */ typedef unsigned int __bitwise blk_features_t; /* supports a volatile write cache */ #define BLK_FEAT_WRITE_CACHE ((__force blk_features_t)(1u << 0)) /* supports passing on the FUA bit */ #define BLK_FEAT_FUA ((__force blk_features_t)(1u << 1)) /* rotational device (hard drive or floppy) */ #define BLK_FEAT_ROTATIONAL ((__force blk_features_t)(1u << 2)) /* contributes to the random number pool */ #define BLK_FEAT_ADD_RANDOM ((__force blk_features_t)(1u << 3)) /* do disk/partitions IO accounting */ #define BLK_FEAT_IO_STAT ((__force blk_features_t)(1u << 4)) /* don't modify data until writeback is done */ #define BLK_FEAT_STABLE_WRITES ((__force blk_features_t)(1u << 5)) /* always completes in submit context */ #define BLK_FEAT_SYNCHRONOUS ((__force blk_features_t)(1u << 6)) /* supports REQ_NOWAIT */ #define BLK_FEAT_NOWAIT ((__force blk_features_t)(1u << 7)) /* supports DAX */ #define BLK_FEAT_DAX ((__force blk_features_t)(1u << 8)) /* supports I/O polling */ #define BLK_FEAT_POLL ((__force blk_features_t)(1u << 9)) /* is a zoned device */ #define BLK_FEAT_ZONED ((__force blk_features_t)(1u << 10)) /* supports PCI(e) p2p requests */ #define BLK_FEAT_PCI_P2PDMA ((__force blk_features_t)(1u << 12)) /* skip this queue in blk_mq_(un)quiesce_tagset */ #define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) /* atomic writes enabled */ #define BLK_FEAT_ATOMIC_WRITES ((__force blk_features_t)(1u << 14)) /* undocumented magic for bcache */ #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ ((__force blk_features_t)(1u << 15)) /* * Flags automatically inherited when stacking limits. */ #define BLK_FEAT_INHERIT_MASK \ (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \ BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) /* internal flags in queue_limits.flags */ typedef unsigned int __bitwise blk_flags_t; /* do not send FLUSH/FUA commands despite advertising a write cache */ #define BLK_FLAG_WRITE_CACHE_DISABLED ((__force blk_flags_t)(1u << 0)) /* I/O topology is misaligned */ #define BLK_FLAG_MISALIGNED ((__force blk_flags_t)(1u << 1)) /* passthrough command IO accounting */ #define BLK_FLAG_IOSTATS_PASSTHROUGH ((__force blk_flags_t)(1u << 2)) struct queue_limits { blk_features_t features; blk_flags_t flags; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; unsigned int max_hw_sectors; unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_user_sectors; unsigned int max_segment_size; unsigned int max_fast_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_wzeroes_unmap_sectors; unsigned int max_hw_wzeroes_unmap_sectors; unsigned int max_user_wzeroes_unmap_sectors; unsigned int max_hw_zone_append_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned int zone_write_granularity; /* atomic write limits */ unsigned int atomic_write_hw_max; unsigned int atomic_write_max_sectors; unsigned int atomic_write_hw_boundary; unsigned int atomic_write_boundary_sectors; unsigned int atomic_write_hw_unit_min; unsigned int atomic_write_unit_min; unsigned int atomic_write_hw_unit_max; unsigned int atomic_write_unit_max; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; unsigned short max_write_streams; unsigned int write_stream_granularity; unsigned int max_open_zones; unsigned int max_active_zones; /* * Drivers that set dma_alignment to less than 511 must be prepared to * handle individual bvec's that are not a multiple of a SECTOR_SIZE * due to possible offsets. */ unsigned int dma_alignment; unsigned int dma_pad_mask; struct blk_integrity integrity; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); int disk_report_zone(struct gendisk *disk, struct blk_zone *zone, unsigned int idx, struct blk_report_zones_args *args); int blkdev_get_zone_info(struct block_device *bdev, sector_t sector, struct blk_zone *zone); #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_report_zones_cached(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors); int blk_revalidate_disk_zones(struct gendisk *disk); /* * Independent access ranges: struct blk_independent_access_range describes * a range of contiguous sectors that can be accessed using device command * execution resources that are independent from the resources used for * other access ranges. This is typically found with single-LUN multi-actuator * HDDs where each access range is served by a different set of heads. * The set of independent ranges supported by the device is defined using * struct blk_independent_access_ranges. The independent ranges must not overlap * and must include all sectors within the disk capacity (no sector holes * allowed). * For a device with multiple ranges, requests targeting sectors in different * ranges can be executed in parallel. A request can straddle an access range * boundary. */ struct blk_independent_access_range { struct kobject kobj; sector_t sector; sector_t nr_sectors; }; struct blk_independent_access_ranges { struct kobject kobj; bool sysfs_registered; unsigned int nr_ia_ranges; struct blk_independent_access_range ia_range[]; }; struct request_queue { /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. */ void *queuedata; struct elevator_queue *elevator; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; /* * various queue flags, see QUEUE_* below */ unsigned long queue_flags; unsigned int __data_racy rq_timeout; unsigned int queue_depth; refcount_t refs; /* hw dispatch queues */ unsigned int nr_hw_queues; struct blk_mq_hw_ctx * __rcu *queue_hw_ctx __counted_by_ptr(nr_hw_queues); struct percpu_ref q_usage_counter; struct lock_class_key io_lock_cls_key; struct lockdep_map io_lockdep_map; struct lock_class_key q_lock_cls_key; struct lockdep_map q_lockdep_map; struct request *last_merge; spinlock_t queue_lock; int quiesce_depth; struct gendisk *disk; /* * mq queue kobject */ struct kobject *mq_kobj; struct queue_limits limits; #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; #endif /* * Number of contexts that have called blk_set_pm_only(). If this * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; struct blk_queue_stats *stats; struct rq_qos *rq_qos; struct mutex rq_qos_mutex; /* * ida allocated id for this queue. Used to index queues from * ioctx. */ int id; /* * queue settings */ unsigned int nr_requests; /* Max # of requests */ unsigned int async_depth; /* Max # of async requests */ #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; struct kobject *crypto_kobject; #endif struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_tags; struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); struct blkcg_gq *root_blkg; struct list_head blkg_list; struct mutex blkcg_mutex; #endif int node; spinlock_t requeue_lock; struct list_head requeue_list; struct delayed_work requeue_work; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif /* * for flush operations */ struct blk_flush_queue *fq; struct list_head flush_list; /* * Protects against I/O scheduler switching, particularly when updating * q->elevator. Since the elevator update code path may also modify q-> * nr_requests and wbt latency, this lock also protects the sysfs attrs * nr_requests and wbt_lat_usec. Additionally the nr_hw_queues update * may modify hctx tags, reserved-tags and cpumask, so this lock also * helps protect the hctx sysfs/debugfs attrs. To ensure proper locking * order during an elevator or nr_hw_queue update, first freeze the * queue, then acquire ->elevator_lock. */ struct mutex elevator_lock; struct mutex sysfs_lock; /* * Protects queue limits and also sysfs attribute read_ahead_kb. */ struct mutex limits_lock; /* * for reusing dead hctx instance in case of updating * nr_hw_queues */ struct list_head unused_hctx_list; spinlock_t unused_hctx_lock; int mq_freeze_depth; #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; #endif struct rcu_head rcu_head; #ifdef CONFIG_LOCKDEP struct task_struct *mq_freeze_owner; int mq_freeze_owner_depth; /* * Records disk & queue state in current context, used in unfreeze * queue */ bool mq_freeze_disk_dead; bool mq_freeze_queue_dying; #endif wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; /* * Serializes all debugfs metadata operations using the above dentries. */ struct mutex debugfs_mutex; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ enum { QUEUE_FLAG_DYING, /* queue being torn down */ QUEUE_FLAG_NOMERGES, /* disable merge attempts */ QUEUE_FLAG_SAME_COMP, /* complete on same CPU-group */ QUEUE_FLAG_FAIL_IO, /* fake timeout */ QUEUE_FLAG_NOXMERGES, /* No extended merges */ QUEUE_FLAG_SAME_FORCE, /* force complete on same CPU */ QUEUE_FLAG_INIT_DONE, /* queue is initialized */ QUEUE_FLAG_STATS, /* track IO start and completion times */ QUEUE_FLAG_REGISTERED, /* queue has been registered to a disk */ QUEUE_FLAG_QUIESCED, /* queue has been quiesced */ QUEUE_FLAG_RQ_ALLOC_TIME, /* record rq->alloc_time_ns */ QUEUE_FLAG_HCTX_ACTIVE, /* at least one blk-mq hctx is active */ QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */ QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */ QUEUE_FLAG_QOS_ENABLED, /* qos is enabled */ QUEUE_FLAG_BIO_ISSUE_TIME, /* record bio->issue_time_ns */ QUEUE_FLAG_ZONED_QD1_WRITES, /* Limit zoned devices writes to QD=1 */ QUEUE_FLAG_MAX }; #define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_rot(q) ((q)->limits.features & BLK_FEAT_ROTATIONAL) #define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT) #define blk_queue_passthrough_stat(q) \ ((q)->limits.flags & BLK_FLAG_IOSTATS_PASSTHROUGH) #define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX) #define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) #else #define blk_queue_rq_alloc_time(q) false #endif #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) #define blk_queue_skip_tagset_quiesce(q) \ ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE) #define blk_queue_disable_wbt(q) \ test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags) #define blk_queue_no_elv_switch(q) \ test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags) #define blk_queue_zoned_qd1_writes(q) \ test_bit(QUEUE_FLAG_ZONED_QD1_WRITES, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define dma_map_bvec(dev, bv, dir, attrs) \ dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } #ifdef CONFIG_PM static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return q->rpm_status; } #else static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return RPM_ACTIVE; } #endif static inline bool blk_queue_is_zoned(struct request_queue *q) { return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && (q->limits.features & BLK_FEAT_ZONED); } static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { if (!blk_queue_is_zoned(disk->queue)) return 0; return sector >> ilog2(disk->queue->limits.chunk_sectors); } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { return bdev->bd_disk->queue->limits.max_open_zones; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { return bdev->bd_disk->queue->limits.max_active_zones; } static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) return q->queue_depth; return q->nr_requests; } /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, struct fwnode_handle *fwnode); int __must_check device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups); static inline int __must_check add_disk(struct gendisk *disk) { return device_add_disk(NULL, disk, NULL); } void del_gendisk(struct gendisk *gp); void invalidate_disk(struct gendisk *disk); void set_disk_ro(struct gendisk *disk, bool read_only); void disk_uevent(struct gendisk *disk, enum kobject_action action); static inline u8 bdev_partno(const struct block_device *bdev) { return atomic_read(&bdev->__bd_flags) & BD_PARTNO; } static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag) { return atomic_read(&bdev->__bd_flags) & flag; } static inline void bdev_set_flag(struct block_device *bdev, unsigned flag) { atomic_or(flag, &bdev->__bd_flags); } static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag) { atomic_andnot(flag, &bdev->__bd_flags); } static inline bool get_disk_ro(struct gendisk *disk) { return bdev_test_flag(disk->part0, BD_READ_ONLY) || test_bit(GD_READ_ONLY, &disk->state); } static inline bool bdev_read_only(struct block_device *bdev) { return bdev_test_flag(bdev, BD_READ_ONLY) || get_disk_ro(bdev->bd_disk); } bool set_capacity_and_notify(struct gendisk *disk, sector_t size); void disk_force_media_change(struct gendisk *disk); void bdev_mark_dead(struct block_device *bdev, bool surprise); void add_disk_randomness(struct gendisk *disk) __latent_entropy; void rand_initialize_disk(struct gendisk *disk); static inline sector_t get_start_sect(struct block_device *bdev) { return bdev->bd_start_sect; } static inline sector_t bdev_nr_sectors(struct block_device *bdev) { return bdev->bd_nr_sectors; } static inline loff_t bdev_nr_bytes(struct block_device *bdev) { return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) { return bdev_nr_sectors(disk->part0); } static inline u64 sb_bdev_nr_blocks(struct super_block *sb) { return bdev_nr_sectors(sb->s_bdev) >> (sb->s_blocksize_bits - SECTOR_SHIFT); } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int disk_nr_zones(struct gendisk *disk) { return disk->nr_zones; } /** * bio_needs_zone_write_plugging - Check if a BIO needs to be handled with zone * write plugging * @bio: The BIO being submitted * * Return true whenever @bio execution needs to be handled through zone * write plugging (using blk_zone_plug_bio()). Return false otherwise. */ static inline bool bio_needs_zone_write_plugging(struct bio *bio) { enum req_op op = bio_op(bio); /* * Only zoned block devices have a zone write plug hash table. But not * all of them have one (e.g. DM devices may not need one). */ if (!bio->bi_bdev->bd_disk->zone_wplugs_hash) return false; /* Only write operations need zone write plugging. */ if (!op_is_write(op)) return false; /* Ignore empty flush */ if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; /* Ignore BIOs that already have been handled by zone write plugging. */ if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING)) return false; /* * All zone write operations must be handled through zone write plugging * using blk_zone_plug_bio(). */ switch (op) { case REQ_OP_ZONE_APPEND: case REQ_OP_WRITE: case REQ_OP_WRITE_ZEROES: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: return true; default: return false; } } bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); /** * disk_zone_capacity - returns the zone capacity of zone containing @sector * @disk: disk to work with * @sector: sector number within the querying zone * * Returns the zone capacity of a zone containing @sector. @sector can be any * sector in the zone. */ static inline unsigned int disk_zone_capacity(struct gendisk *disk, sector_t sector) { sector_t zone_sectors = disk->queue->limits.chunk_sectors; if (sector + zone_sectors >= get_capacity(disk)) return disk->last_zone_capacity; return disk->zone_capacity; } static inline unsigned int bdev_zone_capacity(struct block_device *bdev, sector_t pos) { return disk_zone_capacity(bdev->bd_disk, pos); } bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; } static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector) { return false; } static inline bool bio_needs_zone_write_plugging(struct bio *bio) { return false; } static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) { return false; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int bdev_nr_zones(struct block_device *bdev) { return disk_nr_zones(bdev->bd_disk); } int bdev_disk_changed(struct gendisk *disk, bool invalidate); void put_disk(struct gendisk *disk); struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node, struct lock_class_key *lkclass); /** * blk_alloc_disk - allocate a gendisk structure * @lim: queue limits to be used for this disk. * @node_id: numa node to allocate on * * Allocate and pre-initialize a gendisk structure for use with BIO based * drivers. * * Returns an ERR_PTR on error, else the allocated disk. * * Context: can sleep */ #define blk_alloc_disk(lim, node_id) \ ({ \ static struct lock_class_key __key; \ \ __blk_alloc_disk(lim, node_id, &__key); \ }) int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); bool disk_check_media_change(struct gendisk *disk); void set_capacity(struct gendisk *disk, sector_t size); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { return 0; } static inline void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { } #endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio); struct bio *bio_split_to_limits(struct bio *bio); struct bio *bio_submit_split_bioset(struct bio *bio, unsigned int split_sectors, struct bio_set *bs); extern int blk_lld_busy(struct request_queue *q); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); /* Convert a request operation REQ_OP_name into the string "name" */ extern const char *blk_op_str(enum req_op op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); /* only poll the hardware once, don't continue until a completion was found */ #define BLK_POLL_ONESHOT (1 << 0) int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_queue; /* this is never NULL */ } /* Convert a zone condition BLK_ZONE_COND_name into the string "name" */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); static inline unsigned int bio_zone_no(struct bio *bio) { return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } static inline bool bio_straddles_zones(struct bio *bio) { return bio_sectors(bio) && bio_zone_no(bio) != disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1); } /* * Return how much within the boundary is left to be used for I/O at a given * offset. */ static inline unsigned int blk_boundary_sectors_left(sector_t offset, unsigned int boundary_sectors) { if (unlikely(!is_power_of_2(boundary_sectors))) return boundary_sectors - sector_div(offset, boundary_sectors); return boundary_sectors - (offset & (boundary_sectors - 1)); } /** * queue_limits_start_update - start an atomic update of queue limits * @q: queue to update * * This functions starts an atomic update of the queue limits. It takes a lock * to prevent other updates and returns a snapshot of the current limits that * the caller can modify. The caller must call queue_limits_commit_update() * to finish the update. * * Context: process context. */ static inline struct queue_limits queue_limits_start_update(struct request_queue *q) __acquires(&q->limits_lock) { mutex_lock(&q->limits_lock); return q->limits; } int queue_limits_commit_update_frozen(struct request_queue *q, struct queue_limits *lim) __releases(&q->limits_lock); int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim) __releases(&q->limits_lock); int queue_limits_set(struct request_queue *q, struct queue_limits *lim) __must_not_hold(&q->limits_lock); int blk_validate_limits(struct queue_limits *lim); /** * queue_limits_cancel_update - cancel an atomic update of queue limits * @q: queue to update * * This functions cancels an atomic update of the queue limits started by * queue_limits_start_update() and should be used when an error occurs after * starting update. */ static inline void queue_limits_cancel_update(struct request_queue *q) __releases(&q->limits_lock) { mutex_unlock(&q->limits_lock); } /* * These helpers are for drivers that have sloppy feature negotiation and might * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O * completion handler when the device returned an indicator that the respective * feature is not actually supported. They are racy and the driver needs to * cope with that. Try to avoid this scheme if you can. */ static inline void blk_queue_disable_discard(struct request_queue *q) { q->limits.max_discard_sectors = 0; } static inline void blk_queue_disable_secure_erase(struct request_queue *q) { q->limits.max_secure_erase_sectors = 0; } static inline void blk_queue_disable_write_zeroes(struct request_queue *q) { q->limits.max_write_zeroes_sectors = 0; q->limits.max_wzeroes_unmap_sectors = 0; } /* * Access functions for manipulating queue properties */ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); struct blk_independent_access_ranges * disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); void disk_set_independent_access_ranges(struct gendisk *disk, struct blk_independent_access_ranges *iars); bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); void blk_mark_disk_dead(struct gendisk *disk); struct rq_list { struct request *head; struct request *tail; }; #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests * into single larger request. As the requests are moved from a per-task list to * the device's request_queue in a batch, this results in improved scalability * as the lock contention for request_queue lock is reduced. * * It is ok not to disable preemption when adding the request to the plug list * or when attempting a merge. For details, please see schedule() where * blk_flush_plug() is called. */ struct blk_plug { struct rq_list mq_list; /* blk-mq requests */ /* if ios_left is > 1, we can batch tag/rq allocations */ struct rq_list cached_rqs; u64 cur_ktime; unsigned short nr_ios; unsigned short rq_count; bool multiple_queues; bool has_elevator; struct list_head cb_list; /* md requires an unplug callback */ }; struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; blk_plug_cb_fn callback; void *data; }; extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); void __blk_flush_plug(struct blk_plug *plug, bool from_schedule); static inline void blk_flush_plug(struct blk_plug *plug, bool async) { if (plug) __blk_flush_plug(plug, async); } static __always_inline void blk_plug_invalidate_ts(void) { if (unlikely(current->flags & PF_BLOCK_TS)) { current->plug->cur_ktime = 0; current->flags &= ~PF_BLOCK_TS; } } int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { }; static inline void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) { } static inline void blk_start_plug(struct blk_plug *plug) { } static inline void blk_finish_plug(struct blk_plug *plug) { } static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } static inline void blk_plug_invalidate_ts(void) { } static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; } static inline long nr_blockdev_pages(void) { return 0; } #endif /* CONFIG_BLOCK */ extern void blk_io_schedule(void); int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask); void __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ #define BLKDEV_ZERO_KILLABLE (1 << 2) /* interruptible by fatal signals */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) { return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, 0); } static inline bool bdev_is_partition(struct block_device *bdev) { return bdev_partno(bdev) != 0; } enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; static inline struct queue_limits *bdev_limits(struct block_device *bdev) { return &bdev_get_queue(bdev)->limits; } static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; } static inline unsigned long queue_virt_boundary(const struct request_queue *q) { return q->limits.virt_boundary_mask; } static inline unsigned int queue_max_sectors(const struct request_queue *q) { return q->limits.max_sectors; } static inline unsigned int queue_max_bytes(struct request_queue *q) { return min_t(unsigned int, queue_max_sectors(q), INT_MAX >> 9) << 9; } static inline unsigned int queue_max_hw_sectors(const struct request_queue *q) { return q->limits.max_hw_sectors; } static inline unsigned short queue_max_segments(const struct request_queue *q) { return q->limits.max_segments; } static inline unsigned short queue_max_discard_segments(const struct request_queue *q) { return q->limits.max_discard_segments; } static inline unsigned int queue_max_segment_size(const struct request_queue *q) { return q->limits.max_segment_size; } static inline bool queue_emulates_zone_append(struct request_queue *q) { return blk_queue_is_zoned(q) && !q->limits.max_hw_zone_append_sectors; } static inline bool bdev_emulates_zone_append(struct block_device *bdev) { return queue_emulates_zone_append(bdev_get_queue(bdev)); } static inline unsigned int bdev_max_zone_append_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_zone_append_sectors; } static inline unsigned int bdev_max_segments(struct block_device *bdev) { return queue_max_segments(bdev_get_queue(bdev)); } static inline unsigned short bdev_max_write_streams(struct block_device *bdev) { if (bdev_is_partition(bdev)) return 0; return bdev_limits(bdev)->max_write_streams; } static inline unsigned queue_logical_block_size(const struct request_queue *q) { return q->limits.logical_block_size; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_physical_block_size(const struct request_queue *q) { return q->limits.physical_block_size; } static inline unsigned int bdev_physical_block_size(struct block_device *bdev) { return queue_physical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_io_min(const struct request_queue *q) { return q->limits.io_min; } static inline unsigned int bdev_io_min(struct block_device *bdev) { return queue_io_min(bdev_get_queue(bdev)); } static inline unsigned int queue_io_opt(const struct request_queue *q) { return q->limits.io_opt; } static inline unsigned int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } static inline unsigned int queue_zone_write_granularity(const struct request_queue *q) { return q->limits.zone_write_granularity; } static inline unsigned int bdev_zone_write_granularity(struct block_device *bdev) { return queue_zone_write_granularity(bdev_get_queue(bdev)); } int bdev_alignment_offset(struct block_device *bdev); unsigned int bdev_discard_alignment(struct block_device *bdev); static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_discard_sectors; } static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { return bdev_limits(bdev)->discard_granularity; } static inline unsigned int bdev_max_secure_erase_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_secure_erase_sectors; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_write_zeroes_sectors; } static inline unsigned int bdev_write_zeroes_unmap_sectors(struct block_device *bdev) { return bdev_limits(bdev)->max_wzeroes_unmap_sectors; } static inline bool bdev_rot(struct block_device *bdev) { return blk_queue_rot(bdev_get_queue(bdev)); } static inline bool bdev_synchronous(struct block_device *bdev) { return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS; } static inline bool bdev_has_integrity_csum(struct block_device *bdev) { struct queue_limits *lim = bdev_limits(bdev); return IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && lim->integrity.csum_type != BLK_INTEGRITY_CSUM_NONE; } static inline bool bdev_stable_writes(struct block_device *bdev) { return bdev_has_integrity_csum(bdev) || (bdev_limits(bdev)->features & BLK_FEAT_STABLE_WRITES); } static inline bool blk_queue_write_cache(struct request_queue *q) { return (q->limits.features & BLK_FEAT_WRITE_CACHE) && !(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED); } static inline bool bdev_write_cache(struct block_device *bdev) { return blk_queue_write_cache(bdev_get_queue(bdev)); } static inline bool bdev_fua(struct block_device *bdev) { return bdev_limits(bdev)->features & BLK_FEAT_FUA; } static inline bool bdev_nowait(struct block_device *bdev) { return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT; } static inline bool bdev_is_zoned(struct block_device *bdev) { return blk_queue_is_zoned(bdev_get_queue(bdev)); } static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) { return disk_zone_no(bdev->bd_disk, sec); } static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (!blk_queue_is_zoned(q)) return 0; return q->limits.chunk_sectors; } static inline sector_t bdev_zone_start(struct block_device *bdev, sector_t sector) { return sector & ~(bdev_zone_sectors(bdev) - 1); } static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, sector_t sector) { return sector & (bdev_zone_sectors(bdev) - 1); } static inline sector_t bio_offset_from_zone_start(struct bio *bio) { return bdev_offset_from_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector); } static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sector) { return bdev_offset_from_zone_start(bdev, sector) == 0; } /* Check whether @sector is a multiple of the zone size. */ static inline bool bdev_is_zone_aligned(struct block_device *bdev, sector_t sector) { return bdev_is_zone_start(bdev, sector); } int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask); static inline unsigned int queue_dma_alignment(const struct request_queue *q) { return q->limits.dma_alignment; } static inline unsigned int queue_atomic_write_unit_max_bytes(const struct request_queue *q) { return q->limits.atomic_write_unit_max; } static inline unsigned int queue_atomic_write_unit_min_bytes(const struct request_queue *q) { return q->limits.atomic_write_unit_min; } static inline unsigned int queue_atomic_write_boundary_bytes(const struct request_queue *q) { return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT; } static inline unsigned int queue_atomic_write_max_bytes(const struct request_queue *q) { return q->limits.atomic_write_max_sectors << SECTOR_SHIFT; } static inline unsigned int bdev_dma_alignment(struct block_device *bdev) { return queue_dma_alignment(bdev_get_queue(bdev)); } static inline unsigned int blk_lim_dma_alignment_and_pad(struct queue_limits *lim) { return lim->dma_alignment | lim->dma_pad_mask; } static inline bool blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits); return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT; } int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") #ifdef CONFIG_BLK_INLINE_ENCRYPTION bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q) { return true; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ enum blk_unique_id { /* these match the Designator Types specified in SPC */ BLK_UID_T10 = 1, BLK_UID_EUI64 = 2, BLK_UID_NAA = 3, }; struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); int (*open)(struct gendisk *disk, blk_mode_t mode); void (*release)(struct gendisk *disk); int (*ioctl)(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg); int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); int (*getgeo)(struct gendisk *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); void (*free_disk)(struct gendisk *disk); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, unsigned int nr_zones, struct blk_report_zones_args *args); char *(*devnode)(struct gendisk *disk, umode_t *mode); /* returns the length of the identifier or a negative errno: */ int (*get_unique_id)(struct gendisk *disk, u8 id[16], enum blk_unique_id id_type); struct module *owner; const struct pr_ops *pr_ops; /* * Special callback for probing GPT entry at a given sector. * Needed by Android devices, used by GPT scanner and MMC blk * driver. */ int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector); }; #ifdef CONFIG_COMPAT extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL #endif static inline void blk_wake_io_task(struct task_struct *waiter) { /* * If we're polling, the task itself is doing the completions. For * that case, we don't need to signal a wakeup, it's enough to just * mark us as RUNNING. */ if (waiter == current) __set_current_state(TASK_RUNNING); else wake_up_process(waiter); } unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for * @start_time: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } int bdev_validate_blocksize(struct block_device *bdev, int block_size); int set_blocksize(struct file *file, int size); int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK #define BLKDEV_MAJOR_MAX 512 #else #define BLKDEV_MAJOR_MAX 0 #endif struct blk_holder_ops { void (*mark_dead)(struct block_device *bdev, bool surprise) __releases(&bdev->bd_holder_lock); /* * Sync the file system mounted on the block device. */ void (*sync)(struct block_device *bdev) __releases(&bdev->bd_holder_lock); /* * Freeze the file system mounted on the block device. */ int (*freeze)(struct block_device *bdev) __releases(&bdev->bd_holder_lock); /* * Thaw the file system mounted on the block device. */ int (*thaw)(struct block_device *bdev) __releases(&bdev->bd_holder_lock); }; /* * For filesystems using @fs_holder_ops, the @holder argument passed to * helpers used to open and claim block devices via * bd_prepare_to_claim() must point to a superblock. */ extern const struct blk_holder_ops fs_holder_ops; /* * Return the correct open flags for blkdev_get_by_* for super block flags * as stored in sb->s_flags. */ #define sb_open_mode(flags) \ (BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \ (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); struct block_device *I_BDEV(struct inode *inode); struct block_device *file_bdev(struct file *bdev_file); bool disk_live(struct gendisk *disk); unsigned int block_size(struct block_device *bdev); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else static inline void invalidate_bdev(struct block_device *bdev) { } static inline int sync_blockdev(struct block_device *bdev) { return 0; } static inline int sync_blockdev_nowait(struct block_device *bdev) { return 0; } static inline void sync_bdevs(bool wait) { } static inline void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask) { } static inline void printk_all_partitions(void) { } static inline int early_lookup_bdev(const char *pathname, dev_t *dev) { return -EINVAL; } #endif /* CONFIG_BLOCK */ int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct rq_list req_list; bool need_ts; void (*complete)(struct io_comp_batch *); void *poll_ctx; }; static inline bool blk_atomic_write_start_sect_aligned(sector_t sector, struct queue_limits *limits) { unsigned int alignment = max(limits->atomic_write_hw_unit_min, limits->atomic_write_hw_boundary); return IS_ALIGNED(sector, alignment >> SECTOR_SHIFT); } static inline bool bdev_can_atomic_write(struct block_device *bdev) { struct request_queue *bd_queue = bdev->bd_queue; struct queue_limits *limits = &bd_queue->limits; if (!limits->atomic_write_unit_min) return false; if (bdev_is_partition(bdev)) return blk_atomic_write_start_sect_aligned(bdev->bd_start_sect, limits); return true; } static inline unsigned int bdev_atomic_write_unit_min_bytes(struct block_device *bdev) { if (!bdev_can_atomic_write(bdev)) return 0; return queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev)); } static inline unsigned int bdev_atomic_write_unit_max_bytes(struct block_device *bdev) { if (!bdev_can_atomic_write(bdev)) return 0; return queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev)); } static inline int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim, unsigned *segs, unsigned max_bytes) { return bio_split_io_at(bio, lim, segs, max_bytes, lim->dma_alignment); } /* * Maximum contiguous integrity buffer allocation. */ #define BLK_INTEGRITY_MAX_SIZE SZ_2M /* * Maximum size of I/O that needs a block layer integrity buffer. Limited * by the number of intervals for which we can fit the integrity buffer into * the buffer size. Because the buffer is a single segment it is also limited * by the maximum segment size. */ static inline unsigned int max_integrity_io_size(struct queue_limits *lim) { return min_t(unsigned int, lim->max_segment_size, (BLK_INTEGRITY_MAX_SIZE / lim->integrity.metadata_size) << lim->integrity.interval_exp); } #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ |
| 43 8 40 64 64 63 63 1 1 49 47 6 2 2 3 1 3 25 21 2 20 26 27 1 16 6 21 20 17 12 47 47 48 46 10 5 5 4 2 41 6 34 10 41 1 1 8 29 14 14 5 4 45 26 40 13 12 47 47 51 1 51 50 50 27 27 27 25 16 15 25 5 25 19 20 20 19 14 39 8 19 25 5 5 25 30 7 25 18 4 14 9 4 5 10 10 1 7 2 1 4 4 29 30 30 30 30 30 20 14 29 28 5 30 1 2 3 2 1 2 1 9 9 2 51 1 1 2 3 3 43 12 34 16 1 4 4 17 2 2 17 15 11 4 11 11 5 1 1 8 8 9 11 1 7 5 3 2 1 34 34 10 2 4 1 3 10 1 1 2 1 1 1 3 4 2 11 1 4 2 2 2 4 5 2 43 1 3 4 4 24 32 2 31 1 2 1 4 16 1 2 5 11 18 5 9 26 16 25 36 36 36 2 4 2 2 11 3 10 19 1 18 8 3 11 2 18 18 3 6 3 6 5 4 44 1 2 1 8 19 18 49 8 41 4 1 1 30 30 4 12 13 25 2 25 25 2 1 1 1 1 2 195 195 195 90 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware vSockets Driver * * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. */ /* Implementation notes: * * - There are two kinds of sockets: those created by user action (such as * calling socket(2)) and those created by incoming connection request packets. * * - There are two "global" tables, one for bound sockets (sockets that have * specified an address that they are responsible for) and one for connected * sockets (sockets that have established a connection with another socket). * These tables are "global" in that all sockets on the system are placed * within them. - Note, though, that the bound table contains an extra entry * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in * that list. The bound table is used solely for lookup of sockets when packets * are received and that's not necessary for SOCK_DGRAM sockets since we create * a datagram handle for each and need not perform a lookup. Keeping SOCK_DGRAM * sockets out of the bound hash buckets will reduce the chance of collisions * when looking for SOCK_STREAM sockets and prevents us from having to check the * socket type in the hash table lookups. * * - Sockets created by user action will either be "client" sockets that * initiate a connection or "server" sockets that listen for connections; we do * not support simultaneous connects (two "client" sockets connecting). * * - "Server" sockets are referred to as listener sockets throughout this * implementation because they are in the TCP_LISTEN state. When a * connection request is received (the second kind of socket mentioned above), * we create a new socket and refer to it as a pending socket. These pending * sockets are placed on the pending connection list of the listener socket. * When future packets are received for the address the listener socket is * bound to, we check if the source of the packet is from one that has an * existing pending connection. If it does, we process the packet for the * pending socket. When that socket reaches the connected state, it is removed * from the listener socket's pending list and enqueued in the listener * socket's accept queue. Callers of accept(2) will accept connected sockets * from the listener socket's accept queue. If the socket cannot be accepted * for some reason then it is marked rejected. Once the connection is * accepted, it is owned by the user process and the responsibility for cleanup * falls with that user process. * * - It is possible that these pending sockets will never reach the connected * state; in fact, we may never receive another packet after the connection * request. Because of this, we must schedule a cleanup function to run in the * future, after some amount of time passes where a connection should have been * established. This function ensures that the socket is off all lists so it * cannot be retrieved, then drops all references to the socket so it is cleaned * up (sock_put() -> sk_free() -> our sk_destruct implementation). Note this * function will also cleanup rejected sockets, those that reach the connected * state but leave it before they have been accepted. * * - Lock ordering for pending or accept queue sockets is: * * lock_sock(listener); * lock_sock_nested(pending, SINGLE_DEPTH_NESTING); * * Using explicit nested locking keeps lockdep happy since normally only one * lock of a given class may be taken at a time. * * - Sockets created by user action will be cleaned up when the user process * calls close(2), causing our release implementation to be called. Our release * implementation will perform some cleanup then drop the last reference so our * sk_destruct implementation is invoked. Our sk_destruct implementation will * perform additional cleanup that's common for both types of sockets. * * - A socket's reference count is what ensures that the structure won't be * freed. Each entry in a list (such as the "global" bound and connected tables * and the listener socket's pending list and connected queue) ensures a * reference. When we defer work until process context and pass a socket as our * argument, we must ensure the reference count is increased to ensure the * socket isn't freed before the function is run; the deferred function will * then drop the reference. * * - sk->sk_state uses the TCP state constants because they are widely used by * other address families and exposed to userspace tools like ss(8): * * TCP_CLOSE - unconnected * TCP_SYN_SENT - connecting * TCP_ESTABLISHED - connected * TCP_CLOSING - disconnecting * TCP_LISTEN - listening * * - Namespaces in vsock support two different modes: "local" and "global". * Each mode defines how the namespace interacts with CIDs. * Each namespace exposes two sysctl files: * * - /proc/sys/net/vsock/ns_mode (read-only) reports the current namespace's * mode, which is set at namespace creation and immutable thereafter. * - /proc/sys/net/vsock/child_ns_mode (write-once) controls what mode future * child namespaces will inherit when created. The initial value matches * the namespace's own ns_mode. * * Changing child_ns_mode only affects newly created namespaces, not the * current namespace or existing children. A "local" namespace cannot set * child_ns_mode to "global". child_ns_mode is write-once, so that it may be * configured and locked down by a namespace manager. Writing a different * value after the first write returns -EBUSY. At namespace creation, ns_mode * is inherited from the parent's child_ns_mode. * * The init_net mode is "global" and cannot be modified. The init_net * child_ns_mode is also write-once, so an init process (e.g. systemd) can * set it to "local" to ensure all new namespaces inherit local mode. * * The modes affect the allocation and accessibility of CIDs as follows: * * - global - access and allocation are all system-wide * - all CID allocation from global namespaces draw from the same * system-wide pool. * - if one global namespace has already allocated some CID, another * global namespace will not be able to allocate the same CID. * - global mode AF_VSOCK sockets can reach any VM or socket in any global * namespace, they are not contained to only their own namespace. * - AF_VSOCK sockets in a global mode namespace cannot reach VMs or * sockets in any local mode namespace. * - local - access and allocation are contained within the namespace * - CID allocation draws only from a private pool local only to the * namespace, and does not affect the CIDs available for allocation in any * other namespace (global or local). * - VMs in a local namespace do not collide with CIDs in any other local * namespace or any global namespace. For example, if a VM in a local mode * namespace is given CID 10, then CID 10 is still available for * allocation in any other namespace, but not in the same namespace. * - AF_VSOCK sockets in a local mode namespace can connect only to VMs or * other sockets within their own namespace. * - sockets bound to VMADDR_CID_ANY in local namespaces will never resolve * to any transport that is not compatible with local mode. There is no * error that propagates to the user (as there is for connection attempts) * because it is possible for some packet to reach this socket from * a different transport that *does* support local mode. For * example, virtio-vsock may not support local mode, but the socket * may still accept a connection from vhost-vsock which does. */ #include <linux/compat.h> #include <linux/types.h> #include <linux/bitops.h> #include <linux/cred.h> #include <linux/errqueue.h> #include <linux/init.h> #include <linux/io.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/poll.h> #include <linux/random.h> #include <linux/skbuff.h> #include <linux/smp.h> #include <linux/uio.h> #include <linux/socket.h> #include <linux/stddef.h> #include <linux/sysctl.h> #include <linux/unistd.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> #include <net/af_vsock.h> #include <net/netns/vsock.h> #include <uapi/linux/vm_sockets.h> #include <uapi/asm-generic/ioctls.h> #define VSOCK_NET_MODE_STR_GLOBAL "global" #define VSOCK_NET_MODE_STR_LOCAL "local" /* 6 chars for "global", 1 for null-terminator, and 1 more for '\n'. * The newline is added by proc_dostring() for read operations. */ #define VSOCK_NET_MODE_STR_MAX 8 static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); static void vsock_close(struct sock *sk, long timeout); /* Protocol family. */ struct proto vsock_proto = { .name = "AF_VSOCK", .owner = THIS_MODULE, .obj_size = sizeof(struct vsock_sock), .close = vsock_close, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = vsock_bpf_update_proto, #endif }; /* The default peer timeout indicates how long we will wait for a peer response * to a control message. */ #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) #define VSOCK_DEFAULT_BUFFER_SIZE (1024 * 256) #define VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256) #define VSOCK_DEFAULT_BUFFER_MIN_SIZE 128 /* Transport used for host->guest communication */ static const struct vsock_transport *transport_h2g; /* Transport used for guest->host communication */ static const struct vsock_transport *transport_g2h; /* Transport used for DGRAM communication */ static const struct vsock_transport *transport_dgram; /* Transport used for local communication */ static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex); /**** UTILS ****/ /* Each bound VSocket is stored in the bind hash table and each connected * VSocket is stored in the connected hash table. * * Unbound sockets are all put on the same list attached to the end of the hash * table (vsock_unbound_sockets). Bound sockets are added to the hash table in * the bucket that their local address hashes to (vsock_bound_sockets(addr) * represents the list that addr hashes to). * * Specifically, we initialize the vsock_bind_table array to a size of * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function * mods with VSOCK_HASH_SIZE to ensure this. */ #define MAX_PORT_RETRIES 24 #define VSOCK_HASH(addr) ((addr)->svm_port % VSOCK_HASH_SIZE) #define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)]) #define vsock_unbound_sockets (&vsock_bind_table[VSOCK_HASH_SIZE]) /* XXX This can probably be implemented in a better way. */ #define VSOCK_CONN_HASH(src, dst) \ (((src)->svm_cid ^ (dst)->svm_port) % VSOCK_HASH_SIZE) #define vsock_connected_sockets(src, dst) \ (&vsock_connected_table[VSOCK_CONN_HASH(src, dst)]) #define vsock_connected_sockets_vsk(vsk) \ vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr) struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; EXPORT_SYMBOL_GPL(vsock_bind_table); struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; EXPORT_SYMBOL_GPL(vsock_connected_table); DEFINE_SPINLOCK(vsock_table_lock); EXPORT_SYMBOL_GPL(vsock_table_lock); /* Autobind this socket to the local address if necessary. */ static int vsock_auto_bind(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); struct sockaddr_vm local_addr; if (vsock_addr_bound(&vsk->local_addr)) return 0; vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); return __vsock_bind(sk, &local_addr); } static void vsock_init_tables(void) { int i; for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++) INIT_LIST_HEAD(&vsock_bind_table[i]); for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) INIT_LIST_HEAD(&vsock_connected_table[i]); } static void __vsock_insert_bound(struct list_head *list, struct vsock_sock *vsk) { sock_hold(&vsk->sk); list_add(&vsk->bound_table, list); } static void __vsock_insert_connected(struct list_head *list, struct vsock_sock *vsk) { sock_hold(&vsk->sk); list_add(&vsk->connected_table, list); } static void __vsock_remove_bound(struct vsock_sock *vsk) { list_del_init(&vsk->bound_table); sock_put(&vsk->sk); } static void __vsock_remove_connected(struct vsock_sock *vsk) { list_del_init(&vsk->connected_table); sock_put(&vsk->sk); } static struct sock *__vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct net *net) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) { struct sock *sk = sk_vsock(vsk); if (vsock_addr_equals_addr(addr, &vsk->local_addr) && vsock_net_check_mode(sock_net(sk), net)) return sk; if (addr->svm_port == vsk->local_addr.svm_port && (vsk->local_addr.svm_cid == VMADDR_CID_ANY || addr->svm_cid == VMADDR_CID_ANY) && vsock_net_check_mode(sock_net(sk), net)) return sk; } return NULL; } static struct sock * __vsock_find_connected_socket_net(struct sockaddr_vm *src, struct sockaddr_vm *dst, struct net *net) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { struct sock *sk = sk_vsock(vsk); if (vsock_addr_equals_addr(src, &vsk->remote_addr) && dst->svm_port == vsk->local_addr.svm_port && vsock_net_check_mode(sock_net(sk), net)) { return sk; } } return NULL; } static void vsock_insert_unbound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); __vsock_insert_bound(vsock_unbound_sockets, vsk); spin_unlock_bh(&vsock_table_lock); } void vsock_insert_connected(struct vsock_sock *vsk) { struct list_head *list = vsock_connected_sockets( &vsk->remote_addr, &vsk->local_addr); spin_lock_bh(&vsock_table_lock); __vsock_insert_connected(list, vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_insert_connected); void vsock_remove_bound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); if (__vsock_in_bound_table(vsk)) __vsock_remove_bound(vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_remove_bound); void vsock_remove_connected(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); if (__vsock_in_connected_table(vsk)) __vsock_remove_connected(vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_remove_connected); /* Find a bound socket, filtering by namespace and namespace mode. * * Use this in transports that are namespace-aware and can provide the * network namespace context. */ struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct net *net) { struct sock *sk; spin_lock_bh(&vsock_table_lock); sk = __vsock_find_bound_socket_net(addr, net); if (sk) sock_hold(sk); spin_unlock_bh(&vsock_table_lock); return sk; } EXPORT_SYMBOL_GPL(vsock_find_bound_socket_net); /* Find a bound socket without namespace filtering. * * Use this in transports that lack namespace context. All sockets are * treated as if in global mode. */ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) { return vsock_find_bound_socket_net(addr, NULL); } EXPORT_SYMBOL_GPL(vsock_find_bound_socket); /* Find a connected socket, filtering by namespace and namespace mode. * * Use this in transports that are namespace-aware and can provide the * network namespace context. */ struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, struct sockaddr_vm *dst, struct net *net) { struct sock *sk; spin_lock_bh(&vsock_table_lock); sk = __vsock_find_connected_socket_net(src, dst, net); if (sk) sock_hold(sk); spin_unlock_bh(&vsock_table_lock); return sk; } EXPORT_SYMBOL_GPL(vsock_find_connected_socket_net); /* Find a connected socket without namespace filtering. * * Use this in transports that lack namespace context. All sockets are * treated as if in global mode. */ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst) { return vsock_find_connected_socket_net(src, dst, NULL); } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) { /* Transport reassignment must not remove the binding. */ if (sock_flag(sk_vsock(vsk), SOCK_DEAD)) vsock_remove_bound(vsk); vsock_remove_connected(vsk); } EXPORT_SYMBOL_GPL(vsock_remove_sock); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)) { int i; spin_lock_bh(&vsock_table_lock); for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { struct vsock_sock *vsk; list_for_each_entry(vsk, &vsock_connected_table[i], connected_table) { if (vsk->transport != transport) continue; fn(sk_vsock(vsk)); } } spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_for_each_connected_socket); void vsock_add_pending(struct sock *listener, struct sock *pending) { struct vsock_sock *vlistener; struct vsock_sock *vpending; vlistener = vsock_sk(listener); vpending = vsock_sk(pending); sock_hold(pending); sock_hold(listener); list_add_tail(&vpending->pending_links, &vlistener->pending_links); sk_acceptq_added(listener); } EXPORT_SYMBOL_GPL(vsock_add_pending); void vsock_remove_pending(struct sock *listener, struct sock *pending) { struct vsock_sock *vpending = vsock_sk(pending); list_del_init(&vpending->pending_links); sock_put(listener); sock_put(pending); sk_acceptq_removed(listener); } EXPORT_SYMBOL_GPL(vsock_remove_pending); void vsock_pending_to_accept(struct sock *listener, struct sock *pending) { struct vsock_sock *vpending = vsock_sk(pending); struct vsock_sock *vlistener = vsock_sk(listener); list_del_init(&vpending->pending_links); list_add_tail(&vpending->accept_queue, &vlistener->accept_queue); } EXPORT_SYMBOL_GPL(vsock_pending_to_accept); void vsock_enqueue_accept(struct sock *listener, struct sock *connected) { struct vsock_sock *vlistener; struct vsock_sock *vconnected; vlistener = vsock_sk(listener); vconnected = vsock_sk(connected); sock_hold(connected); sock_hold(listener); list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue); sk_acceptq_added(listener); } EXPORT_SYMBOL_GPL(vsock_enqueue_accept); static bool vsock_use_local_transport(unsigned int remote_cid) { lockdep_assert_held(&vsock_register_mutex); if (!transport_local) return false; if (remote_cid == VMADDR_CID_LOCAL) return true; if (transport_g2h) { return remote_cid == transport_g2h->get_local_cid(); } else { return remote_cid == VMADDR_CID_HOST; } } static void vsock_deassign_transport(struct vsock_sock *vsk) { if (!vsk->transport) return; vsk->transport->destruct(vsk); module_put(vsk->transport->module); vsk->transport = NULL; } /* Assign a transport to a socket and call the .init transport callback. * * Note: for connection oriented socket this must be called when vsk->remote_addr * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if * g2h is not loaded, will use local transport; * - remote CID <= VMADDR_CID_HOST or remote flags field includes * VMADDR_FLAG_TO_HOST, will use guest->host transport; * - remote CID > VMADDR_CID_HOST and h2g is loaded and h2g claims that CID, * will use host->guest transport; * - h2g not loaded or h2g does not claim that CID and g2h claims the CID via * has_remote_cid, will use guest->host transport (when g2h_fallback=1) * - anything else goes to h2g or returns -ENODEV if no h2g is available */ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) { const struct vsock_transport *new_transport; struct sock *sk = sk_vsock(vsk); unsigned int remote_cid = vsk->remote_addr.svm_cid; __u8 remote_flags; int ret; /* If the packet is coming with the source and destination CIDs higher * than VMADDR_CID_HOST, then a vsock channel where all the packets are * forwarded to the host should be established. Then the host will * need to forward the packets to the guest. * * The flag is set on the (listen) receive path (psk is not NULL). On * the connect path the flag can be set by the user space application. */ if (psk && vsk->local_addr.svm_cid > VMADDR_CID_HOST && vsk->remote_addr.svm_cid > VMADDR_CID_HOST) vsk->remote_addr.svm_flags |= VMADDR_FLAG_TO_HOST; remote_flags = vsk->remote_addr.svm_flags; mutex_lock(&vsock_register_mutex); switch (sk->sk_type) { case SOCK_DGRAM: new_transport = transport_dgram; break; case SOCK_STREAM: case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || (remote_flags & VMADDR_FLAG_TO_HOST)) new_transport = transport_g2h; else if (transport_h2g && (!transport_h2g->has_remote_cid || transport_h2g->has_remote_cid(vsk, remote_cid))) new_transport = transport_h2g; else if (sock_net(sk)->vsock.g2h_fallback && transport_g2h && transport_g2h->has_remote_cid && transport_g2h->has_remote_cid(vsk, remote_cid)) { vsk->remote_addr.svm_flags |= VMADDR_FLAG_TO_HOST; new_transport = transport_g2h; } else { new_transport = transport_h2g; } break; default: ret = -ESOCKTNOSUPPORT; goto err; } if (vsk->transport && vsk->transport == new_transport) { ret = 0; goto err; } /* We increase the module refcnt to prevent the transport unloading * while there are open sockets assigned to it. */ if (!new_transport || !try_module_get(new_transport->module)) { ret = -ENODEV; goto err; } /* It's safe to release the mutex after a successful try_module_get(). * Whichever transport `new_transport` points at, it won't go away until * the last module_put() below or in vsock_deassign_transport(). */ mutex_unlock(&vsock_register_mutex); if (vsk->transport) { /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we * have already held the sock lock. In the other cases, this * function is called on a new socket which is not assigned to * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); /* transport's release() and destruct() can touch some socket * state, since we are reassigning the socket to a new transport * during vsock_connect(), let's reset these fields to have a * clean state. */ sock_reset_flag(sk, SOCK_DONE); sk->sk_state = TCP_CLOSE; WRITE_ONCE(vsk->peer_shutdown, 0); } if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || !new_transport->seqpacket_allow(vsk, remote_cid)) { module_put(new_transport->module); return -ESOCKTNOSUPPORT; } } ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); return ret; } vsk->transport = new_transport; return 0; err: mutex_unlock(&vsock_register_mutex); return ret; } EXPORT_SYMBOL_GPL(vsock_assign_transport); /* * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks. * Otherwise we may race with module removal. Do not use on `vsk->transport`. */ static u32 vsock_registered_transport_cid(const struct vsock_transport **transport) { u32 cid = VMADDR_CID_ANY; mutex_lock(&vsock_register_mutex); if (*transport) cid = (*transport)->get_local_cid(); mutex_unlock(&vsock_register_mutex); return cid; } bool vsock_find_cid(unsigned int cid) { if (cid == vsock_registered_transport_cid(&transport_g2h)) return true; if (transport_h2g && cid == VMADDR_CID_HOST) return true; if (transport_local && cid == VMADDR_CID_LOCAL) return true; return false; } EXPORT_SYMBOL_GPL(vsock_find_cid); static struct sock *vsock_dequeue_accept(struct sock *listener) { struct vsock_sock *vlistener; struct vsock_sock *vconnected; vlistener = vsock_sk(listener); if (list_empty(&vlistener->accept_queue)) return NULL; vconnected = list_entry(vlistener->accept_queue.next, struct vsock_sock, accept_queue); list_del_init(&vconnected->accept_queue); sock_put(listener); /* The caller will need a reference on the connected socket so we let * it call sock_put(). */ return sk_vsock(vconnected); } static bool vsock_is_accept_queue_empty(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); return list_empty(&vsk->accept_queue); } static bool vsock_is_pending(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); return !list_empty(&vsk->pending_links); } static int vsock_send_shutdown(struct sock *sk, int mode) { struct vsock_sock *vsk = vsock_sk(sk); if (!vsk->transport) return -ENODEV; return vsk->transport->shutdown(vsk, mode); } static void vsock_pending_work(struct work_struct *work) { struct sock *sk; struct sock *listener; struct vsock_sock *vsk; bool cleanup; vsk = container_of(work, struct vsock_sock, pending_work.work); sk = sk_vsock(vsk); listener = vsk->listener; cleanup = true; lock_sock(listener); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (vsock_is_pending(sk)) { vsock_remove_pending(listener, sk); } else if (!vsk->rejected) { /* We are not on the pending list and accept() did not reject * us, so we must have been accepted by our user process. We * just need to drop our references to the sockets and be on * our way. */ cleanup = false; goto out; } /* We need to remove ourself from the global connected sockets list so * incoming packets can't find this socket, and to reduce the reference * count. */ vsock_remove_connected(vsk); sk->sk_state = TCP_CLOSE; out: release_sock(sk); release_sock(listener); if (cleanup) sock_put(sk); sock_put(sk); sock_put(listener); } /**** SOCKET OPERATIONS ****/ static int __vsock_bind_connectible(struct vsock_sock *vsk, struct sockaddr_vm *addr) { struct net *net = sock_net(sk_vsock(vsk)); struct sockaddr_vm new_addr; if (!net->vsock.port) net->vsock.port = get_random_u32_above(LAST_RESERVED_PORT); vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); if (addr->svm_port == VMADDR_PORT_ANY) { bool found = false; unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { if (net->vsock.port == VMADDR_PORT_ANY || net->vsock.port <= LAST_RESERVED_PORT) net->vsock.port = LAST_RESERVED_PORT + 1; new_addr.svm_port = net->vsock.port++; if (!__vsock_find_bound_socket_net(&new_addr, net)) { found = true; break; } } if (!found) return -EADDRNOTAVAIL; } else { /* If port is in reserved range, ensure caller * has necessary privileges. */ if (addr->svm_port <= LAST_RESERVED_PORT && !capable(CAP_NET_BIND_SERVICE)) { return -EACCES; } if (__vsock_find_bound_socket_net(&new_addr, net)) return -EADDRINUSE; } vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); /* Remove connection oriented sockets from the unbound list and add them * to the hash table for easy lookup by its address. The unbound list * is simply an extra entry at the end of the hash table, a trick used * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); return 0; } static int __vsock_bind_dgram(struct vsock_sock *vsk, struct sockaddr_vm *addr) { return vsk->transport->dgram_bind(vsk, addr); } static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) { struct vsock_sock *vsk = vsock_sk(sk); int retval; /* First ensure this socket isn't already bound. */ if (vsock_addr_bound(&vsk->local_addr)) return -EINVAL; /* Now bind to the provided address or select appropriate values if * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY). Note that * like AF_INET prevents binding to a non-local IP address (in most * cases), we only allow binding to a local CID. */ if (addr->svm_cid != VMADDR_CID_ANY && !vsock_find_cid(addr->svm_cid)) return -EADDRNOTAVAIL; switch (sk->sk_socket->type) { case SOCK_STREAM: case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; case SOCK_DGRAM: retval = __vsock_bind_dgram(vsk, addr); break; default: retval = -EINVAL; break; } return retval; } static void vsock_connect_timeout(struct work_struct *work); static struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, gfp_t priority, unsigned short type, int kern) { struct sock *sk; struct vsock_sock *psk; struct vsock_sock *vsk; sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto, kern); if (!sk) return NULL; sock_init_data(sock, sk); /* sk->sk_type is normally set in sock_init_data, but only if sock is * non-NULL. We make sure that our sockets always have a type by * setting it here if needed. */ if (!sock) sk->sk_type = type; vsk = vsock_sk(sk); vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); sk->sk_destruct = vsock_sk_destruct; sk->sk_backlog_rcv = vsock_queue_rcv_skb; sock_reset_flag(sk, SOCK_DONE); INIT_LIST_HEAD(&vsk->bound_table); INIT_LIST_HEAD(&vsk->connected_table); vsk->listener = NULL; INIT_LIST_HEAD(&vsk->pending_links); INIT_LIST_HEAD(&vsk->accept_queue); vsk->rejected = false; vsk->sent_request = false; vsk->ignore_connecting_rst = false; WRITE_ONCE(vsk->peer_shutdown, 0); INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout); INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work); psk = parent ? vsock_sk(parent) : NULL; if (parent) { vsk->trusted = psk->trusted; vsk->owner = get_cred(psk->owner); vsk->connect_timeout = psk->connect_timeout; vsk->buffer_size = psk->buffer_size; vsk->buffer_min_size = psk->buffer_min_size; vsk->buffer_max_size = psk->buffer_max_size; security_sk_clone(parent, sk); } else { vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE; vsk->buffer_min_size = VSOCK_DEFAULT_BUFFER_MIN_SIZE; vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE; } return sk; } static bool sock_type_connectible(u16 type) { return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); } static void __vsock_release(struct sock *sk, int level) { struct vsock_sock *vsk; struct sock *pending; vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); /* Indicate to vsock_remove_sock() that the socket is being released and * can be removed from the bound_table. Unlike transport reassignment * case, where the socket must remain bound despite vsock_remove_sock() * being called from the transport release() callback. */ sock_set_flag(sk, SOCK_DEAD); if (vsk->transport) vsk->transport->release(vsk); else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; skb_queue_purge(&sk->sk_receive_queue); /* Clean up any sockets that never were accepted. */ while ((pending = vsock_dequeue_accept(sk)) != NULL) { __vsock_release(pending, SINGLE_DEPTH_NESTING); sock_put(pending); } release_sock(sk); sock_put(sk); } static void vsock_sk_destruct(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); /* Flush MSG_ZEROCOPY leftovers. */ __skb_queue_purge(&sk->sk_error_queue); vsock_deassign_transport(vsk); /* When clearing these addresses, there's no need to set the family and * possibly register the address family with the kernel. */ vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); put_cred(vsk->owner); } static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; err = sock_queue_rcv_skb(sk, skb); if (err) kfree_skb(skb); return err; } struct sock *vsock_create_connected(struct sock *parent) { return __vsock_create(sock_net(parent), NULL, parent, GFP_KERNEL, parent->sk_type, 0); } EXPORT_SYMBOL_GPL(vsock_create_connected); s64 vsock_stream_has_data(struct vsock_sock *vsk) { if (WARN_ON(!vsk->transport)) return 0; return vsk->transport->stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_data); s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); if (WARN_ON(!vsk->transport)) return 0; if (sk->sk_type == SOCK_SEQPACKET) return vsk->transport->seqpacket_has_data(vsk); else return vsock_stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_connectible_has_data); s64 vsock_stream_has_space(struct vsock_sock *vsk) { if (WARN_ON(!vsk->transport)) return 0; return vsk->transport->stream_has_space(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_space); void vsock_data_ready(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); if (vsock_stream_has_data(vsk) >= sk->sk_rcvlowat || sock_flag(sk, SOCK_DONE)) sk->sk_data_ready(sk); } EXPORT_SYMBOL_GPL(vsock_data_ready); /* Dummy callback required by sockmap. * See unconditional call of saved_close() in sock_map_close(). */ static void vsock_close(struct sock *sk, long timeout) { } static int vsock_release(struct socket *sock) { struct sock *sk = sock->sk; if (!sk) return 0; sk->sk_prot->close(sk, 0); __vsock_release(sk, 0); sock->sk = NULL; sock->state = SS_FREE; return 0; } static int vsock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { int err; struct sock *sk; struct sockaddr_vm *vm_addr; sk = sock->sk; if (vsock_addr_cast(addr, addr_len, &vm_addr) != 0) return -EINVAL; lock_sock(sk); err = __vsock_bind(sk, vm_addr); release_sock(sk); return err; } static int vsock_getname(struct socket *sock, struct sockaddr *addr, int peer) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *vm_addr; sk = sock->sk; vsk = vsock_sk(sk); err = 0; lock_sock(sk); if (peer) { if (sock->state != SS_CONNECTED) { err = -ENOTCONN; goto out; } vm_addr = &vsk->remote_addr; } else { vm_addr = &vsk->local_addr; } BUILD_BUG_ON(sizeof(*vm_addr) > sizeof(struct sockaddr_storage)); memcpy(addr, vm_addr, sizeof(*vm_addr)); err = sizeof(*vm_addr); out: release_sock(sk); return err; } void vsock_linger(struct sock *sk) { DEFINE_WAIT_FUNC(wait, woken_wake_function); ssize_t (*unsent)(struct vsock_sock *vsk); struct vsock_sock *vsk = vsock_sk(sk); long timeout; if (!sock_flag(sk, SOCK_LINGER)) return; timeout = sk->sk_lingertime; if (!timeout) return; /* Transports must implement `unsent_bytes` if they want to support * SOCK_LINGER through `vsock_linger()` since we use it to check when * the socket can be closed. */ unsent = vsk->transport->unsent_bytes; if (!unsent) return; add_wait_queue(sk_sleep(sk), &wait); do { if (sk_wait_event(sk, &timeout, unsent(vsk) == 0, &wait)) break; } while (!signal_pending(current) && timeout); remove_wait_queue(sk_sleep(sk), &wait); } EXPORT_SYMBOL_GPL(vsock_linger); static int vsock_shutdown(struct socket *sock, int mode) { int err; struct sock *sk; /* User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode * here like the other address families do. Note also that the * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3), * which is what we want. */ mode++; if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; /* If this is a connection oriented socket and it is not connected then * bail out immediately. If it is a DGRAM socket then we must first * kick the socket so that it wakes up from any sleeping calls, for * example recv(), and then afterwards return the error. */ sk = sock->sk; lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; err = 0; } /* Receive and send shutdowns are treated alike. */ mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN); if (mode) { sk->sk_shutdown |= mode; sk->sk_state_change(sk); if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } } out: release_sock(sk); return err; } static __poll_t vsock_poll_shutdown(struct sock *sk, u32 peer_shutdown) { __poll_t mask = 0; /* INET sockets treat local write shutdown and peer write shutdown as a * case of EPOLLHUP set. */ if (sk->sk_shutdown == SHUTDOWN_MASK || ((sk->sk_shutdown & SEND_SHUTDOWN) && (peer_shutdown & SEND_SHUTDOWN))) mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN || peer_shutdown & SEND_SHUTDOWN) mask |= EPOLLRDHUP; return mask; } static __poll_t vsock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk; __poll_t mask; struct vsock_sock *vsk; sk = sock->sk; vsk = vsock_sk(sk); poll_wait(file, sk_sleep(sk), wait); mask = 0; if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) /* Signify that there has been an error on this socket. */ mask |= EPOLLERR; if (sk_is_readable(sk)) mask |= EPOLLIN | EPOLLRDNORM; if (sock->type == SOCK_DGRAM) { u32 peer_shutdown = READ_ONCE(vsk->peer_shutdown); /* DGRAM sockets do not take lock_sock() in poll(), so use one * lockless snapshot for all shutdown-derived mask bits. */ mask |= vsock_poll_shutdown(sk, peer_shutdown); /* For datagram sockets we can read if there is something in * the queue and write as long as the socket isn't shutdown for * sending. */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { mask |= EPOLLIN | EPOLLRDNORM; } if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; u32 peer_shutdown; lock_sock(sk); transport = vsk->transport; /* Listening sockets that have connections in their accept * queue can be read. */ if (sk->sk_state == TCP_LISTEN && !vsock_is_accept_queue_empty(sk)) mask |= EPOLLIN | EPOLLRDNORM; /* If there is something in the queue then we can read. */ if (transport && transport->stream_is_active(vsk) && !(sk->sk_shutdown & RCV_SHUTDOWN)) { bool data_ready_now = false; int target = sock_rcvlowat(sk, 0, INT_MAX); int ret = transport->notify_poll_in( vsk, target, &data_ready_now); if (ret < 0) { mask |= EPOLLERR; } else { if (data_ready_now) mask |= EPOLLIN | EPOLLRDNORM; } } /* Sockets whose connections have been closed, reset, or * terminated should also be considered read, and we check the * shutdown flag for that. */ peer_shutdown = READ_ONCE(vsk->peer_shutdown); mask |= vsock_poll_shutdown(sk, peer_shutdown); if (sk->sk_shutdown & RCV_SHUTDOWN || peer_shutdown & SEND_SHUTDOWN) { mask |= EPOLLIN | EPOLLRDNORM; } /* Connected sockets that can produce data can be written. */ if (transport && sk->sk_state == TCP_ESTABLISHED) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { bool space_avail_now = false; int ret = transport->notify_poll_out( vsk, 1, &space_avail_now); if (ret < 0) { mask |= EPOLLERR; } else { if (space_avail_now) /* Remove EPOLLWRBAND since INET * sockets are not setting it. */ mask |= EPOLLOUT | EPOLLWRNORM; } } } /* Simulate INET socket poll behaviors, which sets * EPOLLOUT|EPOLLWRNORM when peer is closed and nothing to read, * but local send is not shutdown. */ if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM; } release_sock(sk); } return mask; } static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor) { struct vsock_sock *vsk = vsock_sk(sk); if (WARN_ON_ONCE(!vsk->transport)) return -ENODEV; return vsk->transport->read_skb(vsk, read_actor); } static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; const struct vsock_transport *transport; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* For now, MSG_DONTWAIT is always assumed... */ err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); transport = vsk->transport; err = vsock_auto_bind(vsk); if (err) goto out; /* If the provided message contains an address, use that. Otherwise * fall back on the socket's remote handle (if it has been connected). */ if (msg->msg_name && vsock_addr_cast(msg->msg_name, msg->msg_namelen, &remote_addr) == 0) { /* Ensure this address is of the right type and is a valid * destination. */ if (remote_addr->svm_cid == VMADDR_CID_ANY) remote_addr->svm_cid = transport->get_local_cid(); if (!vsock_addr_bound(remote_addr)) { err = -EINVAL; goto out; } } else if (sock->state == SS_CONNECTED) { remote_addr = &vsk->remote_addr; if (remote_addr->svm_cid == VMADDR_CID_ANY) remote_addr->svm_cid = transport->get_local_cid(); /* XXX Should connect() or this function ensure remote_addr is * bound? */ if (!vsock_addr_bound(&vsk->remote_addr)) { err = -EINVAL; goto out; } } else { err = -EINVAL; goto out; } if (!transport->dgram_allow(vsk, remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; } err = transport->dgram_enqueue(vsk, remote_addr, msg, len); out: release_sock(sk); return err; } static int vsock_dgram_connect(struct socket *sock, struct sockaddr_unsized *addr, int addr_len, int flags) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; sk = sock->sk; vsk = vsock_sk(sk); err = vsock_addr_cast(addr, addr_len, &remote_addr); if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) { lock_sock(sk); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); sock->state = SS_UNCONNECTED; release_sock(sk); return 0; } else if (err != 0) return -EINVAL; lock_sock(sk); err = vsock_auto_bind(vsk); if (err) goto out; if (!vsk->transport->dgram_allow(vsk, remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; } memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); sock->state = SS_CONNECTED; /* sock map disallows redirection of non-TCP sockets with sk_state != * TCP_ESTABLISHED (see sock_map_redirect_allowed()), so we set * TCP_ESTABLISHED here to allow redirection of connected vsock dgrams. * * This doesn't seem to be abnormal state for datagram sockets, as the * same approach can be see in other datagram socket types as well * (such as unix sockets). */ sk->sk_state = TCP_ESTABLISHED; out: release_sock(sk); return err; } int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct vsock_sock *vsk = vsock_sk(sk); return vsk->transport->dgram_dequeue(vsk, msg, len, flags); } int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL struct sock *sk = sock->sk; const struct proto *prot; prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags); #endif return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); static int vsock_do_ioctl(struct socket *sock, unsigned int cmd, int __user *arg) { struct sock *sk = sock->sk; struct vsock_sock *vsk; int ret; vsk = vsock_sk(sk); switch (cmd) { case SIOCINQ: { ssize_t n_bytes; if (!vsk->transport) { ret = -EOPNOTSUPP; break; } if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) { ret = -EINVAL; break; } n_bytes = vsock_stream_has_data(vsk); if (n_bytes < 0) { ret = n_bytes; break; } ret = put_user(n_bytes, arg); break; } case SIOCOUTQ: { ssize_t n_bytes; if (!vsk->transport || !vsk->transport->unsent_bytes) { ret = -EOPNOTSUPP; break; } if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) { ret = -EINVAL; break; } n_bytes = vsk->transport->unsent_bytes(vsk); if (n_bytes < 0) { ret = n_bytes; break; } ret = put_user(n_bytes, arg); break; } default: ret = -ENOIOCTLCMD; } return ret; } static int vsock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int ret; lock_sock(sock->sk); ret = vsock_do_ioctl(sock, cmd, (int __user *)arg); release_sock(sock->sk); return ret; } static const struct proto_ops vsock_dgram_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = vsock_ioctl, .listen = sock_no_listen, .shutdown = vsock_shutdown, .sendmsg = vsock_dgram_sendmsg, .recvmsg = vsock_dgram_recvmsg, .mmap = sock_no_mmap, .read_skb = vsock_read_skb, }; static int vsock_transport_cancel_pkt(struct vsock_sock *vsk) { const struct vsock_transport *transport = vsk->transport; if (!transport || !transport->cancel_pkt) return -EOPNOTSUPP; return transport->cancel_pkt(vsk); } static void vsock_connect_timeout(struct work_struct *work) { struct sock *sk; struct vsock_sock *vsk; vsk = container_of(work, struct vsock_sock, connect_work.work); sk = sk_vsock(vsk); lock_sock(sk); if (sk->sk_state == TCP_SYN_SENT && (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_socket->state = SS_UNCONNECTED; sk->sk_err = ETIMEDOUT; sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); sock_put(sk); } static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr, int addr_len, int flags) { int err; struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; struct sockaddr_vm *remote_addr; long timeout; DEFINE_WAIT(wait); err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); /* XXX AF_UNSPEC should make us disconnect like AF_INET. */ switch (sock->state) { case SS_CONNECTED: err = -EISCONN; goto out; case SS_DISCONNECTING: err = -EINVAL; goto out; case SS_CONNECTING: /* This continues on so we can move sock into the SS_CONNECTED * state once the connection has completed (at which point err * will be set to zero also). Otherwise, we will either wait * for the connection or return -EALREADY should this be a * non-blocking call. */ err = -EALREADY; if (flags & O_NONBLOCK) goto out; break; default: if ((sk->sk_state == TCP_LISTEN) || vsock_addr_cast(addr, addr_len, &remote_addr) != 0) { err = -EINVAL; goto out; } /* Set the remote address that we are connecting to. */ memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); err = vsock_assign_transport(vsk, NULL); if (err) goto out; transport = vsk->transport; /* The hypervisor and well-known contexts do not have socket * endpoints. */ if (!transport || !transport->stream_allow(vsk, remote_addr->svm_cid, remote_addr->svm_port)) { err = -ENETUNREACH; goto out; } if (vsock_msgzerocopy_allow(transport)) { set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); } else if (sock_flag(sk, SOCK_ZEROCOPY)) { /* If this option was set before 'connect()', * when transport was unknown, check that this * feature is supported here. */ err = -EOPNOTSUPP; goto out; } err = vsock_auto_bind(vsk); if (err) goto out; sk->sk_state = TCP_SYN_SENT; err = transport->connect(vsk); if (err < 0) goto out; /* sk_err might have been set as a result of an earlier * (failed) connect attempt. */ sk->sk_err = 0; /* Mark sock as connecting and set the error code to in * progress in case this is a non-blocking connect. */ sock->state = SS_CONNECTING; err = -EINPROGRESS; } /* The receive path will handle all communication until we are able to * enter the connected state. Here we wait for the connection to be * completed or a notification of an error. */ timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* If the socket is already closing or it is in an error state, there * is no point in waiting. */ while (sk->sk_state != TCP_ESTABLISHED && sk->sk_state != TCP_CLOSING && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection * attempt, in case the peer doesn't respond in a * timely manner. We hold on to the socket until the * timeout fires. */ sock_hold(sk); /* If the timeout function is already scheduled, * reschedule it, then ungrab the socket refcount to * keep it balanced. */ if (mod_delayed_work(system_percpu_wq, &vsk->connect_work, timeout)) sock_put(sk); /* Skip ahead to preserve error code set above. */ goto out_wait; } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); /* Connection established. Whatever happens to socket once we * release it, that's not connect()'s concern. No need to go * into signal and timeout handling. Call it a day. * * Note that allowing to "reset" an already established socket * here is racy and insecure. */ if (sk->sk_state == TCP_ESTABLISHED) break; /* If connection was _not_ established and a signal/timeout came * to be, we want the socket's state reset. User space may want * to retry. * * sk_state != TCP_ESTABLISHED implies that socket is not on * vsock_connected_table. We keep the binding and the transport * assigned. */ if (signal_pending(current) || timeout == 0) { err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout); /* Listener might have already responded with * VIRTIO_VSOCK_OP_RESPONSE. Its handling expects our * sk_state == TCP_SYN_SENT, which hereby we break. * In such case VIRTIO_VSOCK_OP_RST will follow. */ sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; /* Try to cancel VIRTIO_VSOCK_OP_REQUEST skb sent out by * transport->connect(). */ vsock_transport_cancel_pkt(vsk); goto out_wait; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } if (sk->sk_err) { err = -sk->sk_err; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; } else { err = 0; } out_wait: finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; } static int vsock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *listener; int err; struct sock *connected; struct vsock_sock *vconnected; long timeout; DEFINE_WAIT(wait); err = 0; listener = sock->sk; lock_sock(listener); if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } if (listener->sk_state != TCP_LISTEN) { err = -EINVAL; goto out; } /* Wait for children sockets to appear; these are the new sockets * created upon connection establishment. */ timeout = sock_rcvtimeo(listener, arg->flags & O_NONBLOCK); while ((connected = vsock_dequeue_accept(listener)) == NULL && listener->sk_err == 0 && timeout != 0) { prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); release_sock(listener); timeout = schedule_timeout(timeout); finish_wait(sk_sleep(listener), &wait); lock_sock(listener); if (signal_pending(current)) { err = sock_intr_errno(timeout); goto out; } } if (listener->sk_err) { err = -listener->sk_err; } else if (!connected) { err = -EAGAIN; } if (connected) { sk_acceptq_removed(listener); lock_sock_nested(connected, SINGLE_DEPTH_NESTING); vconnected = vsock_sk(connected); /* If the listener socket has received an error, then we should * reject this socket and return. Note that we simply mark the * socket rejected, drop our reference, and let the cleanup * function handle the cleanup; the fact that we found it in * the listener's accept queue guarantees that the cleanup * function hasn't run yet. */ if (err) { vconnected->rejected = true; } else { newsock->state = SS_CONNECTED; sock_graft(connected, newsock); set_bit(SOCK_CUSTOM_SOCKOPT, &connected->sk_socket->flags); if (vsock_msgzerocopy_allow(vconnected->transport)) set_bit(SOCK_SUPPORT_ZC, &connected->sk_socket->flags); } release_sock(connected); sock_put(connected); } out: release_sock(listener); return err; } static int vsock_listen(struct socket *sock, int backlog) { int err; struct sock *sk; struct vsock_sock *vsk; sk = sock->sk; lock_sock(sk); if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } if (sock->state != SS_UNCONNECTED) { err = -EINVAL; goto out; } vsk = vsock_sk(sk); if (!vsock_addr_bound(&vsk->local_addr)) { err = -EINVAL; goto out; } sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; err = 0; out: release_sock(sk); return err; } static void vsock_update_buffer_size(struct vsock_sock *vsk, const struct vsock_transport *transport, u64 val) { if (val < vsk->buffer_min_size) val = vsk->buffer_min_size; if (val > vsk->buffer_max_size) val = vsk->buffer_max_size; if (val != vsk->buffer_size && transport && transport->notify_buffer_size) transport->notify_buffer_size(vsk, &val); vsk->buffer_size = val; } static int vsock_connectible_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { int err; struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; u64 val; if (level != AF_VSOCK && level != SOL_SOCKET) return -ENOPROTOOPT; #define COPY_IN(_v) \ do { \ if (optlen < sizeof(_v)) { \ err = -EINVAL; \ goto exit; \ } \ if (copy_from_sockptr(&_v, optval, sizeof(_v)) != 0) { \ err = -EFAULT; \ goto exit; \ } \ } while (0) err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); transport = vsk->transport; if (level == SOL_SOCKET) { int zerocopy; if (optname != SO_ZEROCOPY) { release_sock(sk); return sock_setsockopt(sock, level, optname, optval, optlen); } /* Use 'int' type here, because variable to * set this option usually has this type. */ COPY_IN(zerocopy); if (zerocopy < 0 || zerocopy > 1) { err = -EINVAL; goto exit; } if (transport && !vsock_msgzerocopy_allow(transport)) { err = -EOPNOTSUPP; goto exit; } sock_valbool_flag(sk, SOCK_ZEROCOPY, zerocopy); goto exit; } switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: COPY_IN(val); vsock_update_buffer_size(vsk, transport, val); break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: COPY_IN(val); vsk->buffer_max_size = val; vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: COPY_IN(val); vsk->buffer_min_size = val; vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { struct __kernel_sock_timeval tv; err = sock_copy_user_timeval(&tv, optval, optlen, optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); if (err) break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; } else { err = -ERANGE; } break; } default: err = -ENOPROTOOPT; break; } #undef COPY_IN exit: release_sock(sk); return err; } static int vsock_connectible_getsockopt(struct socket *sock, int level, int optname, sockopt_t *opt) { struct sock *sk = sock->sk; struct vsock_sock *vsk = vsock_sk(sk); union { u64 val64; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; } v; int lv = sizeof(v.val64); int len; if (level != AF_VSOCK) return -ENOPROTOOPT; len = opt->optlen; memset(&v, 0, sizeof(v)); switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: v.val64 = vsk->buffer_size; break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: v.val64 = vsk->buffer_max_size; break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: v.val64 = vsk->buffer_min_size; break; case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: lv = sock_get_timeout(vsk->connect_timeout, &v, optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; default: return -ENOPROTOOPT; } if (len < lv) return -EINVAL; if (len > lv) len = lv; if (copy_to_iter(&v, len, &opt->iter_out) != len) return -EFAULT; opt->optlen = len; return 0; } static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; ssize_t total_written; long timeout; int err; struct vsock_transport_send_notify_data send_data; DEFINE_WAIT_FUNC(wait, woken_wake_function); sk = sock->sk; vsk = vsock_sk(sk); total_written = 0; err = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; lock_sock(sk); transport = vsk->transport; /* Callers should not provide a destination with connection oriented * sockets. */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; } /* Send data only if both sides are not shutdown in the direction. */ if (sk->sk_shutdown & SEND_SHUTDOWN || vsk->peer_shutdown & RCV_SHUTDOWN) { err = -EPIPE; goto out; } if (!transport || sk->sk_state != TCP_ESTABLISHED || !vsock_addr_bound(&vsk->local_addr)) { err = -ENOTCONN; goto out; } if (!vsock_addr_bound(&vsk->remote_addr)) { err = -EDESTADDRREQ; goto out; } if (msg->msg_flags & MSG_ZEROCOPY && !vsock_msgzerocopy_allow(transport)) { err = -EOPNOTSUPP; goto out; } /* Wait for room in the produce queue to enqueue our user's data. */ timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = transport->notify_send_init(vsk, &send_data); if (err < 0) goto out; while (total_written < len) { ssize_t written; add_wait_queue(sk_sleep(sk), &wait); while (vsock_stream_has_space(vsk) == 0 && sk->sk_err == 0 && !(sk->sk_shutdown & SEND_SHUTDOWN) && !(vsk->peer_shutdown & RCV_SHUTDOWN)) { /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } err = transport->notify_send_pre_block(vsk, &send_data); if (err < 0) { remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } release_sock(sk); timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } else if (timeout == 0) { err = -EAGAIN; remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } } remove_wait_queue(sk_sleep(sk), &wait); /* These checks occur both as part of and after the loop * conditional since we need to check before and after * sleeping. */ if (sk->sk_err) { err = -sk->sk_err; goto out_err; } else if ((sk->sk_shutdown & SEND_SHUTDOWN) || (vsk->peer_shutdown & RCV_SHUTDOWN)) { err = -EPIPE; goto out_err; } err = transport->notify_send_pre_enqueue(vsk, &send_data); if (err < 0) goto out_err; /* Note that enqueue will only write as many bytes as are free * in the produce queue, so we don't need to ensure len is * smaller than the queue size. It is the caller's * responsibility to check how many bytes we were able to send. */ if (sk->sk_type == SOCK_SEQPACKET) { written = transport->seqpacket_enqueue(vsk, msg, len - total_written); } else { written = transport->stream_enqueue(vsk, msg, len - total_written); } if (written < 0) { err = written; goto out_err; } total_written += written; err = transport->notify_send_post_enqueue( vsk, written, &send_data); if (err < 0) goto out_err; } out_err: if (total_written > 0) { /* Return number of written bytes only if: * 1) SOCK_STREAM socket. * 2) SOCK_SEQPACKET socket when whole buffer is sent. */ if (sk->sk_type == SOCK_STREAM || total_written == len) err = total_written; } out: if (sk->sk_type == SOCK_STREAM) err = sk_stream_error(sk, msg->msg_flags, err); release_sock(sk); return err; } static int vsock_connectible_wait_data(struct sock *sk, struct wait_queue_entry *wait, long timeout, struct vsock_transport_recv_notify_data *recv_data, size_t target) { const struct vsock_transport *transport; struct vsock_sock *vsk; s64 data; int err; vsk = vsock_sk(sk); err = 0; transport = vsk->transport; while (1) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); data = vsock_connectible_has_data(vsk); if (data != 0) break; if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) || (vsk->peer_shutdown & SEND_SHUTDOWN)) { break; } /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; break; } if (recv_data) { err = transport->notify_recv_pre_block(vsk, target, recv_data); if (err < 0) break; } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); break; } else if (timeout == 0) { err = -EAGAIN; break; } } finish_wait(sk_sleep(sk), wait); if (err) return err; /* Internal transport error when checking for available * data. XXX This should be changed to a connection * reset in a later change. */ if (data < 0) return -ENOMEM; return data; } static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct vsock_transport_recv_notify_data recv_data; const struct vsock_transport *transport; struct vsock_sock *vsk; ssize_t copied; size_t target; long timeout; int err; DEFINE_WAIT(wait); vsk = vsock_sk(sk); transport = vsk->transport; /* We must not copy less than target bytes into the user's buffer * before returning successfully, so we wait for the consume queue to * have that much data to consume before dequeueing. Note that this * makes it impossible to handle cases where target is greater than the * queue size. */ target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); if (target >= transport->stream_rcvhiwat(vsk)) { err = -ENOMEM; goto out; } timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); copied = 0; err = transport->notify_recv_init(vsk, target, &recv_data); if (err < 0) goto out; while (1) { ssize_t read; err = vsock_connectible_wait_data(sk, &wait, timeout, &recv_data, target); if (err <= 0) break; err = transport->notify_recv_pre_dequeue(vsk, target, &recv_data); if (err < 0) break; read = transport->stream_dequeue(vsk, msg, len - copied, flags); if (read < 0) { err = read; break; } copied += read; err = transport->notify_recv_post_dequeue(vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) goto out; if (read >= target || flags & MSG_PEEK) break; target -= read; } if (sk->sk_err) err = -sk->sk_err; else if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; if (copied > 0) err = copied; out: return err; } static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { const struct vsock_transport *transport; struct vsock_sock *vsk; ssize_t msg_len; long timeout; int err = 0; DEFINE_WAIT(wait); vsk = vsock_sk(sk); transport = vsk->transport; timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); if (err <= 0) goto out; msg_len = transport->seqpacket_dequeue(vsk, msg, flags); if (msg_len < 0) { err = msg_len; goto out; } if (sk->sk_err) { err = -sk->sk_err; } else if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; } else { /* User sets MSG_TRUNC, so return real length of * packet. */ if (flags & MSG_TRUNC) err = msg_len; else err = len - msg_data_left(msg); /* Always set MSG_TRUNC if real length of packet is * bigger than user's buffer. */ if (msg_len > len) msg->msg_flags |= MSG_TRUNC; } out: return err; } int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; int err; sk = sock->sk; if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_VSOCK, VSOCK_RECVERR); vsk = vsock_sk(sk); err = 0; lock_sock(sk); transport = vsk->transport; if (!transport || sk->sk_state != TCP_ESTABLISHED) { /* Recvmsg is supposed to return 0 if a peer performs an * orderly shutdown. Differentiate between that case and when a * peer has not connected or a local shutdown occurred with the * SOCK_DONE flag. */ if (sock_flag(sk, SOCK_DONE)) err = 0; else err = -ENOTCONN; goto out; } if (flags & MSG_OOB) { err = -EOPNOTSUPP; goto out; } /* We don't check peer_shutdown flag here since peer may actually shut * down, but there can be data in the queue that a local socket can * receive. */ if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; goto out; } /* It is valid on Linux to pass in a zero-length receive buffer. This * is not an error. We may as well bail out now. */ if (!len) { err = 0; goto out; } if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); return err; } int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL struct sock *sk = sock->sk; const struct proto *prot; prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags); #endif return __vsock_connectible_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) { const struct vsock_transport *transport; struct vsock_sock *vsk; vsk = vsock_sk(sk); if (val > vsk->buffer_size) return -EINVAL; transport = vsk->transport; if (transport && transport->notify_set_rcvlowat) { int err; err = transport->notify_set_rcvlowat(vsk, val); if (err) return err; } WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); return 0; } static const struct proto_ops vsock_stream_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, .getsockopt_iter = vsock_connectible_getsockopt, .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .set_rcvlowat = vsock_set_rcvlowat, .read_skb = vsock_read_skb, }; static const struct proto_ops vsock_seqpacket_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, .getsockopt_iter = vsock_connectible_getsockopt, .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .read_skb = vsock_read_skb, }; static int vsock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct vsock_sock *vsk; struct sock *sk; int ret; if (!sock) return -EINVAL; if (protocol && protocol != PF_VSOCK) return -EPROTONOSUPPORT; switch (sock->type) { case SOCK_DGRAM: sock->ops = &vsock_dgram_ops; break; case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; case SOCK_SEQPACKET: sock->ops = &vsock_seqpacket_ops; break; default: return -ESOCKTNOSUPPORT; } sock->state = SS_UNCONNECTED; sk = __vsock_create(net, sock, NULL, GFP_KERNEL, 0, kern); if (!sk) return -ENOMEM; vsk = vsock_sk(sk); if (sock->type == SOCK_DGRAM) { ret = vsock_assign_transport(vsk, NULL); if (ret < 0) { sock->sk = NULL; sock_put(sk); return ret; } } /* SOCK_DGRAM doesn't have 'setsockopt' callback set in its * proto_ops, so there is no handler for custom logic. */ if (sock_type_connectible(sock->type)) set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); vsock_insert_unbound(vsk); return 0; } static const struct net_proto_family vsock_family_ops = { .family = AF_VSOCK, .create = vsock_create, .owner = THIS_MODULE, }; static long vsock_dev_do_ioctl(struct file *filp, unsigned int cmd, void __user *ptr) { u32 __user *p = ptr; int retval = 0; u32 cid; switch (cmd) { case IOCTL_VM_SOCKETS_GET_LOCAL_CID: /* To be compatible with the VMCI behavior, we prioritize the * guest CID instead of well-know host CID (VMADDR_CID_HOST). */ cid = vsock_registered_transport_cid(&transport_g2h); if (cid == VMADDR_CID_ANY) cid = vsock_registered_transport_cid(&transport_h2g); if (cid == VMADDR_CID_ANY) cid = vsock_registered_transport_cid(&transport_local); if (put_user(cid, p) != 0) retval = -EFAULT; break; default: retval = -ENOIOCTLCMD; } return retval; } static long vsock_dev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return vsock_dev_do_ioctl(filp, cmd, (void __user *)arg); } #ifdef CONFIG_COMPAT static long vsock_dev_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return vsock_dev_do_ioctl(filp, cmd, compat_ptr(arg)); } #endif static const struct file_operations vsock_device_ops = { .owner = THIS_MODULE, .unlocked_ioctl = vsock_dev_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = vsock_dev_compat_ioctl, #endif .open = nonseekable_open, }; static struct miscdevice vsock_device = { .name = "vsock", .fops = &vsock_device_ops, }; static int __vsock_net_mode_string(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos, enum vsock_net_mode mode, enum vsock_net_mode *new_mode) { char data[VSOCK_NET_MODE_STR_MAX] = {0}; struct ctl_table tmp; int ret; if (!table->data || !table->maxlen || !*lenp) { *lenp = 0; return 0; } tmp = *table; tmp.data = data; if (!write) { const char *p; switch (mode) { case VSOCK_NET_MODE_GLOBAL: p = VSOCK_NET_MODE_STR_GLOBAL; break; case VSOCK_NET_MODE_LOCAL: p = VSOCK_NET_MODE_STR_LOCAL; break; default: WARN_ONCE(true, "netns has invalid vsock mode"); *lenp = 0; return 0; } strscpy(data, p, sizeof(data)); tmp.maxlen = strlen(p); } ret = proc_dostring(&tmp, write, buffer, lenp, ppos); if (ret || !write) return ret; if (*lenp >= sizeof(data)) return -EINVAL; if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data))) *new_mode = VSOCK_NET_MODE_GLOBAL; else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data))) *new_mode = VSOCK_NET_MODE_LOCAL; else return -EINVAL; return 0; } static int vsock_net_mode_string(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; if (write) return -EPERM; net = container_of(table->data, struct net, vsock.mode); return __vsock_net_mode_string(table, write, buffer, lenp, ppos, vsock_net_mode(net), NULL); } static int vsock_net_child_mode_string(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { enum vsock_net_mode new_mode; struct net *net; int ret; net = container_of(table->data, struct net, vsock.child_ns_mode); ret = __vsock_net_mode_string(table, write, buffer, lenp, ppos, vsock_net_child_mode(net), &new_mode); if (ret) return ret; if (write) { /* Prevent a "local" namespace from escalating to "global", * which would give nested namespaces access to global CIDs. */ if (vsock_net_mode(net) == VSOCK_NET_MODE_LOCAL && new_mode == VSOCK_NET_MODE_GLOBAL) return -EPERM; if (!vsock_net_set_child_mode(net, new_mode)) return -EBUSY; } return 0; } static struct ctl_table vsock_table[] = { { .procname = "ns_mode", .data = &init_net.vsock.mode, .maxlen = VSOCK_NET_MODE_STR_MAX, .mode = 0444, .proc_handler = vsock_net_mode_string }, { .procname = "child_ns_mode", .data = &init_net.vsock.child_ns_mode, .maxlen = VSOCK_NET_MODE_STR_MAX, .mode = 0644, .proc_handler = vsock_net_child_mode_string }, { .procname = "g2h_fallback", .data = &init_net.vsock.g2h_fallback, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static int __net_init vsock_sysctl_register(struct net *net) { struct ctl_table *table; if (net_eq(net, &init_net)) { table = vsock_table; } else { table = kmemdup(vsock_table, sizeof(vsock_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->vsock.mode; table[1].data = &net->vsock.child_ns_mode; table[2].data = &net->vsock.g2h_fallback; } net->vsock.sysctl_hdr = register_net_sysctl_sz(net, "net/vsock", table, ARRAY_SIZE(vsock_table)); if (!net->vsock.sysctl_hdr) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void vsock_sysctl_unregister(struct net *net) { const struct ctl_table *table; table = net->vsock.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->vsock.sysctl_hdr); if (!net_eq(net, &init_net)) kfree(table); } static void vsock_net_init(struct net *net) { if (net_eq(net, &init_net)) net->vsock.mode = VSOCK_NET_MODE_GLOBAL; else net->vsock.mode = vsock_net_child_mode(current->nsproxy->net_ns); net->vsock.child_ns_mode = net->vsock.mode; net->vsock.child_ns_mode_locked = 0; net->vsock.g2h_fallback = 1; } static __net_init int vsock_sysctl_init_net(struct net *net) { vsock_net_init(net); if (vsock_sysctl_register(net)) return -ENOMEM; return 0; } static __net_exit void vsock_sysctl_exit_net(struct net *net) { vsock_sysctl_unregister(net); } static struct pernet_operations vsock_sysctl_ops = { .init = vsock_sysctl_init_net, .exit = vsock_sysctl_exit_net, }; static int __init vsock_init(void) { int err = 0; vsock_init_tables(); vsock_proto.owner = THIS_MODULE; vsock_device.minor = MISC_DYNAMIC_MINOR; err = misc_register(&vsock_device); if (err) { pr_err("Failed to register misc device\n"); goto err_reset_transport; } err = proto_register(&vsock_proto, 1); /* we want our slab */ if (err) { pr_err("Cannot register vsock protocol\n"); goto err_deregister_misc; } err = sock_register(&vsock_family_ops); if (err) { pr_err("could not register af_vsock (%d) address family: %d\n", AF_VSOCK, err); goto err_unregister_proto; } if (register_pernet_subsys(&vsock_sysctl_ops)) { err = -ENOMEM; goto err_unregister_sock; } vsock_bpf_build_proto(); return 0; err_unregister_sock: sock_unregister(AF_VSOCK); err_unregister_proto: proto_unregister(&vsock_proto); err_deregister_misc: misc_deregister(&vsock_device); err_reset_transport: return err; } static void __exit vsock_exit(void) { misc_deregister(&vsock_device); sock_unregister(AF_VSOCK); proto_unregister(&vsock_proto); unregister_pernet_subsys(&vsock_sysctl_ops); } const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk) { return vsk->transport; } EXPORT_SYMBOL_GPL(vsock_core_get_transport); int vsock_core_register(const struct vsock_transport *t, int features) { const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local; int err = mutex_lock_interruptible(&vsock_register_mutex); if (err) return err; t_h2g = transport_h2g; t_g2h = transport_g2h; t_dgram = transport_dgram; t_local = transport_local; if (features & VSOCK_TRANSPORT_F_H2G) { if (t_h2g) { err = -EBUSY; goto err_busy; } t_h2g = t; } if (features & VSOCK_TRANSPORT_F_G2H) { if (t_g2h) { err = -EBUSY; goto err_busy; } t_g2h = t; } if (features & VSOCK_TRANSPORT_F_DGRAM) { if (t_dgram) { err = -EBUSY; goto err_busy; } t_dgram = t; } if (features & VSOCK_TRANSPORT_F_LOCAL) { if (t_local) { err = -EBUSY; goto err_busy; } t_local = t; } transport_h2g = t_h2g; transport_g2h = t_g2h; transport_dgram = t_dgram; transport_local = t_local; err_busy: mutex_unlock(&vsock_register_mutex); return err; } EXPORT_SYMBOL_GPL(vsock_core_register); void vsock_core_unregister(const struct vsock_transport *t) { mutex_lock(&vsock_register_mutex); if (transport_h2g == t) transport_h2g = NULL; if (transport_g2h == t) transport_g2h = NULL; if (transport_dgram == t) transport_dgram = NULL; if (transport_local == t) transport_local = NULL; mutex_unlock(&vsock_register_mutex); } EXPORT_SYMBOL_GPL(vsock_core_unregister); module_init(vsock_init); module_exit(vsock_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); MODULE_VERSION("1.0.2.0-k"); MODULE_LICENSE("GPL v2"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Socket buffer accounting * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" #define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. */ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } /* * Note the re-emergence of a socket buffer from a queue or buffer. */ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { if (skb) { int n = atomic_read(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } } /* * Note the addition of a ref on a socket buffer. */ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); skb_get(skb); } /* * Note the destruction of a socket buffer. */ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { if (skb) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); consume_skb(skb); } } /* * Clear a queue of socket buffers. */ void rxrpc_purge_queue(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, rxrpc_skb_put_purge); consume_skb(skb); } } |
| 4500 426 50 426 2417 344 4500 59 160 155 2696 4723 4719 4498 2696 40 39 159 166 4494 2293 1 2296 4509 344 4506 4505 166 4496 2723 176 212 2698 2697 107 4505 4502 341 344 166 166 2720 176 3 133 8956 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/leafops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(const struct folio *folio) { return !folio_test_swapbacked(folio); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(const struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN static inline bool lru_gen_switching(void) { DECLARE_STATIC_KEY_FALSE(lru_switch); return static_branch_unlikely(&lru_switch); } #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment on MAX_NR_TIERS */ return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(const struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags.f); if (!(flags & BIT(PG_referenced))) return 0; /* * Return the total number of accesses including PG_referenced. Also see * the comment on LRU_REFS_FLAGS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(const struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags.f); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(const struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec, const struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); const struct lru_gen_folio *lrugen = &lruvec->lrugen; /* * +-----------------------------------+-----------------------------------+ * | Accessed through page tables and | Accessed through file descriptors | * | promoted by folio_update_gen() | and protected by folio_inc_gen() | * +-----------------------------------+-----------------------------------+ * | PG_active (set while isolated) | | * +-----------------+-----------------+-----------------+-----------------+ * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | * +-----------------------------------+-----------------------------------+ * |<---------- MIN_NR_GENS ---------->| | * |<---------------------------- MAX_NR_GENS ---------------------------->| */ if (folio_test_active(folio)) gen = MIN_NR_GENS - folio_test_workingset(folio); else if (reclaiming) gen = MAX_NR_GENS; else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) gen = MIN_NR_GENS; else gen = MAX_NR_GENS - (folio_test_workingset(folio) || folio_test_referenced(folio)); return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ set_mask_bits(&folio->flags.f, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags.f, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, const struct folio *old) { unsigned long refs = READ_ONCE(old->flags.f) & LRU_REFS_MASK; set_mask_bits(&new->flags.f, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_switching(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, const struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ void pfnmap_track_ctx_release(struct kref *ref); static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(const struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(const struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( softleaf_t entry, struct vm_area_struct *dst_vma) { const pte_marker srcm = softleaf_to_marker(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * Returns true if an uffd-wp pte was installed, false otherwise. */ static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { bool arm_uffd_pte = false; if (!uffd_supports_wp_marker()) return false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); return true; } return false; } static inline bool vma_has_recency(const struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif /** * num_pages_contiguous() - determine the number of contiguous pages * that represent contiguous PFNs * @pages: an array of page pointers * @nr_pages: length of the array, at least 1 * * Determine the number of contiguous pages that represent contiguous PFNs * in @pages, starting from the first page. * * In some kernel configs contiguous PFNs will not have contiguous struct * pages. In these configurations num_pages_contiguous() will return a num * smaller than ideal number. The caller should continue to check for pfn * contiguity after each call to num_pages_contiguous(). * * Returns the number of contiguous pages. */ static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages) { struct page *cur_page = pages[0]; unsigned long section = memdesc_section(cur_page->flags); size_t i; for (i = 1; i < nr_pages; i++) { if (++cur_page != pages[i]) break; /* * In unproblematic kernel configs, page_to_section() == 0 and * the whole check will get optimized out. */ if (memdesc_section(cur_page->flags) != section) break; } return i; } #endif |
| 16905 17193 5564 2629 2624 1011 18753 4 5866 1050 1214 959 1050 106 106 4 18 54 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_FIND_H_ #define __LINUX_FIND_H_ #ifndef __LINUX_BITMAP_H #error only <linux/bitmap.h> can be included directly #endif #include <linux/bitops.h> unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, unsigned long start); unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); #endif unsigned long find_random_bit(const unsigned long *addr, unsigned long size); #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr, size, offset); } #endif #ifndef find_next_and_bit /** * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & *addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_and_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_andnot_bit /** * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits * in *addr2 * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_or_bit /** * find_next_or_bit - find the next set bit in either memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = (*addr1 | *addr2) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_or_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit(addr, size, offset); } #endif #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_bit(addr, size); } #endif /** * find_nth_bit - find N'th set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * The following is semantically equivalent: * idx = find_nth_bit(addr, size, 0); * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_bit(addr, size, n); } /** * find_nth_and_bit - find N'th set bit in 2 memory regions * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_bit(addr1, addr2, size, n); } /** * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, * excluding those set in 3rd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @addr3: The 3rd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static __always_inline unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); } #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_bit(addr1, addr2, size); } #endif /** * find_first_andnot_bit - find the first bit set in 1st memory region and unset in 2nd * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns >= @size. */ static __always_inline unsigned long find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_andnot_bit(addr1, addr2, size); } /** * find_first_and_and_bit - find the first set bit in 3 memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @addr3: The third address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_and_bit(addr1, addr2, addr3, size); } #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit(addr, size); } #endif #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region * @addr: The address to start the search at * @size: The number of bits to search * * Returns the bit number of the last set bit, or size. */ static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __fls(val) : size; } return _find_last_bit(addr, size); } #endif /** * find_next_and_bit_wrap - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_and_bit(addr1, addr2, offset); return bit < offset ? bit : size; } /** * find_next_bit_wrap - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { unsigned long bit = find_next_bit(addr, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_bit(addr, offset); return bit < offset ? bit : size; } /* * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { unsigned long bit; /* If not wrapped around */ if (n > start) { /* and have a bit, just return it. */ bit = find_next_bit(bitmap, size, n); if (bit < size) return bit; /* Otherwise, wrap around and ... */ n = 0; } /* Search the other part. */ bit = find_next_bit(bitmap, start, n); return bit < start ? bit : size; } /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on * @size: bitmap size in number of bits * @offset: bit offset at which to start searching * * Returns the bit offset for the next set clump; the found clump value is * copied to the location pointed by @clump. If no bits are set, returns @size. */ extern unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset); #define find_first_clump8(clump, bits, size) \ find_next_clump8((clump), (bits), (size), 0) #if defined(__LITTLE_ENDIAN) static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit_le(addr, size, offset); } #endif #ifndef find_first_zero_bit_le static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit_le(addr, size); } #endif #ifndef find_next_bit_le static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit_le(addr, size, offset); } #endif #else #error "Please fix <asm/byteorder.h>" #endif #define for_each_set_bit(bit, addr, size) \ for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_and_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_andnot_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_or_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ for ((bit) = 0; \ (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit) * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_bit((addr), (size), b), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_bit((addr), (size), (b)), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first unset bit) * @e: bit offset of end of current bitrange (first set bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first unset bit); must be initialized * @e: bit offset of end of current bitrange (first set bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bit_wrap - iterate over all set bits starting from @start, and * wrapping around the end of bitmap. * @bit: offset for current iteration * @addr: bitmap address to base the search on * @size: bitmap size in number of bits * @start: Starting bit for bitmap traversing, wrapping around the bitmap end */ #define for_each_set_bit_wrap(bit, addr, size, start) \ for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ (bit) < (size); \ (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset * @clump: location to store copy of current 8-bit clump * @bits: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_clump8(start, clump, bits, size) \ for ((start) = find_first_clump8(&(clump), (bits), (size)); \ (start) < (size); \ (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) #endif /*__LINUX_FIND_H_ */ |
| 11 1 7 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lib/ts_fsm.c A naive finite state machine text search approach * * Authors: Thomas Graf <tgraf@suug.ch> * * ========================================================================== * * A finite state machine consists of n states (struct ts_fsm_token) * representing the pattern as a finite automaton. The data is read * sequentially on an octet basis. Every state token specifies the number * of recurrences and the type of value accepted which can be either a * specific character or ctype based set of characters. The available * type of recurrences include 1, (0|1), [0 n], and [1 n]. * * The algorithm differs between strict/non-strict mode specifying * whether the pattern has to start at the first octet. Strict mode * is enabled by default and can be disabled by inserting * TS_FSM_HEAD_IGNORE as the first token in the chain. * * The runtime performance of the algorithm should be around O(n), * however while in strict mode the average runtime can be better. */ #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/textsearch.h> #include <linux/textsearch_fsm.h> struct ts_fsm { unsigned int ntokens; struct ts_fsm_token tokens[]; }; /* other values derived from ctype.h */ #define _A 0x100 /* ascii */ #define _W 0x200 /* wildcard */ /* Map to _ctype flags and some magic numbers */ static const u16 token_map[TS_FSM_TYPE_MAX+1] = { [TS_FSM_SPECIFIC] = 0, [TS_FSM_WILDCARD] = _W, [TS_FSM_CNTRL] = _C, [TS_FSM_LOWER] = _L, [TS_FSM_UPPER] = _U, [TS_FSM_PUNCT] = _P, [TS_FSM_SPACE] = _S, [TS_FSM_DIGIT] = _D, [TS_FSM_XDIGIT] = _D | _X, [TS_FSM_ALPHA] = _U | _L, [TS_FSM_ALNUM] = _U | _L | _D, [TS_FSM_PRINT] = _P | _U | _L | _D | _SP, [TS_FSM_GRAPH] = _P | _U | _L | _D, [TS_FSM_ASCII] = _A, }; static const u16 token_lookup_tbl[256] = { _W|_A|_C, _W|_A|_C, _W|_A|_C, _W|_A|_C, /* 0- 3 */ _W|_A|_C, _W|_A|_C, _W|_A|_C, _W|_A|_C, /* 4- 7 */ _W|_A|_C, _W|_A|_C|_S, _W|_A|_C|_S, _W|_A|_C|_S, /* 8- 11 */ _W|_A|_C|_S, _W|_A|_C|_S, _W|_A|_C, _W|_A|_C, /* 12- 15 */ _W|_A|_C, _W|_A|_C, _W|_A|_C, _W|_A|_C, /* 16- 19 */ _W|_A|_C, _W|_A|_C, _W|_A|_C, _W|_A|_C, /* 20- 23 */ _W|_A|_C, _W|_A|_C, _W|_A|_C, _W|_A|_C, /* 24- 27 */ _W|_A|_C, _W|_A|_C, _W|_A|_C, _W|_A|_C, /* 28- 31 */ _W|_A|_S|_SP, _W|_A|_P, _W|_A|_P, _W|_A|_P, /* 32- 35 */ _W|_A|_P, _W|_A|_P, _W|_A|_P, _W|_A|_P, /* 36- 39 */ _W|_A|_P, _W|_A|_P, _W|_A|_P, _W|_A|_P, /* 40- 43 */ _W|_A|_P, _W|_A|_P, _W|_A|_P, _W|_A|_P, /* 44- 47 */ _W|_A|_D, _W|_A|_D, _W|_A|_D, _W|_A|_D, /* 48- 51 */ _W|_A|_D, _W|_A|_D, _W|_A|_D, _W|_A|_D, /* 52- 55 */ _W|_A|_D, _W|_A|_D, _W|_A|_P, _W|_A|_P, /* 56- 59 */ _W|_A|_P, _W|_A|_P, _W|_A|_P, _W|_A|_P, /* 60- 63 */ _W|_A|_P, _W|_A|_U|_X, _W|_A|_U|_X, _W|_A|_U|_X, /* 64- 67 */ _W|_A|_U|_X, _W|_A|_U|_X, _W|_A|_U|_X, _W|_A|_U, /* 68- 71 */ _W|_A|_U, _W|_A|_U, _W|_A|_U, _W|_A|_U, /* 72- 75 */ _W|_A|_U, _W|_A|_U, _W|_A|_U, _W|_A|_U, /* 76- 79 */ _W|_A|_U, _W|_A|_U, _W|_A|_U, _W|_A|_U, /* 80- 83 */ _W|_A|_U, _W|_A|_U, _W|_A|_U, _W|_A|_U, /* 84- 87 */ _W|_A|_U, _W|_A|_U, _W|_A|_U, _W|_A|_P, /* 88- 91 */ _W|_A|_P, _W|_A|_P, _W|_A|_P, _W|_A|_P, /* 92- 95 */ _W|_A|_P, _W|_A|_L|_X, _W|_A|_L|_X, _W|_A|_L|_X, /* 96- 99 */ _W|_A|_L|_X, _W|_A|_L|_X, _W|_A|_L|_X, _W|_A|_L, /* 100-103 */ _W|_A|_L, _W|_A|_L, _W|_A|_L, _W|_A|_L, /* 104-107 */ _W|_A|_L, _W|_A|_L, _W|_A|_L, _W|_A|_L, /* 108-111 */ _W|_A|_L, _W|_A|_L, _W|_A|_L, _W|_A|_L, /* 112-115 */ _W|_A|_L, _W|_A|_L, _W|_A|_L, _W|_A|_L, /* 116-119 */ _W|_A|_L, _W|_A|_L, _W|_A|_L, _W|_A|_P, /* 120-123 */ _W|_A|_P, _W|_A|_P, _W|_A|_P, _W|_A|_C, /* 124-127 */ _W, _W, _W, _W, /* 128-131 */ _W, _W, _W, _W, /* 132-135 */ _W, _W, _W, _W, /* 136-139 */ _W, _W, _W, _W, /* 140-143 */ _W, _W, _W, _W, /* 144-147 */ _W, _W, _W, _W, /* 148-151 */ _W, _W, _W, _W, /* 152-155 */ _W, _W, _W, _W, /* 156-159 */ _W|_S|_SP, _W|_P, _W|_P, _W|_P, /* 160-163 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 164-167 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 168-171 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 172-175 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 176-179 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 180-183 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 184-187 */ _W|_P, _W|_P, _W|_P, _W|_P, /* 188-191 */ _W|_U, _W|_U, _W|_U, _W|_U, /* 192-195 */ _W|_U, _W|_U, _W|_U, _W|_U, /* 196-199 */ _W|_U, _W|_U, _W|_U, _W|_U, /* 200-203 */ _W|_U, _W|_U, _W|_U, _W|_U, /* 204-207 */ _W|_U, _W|_U, _W|_U, _W|_U, /* 208-211 */ _W|_U, _W|_U, _W|_U, _W|_P, /* 212-215 */ _W|_U, _W|_U, _W|_U, _W|_U, /* 216-219 */ _W|_U, _W|_U, _W|_U, _W|_L, /* 220-223 */ _W|_L, _W|_L, _W|_L, _W|_L, /* 224-227 */ _W|_L, _W|_L, _W|_L, _W|_L, /* 228-231 */ _W|_L, _W|_L, _W|_L, _W|_L, /* 232-235 */ _W|_L, _W|_L, _W|_L, _W|_L, /* 236-239 */ _W|_L, _W|_L, _W|_L, _W|_L, /* 240-243 */ _W|_L, _W|_L, _W|_L, _W|_P, /* 244-247 */ _W|_L, _W|_L, _W|_L, _W|_L, /* 248-251 */ _W|_L, _W|_L, _W|_L, _W|_L}; /* 252-255 */ static inline int match_token(struct ts_fsm_token *t, u8 d) { if (t->type) return (token_lookup_tbl[d] & t->type) != 0; else return t->value == d; } static unsigned int fsm_find(struct ts_config *conf, struct ts_state *state) { struct ts_fsm *fsm = ts_config_priv(conf); struct ts_fsm_token *cur = NULL, *next; unsigned int match_start, block_idx = 0, tok_idx; unsigned block_len = 0, strict, consumed = state->offset; const u8 *data; #define GET_NEXT_BLOCK() \ ({ consumed += block_idx; \ block_idx = 0; \ block_len = conf->get_next_block(consumed, &data, conf, state); }) #define TOKEN_MISMATCH() \ do { \ if (strict) \ goto no_match; \ block_idx++; \ goto startover; \ } while(0) #define end_of_data() unlikely(block_idx >= block_len && !GET_NEXT_BLOCK()) if (end_of_data()) goto no_match; strict = fsm->tokens[0].recur != TS_FSM_HEAD_IGNORE; startover: match_start = consumed + block_idx; for (tok_idx = 0; tok_idx < fsm->ntokens; tok_idx++) { cur = &fsm->tokens[tok_idx]; if (likely(tok_idx < (fsm->ntokens - 1))) next = &fsm->tokens[tok_idx + 1]; else next = NULL; switch (cur->recur) { case TS_FSM_SINGLE: if (end_of_data()) goto no_match; if (!match_token(cur, data[block_idx])) TOKEN_MISMATCH(); break; case TS_FSM_PERHAPS: if (end_of_data() || !match_token(cur, data[block_idx])) continue; break; case TS_FSM_MULTI: if (end_of_data()) goto no_match; if (!match_token(cur, data[block_idx])) TOKEN_MISMATCH(); block_idx++; fallthrough; case TS_FSM_ANY: if (next == NULL) goto found_match; if (end_of_data()) continue; while (!match_token(next, data[block_idx])) { if (!match_token(cur, data[block_idx])) TOKEN_MISMATCH(); block_idx++; if (end_of_data()) goto no_match; } continue; /* * Optimization: Prefer small local loop over jumping * back and forth until garbage at head is munched. */ case TS_FSM_HEAD_IGNORE: if (end_of_data()) continue; while (!match_token(next, data[block_idx])) { /* * Special case, don't start over upon * a mismatch, give the user the * chance to specify the type of data * allowed to be ignored. */ if (!match_token(cur, data[block_idx])) goto no_match; block_idx++; if (end_of_data()) goto no_match; } match_start = consumed + block_idx; continue; } block_idx++; } if (end_of_data()) goto found_match; no_match: return UINT_MAX; found_match: state->offset = consumed + block_idx; return match_start; } static struct ts_config *fsm_init(const void *pattern, unsigned int len, gfp_t gfp_mask, int flags) { int i, err = -EINVAL; struct ts_config *conf; struct ts_fsm *fsm; struct ts_fsm_token *tokens = (struct ts_fsm_token *) pattern; unsigned int ntokens = len / sizeof(*tokens); size_t priv_size = sizeof(*fsm) + len; if (len % sizeof(struct ts_fsm_token) || ntokens < 1) goto errout; if (flags & TS_IGNORECASE) goto errout; for (i = 0; i < ntokens; i++) { struct ts_fsm_token *t = &tokens[i]; if (t->type > TS_FSM_TYPE_MAX || t->recur > TS_FSM_RECUR_MAX) goto errout; if (t->recur == TS_FSM_HEAD_IGNORE && (i != 0 || i == (ntokens - 1))) goto errout; } conf = alloc_ts_config(priv_size, gfp_mask); if (IS_ERR(conf)) return conf; conf->flags = flags; fsm = ts_config_priv(conf); fsm->ntokens = ntokens; memcpy(fsm->tokens, pattern, len); for (i = 0; i < fsm->ntokens; i++) { struct ts_fsm_token *t = &fsm->tokens[i]; t->type = token_map[t->type]; } return conf; errout: return ERR_PTR(err); } static void *fsm_get_pattern(struct ts_config *conf) { struct ts_fsm *fsm = ts_config_priv(conf); return fsm->tokens; } static unsigned int fsm_get_pattern_len(struct ts_config *conf) { struct ts_fsm *fsm = ts_config_priv(conf); return fsm->ntokens * sizeof(struct ts_fsm_token); } static struct ts_ops fsm_ops = { .name = "fsm", .find = fsm_find, .init = fsm_init, .get_pattern = fsm_get_pattern, .get_pattern_len = fsm_get_pattern_len, .owner = THIS_MODULE, .list = LIST_HEAD_INIT(fsm_ops.list) }; static int __init init_fsm(void) { return textsearch_register(&fsm_ops); } static void __exit exit_fsm(void) { textsearch_unregister(&fsm_ops); } MODULE_DESCRIPTION("naive finite state machine text search"); MODULE_LICENSE("GPL"); module_init(init_fsm); module_exit(exit_fsm); |
| 3 3 3 3 15 12 7 18 15 3 21 5 6 3 9 13 28 26 26 19 1 4 1 3 27 3 2 2 2 2 2 3 6 6 2 31 28 3 16 15 4 3 15 16 16 14 15 15 7 1 1 3 2 1 2 18 4 1 16 7 9 4 3 1 3 263 1 1 1 1 1 1 18 1 18 2 4 1 2 1 7 4 216 22 5 16 14 12 7 3 22 21 21 17 20 18 16 6 3 6 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 1 23 23 1 90 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-only /* By Ross Biro 1/23/92 */ /* * Pentium III FXSR, SSE support * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/ptrace.h> #include <linux/user.h> #include <linux/elf.h> #include <linux/security.h> #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/signal.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/processor.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> #include <asm/fpu/xstate.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> #include <asm/prctl.h> #include <asm/proto.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> #include <asm/syscall.h> #include <asm/fsgsbase.h> #include <asm/io_bitmap.h> #include "tls.h" enum x86_regset_32 { REGSET32_GENERAL, REGSET32_FP, REGSET32_XFP, REGSET32_XSTATE, REGSET32_TLS, REGSET32_IOPERM, }; enum x86_regset_64 { REGSET64_GENERAL, REGSET64_FP, REGSET64_IOPERM, REGSET64_XSTATE, REGSET64_SSP, }; #define REGSET_GENERAL \ ({ \ BUILD_BUG_ON((int)REGSET32_GENERAL != (int)REGSET64_GENERAL); \ REGSET32_GENERAL; \ }) #define REGSET_FP \ ({ \ BUILD_BUG_ON((int)REGSET32_FP != (int)REGSET64_FP); \ REGSET32_FP; \ }) struct pt_regs_offset { const char *name; int offset; }; #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} #define REG_OFFSET_END {.name = NULL, .offset = 0} static const struct pt_regs_offset regoffset_table[] = { #ifdef CONFIG_X86_64 REG_OFFSET_NAME(r15), REG_OFFSET_NAME(r14), REG_OFFSET_NAME(r13), REG_OFFSET_NAME(r12), REG_OFFSET_NAME(r11), REG_OFFSET_NAME(r10), REG_OFFSET_NAME(r9), REG_OFFSET_NAME(r8), #endif REG_OFFSET_NAME(bx), REG_OFFSET_NAME(cx), REG_OFFSET_NAME(dx), REG_OFFSET_NAME(si), REG_OFFSET_NAME(di), REG_OFFSET_NAME(bp), REG_OFFSET_NAME(ax), #ifdef CONFIG_X86_32 REG_OFFSET_NAME(ds), REG_OFFSET_NAME(es), REG_OFFSET_NAME(fs), REG_OFFSET_NAME(gs), #endif REG_OFFSET_NAME(orig_ax), REG_OFFSET_NAME(ip), REG_OFFSET_NAME(cs), REG_OFFSET_NAME(flags), REG_OFFSET_NAME(sp), REG_OFFSET_NAME(ss), REG_OFFSET_END, }; /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register * * regs_query_register_offset() returns the offset of a register in struct * pt_regs from its name. If the name is invalid, this returns -EINVAL; */ int regs_query_register_offset(const char *name) { const struct pt_regs_offset *roff; for (roff = regoffset_table; roff->name != NULL; roff++) if (!strcmp(roff->name, name)) return roff->offset; return -EINVAL; } /** * regs_query_register_name() - query register name from its offset * @offset: the offset of a register in struct pt_regs. * * regs_query_register_name() returns the name of a register from its * offset in struct pt_regs. If the @offset is invalid, this returns NULL; */ const char *regs_query_register_name(unsigned int offset) { const struct pt_regs_offset *roff; for (roff = regoffset_table; roff->name != NULL; roff++) if (roff->offset == offset) return roff->name; return NULL; } /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ /* * Determines which flags the user has access to [1 = access, 0 = no access]. */ #define FLAG_MASK_32 ((unsigned long) \ (X86_EFLAGS_CF | X86_EFLAGS_PF | \ X86_EFLAGS_AF | X86_EFLAGS_ZF | \ X86_EFLAGS_SF | X86_EFLAGS_TF | \ X86_EFLAGS_DF | X86_EFLAGS_OF | \ X86_EFLAGS_RF | X86_EFLAGS_AC)) /* * Determines whether a value may be installed in a segment register. */ static inline bool invalid_selector(u16 value) { return unlikely(value != 0 && (value & SEGMENT_RPL_MASK) != USER_RPL); } #ifdef CONFIG_X86_32 #define FLAG_MASK FLAG_MASK_32 static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); return ®s->bx + (regno >> 2); } static u16 get_segment_reg(struct task_struct *task, unsigned long offset) { /* * Returning the value truncates it to 16 bits. */ unsigned int retval; if (offset != offsetof(struct user_regs_struct, gs)) retval = *pt_regs_access(task_pt_regs(task), offset); else { if (task == current) savesegment(gs, retval); else retval = task->thread.gs; } return retval; } static int set_segment_reg(struct task_struct *task, unsigned long offset, u16 value) { if (WARN_ON_ONCE(task == current)) return -EIO; /* * The value argument was already truncated to 16 bits. */ if (invalid_selector(value)) return -EIO; /* * For %cs and %ss we cannot permit a null selector. * We can permit a bogus selector as long as it has USER_RPL. * Null selectors are fine for other segment registers, but * we will never get back to user mode with invalid %cs or %ss * and will take the trap in iret instead. Much code relies * on user_mode() to distinguish a user trap frame (which can * safely use invalid selectors) from a kernel trap frame. */ switch (offset) { case offsetof(struct user_regs_struct, cs): case offsetof(struct user_regs_struct, ss): if (unlikely(value == 0)) return -EIO; fallthrough; default: *pt_regs_access(task_pt_regs(task), offset) = value; break; case offsetof(struct user_regs_struct, gs): task->thread.gs = value; } return 0; } #else /* CONFIG_X86_64 */ #define FLAG_MASK (FLAG_MASK_32 | X86_EFLAGS_NT) static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long offset) { BUILD_BUG_ON(offsetof(struct pt_regs, r15) != 0); return ®s->r15 + (offset / sizeof(regs->r15)); } static u16 get_segment_reg(struct task_struct *task, unsigned long offset) { /* * Returning the value truncates it to 16 bits. */ unsigned int seg; switch (offset) { case offsetof(struct user_regs_struct, fs): if (task == current) { /* Older gas can't assemble movq %?s,%r?? */ asm("movl %%fs,%0" : "=r" (seg)); return seg; } return task->thread.fsindex; case offsetof(struct user_regs_struct, gs): if (task == current) { asm("movl %%gs,%0" : "=r" (seg)); return seg; } return task->thread.gsindex; case offsetof(struct user_regs_struct, ds): if (task == current) { asm("movl %%ds,%0" : "=r" (seg)); return seg; } return task->thread.ds; case offsetof(struct user_regs_struct, es): if (task == current) { asm("movl %%es,%0" : "=r" (seg)); return seg; } return task->thread.es; case offsetof(struct user_regs_struct, cs): case offsetof(struct user_regs_struct, ss): break; } return *pt_regs_access(task_pt_regs(task), offset); } static int set_segment_reg(struct task_struct *task, unsigned long offset, u16 value) { if (WARN_ON_ONCE(task == current)) return -EIO; /* * The value argument was already truncated to 16 bits. */ if (invalid_selector(value)) return -EIO; /* * Writes to FS and GS will change the stored selector. Whether * this changes the segment base as well depends on whether * FSGSBASE is enabled. */ switch (offset) { case offsetof(struct user_regs_struct,fs): task->thread.fsindex = value; break; case offsetof(struct user_regs_struct,gs): task->thread.gsindex = value; break; case offsetof(struct user_regs_struct,ds): task->thread.ds = value; break; case offsetof(struct user_regs_struct,es): task->thread.es = value; break; /* * Can't actually change these in 64-bit mode. */ case offsetof(struct user_regs_struct,cs): if (unlikely(value == 0)) return -EIO; task_pt_regs(task)->cs = value; break; case offsetof(struct user_regs_struct,ss): if (unlikely(value == 0)) return -EIO; task_pt_regs(task)->ss = value; break; } return 0; } #endif /* CONFIG_X86_32 */ static unsigned long get_flags(struct task_struct *task) { unsigned long retval = task_pt_regs(task)->flags; /* * If the debugger set TF, hide it from the readout. */ if (test_tsk_thread_flag(task, TIF_FORCED_TF)) retval &= ~X86_EFLAGS_TF; return retval; } static int set_flags(struct task_struct *task, unsigned long value) { struct pt_regs *regs = task_pt_regs(task); /* * If the user value contains TF, mark that * it was not "us" (the debugger) that set it. * If not, make sure it stays set if we had. */ if (value & X86_EFLAGS_TF) clear_tsk_thread_flag(task, TIF_FORCED_TF); else if (test_tsk_thread_flag(task, TIF_FORCED_TF)) value |= X86_EFLAGS_TF; regs->flags = (regs->flags & ~FLAG_MASK) | (value & FLAG_MASK); return 0; } static int putreg(struct task_struct *child, unsigned long offset, unsigned long value) { switch (offset) { case offsetof(struct user_regs_struct, cs): case offsetof(struct user_regs_struct, ds): case offsetof(struct user_regs_struct, es): case offsetof(struct user_regs_struct, fs): case offsetof(struct user_regs_struct, gs): case offsetof(struct user_regs_struct, ss): return set_segment_reg(child, offset, value); case offsetof(struct user_regs_struct, flags): return set_flags(child, value); #ifdef CONFIG_X86_64 case offsetof(struct user_regs_struct,fs_base): if (value >= TASK_SIZE_MAX) return -EIO; x86_fsbase_write_task(child, value); return 0; case offsetof(struct user_regs_struct,gs_base): if (value >= TASK_SIZE_MAX) return -EIO; x86_gsbase_write_task(child, value); return 0; #endif } *pt_regs_access(task_pt_regs(child), offset) = value; return 0; } static unsigned long getreg(struct task_struct *task, unsigned long offset) { switch (offset) { case offsetof(struct user_regs_struct, cs): case offsetof(struct user_regs_struct, ds): case offsetof(struct user_regs_struct, es): case offsetof(struct user_regs_struct, fs): case offsetof(struct user_regs_struct, gs): case offsetof(struct user_regs_struct, ss): return get_segment_reg(task, offset); case offsetof(struct user_regs_struct, flags): return get_flags(task); #ifdef CONFIG_X86_64 case offsetof(struct user_regs_struct, fs_base): return x86_fsbase_read_task(task); case offsetof(struct user_regs_struct, gs_base): return x86_gsbase_read_task(task); #endif } return *pt_regs_access(task_pt_regs(task), offset); } static int genregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int reg; for (reg = 0; to.left; reg++) membuf_store(&to, getreg(target, reg * sizeof(unsigned long))); return 0; } static int genregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret = 0; if (kbuf) { const unsigned long *k = kbuf; while (count >= sizeof(*k) && !ret) { ret = putreg(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } } else { const unsigned long __user *u = ubuf; while (count >= sizeof(*u) && !ret) { unsigned long word; ret = __get_user(word, u++); if (ret) break; ret = putreg(target, pos, word); count -= sizeof(*u); pos += sizeof(*u); } } return ret; } static void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { int i; struct thread_struct *thread = &(current->thread); /* * Store in the virtual DR6 register the fact that the breakpoint * was hit so the thread's debugger will see it. */ for (i = 0; i < HBP_NUM; i++) { if (thread->ptrace_bps[i] == bp) break; } thread->virtual_dr6 |= (DR_TRAP0 << i); } /* * Walk through every ptrace breakpoints for this thread and * build the dr7 value on top of their attributes. * */ static unsigned long ptrace_get_dr7(struct perf_event *bp[]) { int i; int dr7 = 0; struct arch_hw_breakpoint *info; for (i = 0; i < HBP_NUM; i++) { if (bp[i] && !bp[i]->attr.disabled) { info = counter_arch_bp(bp[i]); dr7 |= encode_dr7(i, info->len, info->type); } } return dr7; } static int ptrace_fill_bp_fields(struct perf_event_attr *attr, int len, int type, bool disabled) { int err, bp_len, bp_type; err = arch_bp_generic_fields(len, type, &bp_len, &bp_type); if (!err) { attr->bp_len = bp_len; attr->bp_type = bp_type; attr->disabled = disabled; } return err; } static struct perf_event * ptrace_register_breakpoint(struct task_struct *tsk, int len, int type, unsigned long addr, bool disabled) { struct perf_event_attr attr; int err; ptrace_breakpoint_init(&attr); attr.bp_addr = addr; err = ptrace_fill_bp_fields(&attr, len, type, disabled); if (err) return ERR_PTR(err); return register_user_hw_breakpoint(&attr, ptrace_triggered, NULL, tsk); } static int ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, int disabled) { struct perf_event_attr attr = bp->attr; int err; err = ptrace_fill_bp_fields(&attr, len, type, disabled); if (err) return err; return modify_user_hw_breakpoint(bp, &attr); } /* * Handle ptrace writes to debug register 7. */ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data) { struct thread_struct *thread = &tsk->thread; unsigned long old_dr7; bool second_pass = false; int i, rc, ret = 0; data &= ~DR_CONTROL_RESERVED; old_dr7 = ptrace_get_dr7(thread->ptrace_bps); restore: rc = 0; for (i = 0; i < HBP_NUM; i++) { unsigned len, type; bool disabled = !decode_dr7(data, i, &len, &type); struct perf_event *bp = thread->ptrace_bps[i]; if (!bp) { if (disabled) continue; bp = ptrace_register_breakpoint(tsk, len, type, 0, disabled); if (IS_ERR(bp)) { rc = PTR_ERR(bp); break; } thread->ptrace_bps[i] = bp; continue; } rc = ptrace_modify_breakpoint(bp, len, type, disabled); if (rc) break; } /* Restore if the first pass failed, second_pass shouldn't fail. */ if (rc && !WARN_ON(second_pass)) { ret = rc; data = old_dr7; second_pass = true; goto restore; } return ret; } /* * Handle PTRACE_PEEKUSR calls for the debug register area. */ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) { struct thread_struct *thread = &tsk->thread; unsigned long val = 0; if (n < HBP_NUM) { int index = array_index_nospec(n, HBP_NUM); struct perf_event *bp = thread->ptrace_bps[index]; if (bp) val = bp->hw.info.address; } else if (n == 6) { val = thread->virtual_dr6 ^ DR6_RESERVED; /* Flip back to arch polarity */ } else if (n == 7) { val = thread->ptrace_dr7; } return val; } static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, unsigned long addr) { struct thread_struct *t = &tsk->thread; struct perf_event *bp = t->ptrace_bps[nr]; int err = 0; if (!bp) { /* * Put stub len and type to create an inactive but correct bp. * * CHECKME: the previous code returned -EIO if the addr wasn't * a valid task virtual addr. The new one will return -EINVAL in * this case. * -EINVAL may be what we want for in-kernel breakpoints users, * but -EIO looks better for ptrace, since we refuse a register * writing for the user. And anyway this is the previous * behaviour. */ bp = ptrace_register_breakpoint(tsk, X86_BREAKPOINT_LEN_1, X86_BREAKPOINT_WRITE, addr, true); if (IS_ERR(bp)) err = PTR_ERR(bp); else t->ptrace_bps[nr] = bp; } else { struct perf_event_attr attr = bp->attr; attr.bp_addr = addr; err = modify_user_hw_breakpoint(bp, &attr); } return err; } /* * Handle PTRACE_POKEUSR calls for the debug register area. */ static int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val) { struct thread_struct *thread = &tsk->thread; /* There are no DR4 or DR5 registers */ int rc = -EIO; if (n < HBP_NUM) { rc = ptrace_set_breakpoint_addr(tsk, n, val); } else if (n == 6) { thread->virtual_dr6 = val ^ DR6_RESERVED; /* Flip to positive polarity */ rc = 0; } else if (n == 7) { rc = ptrace_write_dr7(tsk, val); if (!rc) thread->ptrace_dr7 = val; } return rc; } /* * These access the current or another (stopped) task's io permission * bitmap for debugging or core dump. */ static int ioperm_active(struct task_struct *target, const struct user_regset *regset) { struct io_bitmap *iobm = target->thread.io_bitmap; return iobm ? DIV_ROUND_UP(iobm->max, regset->size) : 0; } static int ioperm_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct io_bitmap *iobm = target->thread.io_bitmap; if (!iobm) return -ENXIO; return membuf_write(&to, iobm->bitmap, IO_BITMAP_BYTES); } /* * Called by kernel/ptrace.c when detaching.. * * Make sure the single step bit is not set. */ void ptrace_disable(struct task_struct *child) { user_disable_single_step(child); } #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION static const struct user_regset_view user_x86_32_view; /* Initialized below. */ #endif #ifdef CONFIG_X86_64 static const struct user_regset_view user_x86_64_view; /* Initialized below. */ #endif long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { int ret; unsigned long __user *datap = (unsigned long __user *)data; #ifdef CONFIG_X86_64 /* This is native 64-bit ptrace() */ const struct user_regset_view *regset_view = &user_x86_64_view; #else /* This is native 32-bit ptrace() */ const struct user_regset_view *regset_view = &user_x86_32_view; #endif switch (request) { /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: { unsigned long tmp; ret = -EIO; if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user)) break; tmp = 0; /* Default return condition */ if (addr < sizeof(struct user_regs_struct)) tmp = getreg(child, addr); else if (addr >= offsetof(struct user, u_debugreg[0]) && addr <= offsetof(struct user, u_debugreg[7])) { addr -= offsetof(struct user, u_debugreg[0]); tmp = ptrace_get_debugreg(child, addr / sizeof(data)); } ret = put_user(tmp, datap); break; } case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ ret = -EIO; if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user)) break; if (addr < sizeof(struct user_regs_struct)) ret = putreg(child, addr, data); else if (addr >= offsetof(struct user, u_debugreg[0]) && addr <= offsetof(struct user, u_debugreg[7])) { addr -= offsetof(struct user, u_debugreg[0]); ret = ptrace_set_debugreg(child, addr / sizeof(data), data); } break; case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, regset_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, regset_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ return copy_regset_to_user(child, regset_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ return copy_regset_from_user(child, regset_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); #ifdef CONFIG_X86_32 case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, REGSET32_XFP, 0, sizeof(struct user_fxsr_struct), datap) ? -EIO : 0; case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, REGSET32_XFP, 0, sizeof(struct user_fxsr_struct), datap) ? -EIO : 0; #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION case PTRACE_GET_THREAD_AREA: if ((int) addr < 0) return -EIO; ret = do_get_thread_area(child, addr, (struct user_desc __user *)data); break; case PTRACE_SET_THREAD_AREA: if ((int) addr < 0) return -EIO; ret = do_set_thread_area(child, addr, (struct user_desc __user *)data, 0); break; #endif #ifdef CONFIG_X86_64 /* normal 64bit interface to access TLS data. Works just like arch_prctl, except that the arguments are reversed. */ case PTRACE_ARCH_PRCTL: ret = do_arch_prctl_64(child, data, addr); break; #endif default: ret = ptrace_request(child, request, addr, data); break; } return ret; } #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> #include <linux/syscalls.h> #include <asm/ia32.h> #include <asm/user32.h> #define R32(l,q) \ case offsetof(struct user32, regs.l): \ regs->q = value; break #define SEG32(rs) \ case offsetof(struct user32, regs.rs): \ return set_segment_reg(child, \ offsetof(struct user_regs_struct, rs), \ value); \ break static int putreg32(struct task_struct *child, unsigned regno, u32 value) { struct pt_regs *regs = task_pt_regs(child); int ret; switch (regno) { SEG32(cs); SEG32(ds); SEG32(es); /* * A 32-bit ptracer on a 64-bit kernel expects that writing * FS or GS will also update the base. This is needed for * operations like PTRACE_SETREGS to fully restore a saved * CPU state. */ case offsetof(struct user32, regs.fs): ret = set_segment_reg(child, offsetof(struct user_regs_struct, fs), value); if (ret == 0) child->thread.fsbase = x86_fsgsbase_read_task(child, value); return ret; case offsetof(struct user32, regs.gs): ret = set_segment_reg(child, offsetof(struct user_regs_struct, gs), value); if (ret == 0) child->thread.gsbase = x86_fsgsbase_read_task(child, value); return ret; SEG32(ss); R32(ebx, bx); R32(ecx, cx); R32(edx, dx); R32(edi, di); R32(esi, si); R32(ebp, bp); R32(eax, ax); R32(eip, ip); R32(esp, sp); case offsetof(struct user32, regs.orig_eax): /* * Warning: bizarre corner case fixup here. A 32-bit * debugger setting orig_eax to -1 wants to disable * syscall restart. Make sure that the syscall * restart code sign-extends orig_ax. Also make sure * we interpret the -ERESTART* codes correctly if * loaded into regs->ax in case the task is not * actually still sitting at the exit from a 32-bit * syscall with TS_COMPAT still set. */ regs->orig_ax = value; if (syscall_get_nr(child, regs) != -1) child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): return set_flags(child, value); case offsetof(struct user32, u_debugreg[0]) ... offsetof(struct user32, u_debugreg[7]): regno -= offsetof(struct user32, u_debugreg[0]); return ptrace_set_debugreg(child, regno / 4, value); default: if (regno > sizeof(struct user32) || (regno & 3)) return -EIO; /* * Other dummy fields in the virtual user structure * are ignored */ break; } return 0; } #undef R32 #undef SEG32 #define R32(l,q) \ case offsetof(struct user32, regs.l): \ *val = regs->q; break #define SEG32(rs) \ case offsetof(struct user32, regs.rs): \ *val = get_segment_reg(child, \ offsetof(struct user_regs_struct, rs)); \ break static int getreg32(struct task_struct *child, unsigned regno, u32 *val) { struct pt_regs *regs = task_pt_regs(child); switch (regno) { SEG32(ds); SEG32(es); SEG32(fs); SEG32(gs); R32(cs, cs); R32(ss, ss); R32(ebx, bx); R32(ecx, cx); R32(edx, dx); R32(edi, di); R32(esi, si); R32(ebp, bp); R32(eax, ax); R32(orig_eax, orig_ax); R32(eip, ip); R32(esp, sp); case offsetof(struct user32, regs.eflags): *val = get_flags(child); break; case offsetof(struct user32, u_debugreg[0]) ... offsetof(struct user32, u_debugreg[7]): regno -= offsetof(struct user32, u_debugreg[0]); *val = ptrace_get_debugreg(child, regno / 4); break; default: if (regno > sizeof(struct user32) || (regno & 3)) return -EIO; /* * Other dummy fields in the virtual user structure * are ignored */ *val = 0; break; } return 0; } #undef R32 #undef SEG32 static int genregs32_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int reg; for (reg = 0; to.left; reg++) { u32 val; getreg32(target, reg * 4, &val); membuf_store(&to, val); } return 0; } static int genregs32_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret = 0; if (kbuf) { const compat_ulong_t *k = kbuf; while (count >= sizeof(*k) && !ret) { ret = putreg32(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } } else { const compat_ulong_t __user *u = ubuf; while (count >= sizeof(*u) && !ret) { compat_ulong_t word; ret = __get_user(word, u++); if (ret) break; ret = putreg32(target, pos, word); count -= sizeof(*u); pos += sizeof(*u); } } return ret; } static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { unsigned long addr = caddr; unsigned long data = cdata; void __user *datap = compat_ptr(data); int ret; __u32 val; switch (request) { case PTRACE_PEEKUSR: ret = getreg32(child, addr, &val); if (ret == 0) ret = put_user(val, (__u32 __user *)datap); break; case PTRACE_POKEUSR: ret = putreg32(child, addr, data); break; case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, &user_x86_32_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct32), datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, &user_x86_32_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct32), datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, REGSET_FP, 0, sizeof(struct user_i387_ia32_struct), datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ return copy_regset_from_user( child, &user_x86_32_view, REGSET_FP, 0, sizeof(struct user_i387_ia32_struct), datap); case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, REGSET32_XFP, 0, sizeof(struct user32_fxsr_struct), datap); case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, REGSET32_XFP, 0, sizeof(struct user32_fxsr_struct), datap); case PTRACE_GET_THREAD_AREA: case PTRACE_SET_THREAD_AREA: return arch_ptrace(child, request, addr, data); default: return compat_ptrace_request(child, request, addr, data); } return ret; } #endif /* CONFIG_IA32_EMULATION */ #ifdef CONFIG_X86_X32_ABI static long x32_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { unsigned long addr = caddr; unsigned long data = cdata; void __user *datap = compat_ptr(data); int ret; switch (request) { /* Read 32bits at location addr in the USER area. Only allow to return the lower 32bits of segment and debug registers. */ case PTRACE_PEEKUSR: { u32 tmp; ret = -EIO; if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || addr < offsetof(struct user_regs_struct, cs)) break; tmp = 0; /* Default return condition */ if (addr < sizeof(struct user_regs_struct)) tmp = getreg(child, addr); else if (addr >= offsetof(struct user, u_debugreg[0]) && addr <= offsetof(struct user, u_debugreg[7])) { addr -= offsetof(struct user, u_debugreg[0]); tmp = ptrace_get_debugreg(child, addr / sizeof(data)); } ret = put_user(tmp, (__u32 __user *)datap); break; } /* Write the word at location addr in the USER area. Only allow to update segment and debug registers with the upper 32bits zero-extended. */ case PTRACE_POKEUSR: ret = -EIO; if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || addr < offsetof(struct user_regs_struct, cs)) break; if (addr < sizeof(struct user_regs_struct)) ret = putreg(child, addr, data); else if (addr >= offsetof(struct user, u_debugreg[0]) && addr <= offsetof(struct user, u_debugreg[7])) { addr -= offsetof(struct user, u_debugreg[0]); ret = ptrace_set_debugreg(child, addr / sizeof(data), data); } break; case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, &user_x86_64_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, &user_x86_64_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ return copy_regset_to_user(child, &user_x86_64_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ return copy_regset_from_user(child, &user_x86_64_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); default: return compat_ptrace_request(child, request, addr, data); } return ret; } #endif #ifdef CONFIG_COMPAT long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { #ifdef CONFIG_X86_X32_ABI if (!in_ia32_syscall()) return x32_arch_ptrace(child, request, caddr, cdata); #endif #ifdef CONFIG_IA32_EMULATION return ia32_arch_ptrace(child, request, caddr, cdata); #else return 0; #endif } #endif /* CONFIG_COMPAT */ #ifdef CONFIG_X86_64 static struct user_regset x86_64_regsets[] __ro_after_init = { [REGSET64_GENERAL] = { USER_REGSET_NOTE_TYPE(PRSTATUS), .n = sizeof(struct user_regs_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), .regset_get = genregs_get, .set = genregs_set }, [REGSET64_FP] = { USER_REGSET_NOTE_TYPE(PRFPREG), .n = sizeof(struct fxregs_state) / sizeof(long), .size = sizeof(long), .align = sizeof(long), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, [REGSET64_XSTATE] = { USER_REGSET_NOTE_TYPE(X86_XSTATE), .size = sizeof(u64), .align = sizeof(u64), .active = xstateregs_active, .regset_get = xstateregs_get, .set = xstateregs_set }, [REGSET64_IOPERM] = { USER_REGSET_NOTE_TYPE(386_IOPERM), .n = IO_BITMAP_LONGS, .size = sizeof(long), .align = sizeof(long), .active = ioperm_active, .regset_get = ioperm_get }, #ifdef CONFIG_X86_USER_SHADOW_STACK [REGSET64_SSP] = { USER_REGSET_NOTE_TYPE(X86_SHSTK), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = ssp_active, .regset_get = ssp_get, .set = ssp_set }, #endif }; static const struct user_regset_view user_x86_64_view = { .name = "x86_64", .e_machine = EM_X86_64, .regsets = x86_64_regsets, .n = ARRAY_SIZE(x86_64_regsets) }; #else /* CONFIG_X86_32 */ #define user_regs_struct32 user_regs_struct #define genregs32_get genregs_get #define genregs32_set genregs_set #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION static struct user_regset x86_32_regsets[] __ro_after_init = { [REGSET32_GENERAL] = { USER_REGSET_NOTE_TYPE(PRSTATUS), .n = sizeof(struct user_regs_struct32) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = genregs32_get, .set = genregs32_set }, [REGSET32_FP] = { USER_REGSET_NOTE_TYPE(PRFPREG), .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = regset_fpregs_active, .regset_get = fpregs_get, .set = fpregs_set }, [REGSET32_XFP] = { USER_REGSET_NOTE_TYPE(PRXFPREG), .n = sizeof(struct fxregs_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, [REGSET32_XSTATE] = { USER_REGSET_NOTE_TYPE(X86_XSTATE), .size = sizeof(u64), .align = sizeof(u64), .active = xstateregs_active, .regset_get = xstateregs_get, .set = xstateregs_set }, [REGSET32_TLS] = { USER_REGSET_NOTE_TYPE(386_TLS), .n = GDT_ENTRY_TLS_ENTRIES, .bias = GDT_ENTRY_TLS_MIN, .size = sizeof(struct user_desc), .align = sizeof(struct user_desc), .active = regset_tls_active, .regset_get = regset_tls_get, .set = regset_tls_set }, [REGSET32_IOPERM] = { USER_REGSET_NOTE_TYPE(386_IOPERM), .n = IO_BITMAP_BYTES / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = ioperm_active, .regset_get = ioperm_get }, }; static const struct user_regset_view user_x86_32_view = { .name = "i386", .e_machine = EM_386, .regsets = x86_32_regsets, .n = ARRAY_SIZE(x86_32_regsets) }; #endif /* * This represents bytes 464..511 in the memory layout exported through * the REGSET_XSTATE interface. */ u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) { #ifdef CONFIG_X86_64 x86_64_regsets[REGSET64_XSTATE].n = size / sizeof(u64); #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION x86_32_regsets[REGSET32_XSTATE].n = size / sizeof(u64); #endif xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask; } /* * This is used by the core dump code to decide which regset to dump. The * core dump code writes out the resulting .e_machine and the corresponding * regsets. This is suboptimal if the task is messing around with its CS.L * field, but at worst the core dump will end up missing some information. * * Unfortunately, it is also used by the broken PTRACE_GETREGSET and * PTRACE_SETREGSET APIs. These APIs look at the .regsets field but have * no way to make sure that the e_machine they use matches the caller's * expectations. The result is that the data format returned by * PTRACE_GETREGSET depends on the returned CS field (and even the offset * of the returned CS field depends on its value!) and the data format * accepted by PTRACE_SETREGSET is determined by the old CS value. The * upshot is that it is basically impossible to use these APIs correctly. * * The best way to fix it in the long run would probably be to add new * improved ptrace() APIs to read and write registers reliably, possibly by * allowing userspace to select the ELF e_machine variant that they expect. */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_IA32_EMULATION if (!user_64bit_mode(task_pt_regs(task))) #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION return &user_x86_32_view; #endif #ifdef CONFIG_X86_64 return &user_x86_64_view; #endif } void send_sigtrap(struct pt_regs *regs, int error_code, int si_code) { struct task_struct *tsk = current; tsk->thread.trap_nr = X86_TRAP_DB; tsk->thread.error_code = error_code; /* Send us the fake SIGTRAP */ force_sig_fault(SIGTRAP, si_code, user_mode(regs) ? (void __user *)regs->ip : NULL); } void user_single_step_report(struct pt_regs *regs) { send_sigtrap(regs, 0, TRAP_BRKPT); } |
| 1515 1042 2829 1530 1525 1515 12 1 1524 1527 1524 2042 678 2038 2042 649 1508 1509 1509 880 678 678 879 677 680 678 2148 2150 851 1664 1042 868 1665 1041 1042 3 71 70 70 1 199 200 199 6 6 6 306 267 284 173 156 155 267 267 267 267 120 227 10 282 2090 2088 129 18 10 2 9 18 55 55 49 51 51 51 51 49 46 55 55 55 59 59 57 55 55 43 43 43 43 22 26 43 43 43 43 411 412 43 3078 1717 2457 1 118 2554 228 4488 4 85 121 6 118 121 121 121 121 4488 36 4472 4488 4 4492 2458 2453 2354 2456 2458 13 3 11 2501 2505 2507 2509 186 188 188 186 188 187 186 54 187 188 188 102 130 186 188 188 178 165 82 170 188 130 8 6 3 2 5 41 114 106 113 102 186 186 186 186 188 188 70 293 291 187 188 115 116 116 116 98 27 115 112 115 57 71 11 1 16 7 20 27 98 91 43 76 97 115 17 10 2 44 62 4 3 110 48 87 112 112 25 95 95 26 111 116 115 16 107 1042 1042 1042 198 71 8 200 198 198 199 115 198 199 200 56 198 198 199 16 184 3 9 149 200 199 24 199 16 184 199 107 200 183 16 16 9 1 8 87 85 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0 /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <linux/oom.h> #include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> #include "internal.h" #include "swap.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_assign(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } static void check_anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { /* The write lock must be held. */ mmap_assert_write_locked(src->vm_mm); /* If not a fork then must be on same mm. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && dst->vm_mm != src->vm_mm); /* If we have anything to do src->anon_vma must be provided. */ VM_WARN_ON_ONCE(!src->anon_vma && !list_empty(&src->anon_vma_chain)); VM_WARN_ON_ONCE(!src->anon_vma && dst->anon_vma); /* We are establishing a new anon_vma_chain. */ VM_WARN_ON_ONCE(!list_empty(&dst->anon_vma_chain)); /* * On fork, dst->anon_vma is set NULL (temporarily). Otherwise, anon_vma * must be the same across dst and src. */ VM_WARN_ON_ONCE(dst->anon_vma && dst->anon_vma != src->anon_vma); /* * Essentially equivalent to above - if not a no-op, we should expect * dst->anon_vma to be set for everything except a fork. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && src->anon_vma && !dst->anon_vma); /* For the anon_vma to be compatible, it can only be singular. */ VM_WARN_ON_ONCE(operation == VMA_OP_MERGE_UNFAULTED && !list_is_singular(&src->anon_vma_chain)); #ifdef CONFIG_PER_VMA_LOCK /* Only merging an unfaulted VMA leaves the destination attached. */ VM_WARN_ON_ONCE(operation != VMA_OP_MERGE_UNFAULTED && vma_is_attached(dst)); #endif } static void maybe_reuse_anon_vma(struct vm_area_struct *dst, struct anon_vma *anon_vma) { /* If already populated, nothing to do.*/ if (dst->anon_vma) return; /* * We reuse an anon_vma if any linking VMAs were unmapped and it has * only a single child at most. */ if (anon_vma->num_active_vmas > 0) return; if (anon_vma->num_children > 1) return; dst->anon_vma = anon_vma; anon_vma->num_active_vmas++; } static void cleanup_partial_anon_vmas(struct vm_area_struct *vma); /** * anon_vma_clone - Establishes new anon_vma_chain objects in @dst linking to * all of the anon_vma objects contained within @src anon_vma_chain's. * @dst: The destination VMA with an empty anon_vma_chain. * @src: The source VMA we wish to duplicate. * @operation: The type of operation which resulted in the clone. * * This is the heart of the VMA side of the anon_vma implementation - we invoke * this function whenever we need to set up a new VMA's anon_vma state. * * This is invoked for: * * - VMA Merge, but only when @dst is unfaulted and @src is faulted - meaning we * clone @src into @dst. * - VMA split. * - VMA (m)remap. * - Fork of faulted VMA. * * In all cases other than fork this is simply a duplication. Fork additionally * adds a new active anon_vma. * * ONLY in the case of fork do we try to 'reuse' existing anon_vma's in an * anon_vma hierarchy, reusing anon_vma's which have no VMA associated with them * but do have a single child. This is to avoid waste of memory when repeatedly * forking. * * Returns: 0 on success, -ENOMEM on failure. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { struct anon_vma_chain *avc, *pavc; struct anon_vma *active_anon_vma = src->anon_vma; check_anon_vma_clone(dst, src, operation); if (!active_anon_vma) return 0; /* * Allocate AVCs. We don't need an anon_vma lock for this as we * are not updating the anon_vma rbtree nor are we changing * anon_vma statistics. * * Either src, dst have the same mm for which we hold an exclusive mmap * write lock, or we are forking and we hold it on src->vm_mm and dst is * not yet accessible to other threads so there's no possibliity of the * unlinked AVC's being observed yet. */ list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; anon_vma_chain_assign(dst, avc, pavc->anon_vma); } /* * Now link the anon_vma's back to the newly inserted AVCs. * Note that all anon_vma's share the same root. */ anon_vma_lock_write(src->anon_vma); list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); if (operation == VMA_OP_FORK) maybe_reuse_anon_vma(dst, anon_vma); } if (operation != VMA_OP_FORK) dst->anon_vma->num_active_vmas++; anon_vma_unlock_write(active_anon_vma); return 0; enomem_failure: cleanup_partial_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int rc; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; anon_vma = anon_vma_alloc(); if (!anon_vma) return -ENOMEM; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) { put_anon_vma(anon_vma); return -ENOMEM; } /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ rc = anon_vma_clone(vma, pvma, VMA_OP_FORK); /* An error arose or an existing anon_vma was reused, all done then. */ if (rc || vma->anon_vma) { put_anon_vma(anon_vma); anon_vma_chain_free(avc); return rc; } /* * OK no reuse, so add our own anon_vma. * * Since it is not linked anywhere we can safely manipulate anon_vma * fields without a lock. */ anon_vma->num_active_vmas = 1; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); /* Now let rmap see it. */ anon_vma_lock_write(anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; } /* * In the unfortunate case of anon_vma_clone() failing to allocate memory we * have to clean things up. * * Since we allocate anon_vma_chain's before we insert them into the interval * trees, we simply have to free up the AVC's and remove the entries from the * VMA's anon_vma_chain. */ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { list_del(&avc->same_vma); anon_vma_chain_free(avc); } /* * The anon_vma assigned to this VMA is no longer valid, as we were not * able to correctly clone AVC state. Avoid inconsistent anon_vma tree * state by resetting. */ vma->anon_vma = NULL; } /** * unlink_anon_vmas() - remove all links between a VMA and anon_vma's, freeing * anon_vma_chain objects. * @vma: The VMA whose links to anon_vma objects is to be severed. * * As part of the process anon_vma_chain's are freed, * anon_vma->num_children,num_active_vmas is updated as required and, if the * relevant anon_vma references no further VMAs, its reference count is * decremented. */ void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *active_anon_vma = vma->anon_vma; /* Always hold mmap lock, read-lock on unmap possibly. */ mmap_assert_locked(vma->vm_mm); /* Unfaulted is a no-op. */ if (!active_anon_vma) { VM_WARN_ON_ONCE(!list_empty(&vma->anon_vma_chain)); return; } anon_vma_lock_write(active_anon_vma); /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } active_anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; anon_vma_unlock_write(active_anon_vma); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe folio_mapped() [ hence all those folio_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should hold folio lock when calling this. */ struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, start, end); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { flush_tlb_mm(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibility to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { if (folio_test_anon(folio)) { struct anon_vma *anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !anon_vma || vma->anon_vma->root != anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* KSM folios don't reach here because of the !anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; vm_flags_t vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int ptes = 0, referenced = 0; unsigned int nr; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; nr = 1; if (vma->vm_flags & VM_LOCKED) { ptes++; pra->mapcount--; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) continue; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_maybe_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (pvmw.pte && folio_test_large(folio)) { const unsigned long end_addr = pmd_addr_end(address, vma->vm_end); const unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT; pte_t pteval = ptep_get(pvmw.pte); nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr); } /* * When LRU is switching, we don’t know where the surrounding folios * are. —they could be on active/inactive lists or on MGLRU. So the * simplest approach is to disable this look-around optimization. */ if (lru_gen_enabled() && !lru_gen_switching() && pvmw.pte) { if (lru_gen_look_around(&pvmw, nr)) referenced++; } else if (pvmw.pte) { if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } ptes += nr; pra->mapcount -= nr; /* * If we are sure that we batched the entire folio, * we can just optimize and stop right here. */ if (ptes == pvmw.nr_pages) { page_vma_mapped_walk_done(&pvmw); break; } /* Skip the batched PTEs */ pvmw.pte += nr - 1; pvmw.address += (nr - 1) * PAGE_SIZE; } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, vm_flags_t *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; VM_WARN_ON_ONCE_FOLIO(folio_is_zone_device(folio), folio); *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); /* * PFN swap PTEs, such as device-exclusive ones, that * actually map pages are clean and not writable from a * CPU perspective. The MMU notifier takes care of any * device aspects. */ if (!pte_present(entry)) continue; if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry = pmdp_get(pmd); /* * Please see the comment above (!pte_present). * A non present PMD is not writable from a CPU * perspective. */ if (!pmd_present(entry)) continue; if (!pmd_dirty(entry) && !pmd_write(entry)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); struct wrprotect_file_state { int cleaned; pgoff_t pgoff; unsigned long pfn; unsigned long nr_pages; }; static bool mapping_wrprotect_range_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg; struct page_vma_mapped_walk pvmw = { .pfn = state->pfn, .nr_pages = state->nr_pages, .pgoff = state->pgoff, .vma = vma, .address = address, .flags = PVMW_SYNC, }; state->cleaned += page_vma_mkclean_one(&pvmw); return true; } static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked); /** * mapping_wrprotect_range() - Write-protect all mappings in a specified range. * * @mapping: The mapping whose reverse mapping should be traversed. * @pgoff: The page offset at which @pfn is mapped within @mapping. * @pfn: The PFN of the page mapped in @mapping at @pgoff. * @nr_pages: The number of physically contiguous base pages spanned. * * Traverses the reverse mapping, finding all VMAs which contain a shared * mapping of the pages in the specified range in @mapping, and write-protects * them (that is, updates the page tables to mark the mappings read-only such * that a write protection fault arises when the mappings are written to). * * The @pfn value need not refer to a folio, but rather can reference a kernel * allocation which is mapped into userland. We therefore do not require that * the page maps to a folio with a valid mapping or index field, rather the * caller specifies these in @mapping and @pgoff. * * Return: the number of write-protected PTEs, or an error. */ int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff, unsigned long pfn, unsigned long nr_pages) { struct wrprotect_file_state state = { .cleaned = 0, .pgoff = pgoff, .pfn = pfn, .nr_pages = nr_pages, }; struct rmap_walk_control rwc = { .arg = (void *)&state, .rmap_one = mapping_wrprotect_range_one, .invalid_vma = invalid_mkclean_vma, }; if (!mapping) return 0; __rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc, /* locked = */false); return state.cleaned; } EXPORT_SYMBOL_GPL(mapping_wrprotect_range); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first = 0, nr = 0, nr_pmdmapped = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_add_return_large_mapcount(folio, orig_nr_pages, vma); if (nr == orig_nr_pages) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; folio_add_large_mapcount(folio, orig_nr_pages, vma); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { if (level == PGTABLE_LEVEL_PMD && first) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_inc_return_large_mapcount(folio, vma); if (nr == 1) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); /* * We only track PMD mappings of PMD-sized * folios separately. */ if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } folio_inc_large_mapcount(folio, vma); break; default: BUILD_BUG(); } __folio_mod_stat(folio, nr, nr_pmdmapped); } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += FOLIO_MAPPING_ANON; /* * Ensure that anon_vma and the FOLIO_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the FOLIO_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + FOLIO_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(const struct folio *folio, const struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum pgtable_level level) { int i; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); if (flags & RMAP_EXCLUSIVE) { switch (level) { case PGTABLE_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case PGTABLE_LEVEL_PMD: SetPageAnonExclusive(page); break; case PGTABLE_LEVEL_PUD: /* * Keep the compiler happy, we don't support anonymous * PUD mappings. */ WARN_ON_ONCE(1); break; default: BUILD_BUG(); } } VM_WARN_ON_FOLIO(!folio_test_large(folio) && PageAnonExclusive(page) && atomic_read(&folio->_mapcount) > 0, folio); for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; VM_WARN_ON_FOLIO(folio_test_large(folio) && folio_entire_mapcount(folio) > 1 && PageAnonExclusive(cur_page), folio); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) continue; /* * While PTE-mapping a THP we have a PMD and a PTE * mapping. */ VM_WARN_ON_FOLIO(atomic_read(&cur_page->_mapcount) > 0 && PageAnonExclusive(cur_page), folio); } /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, PGTABLE_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const bool exclusive = flags & RMAP_EXCLUSIVE; int nr = 1, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; nr = folio_large_nr_pages(folio); for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } folio_set_large_mapcount(folio, nr, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, nr); } else { nr = folio_large_nr_pages(folio); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_set_large_mapcount(folio, 1, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } VM_WARN_ON_ONCE(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end); __folio_mod_stat(folio, nr, nr_pmdmapped); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last = 0, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_sub_return_large_mapcount(folio, nr_pages, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = nr < folio_large_nr_pages(folio) && !folio_entire_mapcount(folio); nr = 0; } break; } folio_sub_large_mapcount(folio, nr_pages, vma); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; partially_mapped = nr && atomic_read(mapped); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { last = atomic_add_negative(-1, &folio->_entire_mapcount); if (level == PGTABLE_LEVEL_PMD && last) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_dec_return_large_mapcount(folio, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = last && nr < folio_large_nr_pages(folio); nr = 0; } break; } folio_dec_large_mapcount(folio, vma); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - nr; /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr && nr < nr_pmdmapped; break; default: BUILD_BUG(); } /* * Queue anon large folio for deferred split if at least one page of * the folio is unmapped and at least one page is still mapped. * * Check partially_mapped first to ensure it is a large folio. * * Device private folios do not support deferred splitting and * shrinker based scanning of the folios to free. */ if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio) && !folio_is_device_private(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static inline unsigned int folio_unmap_pte_batch(struct folio *folio, struct page_vma_mapped_walk *pvmw, enum ttu_flags flags, pte_t pte) { unsigned long end_addr, addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; unsigned int max_nr; if (flags & TTU_HWPOISON) return 1; if (!folio_test_large(folio)) return 1; /* We may only batch within a single VMA and a single page table. */ end_addr = pmd_addr_end(addr, vma->vm_end); max_nr = (end_addr - addr) >> PAGE_SHIFT; /* We only support lazyfree or file folios batching for now ... */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) return 1; if (pte_unused(pte)) return 1; if (userfaultfd_wp(vma)) return 1; /* * If unmap fails, we need to restore the ptes. To avoid accidentally * upgrading write permissions for ptes that were not originally * writable, and to avoid losing the soft-dirty bit, use the * appropriate FPB flags. */ return folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr, FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long nr_pages = 1, end_addr; unsigned long pfn; unsigned long hsz = 0; int ptes = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before folio_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { nr_pages = 1; /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { ptes++; /* * Set 'ret' to indicate the page cannot be unmapped. * * Do not jump to walk_abort immediately as additional * iteration might be required to detect fully mapped * folio an mlock it. */ ret = false; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) goto walk_done; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); goto walk_done; } if (!pvmw.pte) { if (folio_test_lazyfree(folio)) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; /* * unmap_huge_pmd_locked has either already marked * the folio as swap-backed or decided to retain it * due to GUP or speculative references. */ goto walk_abort; } if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); /* Nuke the page table entry. */ pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages); /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ if (should_defer_flush(mm, flags)) set_tlb_ubc_flush_pending(mm, pteval, address, end_addr); else flush_tlb_range(vma, address, end_addr); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else { pte_clear(mm, address, pvmw.pte); } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { /* * redirtied either using the page table or a previously * obtained GUP reference. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); folio_set_swapbacked(folio); goto walk_abort; } else if (ref_count != 1 + map_count) { /* * Additional reference. Could be a GUP reference or any * speculative reference. GUP users must mark the folio * dirty if there was a modification. This folio cannot be * reclaimed right now either way, so act just like nothing * happened. * We'll come back here later and detect if the folio was * dirtied when the additional reference is gone. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); goto walk_abort; } add_mm_counter(mm, MM_ANONPAGES, -nr_pages); goto discard; } if (folio_dup_swap(folio, subpage) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (likely(pte_present(pteval))) { if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ add_mm_counter(mm, mm_counter_file(folio), -nr_pages); } discard: if (unlikely(folio_test_hugetlb(folio))) { hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put_refs(folio, nr_pages); /* * If we are sure that we batched the entire folio and cleared * all PTEs, we can just optimize and stop right here. */ if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, writable, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before folio_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* PMD-mapped THP migration entry */ if (!pvmw.pte) { __maybe_unused unsigned long pfn; __maybe_unused pmd_t pmdval; if (flags & TTU_SPLIT_HUGE_PMD) { /* * split_huge_pmd_locked() might leave the * folio mapped through PTEs. Retry the walk * so we can detect this scenario and properly * abort the walk. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, true); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION pmdval = pmdp_get(pvmw.pmd); if (likely(pmd_present(pmdval))) pfn = pmd_pfn(pmdval); else pfn = softleaf_to_pfn(softleaf_from_pmd(pmdval)); subpage = folio_page(folio, pfn - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; #endif } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else if (likely(pte_present(pteval))) { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pte_clear(mm, address, pvmw.pte); writable = softleaf_is_device_private_write(entry); } VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) && !anon_exclusive, folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage)) { VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio); pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else { swp_entry_t entry; pte_t swp_pte; /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (writable) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (likely(pte_present(pteval))) { if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { swp_pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE /** * make_device_exclusive() - Mark a page for exclusive use by a device * @mm: mm_struct of associated target process * @addr: the virtual address to mark for exclusive device access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * @foliop: folio pointer will be stored here on success. * * This function looks up the page mapped at the given address, grabs a * folio reference, locks the folio and replaces the PTE with special * device-exclusive PFN swap entry, preventing access through the process * page tables. The function will return with the folio locked and referenced. * * On fault, the device-exclusive entries are replaced with the original PTE * under folio lock, after calling MMU notifiers. * * Only anonymous non-hugetlb folios are supported and the VMA must have * write permissions such that we can fault in the anonymous page writable * in order to mark it exclusive. The caller must hold the mmap_lock in read * mode. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the folio lock and reference after * which point CPU access to the page will revoke the exclusive access. * * Notes: * #. This function always operates on individual PTEs mapping individual * pages. PMD-sized THPs are first remapped to be mapped by PTEs before * the conversion happens on a single PTE corresponding to @addr. * #. While concurrent access through the process page tables is prevented, * concurrent access through other page references (e.g., earlier GUP * invocation) is not handled and not supported. * #. device-exclusive entries are considered "clean" and "old" by core-mm. * Device drivers must update the folio state when informed by MMU * notifiers. * * Returns: pointer to mapped page on success, otherwise a negative error. */ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, void *owner, struct folio **foliop) { struct mmu_notifier_range range; struct folio *folio, *fw_folio; struct vm_area_struct *vma; struct folio_walk fw; struct page *page; swp_entry_t entry; pte_t swp_pte; int ret; mmap_assert_locked(mm); addr = PAGE_ALIGN_DOWN(addr); /* * Fault in the page writable and try to lock it; note that if the * address would already be marked for exclusive use by a device, * the GUP call would undo that first by triggering a fault. * * If any other device would already map this page exclusively, the * fault will trigger a conversion to an ordinary * (non-device-exclusive) PTE and issue a MMU_NOTIFY_EXCLUSIVE. */ retry: page = get_user_page_vma_remote(mm, addr, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, &vma); if (IS_ERR(page)) return page; folio = page_folio(page); if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) { folio_put(folio); return ERR_PTR(-EOPNOTSUPP); } ret = folio_lock_killable(folio); if (ret) { folio_put(folio); return ERR_PTR(ret); } /* * Inform secondary MMUs that we are going to convert this PTE to * device-exclusive, such that they unmap it now. Note that the * caller must filter this event out to prevent livelocks. */ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, mm, addr, addr + PAGE_SIZE, owner); mmu_notifier_invalidate_range_start(&range); /* * Let's do a second walk and make sure we still find the same page * mapped writable. Note that any page of an anonymous folio can * only be mapped writable using exactly one PTE ("exclusive"), so * there cannot be other mappings. */ fw_folio = folio_walk_start(&fw, vma, addr, 0); if (fw_folio != folio || fw.page != page || fw.level != FW_LEVEL_PTE || !pte_write(fw.pte)) { if (fw_folio) folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); folio_unlock(folio); folio_put(folio); goto retry; } /* Nuke the page table entry so we get the uptodate dirty bit. */ flush_cache_page(vma, addr, page_to_pfn(page)); fw.pte = ptep_clear_flush(vma, addr, fw.ptep); /* Set the dirty flag on the folio now the PTE is gone. */ if (pte_dirty(fw.pte)) folio_mark_dirty(folio); /* * Store the pfn of the page in a special device-exclusive PFN swap PTE. * do_swap_page() will trigger the conversion back while holding the * folio lock. */ entry = make_device_exclusive_entry(page_to_pfn(page)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(fw.pte)) swp_pte = pte_swp_mksoft_dirty(swp_pte); /* The pte is writable, uffd-wp does not apply. */ set_pte_at(mm, addr, fw.ptep, swp_pte); folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); *foliop = folio; return page; } EXPORT_SYMBOL_GPL(make_device_exclusive); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on folio_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; /* * The folio lock ensures that folio->mapping can't be changed under us * to an anon_vma with different root. */ VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /** * __rmap_walk_file() - Traverse the reverse mapping for a file-backed mapping * of a page mapped within a specified page cache object at a specified offset. * * @folio: Either the folio whose mappings to traverse, or if NULL, * the callbacks specified in @rwc will be configured such * as to be able to look up mappings correctly. * @mapping: The page cache object whose mapping VMAs we intend to * traverse. If @folio is non-NULL, this should be equal to * folio_mapping(folio). * @pgoff_start: The offset within @mapping of the page which we are * looking up. If @folio is non-NULL, this should be equal * to folio_pgoff(folio). * @nr_pages: The number of pages mapped by the mapping. If @folio is * non-NULL, this should be equal to folio_nr_pages(folio). * @rwc: The reverse mapping walk control object describing how * the traversal should proceed. * @locked: Is the @mapping already locked? If not, we acquire the * lock. */ static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked) { pgoff_t pgoff_end = pgoff_start + nr_pages - 1; struct vm_area_struct *vma; VM_WARN_ON_FOLIO(folio && mapping != folio_mapping(folio), folio); VM_WARN_ON_FOLIO(folio && pgoff_start != folio_pgoff(folio), folio); VM_WARN_ON_FOLIO(folio && nr_pages != folio_nr_pages(folio), folio); if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, nr_pages); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { /* * The folio lock not only makes sure that folio->mapping cannot * suddenly be NULLified by truncation, it makes sure that the structure * at mapping cannot be freed and reused yet, so we can safely take * mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio->mapping) return; __rmap_walk_file(folio, folio->mapping, folio->index, folio_nr_pages(folio), rwc, locked); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 19 591 592 19 19 19 200 200 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | // SPDX-License-Identifier: GPL-2.0 #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { ASSERT_RTNL(); info->family = AF_INET; /* Paired with READ_ONCE() in fib4_seq_read() */ WRITE_ONCE(net->ipv4.fib_seq, net->ipv4.fib_seq + 1); return call_fib_notifiers(net, event_type, info); } static unsigned int fib4_seq_read(const struct net *net) { /* Paired with WRITE_ONCE() in call_fib4_notifiers() */ return READ_ONCE(net->ipv4.fib_seq) + fib4_rules_seq_read(net); } static int fib4_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; err = fib4_rules_dump(net, nb, extack); if (err) return err; return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { .family = AF_INET, .fib_seq_read = fib4_seq_read, .fib_dump = fib4_dump, .owner = THIS_MODULE, }; int __net_init fib4_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.fib_seq = 0; ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.notifier_ops = ops; return 0; } void __net_exit fib4_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.notifier_ops); } |
| 2 14 14 15 14 1 13 2 7 7 3 3 10 12 12 6 2 15 16 7 9 12 11 6 12 17 21 21 3 17 22 1 1 1 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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-only #include <linux/module.h> #include <linux/sock_diag.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/packet_diag.h> #include <linux/percpu.h> #include <net/net_namespace.h> #include <net/sock.h> #include "internal.h" static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb) { struct packet_diag_info pinfo; pinfo.pdi_index = po->ifindex; pinfo.pdi_version = po->tp_version; pinfo.pdi_reserve = po->tp_reserve; pinfo.pdi_copy_thresh = READ_ONCE(po->copy_thresh); pinfo.pdi_tstamp = READ_ONCE(po->tp_tstamp); pinfo.pdi_flags = 0; if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) pinfo.pdi_flags |= PDI_RUNNING; if (packet_sock_flag(po, PACKET_SOCK_AUXDATA)) pinfo.pdi_flags |= PDI_AUXDATA; if (packet_sock_flag(po, PACKET_SOCK_ORIGDEV)) pinfo.pdi_flags |= PDI_ORIGDEV; if (READ_ONCE(po->vnet_hdr_sz)) pinfo.pdi_flags |= PDI_VNETHDR; if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) pinfo.pdi_flags |= PDI_LOSS; return nla_put(nlskb, PACKET_DIAG_INFO, sizeof(pinfo), &pinfo); } static int pdiag_put_mclist(const struct packet_sock *po, struct sk_buff *nlskb) { struct nlattr *mca; struct packet_mclist *ml; mca = nla_nest_start_noflag(nlskb, PACKET_DIAG_MCLIST); if (!mca) return -EMSGSIZE; rtnl_lock(); for (ml = po->mclist; ml; ml = ml->next) { struct packet_diag_mclist *dml; dml = nla_reserve_nohdr(nlskb, sizeof(*dml)); if (!dml) { rtnl_unlock(); nla_nest_cancel(nlskb, mca); return -EMSGSIZE; } dml->pdmc_index = ml->ifindex; dml->pdmc_type = ml->type; dml->pdmc_alen = ml->alen; dml->pdmc_count = ml->count; BUILD_BUG_ON(sizeof(dml->pdmc_addr) != sizeof(ml->addr)); memcpy(dml->pdmc_addr, ml->addr, sizeof(ml->addr)); } rtnl_unlock(); nla_nest_end(nlskb, mca); return 0; } static int pdiag_put_ring(struct packet_ring_buffer *ring, int ver, int nl_type, struct sk_buff *nlskb) { struct packet_diag_ring pdr; if (!ring->pg_vec) return 0; pdr.pdr_block_size = ring->pg_vec_pages << PAGE_SHIFT; pdr.pdr_block_nr = ring->pg_vec_len; pdr.pdr_frame_size = ring->frame_size; pdr.pdr_frame_nr = ring->frame_max + 1; if (ver > TPACKET_V2) { pdr.pdr_retire_tmo = ktime_to_ms(ring->prb_bdqc.interval_ktime); pdr.pdr_sizeof_priv = ring->prb_bdqc.blk_sizeof_priv; pdr.pdr_features = ring->prb_bdqc.feature_req_word; } else { pdr.pdr_retire_tmo = 0; pdr.pdr_sizeof_priv = 0; pdr.pdr_features = 0; } return nla_put(nlskb, nl_type, sizeof(pdr), &pdr); } static int pdiag_put_rings_cfg(struct packet_sock *po, struct sk_buff *skb) { int ret; mutex_lock(&po->pg_vec_lock); ret = pdiag_put_ring(&po->rx_ring, po->tp_version, PACKET_DIAG_RX_RING, skb); if (!ret) ret = pdiag_put_ring(&po->tx_ring, po->tp_version, PACKET_DIAG_TX_RING, skb); mutex_unlock(&po->pg_vec_lock); return ret; } static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) { int ret = 0; mutex_lock(&fanout_mutex); if (po->fanout) { u32 val; val = (u32)po->fanout->id | ((u32)po->fanout->type << 16); ret = nla_put_u32(nlskb, PACKET_DIAG_FANOUT, val); } mutex_unlock(&fanout_mutex); return ret; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, bool may_report_filterinfo, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, u64 sk_ino) { struct nlmsghdr *nlh; struct packet_diag_msg *rp; struct packet_sock *po = pkt_sk(sk); nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rp), flags); if (!nlh) return -EMSGSIZE; rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); if ((req->pdiag_show & PACKET_SHOW_INFO) && pdiag_put_info(po, skb)) goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_INFO) && nla_put_u32(skb, PACKET_DIAG_UID, from_kuid_munged(user_ns, sk_uid(sk)))) goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_MCLIST) && pdiag_put_mclist(po, skb)) goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_RING_CFG) && pdiag_put_rings_cfg(po, skb)) goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_FANOUT) && pdiag_put_fanout(po, skb)) goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_MEMINFO) && sock_diag_put_meminfo(sk, skb, PACKET_DIAG_MEMINFO)) goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_FILTER) && sock_diag_put_filterinfo(may_report_filterinfo, sk, skb, PACKET_DIAG_FILTER)) goto out_nlmsg_trim; nlmsg_end(skb, nlh); return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { int num = 0, s_num = cb->args[0]; struct packet_diag_req *req; struct net *net; struct sock *sk; bool may_report_filterinfo; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN); mutex_lock(&net->packet.sklist_lock); sk_for_each(sk, &net->packet.sklist) { if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next; if (sk_diag_fill(sk, skb, req, may_report_filterinfo, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, sock_i_ino(sk)) < 0) goto done; next: num++; } done: mutex_unlock(&net->packet.sklist_lock); cb->args[0] = num; return skb->len; } static int packet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct packet_diag_req); struct net *net = sock_net(skb->sk); struct packet_diag_req *req; if (nlmsg_len(h) < hdrlen) return -EINVAL; req = nlmsg_data(h); /* Make it possible to support protocol filtering later */ if (req->sdiag_protocol) return -EINVAL; if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = packet_diag_dump, }; return netlink_dump_start(net->diag_nlsk, skb, h, &c); } else return -EOPNOTSUPP; } static const struct sock_diag_handler packet_diag_handler = { .owner = THIS_MODULE, .family = AF_PACKET, .dump = packet_diag_handler_dump, }; static int __init packet_diag_init(void) { return sock_diag_register(&packet_diag_handler); } static void __exit packet_diag_exit(void) { sock_diag_unregister(&packet_diag_handler); } module_init(packet_diag_init); module_exit(packet_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("PACKET socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 17 /* AF_PACKET */); |
| 429 17 425 12 415 248 178 12 2 417 165 1813 12 67 67 39 12 220 225 418 421 177 255 12 7 410 420 178 409 402 1 6 5 2 220 126 220 283 425 423 165 258 12 412 107 107 107 426 12 416 166 261 411 107 251 178 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/gen_stats.c * * Authors: Thomas Graf <tgraf@suug.ch> * Jamal Hadi Salim * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * See Documentation/networking/gen_stats.rst */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/socket.h> #include <linux/rtnetlink.h> #include <linux/gen_stats.h> #include <net/netlink.h> #include <net/gen_stats.h> #include <net/sch_generic.h> static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size, int padattr) { if (nla_put_64bit(d->skb, type, size, buf, padattr)) goto nla_put_failure; return 0; nla_put_failure: if (d->lock) spin_unlock_bh(d->lock); kfree(d->xstats); d->xstats = NULL; d->xstats_len = 0; return -1; } /** * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode * @skb: socket buffer to put statistics TLVs into * @type: TLV type for top level statistic TLV * @tc_stats_type: TLV type for backward compatibility struct tc_stats TLV * @xstats_type: TLV type for backward compatibility xstats TLV * @lock: statistics lock * @d: dumping handle * @padattr: padding attribute * * Initializes the dumping handle, grabs the statistic lock and appends * an empty TLV header to the socket buffer for use a container for all * other statistic TLVS. * * The dumping handle is marked to be in backward compatibility mode telling * all gnet_stats_copy_XXX() functions to fill a local copy of struct tc_stats. * * Returns 0 on success or -1 if the room in the socket buffer was not sufficient. */ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, int xstats_type, spinlock_t *lock, struct gnet_dump *d, int padattr) __acquires(lock) { memset(d, 0, sizeof(*d)); if (type) d->tail = (struct nlattr *)skb_tail_pointer(skb); d->skb = skb; d->compat_tc_stats = tc_stats_type; d->compat_xstats = xstats_type; d->padattr = padattr; if (lock) { d->lock = lock; spin_lock_bh(lock); } if (d->tail) { int ret = gnet_stats_copy(d, type, NULL, 0, padattr); /* The initial attribute added in gnet_stats_copy() may be * preceded by a padding attribute, in which case d->tail will * end up pointing at the padding instead of the real attribute. * Fix this so gnet_stats_finish_copy() adjusts the length of * the right attribute. */ if (ret == 0 && d->tail->nla_type == padattr) d->tail = (struct nlattr *)((char *)d->tail + NLA_ALIGN(d->tail->nla_len)); return ret; } return 0; } EXPORT_SYMBOL(gnet_stats_start_copy_compat); /** * gnet_stats_start_copy - start dumping procedure in compatibility mode * @skb: socket buffer to put statistics TLVs into * @type: TLV type for top level statistic TLV * @lock: statistics lock * @d: dumping handle * @padattr: padding attribute * * Initializes the dumping handle, grabs the statistic lock and appends * an empty TLV header to the socket buffer for use a container for all * other statistic TLVS. * * Returns 0 on success or -1 if the room in the socket buffer was not sufficient. */ int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr) { return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d, padattr); } EXPORT_SYMBOL(gnet_stats_start_copy); /* Must not be inlined, due to u64_stats seqcount_t lockdep key */ void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b) { u64_stats_set(&b->bytes, 0); u64_stats_set(&b->packets, 0); u64_stats_init(&b->syncp); } EXPORT_SYMBOL(gnet_stats_basic_sync_init); static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, const struct gnet_stats_basic_sync __percpu *cpu) { u64 t_bytes = 0, t_packets = 0; int i; for_each_possible_cpu(i) { const struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); unsigned int start; u64 bytes, packets; do { start = u64_stats_fetch_begin(&bcpu->syncp); bytes = u64_stats_read(&bcpu->bytes); packets = u64_stats_read(&bcpu->packets); } while (u64_stats_fetch_retry(&bcpu->syncp, start)); t_bytes += bytes; t_packets += packets; } _bstats_update(bstats, t_bytes, t_packets); } void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, const struct gnet_stats_basic_sync __percpu *cpu, const struct gnet_stats_basic_sync *b, bool running) { unsigned int start; u64 bytes = 0; u64 packets = 0; WARN_ON_ONCE((cpu || running) && in_hardirq()); if (cpu) { gnet_stats_add_basic_cpu(bstats, cpu); return; } do { if (running) start = u64_stats_fetch_begin(&b->syncp); bytes = u64_stats_read(&b->bytes); packets = u64_stats_read(&b->packets); } while (running && u64_stats_fetch_retry(&b->syncp, start)); _bstats_update(bstats, bytes, packets); } EXPORT_SYMBOL(gnet_stats_add_basic); static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, const struct gnet_stats_basic_sync __percpu *cpu, const struct gnet_stats_basic_sync *b, bool running) { unsigned int start; if (cpu) { u64 t_bytes = 0, t_packets = 0; int i; for_each_possible_cpu(i) { const struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); u64 bytes, packets; do { start = u64_stats_fetch_begin(&bcpu->syncp); bytes = u64_stats_read(&bcpu->bytes); packets = u64_stats_read(&bcpu->packets); } while (u64_stats_fetch_retry(&bcpu->syncp, start)); t_bytes += bytes; t_packets += packets; } *ret_bytes = t_bytes; *ret_packets = t_packets; return; } do { if (running) start = u64_stats_fetch_begin(&b->syncp); *ret_bytes = u64_stats_read(&b->bytes); *ret_packets = u64_stats_read(&b->packets); } while (running && u64_stats_fetch_retry(&b->syncp, start)); } static int ___gnet_stats_copy_basic(struct gnet_dump *d, const struct gnet_stats_basic_sync __percpu *cpu, const struct gnet_stats_basic_sync *b, int type, bool running) { u64 bstats_bytes, bstats_packets; gnet_stats_read_basic(&bstats_bytes, &bstats_packets, cpu, b, running); if (d->compat_tc_stats && type == TCA_STATS_BASIC) { d->tc_stats.bytes = bstats_bytes; d->tc_stats.packets = bstats_packets; } if (d->tail) { struct gnet_stats_basic sb; int res; memset(&sb, 0, sizeof(sb)); sb.bytes = bstats_bytes; sb.packets = bstats_packets; res = gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD); if (res < 0 || sb.packets == bstats_packets) return res; /* emit 64bit stats only if needed */ return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats_packets, sizeof(bstats_packets), TCA_STATS_PAD); } return 0; } /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics * @running: true if @b represents a running qdisc, thus @b's * internal values might change during basic reads. * Only used if @cpu is NULL * * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_basic(struct gnet_dump *d, const struct gnet_stats_basic_sync __percpu *cpu, const struct gnet_stats_basic_sync *b, bool running) { return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC, running); } EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics * @running: true if @b represents a running qdisc, thus @b's * internal values might change during basic reads. * Only used if @cpu is NULL * * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_basic_hw(struct gnet_dump *d, const struct gnet_stats_basic_sync __percpu *cpu, const struct gnet_stats_basic_sync *b, bool running) { return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC_HW, running); } EXPORT_SYMBOL(gnet_stats_copy_basic_hw); /** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV * @d: dumping handle * @rate_est: rate estimator * * Appends the rate estimator statistics to the top level TLV created by * gnet_stats_start_copy(). * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **rate_est) { struct gnet_stats_rate_est64 sample; struct gnet_stats_rate_est est; int res; if (!gen_estimator_read(rate_est, &sample)) return 0; est.bps = min_t(u64, UINT_MAX, sample.bps); /* we have some time before reaching 2^32 packets per second */ est.pps = sample.pps; if (d->compat_tc_stats) { d->tc_stats.bps = est.bps; d->tc_stats.pps = est.pps; } if (d->tail) { res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est), TCA_STATS_PAD); if (res < 0 || est.bps == sample.bps) return res; /* emit 64bit stats only if needed */ return gnet_stats_copy(d, TCA_STATS_RATE_EST64, &sample, sizeof(sample), TCA_STATS_PAD); } return 0; } EXPORT_SYMBOL(gnet_stats_copy_rate_est); static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats, const struct gnet_stats_queue __percpu *q) { int i; for_each_possible_cpu(i) { const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i); qstats->qlen += READ_ONCE(qcpu->qlen); qstats->backlog += READ_ONCE(qcpu->backlog); qstats->drops += READ_ONCE(qcpu->drops); qstats->requeues += READ_ONCE(qcpu->requeues); qstats->overlimits += READ_ONCE(qcpu->overlimits); } } void gnet_stats_add_queue(struct gnet_stats_queue *qstats, const struct gnet_stats_queue __percpu *cpu, const struct gnet_stats_queue *q) { if (cpu) { gnet_stats_add_queue_cpu(qstats, cpu); } else { qstats->qlen += READ_ONCE(q->qlen); qstats->backlog += READ_ONCE(q->backlog); qstats->drops += READ_ONCE(q->drops); qstats->requeues += READ_ONCE(q->requeues); qstats->overlimits += READ_ONCE(q->overlimits); } } EXPORT_SYMBOL(gnet_stats_add_queue); /** * gnet_stats_copy_queue - copy queue statistics into statistics TLV * @d: dumping handle * @cpu_q: per cpu queue statistics * @q: queue statistics * @qlen: queue length statistics * * Appends the queue statistics to the top level TLV created by * gnet_stats_start_copy(). Using per cpu queue statistics if * they are available. * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_queue(struct gnet_dump *d, const struct gnet_stats_queue __percpu *cpu_q, const struct gnet_stats_queue *q, __u32 qlen) { struct gnet_stats_queue qstats = {0}; gnet_stats_add_queue(&qstats, cpu_q, q); qstats.qlen = qlen; if (d->compat_tc_stats) { d->tc_stats.drops = qstats.drops; d->tc_stats.qlen = qstats.qlen; d->tc_stats.backlog = qstats.backlog; d->tc_stats.overlimits = qstats.overlimits; } if (d->tail) return gnet_stats_copy(d, TCA_STATS_QUEUE, &qstats, sizeof(qstats), TCA_STATS_PAD); return 0; } EXPORT_SYMBOL(gnet_stats_copy_queue); /** * gnet_stats_copy_app - copy application specific statistics into statistics TLV * @d: dumping handle * @st: application specific statistics data * @len: length of data * * Appends the application specific statistics to the top level TLV created by * gnet_stats_start_copy() and remembers the data for XSTATS if the dumping * handle is in backward compatibility mode. * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) { if (d->compat_xstats) { d->xstats = kmemdup(st, len, GFP_ATOMIC); if (!d->xstats) goto err_out; d->xstats_len = len; } if (d->tail) return gnet_stats_copy(d, TCA_STATS_APP, st, len, TCA_STATS_PAD); return 0; err_out: if (d->lock) spin_unlock_bh(d->lock); d->xstats_len = 0; return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); /** * gnet_stats_finish_copy - finish dumping procedure * @d: dumping handle * * Corrects the length of the top level TLV to include all TLVs added * by gnet_stats_copy_XXX() calls. Adds the backward compatibility TLVs * if gnet_stats_start_copy_compat() was used and releases the statistics * lock. * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_finish_copy(struct gnet_dump *d) { if (d->tail) d->tail->nla_len = skb_tail_pointer(d->skb) - (u8 *)d->tail; if (d->compat_tc_stats) if (gnet_stats_copy(d, d->compat_tc_stats, &d->tc_stats, sizeof(d->tc_stats), d->padattr) < 0) return -1; if (d->compat_xstats && d->xstats) { if (gnet_stats_copy(d, d->compat_xstats, d->xstats, d->xstats_len, d->padattr) < 0) return -1; } if (d->lock) spin_unlock_bh(d->lock); kfree(d->xstats); d->xstats = NULL; d->xstats_len = 0; return 0; } EXPORT_SYMBOL(gnet_stats_finish_copy); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TTY_BUFFER_H #define _LINUX_TTY_BUFFER_H #include <linux/atomic.h> #include <linux/llist.h> #include <linux/mutex.h> #include <linux/workqueue.h> struct tty_buffer { union { struct tty_buffer *next; struct llist_node free; }; unsigned int used; unsigned int size; unsigned int commit; unsigned int lookahead; /* Lazy update on recv, can become less than "read" */ unsigned int read; bool flags; /* Data points here */ u8 data[] __aligned(sizeof(unsigned long)); }; static inline u8 *char_buf_ptr(struct tty_buffer *b, unsigned int ofs) { return b->data + ofs; } static inline u8 *flag_buf_ptr(struct tty_buffer *b, unsigned int ofs) { return char_buf_ptr(b, ofs) + b->size; } struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct workqueue_struct *flip_wq; struct work_struct work; struct mutex lock; atomic_t priority; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t mem_used; /* In-use buffers excluding free list */ int mem_limit; struct tty_buffer *tail; /* Active buffer */ }; /* * When a break, frame error, or parity error happens, these codes are * stuffed into the flags buffer. */ #define TTY_NORMAL 0 #define TTY_BREAK 1 #define TTY_FRAME 2 #define TTY_PARITY 3 #define TTY_OVERRUN 4 #endif |
| 37 20 9 12 12 1 12 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 | #ifndef __LINUX_MROUTE_BASE_H #define __LINUX_MROUTE_BASE_H #include <linux/netdevice.h> #include <linux/rhashtable-types.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> /** * struct vif_device - interface representor for multicast routing * @dev: network device being used * @dev_tracker: refcount tracker for @dev reference * @bytes_in: statistic; bytes ingressing * @bytes_out: statistic; bytes egresing * @pkt_in: statistic; packets ingressing * @pkt_out: statistic; packets egressing * @rate_limit: Traffic shaping (NI) * @threshold: TTL threshold * @flags: Control flags * @link: Physical interface index * @dev_parent_id: device parent id * @local: Local address * @remote: Remote address for tunnels */ struct vif_device { struct net_device __rcu *dev; netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; unsigned long rate_limit; unsigned char threshold; unsigned short flags; int link; /* Currently only used by ipmr */ struct netdev_phys_item_id dev_parent_id; __be32 local, remote; }; struct vif_entry_notifier_info { struct fib_notifier_info info; struct net_device *dev; unsigned short vif_index; unsigned short vif_flags; u32 tb_id; }; static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, .extack = extack, }, .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, }; return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, atomic_t *ipmr_seq) { struct vif_entry_notifier_info info = { .info = { .family = family, }, .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, }; ASSERT_RTNL(); atomic_inc(ipmr_seq); return call_fib_notifiers(net, event_type, &info.info); } #ifndef MAXVIFS /* This one is nasty; value is defined in uapi using different symbols for * mroute and morute6 but both map into same 32. */ #define MAXVIFS 32 #endif /* Note: This helper is deprecated. */ #define VIF_EXISTS(_mrt, _idx) (!!rcu_access_pointer((_mrt)->vif_table[_idx].dev)) /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) * MFC_OFFLOAD - the entry was offloaded to the hardware */ enum { MFC_STATIC = BIT(0), MFC_OFFLOAD = BIT(1), }; /** * struct mr_mfc - common multicast routing entries * @mnode: rhashtable list * @mfc_parent: source interface (iif) * @mfc_flags: entry flags * @expires: unresolved entry expire time * @unresolved: unresolved cached skbs * @last_assert: time of last assert * @minvif: minimum VIF id * @maxvif: maximum VIF id * @bytes: bytes that have passed for this entry * @pkt: packets that have passed for this entry * @wrong_if: number of wrong source interface hits * @lastuse: time of last use of the group (traffic or update) * @ttls: OIF TTL threshold array * @refcount: reference count for this entry * @list: global entry list * @rcu: used for entry destruction * @free: Operation used for freeing an entry under RCU */ struct mr_mfc { struct rhlist_head mnode; unsigned short mfc_parent; int mfc_flags; union { struct { unsigned long expires; struct sk_buff_head unresolved; } unres; struct { unsigned long last_assert; int minvif; int maxvif; atomic_long_t bytes; atomic_long_t pkt; atomic_long_t wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; refcount_t refcount; } res; } mfc_un; struct list_head list; struct rcu_head rcu; void (*free)(struct rcu_head *head); }; static inline void mr_cache_put(struct mr_mfc *c) { if (refcount_dec_and_test(&c->mfc_un.res.refcount)) call_rcu(&c->rcu, c->free); } static inline void mr_cache_hold(struct mr_mfc *c) { refcount_inc(&c->mfc_un.res.refcount); } struct mfc_entry_notifier_info { struct fib_notifier_info info; struct mr_mfc *mfc; u32 tb_id; }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id, struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, .extack = extack, }, .mfc = mfc, .tb_id = tb_id }; return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id, atomic_t *ipmr_seq) { struct mfc_entry_notifier_info info = { .info = { .family = family, }, .mfc = mfc, .tb_id = tb_id }; atomic_inc(ipmr_seq); return call_fib_notifiers(net, event_type, &info.info); } struct mr_table; /** * struct mr_table_ops - callbacks and info for protocol-specific ops * @rht_params: parameters for accessing the MFC hash * @cmparg_any: a hash key to be used for matching on (*,*) routes */ struct mr_table_ops { const struct rhashtable_params *rht_params; void *cmparg_any; }; /** * struct mr_table - a multicast routing table * @work: used for table destruction * @list: entry within a list of multicast routing tables * @net: net where this table belongs * @ops: protocol specific operations * @id: identifier of the table * @mroute_sk: socket associated with the table * @ipmr_expire_timer: timer for handling unresolved routes * @mfc_unres_queue: list of unresolved MFC entries * @vif_table: array containing all possible vifs * @mfc_hash: Hash table of all resolved routes for easy lookup * @mfc_cache_list: list of resovled routes for possible traversal * @maxvif: Identifier of highest value vif currently in use * @cache_resolve_queue_len: current size of unresolved queue * @mroute_do_assert: Whether to inform userspace on wrong ingress * @mroute_do_pim: Whether to receive IGMP PIMv1 * @mroute_reg_vif_num: PIM-device vif index */ struct mr_table { struct rcu_work work; struct list_head list; possible_net_t net; struct mr_table_ops ops; u32 id; struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; struct vif_device vif_table[MAXVIFS]; struct rhltable mfc_hash; struct list_head mfc_cache_list; int maxvif; u32 cache_resolve_queue_len; bool mroute_do_assert; bool mroute_do_pim; bool mroute_do_wrvifwhole; int mroute_reg_vif_num; }; static inline bool mr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } #ifdef CONFIG_IP_MROUTE_COMMON void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask); void mr_table_free(struct mr_table *mrt); struct mr_table * mr_table_alloc(struct net *net, u32 id, struct mr_table_ops *ops, void (*expire_func)(struct timer_list *t), void (*table_set)(struct mr_table *mrt, struct net *net)); /* These actually return 'struct mr_mfc *', but to avoid need for explicit * castings they simply return void. */ void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent); void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi); void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm); int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, struct netlink_callback *cb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask) { } static inline void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) { return NULL; } static inline void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi) { return NULL; } static inline struct mr_mfc *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg) { return NULL; } static inline int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm) { return -EINVAL; } static inline int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter) { return -EINVAL; } static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack) { return -EINVAL; } #endif static inline void *mr_mfc_find(struct mr_table *mrt, void *hasharg) { return mr_mfc_find_parent(mrt, hasharg, -1); } #ifdef CONFIG_PROC_FS struct mr_vif_iter { struct seq_net_private p; struct mr_table *mrt; int ct; }; struct mr_mfc_iter { struct seq_net_private p; struct mr_table *mrt; struct list_head *cache; /* Lock protecting the mr_table's unresolved queue */ spinlock_t *lock; }; #ifdef CONFIG_IP_MROUTE_COMMON void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos); void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos); static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) { return *pos ? mr_vif_seq_idx(seq_file_net(seq), seq->private, *pos - 1) : SEQ_START_TOKEN; } /* These actually return 'struct mr_mfc *', but to avoid need for explicit * castings they simply return void. */ void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos); void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos); static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, struct mr_table *mrt, spinlock_t *lock) { struct mr_mfc_iter *it = seq->private; it->mrt = mrt; it->cache = NULL; it->lock = lock; return *pos ? mr_mfc_seq_idx(seq_file_net(seq), seq->private, *pos - 1) : SEQ_START_TOKEN; } static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) { struct mr_mfc_iter *it = seq->private; struct mr_table *mrt = it->mrt; if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(it->lock); else if (it->cache == &mrt->mfc_cache_list) rcu_read_unlock(); } #else static inline void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos) { return NULL; } static inline void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return NULL; } static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) { return NULL; } static inline void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos) { return NULL; } static inline void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return NULL; } static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, struct mr_table *mrt, spinlock_t *lock) { return NULL; } static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) { } #endif #endif #endif |
| 1670 7769 7621 127 1669 1669 7781 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Latched RB-trees * * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> * * Since RB-trees have non-atomic modifications they're not immediately suited * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for * lockless lookups; we cannot guarantee they return a correct result. * * The simplest solution is a seqlock + RB-tree, this will allow lockless * lookups; but has the constraint (inherent to the seqlock) that read sides * cannot nest in write sides. * * If we need to allow unconditional lookups (say as required for NMI context * usage) we need a more complex setup; this data structure provides this by * employing the latch technique -- see @write_seqcount_latch_begin -- to * implement a latched RB-tree which does allow for unconditional lookups by * virtue of always having (at least) one stable copy of the tree. * * However, while we have the guarantee that there is at all times one stable * copy, this does not guarantee an iteration will not observe modifications. * What might have been a stable copy at the start of the iteration, need not * remain so for the duration of the iteration. * * Therefore, this does require a lockless RB-tree iteration to be non-fatal; * see the comment in lib/rbtree.c. Note however that we only require the first * condition -- not seeing partial stores -- because the latch thing isolates * us from loops. If we were to interrupt a modification the lookup would be * pointed at the stable tree and complete while the modification was halted. */ #ifndef RB_TREE_LATCH_H #define RB_TREE_LATCH_H #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/rcupdate.h> struct latch_tree_node { struct rb_node node[2]; }; struct latch_tree_root { seqcount_latch_t seq; struct rb_root tree[2]; }; /** * latch_tree_ops - operators to define the tree order * @less: used for insertion; provides the (partial) order between two elements. * @comp: used for lookups; provides the order between the search key and an element. * * The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * latch_tree_find(). */ struct latch_tree_ops { bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); int (*comp)(void *key, struct latch_tree_node *b); }; static __always_inline struct latch_tree_node * __lt_from_rb(struct rb_node *node, int idx) { return container_of(node, struct latch_tree_node, node[idx]); } static __always_inline void __lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) { struct rb_root *root = <r->tree[idx]; struct rb_node **link = &root->rb_node; struct rb_node *node = <n->node[idx]; struct rb_node *parent = NULL; struct latch_tree_node *ltp; while (*link) { parent = *link; ltp = __lt_from_rb(parent, idx); if (less(ltn, ltp)) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node_rcu(node, parent, link); rb_insert_color(node, root); } static __always_inline void __lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) { rb_erase(<n->node[idx], <r->tree[idx]); } static __always_inline struct latch_tree_node * __lt_find(void *key, struct latch_tree_root *ltr, int idx, int (*comp)(void *key, struct latch_tree_node *node)) { struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); struct latch_tree_node *ltn; int c; while (node) { ltn = __lt_from_rb(node, idx); c = comp(key, ltn); if (c < 0) node = rcu_dereference_raw(node->rb_left); else if (c > 0) node = rcu_dereference_raw(node->rb_right); else return ltn; } return NULL; } /** * latch_tree_insert() - insert @node into the trees @root * @node: nodes to insert * @root: trees to insert @node into * @ops: operators defining the node order * * It inserts @node into @root in an ordered fashion such that we can always * observe one complete tree. See the comment for write_seqcount_latch_begin(). * * The inserts use rcu_assign_pointer() to publish the element such that the * tree structure is stored before we can observe the new @node. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_insert(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { write_seqcount_latch_begin(&root->seq); __lt_insert(node, root, 0, ops->less); write_seqcount_latch(&root->seq); __lt_insert(node, root, 1, ops->less); write_seqcount_latch_end(&root->seq); } /** * latch_tree_erase() - removes @node from the trees @root * @node: nodes to remote * @root: trees to remove @node from * @ops: operators defining the node order * * Removes @node from the trees @root in an ordered fashion such that we can * always observe one complete tree. See the comment for * write_seqcount_latch_begin(). * * It is assumed that @node will observe one RCU quiescent state before being * reused of freed. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_erase(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { write_seqcount_latch_begin(&root->seq); __lt_erase(node, root, 0); write_seqcount_latch(&root->seq); __lt_erase(node, root, 1); write_seqcount_latch_end(&root->seq); } /** * latch_tree_find() - find the node matching @key in the trees @root * @key: search key * @root: trees to search for @key * @ops: operators defining the node order * * Does a lockless lookup in the trees @root for the node matching @key. * * It is assumed that this is called while holding the appropriate RCU read * side lock. * * If the operators define a partial order on the elements (there are multiple * elements which have the same key value) it is undefined which of these * elements will be found. Nor is it possible to iterate the tree to find * further elements with the same key value. * * Returns: a pointer to the node matching @key or NULL. */ static __always_inline struct latch_tree_node * latch_tree_find(void *key, struct latch_tree_root *root, const struct latch_tree_ops *ops) { struct latch_tree_node *node; unsigned int seq; do { seq = read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } #endif /* RB_TREE_LATCH_H */ |
| 21 18 7 21 9 12 12 12 11 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 | // SPDX-License-Identifier: GPL-2.0 /* * Provide a default dump_stack() function for architectures * which don't implement their own. */ #include <linux/kernel.h> #include <linux/buildid.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/smp.h> #include <linux/atomic.h> #include <linux/kexec.h> #include <linux/utsname.h> #include <linux/stop_machine.h> static char dump_stack_arch_desc_str[128]; /** * dump_stack_set_arch_desc - set arch-specific str to show with task dumps * @fmt: printf-style format string * @...: arguments for the format string * * The configured string will be printed right after utsname during task * dumps. Usually used to add arch-specific system identifiers. If an * arch wants to make use of such an ID string, it should initialize this * as soon as possible during boot. */ void __init dump_stack_set_arch_desc(const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(dump_stack_arch_desc_str, sizeof(dump_stack_arch_desc_str), fmt, args); va_end(args); } #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) #define BUILD_ID_FMT " %20phN" #define BUILD_ID_VAL vmlinux_build_id #else #define BUILD_ID_FMT "%s" #define BUILD_ID_VAL "" #endif /** * dump_stack_print_info - print generic debug info for dump_stack() * @log_lvl: log level * * Arch-specific dump_stack() implementations can use this function to * print out the same debug information as the generic dump_stack(). */ void dump_stack_print_info(const char *log_lvl) { printk("%sCPU: %d UID: %u PID: %d Comm: %.20s %s%s %s %.*s %s " BUILD_ID_FMT "\n", log_lvl, raw_smp_processor_id(), __kuid_val(current_real_cred()->euid), current->pid, current->comm, kexec_crash_loaded() ? "Kdump: loaded " : "", print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version, preempt_model_str(), BUILD_ID_VAL); if (get_taint()) printk("%s%s\n", log_lvl, print_tainted_verbose()); if (dump_stack_arch_desc_str[0] != '\0') printk("%sHardware name: %s\n", log_lvl, dump_stack_arch_desc_str); print_worker_info(log_lvl, current); print_stop_info(log_lvl, current); print_scx_info(log_lvl, current); } /** * show_regs_print_info - print generic debug info for show_regs() * @log_lvl: log level * * show_regs() implementations can use this function to print out generic * debug information. */ void show_regs_print_info(const char *log_lvl) { dump_stack_print_info(log_lvl); } static void __dump_stack(const char *log_lvl) { dump_stack_print_info(log_lvl); show_stack(NULL, NULL, log_lvl); } /** * dump_stack_lvl - dump the current task information and its stack trace * @log_lvl: log level * * Architectures can override this implementation by implementing its own. */ asmlinkage __visible void dump_stack_lvl(const char *log_lvl) { bool in_panic = panic_on_this_cpu(); unsigned long flags; /* * Permit this cpu to perform nested stack dumps while serialising * against other CPUs, unless this CPU is in panic. * * When in panic, non-panic CPUs are not permitted to store new * printk messages so there is no need to synchronize the output. * This avoids potential deadlock in panic() if another CPU is * holding and unable to release the printk_cpu_sync. */ if (!in_panic) printk_cpu_sync_get_irqsave(flags); __dump_stack(log_lvl); if (!in_panic) printk_cpu_sync_put_irqrestore(flags); } EXPORT_SYMBOL(dump_stack_lvl); asmlinkage __visible void dump_stack(void) { dump_stack_lvl(KERN_DEFAULT); } EXPORT_SYMBOL(dump_stack); |
| 30 1 3 26 29 21 21 15 9 2 7 7 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 | /* * Routines to compress and uncompress tcp packets (for transmission * over low speed serial lines). * * Copyright (c) 1989 Regents of the University of California. * All rights reserved. * * Redistribution and use in source and binary forms are permitted * provided that the above copyright notice and this paragraph are * duplicated in all such forms and that any documentation, * advertising materials, and other materials related to such * distribution and use acknowledge that the software was developed * by the University of California, Berkeley. The name of the * University may not be used to endorse or promote products derived * from this software without specific prior written permission. * THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR * IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. * * Van Jacobson (van@helios.ee.lbl.gov), Dec 31, 1989: * - Initial distribution. * * * modified for KA9Q Internet Software Package by * Katie Stevens (dkstevens@ucdavis.edu) * University of California, Davis * Computing Services * - 01-31-90 initial adaptation (from 1.19) * PPP.05 02-15-90 [ks] * PPP.08 05-02-90 [ks] use PPP protocol field to signal compression * PPP.15 09-90 [ks] improve mbuf handling * PPP.16 11-02 [karn] substantially rewritten to use NOS facilities * * - Feb 1991 Bill_Simpson@um.cc.umich.edu * variable number of conversation slots * allow zero or one slots * separate routines * status display * - Jul 1994 Dmitry Gorodchanin * Fixes for memory leaks. * - Oct 1994 Dmitry Gorodchanin * Modularization. * - Jan 1995 Bjorn Ekwall * Use ip_fast_csum from ip.h * - July 1995 Christos A. Polyzols * Spotted bug in tcp option checking * * * This module is a difficult issue. It's clearly inet code but it's also clearly * driver code belonging close to PPP and SLIP */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/kernel.h> #include <net/slhc_vj.h> #ifdef CONFIG_INET /* Entire module is for IP only */ #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/termios.h> #include <linux/in.h> #include <linux/fcntl.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <net/ip.h> #include <net/protocol.h> #include <net/icmp.h> #include <net/tcp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <net/checksum.h> #include <linux/unaligned.h> static unsigned char *encode(unsigned char *cp, unsigned short n); static long decode(unsigned char **cpp, const unsigned char *end); static unsigned char * put16(unsigned char *cp, unsigned short x); static long pull16(unsigned char **cpp, const unsigned char *end); /* Allocate compression data structure * slots must be in range 0 to 255 (zero meaning no compression) * Returns pointer to structure or ERR_PTR() on error. */ struct slcompress * slhc_init(int rslots, int tslots) { short i; struct cstate *ts; struct slcompress *comp; if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255) return ERR_PTR(-EINVAL); comp = kzalloc_obj(struct slcompress); if (! comp) goto out_fail; if (rslots > 0) { size_t rsize = rslots * sizeof(struct cstate); comp->rstate = kzalloc(rsize, GFP_KERNEL); if (! comp->rstate) goto out_free; comp->rslot_limit = rslots - 1; } if (tslots > 0) { size_t tsize = tslots * sizeof(struct cstate); comp->tstate = kzalloc(tsize, GFP_KERNEL); if (! comp->tstate) goto out_free2; comp->tslot_limit = tslots - 1; } comp->xmit_oldest = 0; comp->xmit_current = 255; comp->recv_current = 255; /* * don't accept any packets with implicit index until we get * one with an explicit index. Otherwise the uncompress code * will try to use connection 255, which is almost certainly * out of range */ comp->flags |= SLF_TOSS; if ( tslots > 0 ) { ts = comp->tstate; for(i = comp->tslot_limit; i > 0; --i){ ts[i].cs_this = i; ts[i].next = &(ts[i - 1]); } ts[0].next = &(ts[comp->tslot_limit]); ts[0].cs_this = 0; } return comp; out_free2: kfree(comp->rstate); out_free: kfree(comp); out_fail: return ERR_PTR(-ENOMEM); } /* Free a compression data structure */ void slhc_free(struct slcompress *comp) { if ( IS_ERR_OR_NULL(comp) ) return; if ( comp->tstate != NULLSLSTATE ) kfree( comp->tstate ); if ( comp->rstate != NULLSLSTATE ) kfree( comp->rstate ); kfree( comp ); } /* Put a short in host order into a char array in network order */ static inline unsigned char * put16(unsigned char *cp, unsigned short x) { *cp++ = x >> 8; *cp++ = x; return cp; } /* Encode a number */ static unsigned char * encode(unsigned char *cp, unsigned short n) { if(n >= 256 || n == 0){ *cp++ = 0; cp = put16(cp,n); } else { *cp++ = n; } return cp; } /* Pull a 16-bit integer in host order from buffer in network byte order. * Returns -1 if the buffer is exhausted, otherwise the 16-bit value. */ static long pull16(unsigned char **cpp, const unsigned char *end) { long rval; if (*cpp + 2 > end) return -1; rval = *(*cpp)++; rval <<= 8; rval |= *(*cpp)++; return rval; } /* Decode a number. Returns -1 if the buffer is exhausted. */ static long decode(unsigned char **cpp, const unsigned char *end) { int x; if (*cpp >= end) return -1; x = *(*cpp)++; if (x == 0) return pull16(cpp, end); return x & 0xff; } /* * icp and isize are the original packet. * ocp is a place to put a copy if necessary. * cpp is initially a pointer to icp. If the copy is used, * change it to ocp. */ int slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, unsigned char *ocp, unsigned char **cpp, int compress_cid) { struct cstate *ocs = &(comp->tstate[comp->xmit_oldest]); struct cstate *lcs = ocs; struct cstate *cs = lcs->next; unsigned long deltaS, deltaA; short changes = 0; int nlen, hlen; unsigned char new_seq[16]; unsigned char *cp = new_seq; struct iphdr *ip; struct tcphdr *th, *oth; __sum16 csum; /* * Don't play with runt packets. */ if(isize<sizeof(struct iphdr)) return isize; ip = (struct iphdr *) icp; if (ip->version != 4 || ip->ihl < 5) return isize; /* Bail if this packet isn't TCP, or is an IP fragment */ if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) { /* Send as regular IP */ if(ip->protocol != IPPROTO_TCP) comp->sls_o_nontcp++; else comp->sls_o_tcp++; return isize; } nlen = ip->ihl * 4; if (isize < nlen + sizeof(*th)) return isize; th = (struct tcphdr *)(icp + nlen); if (th->doff < sizeof(struct tcphdr) / 4) return isize; hlen = nlen + th->doff * 4; /* Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or * some other control bit is set). Also uncompressible if * it's a runt. */ if(hlen > isize || th->syn || th->fin || th->rst || ! (th->ack)){ /* TCP connection stuff; send as regular IP */ comp->sls_o_tcp++; return isize; } /* * Packet is compressible -- we're going to send either a * COMPRESSED_TCP or UNCOMPRESSED_TCP packet. Either way, * we need to locate (or create) the connection state. * * States are kept in a circularly linked list with * xmit_oldest pointing to the end of the list. The * list is kept in lru order by moving a state to the * head of the list whenever it is referenced. Since * the list is short and, empirically, the connection * we want is almost always near the front, we locate * states via linear search. If we don't find a state * for the datagram, the oldest state is (re-)used. */ for ( ; ; ) { if( ip->saddr == cs->cs_ip.saddr && ip->daddr == cs->cs_ip.daddr && th->source == cs->cs_tcp.source && th->dest == cs->cs_tcp.dest) goto found; /* if current equal oldest, at end of list */ if ( cs == ocs ) break; lcs = cs; cs = cs->next; comp->sls_o_searches++; } /* * Didn't find it -- re-use oldest cstate. Send an * uncompressed packet that tells the other side what * connection number we're using for this conversation. * * Note that since the state list is circular, the oldest * state points to the newest and we only need to set * xmit_oldest to update the lru linkage. */ comp->sls_o_misses++; comp->xmit_oldest = lcs->cs_this; goto uncompressed; found: /* * Found it -- move to the front on the connection list. */ if(lcs == ocs) { /* found at most recently used */ } else if (cs == ocs) { /* found at least recently used */ comp->xmit_oldest = lcs->cs_this; } else { /* more than 2 elements */ lcs->next = cs->next; cs->next = ocs->next; ocs->next = cs; } /* * Make sure that only what we expect to change changed. * Check the following: * IP protocol version, header length & type of service. * The "Don't fragment" bit. * The time-to-live field. * The TCP header length. * IP options, if any. * TCP options, if any. * If any of these things are different between the previous & * current datagram, we send the current datagram `uncompressed'. */ oth = &cs->cs_tcp; if(ip->version != cs->cs_ip.version || ip->ihl != cs->cs_ip.ihl || ip->tos != cs->cs_ip.tos || (ip->frag_off & htons(0x4000)) != (cs->cs_ip.frag_off & htons(0x4000)) || ip->ttl != cs->cs_ip.ttl || th->doff != cs->cs_tcp.doff || (ip->ihl > 5 && memcmp(ip+1,cs->cs_ipopt,((ip->ihl)-5)*4) != 0) || (th->doff > 5 && memcmp(th+1,cs->cs_tcpopt,((th->doff)-5)*4) != 0)){ goto uncompressed; } /* * Figure out which of the changing fields changed. The * receiver expects changes in the order: urgent, window, * ack, seq (the order minimizes the number of temporaries * needed in this section of code). */ if(th->urg){ deltaS = ntohs(th->urg_ptr); cp = encode(cp,deltaS); changes |= NEW_U; } else if(th->urg_ptr != oth->urg_ptr){ /* argh! URG not set but urp changed -- a sensible * implementation should never do this but RFC793 * doesn't prohibit the change so we have to deal * with it. */ goto uncompressed; } if((deltaS = ntohs(th->window) - ntohs(oth->window)) != 0){ cp = encode(cp,deltaS); changes |= NEW_W; } if((deltaA = ntohl(th->ack_seq) - ntohl(oth->ack_seq)) != 0L){ if(deltaA > 0x0000ffff) goto uncompressed; cp = encode(cp,deltaA); changes |= NEW_A; } if((deltaS = ntohl(th->seq) - ntohl(oth->seq)) != 0L){ if(deltaS > 0x0000ffff) goto uncompressed; cp = encode(cp,deltaS); changes |= NEW_S; } switch(changes){ case 0: /* Nothing changed. If this packet contains data and the * last one didn't, this is probably a data packet following * an ack (normal on an interactive connection) and we send * it compressed. Otherwise it's probably a retransmit, * retransmitted ack or window probe. Send it uncompressed * in case the other side missed the compressed version. */ if(ip->tot_len != cs->cs_ip.tot_len && ntohs(cs->cs_ip.tot_len) == hlen) break; goto uncompressed; case SPECIAL_I: case SPECIAL_D: /* actual changes match one of our special case encodings -- * send packet uncompressed. */ goto uncompressed; case NEW_S|NEW_A: if(deltaS == deltaA && deltaS == ntohs(cs->cs_ip.tot_len) - hlen){ /* special case for echoed terminal traffic */ changes = SPECIAL_I; cp = new_seq; } break; case NEW_S: if(deltaS == ntohs(cs->cs_ip.tot_len) - hlen){ /* special case for data xfer */ changes = SPECIAL_D; cp = new_seq; } break; } deltaS = ntohs(ip->id) - ntohs(cs->cs_ip.id); if(deltaS != 1){ cp = encode(cp,deltaS); changes |= NEW_I; } if(th->psh) changes |= TCP_PUSH_BIT; /* Grab the cksum before we overwrite it below. Then update our * state with this packet's header. */ csum = th->check; memcpy(&cs->cs_ip,ip,20); memcpy(&cs->cs_tcp,th,20); /* We want to use the original packet as our compressed packet. * (cp - new_seq) is the number of bytes we need for compressed * sequence numbers. In addition we need one byte for the change * mask, one for the connection id and two for the tcp checksum. * So, (cp - new_seq) + 4 bytes of header are needed. */ deltaS = cp - new_seq; if(compress_cid == 0 || comp->xmit_current != cs->cs_this){ cp = ocp; *cpp = ocp; *cp++ = changes | NEW_C; *cp++ = cs->cs_this; comp->xmit_current = cs->cs_this; } else { cp = ocp; *cpp = ocp; *cp++ = changes; } *(__sum16 *)cp = csum; cp += 2; /* deltaS is now the size of the change section of the compressed header */ memcpy(cp,new_seq,deltaS); /* Write list of deltas */ memcpy(cp+deltaS,icp+hlen,isize-hlen); comp->sls_o_compressed++; ocp[0] |= SL_TYPE_COMPRESSED_TCP; return isize - hlen + deltaS + (cp - ocp); /* Update connection state cs & send uncompressed packet (i.e., * a regular ip/tcp packet but with the 'conversation id' we hope * to use on future compressed packets in the protocol field). */ uncompressed: memcpy(&cs->cs_ip,ip,20); memcpy(&cs->cs_tcp,th,20); if (ip->ihl > 5) memcpy(cs->cs_ipopt, ip+1, ((ip->ihl) - 5) * 4); if (th->doff > 5) memcpy(cs->cs_tcpopt, th+1, ((th->doff) - 5) * 4); comp->xmit_current = cs->cs_this; comp->sls_o_uncompressed++; memcpy(ocp, icp, isize); *cpp = ocp; ocp[9] = cs->cs_this; ocp[0] |= SL_TYPE_UNCOMPRESSED_TCP; return isize; } int slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) { int changes; long x; struct tcphdr *thp; struct iphdr *ip; struct cstate *cs; int len, hdrlen; unsigned char *cp = icp; const unsigned char *end = icp + isize; /* We've got a compressed packet; read the change byte */ comp->sls_i_compressed++; if(isize < 3){ comp->sls_i_error++; return 0; } if (!comp->rstate) goto bad; changes = *cp++; if(changes & NEW_C){ /* Make sure the state index is in range, then grab the state. * If we have a good state index, clear the 'discard' flag. */ x = *cp++; /* Read conn index */ if(x < 0 || x > comp->rslot_limit) goto bad; /* Check if the cstate is initialized */ if (!comp->rstate[x].initialized) goto bad; comp->flags &=~ SLF_TOSS; comp->recv_current = x; } else { /* this packet has an implicit state index. If we've * had a line error since the last time we got an * explicit state index, we have to toss the packet. */ if(comp->flags & SLF_TOSS){ comp->sls_i_tossed++; return 0; } } cs = &comp->rstate[comp->recv_current]; thp = &cs->cs_tcp; ip = &cs->cs_ip; if (cp + 2 > end) goto bad; thp->check = *(__sum16 *)cp; cp += 2; thp->psh = (changes & TCP_PUSH_BIT) ? 1 : 0; /* * we can use the same number for the length of the saved header and * the current one, because the packet wouldn't have been sent * as compressed unless the options were the same as the previous one */ hdrlen = ip->ihl * 4 + thp->doff * 4; switch(changes & SPECIALS_MASK){ case SPECIAL_I: /* Echoed terminal traffic */ { short i; i = ntohs(ip->tot_len) - hdrlen; thp->ack_seq = htonl( ntohl(thp->ack_seq) + i); thp->seq = htonl( ntohl(thp->seq) + i); } break; case SPECIAL_D: /* Unidirectional data */ thp->seq = htonl( ntohl(thp->seq) + ntohs(ip->tot_len) - hdrlen); break; default: if(changes & NEW_U){ thp->urg = 1; if((x = decode(&cp, end)) == -1) { goto bad; } thp->urg_ptr = htons(x); } else thp->urg = 0; if(changes & NEW_W){ if((x = decode(&cp, end)) == -1) { goto bad; } thp->window = htons( ntohs(thp->window) + x); } if(changes & NEW_A){ if((x = decode(&cp, end)) == -1) { goto bad; } thp->ack_seq = htonl( ntohl(thp->ack_seq) + x); } if(changes & NEW_S){ if((x = decode(&cp, end)) == -1) { goto bad; } thp->seq = htonl( ntohl(thp->seq) + x); } break; } if(changes & NEW_I){ if((x = decode(&cp, end)) == -1) { goto bad; } ip->id = htons (ntohs (ip->id) + x); } else ip->id = htons (ntohs (ip->id) + 1); /* * At this point, cp points to the first byte of data in the * packet. Put the reconstructed TCP and IP headers back on the * packet. Recalculate IP checksum (but not TCP checksum). */ len = isize - (cp - icp); if (len < 0) goto bad; len += hdrlen; ip->tot_len = htons(len); ip->check = 0; memmove(icp + hdrlen, cp, len - hdrlen); cp = icp; memcpy(cp, ip, 20); cp += 20; if (ip->ihl > 5) { memcpy(cp, cs->cs_ipopt, (ip->ihl - 5) * 4); cp += (ip->ihl - 5) * 4; } put_unaligned(ip_fast_csum(icp, ip->ihl), &((struct iphdr *)icp)->check); memcpy(cp, thp, 20); cp += 20; if (thp->doff > 5) { memcpy(cp, cs->cs_tcpopt, ((thp->doff) - 5) * 4); cp += ((thp->doff) - 5) * 4; } return len; bad: comp->sls_i_error++; return slhc_toss( comp ); } int slhc_remember(struct slcompress *comp, unsigned char *icp, int isize) { const struct tcphdr *th; unsigned char index; struct iphdr *iph; struct cstate *cs; unsigned int ihl; if (!comp->rstate) { comp->sls_i_error++; return slhc_toss(comp); } /* The packet is shorter than a legal IP header. * Also make sure isize is positive. */ if (isize < (int)sizeof(struct iphdr)) { runt: comp->sls_i_runt++; return slhc_toss(comp); } iph = (struct iphdr *)icp; /* Peek at the IP header's IHL field to find its length */ ihl = iph->ihl; /* The IP header length field is too small, * or packet is shorter than the IP header followed * by minimal tcp header. */ if (ihl < 5 || isize < ihl * 4 + sizeof(struct tcphdr)) goto runt; index = iph->protocol; iph->protocol = IPPROTO_TCP; if (ip_fast_csum(icp, ihl)) { /* Bad IP header checksum; discard */ comp->sls_i_badcheck++; return slhc_toss(comp); } if (index > comp->rslot_limit) { comp->sls_i_error++; return slhc_toss(comp); } th = (struct tcphdr *)(icp + ihl * 4); if (th->doff < sizeof(struct tcphdr) / 4) goto runt; if (isize < ihl * 4 + th->doff * 4) goto runt; /* Update local state */ cs = &comp->rstate[comp->recv_current = index]; comp->flags &=~ SLF_TOSS; memcpy(&cs->cs_ip, iph, sizeof(*iph)); memcpy(&cs->cs_tcp, th, sizeof(*th)); if (ihl > 5) memcpy(cs->cs_ipopt, &iph[1], (ihl - 5) * 4); if (th->doff > 5) memcpy(cs->cs_tcpopt, &th[1], (th->doff - 5) * 4); cs->cs_hsize = ihl*2 + th->doff*2; cs->initialized = true; /* Put headers back on packet * Neither header checksum is recalculated */ comp->sls_i_uncompressed++; return isize; } int slhc_toss(struct slcompress *comp) { if ( comp == NULLSLCOMPR ) return 0; comp->flags |= SLF_TOSS; return 0; } #else /* CONFIG_INET */ int slhc_toss(struct slcompress *comp) { printk(KERN_DEBUG "Called IP function on non IP-system: slhc_toss"); return -EINVAL; } int slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) { printk(KERN_DEBUG "Called IP function on non IP-system: slhc_uncompress"); return -EINVAL; } int slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, unsigned char *ocp, unsigned char **cpp, int compress_cid) { printk(KERN_DEBUG "Called IP function on non IP-system: slhc_compress"); return -EINVAL; } int slhc_remember(struct slcompress *comp, unsigned char *icp, int isize) { printk(KERN_DEBUG "Called IP function on non IP-system: slhc_remember"); return -EINVAL; } void slhc_free(struct slcompress *comp) { printk(KERN_DEBUG "Called IP function on non IP-system: slhc_free"); } struct slcompress * slhc_init(int rslots, int tslots) { printk(KERN_DEBUG "Called IP function on non IP-system: slhc_init"); return NULL; } #endif /* CONFIG_INET */ /* VJ header compression */ EXPORT_SYMBOL(slhc_init); EXPORT_SYMBOL(slhc_free); EXPORT_SYMBOL(slhc_remember); EXPORT_SYMBOL(slhc_compress); EXPORT_SYMBOL(slhc_uncompress); EXPORT_SYMBOL(slhc_toss); MODULE_DESCRIPTION("Compression helpers for SLIP (serial line)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 | // SPDX-License-Identifier: GPL-2.0-or-later /* * X.25 Packet Layer release 002 * * This is ALPHA test software. This code may break your machine, randomly fail to work with new * releases, misbehave and/or generally screw up. It might even work. * * This code REQUIRES 2.1.15 or higher * * History * X.25 001 Jonathan Naylor Started coding. * 2000-09-04 Henner Eisen Prevent freeing a dangling skb. */ #define pr_fmt(fmt) "X25: " fmt #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/if_arp.h> #include <net/x25.h> #include <net/x25device.h> static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) { struct sock *sk; unsigned short frametype; unsigned int lci; if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) return 0; frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); /* * LCI of zero is always for us, and its always a link control * frame. */ if (lci == 0) { x25_link_control(skb, nb, frametype); return 0; } /* * Find an existing socket. */ if ((sk = x25_find_socket(lci, nb)) != NULL) { int queued = 1; skb_reset_transport_header(skb); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { queued = x25_process_rx_frame(sk, skb); } else { queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); } bh_unlock_sock(sk); sock_put(sk); return queued; } /* * Is is a Call Request ? if so process it. */ if (frametype == X25_CALL_REQUEST) return x25_rx_call_request(skb, nb, lci); /* * Its not a Call Request, nor is it a control frame. * Can we forward it? */ if (x25_forward_data(lci, nb, skb)) { if (frametype == X25_CLEAR_CONFIRMATION) { x25_clear_forward_by_lci(lci); } kfree_skb(skb); return 1; } /* x25_transmit_clear_request(nb, lci, 0x0D); */ if (frametype != X25_CLEAR_CONFIRMATION) pr_debug("x25_receive_data(): unknown frame type %2x\n",frametype); return 0; } int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { struct sk_buff *nskb; struct x25_neigh *nb; if (!net_eq(dev_net(dev), &init_net)) goto drop; nskb = skb_copy(skb, GFP_ATOMIC); if (!nskb) goto drop; kfree_skb(skb); skb = nskb; /* * Packet received from unrecognised device, throw it away. */ nb = x25_get_neigh(dev); if (!nb) { pr_debug("unknown neighbour - %s\n", dev->name); goto drop; } if (!pskb_may_pull(skb, 1)) { x25_neigh_put(nb); goto drop; } switch (skb->data[0]) { case X25_IFACE_DATA: skb_pull(skb, 1); if (x25_receive_data(skb, nb)) { x25_neigh_put(nb); goto out; } break; case X25_IFACE_CONNECT: x25_link_established(nb); break; case X25_IFACE_DISCONNECT: x25_link_terminated(nb); break; } x25_neigh_put(nb); drop: kfree_skb(skb); out: return 0; } void x25_establish_link(struct x25_neigh *nb) { struct sk_buff *skb; unsigned char *ptr; switch (nb->dev->type) { case ARPHRD_X25: if ((skb = alloc_skb(1, GFP_ATOMIC)) == NULL) { pr_err("x25_dev: out of memory\n"); return; } ptr = skb_put(skb, 1); *ptr = X25_IFACE_CONNECT; break; default: return; } skb->protocol = htons(ETH_P_X25); skb->dev = nb->dev; dev_queue_xmit(skb); } void x25_send_frame(struct sk_buff *skb, struct x25_neigh *nb) { unsigned char *dptr; skb_reset_network_header(skb); switch (nb->dev->type) { case ARPHRD_X25: dptr = skb_push(skb, 1); *dptr = X25_IFACE_DATA; break; default: kfree_skb(skb); return; } skb->protocol = htons(ETH_P_X25); skb->dev = nb->dev; dev_queue_xmit(skb); } |
| 41258 2828 40823 4834 1667 6358 37501 617 6419 47 49 49 52 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> #include <linux/cleanup.h> #include <linux/err.h> struct file; extern void fput(struct file *); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); /* either a reference to struct file + flags * (cloned vs. borrowed, pos locked), with * flags stored in lower bits of value, * or empty (represented by 0). */ struct fd { unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 #define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) static inline bool fd_empty(struct fd f) { return unlikely(!f.word); } #define EMPTY_FD (struct fd){0} static inline struct fd BORROWED_FD(struct file *f) { return (struct fd){(unsigned long)f}; } static inline struct fd CLONED_FD(struct file *f) { return (struct fd){(unsigned long)f | FDPUT_FPUT}; } static inline void fdput(struct fd fd) { if (unlikely(fd.word & FDPUT_FPUT)) fput(fd_file(fd)); } extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); extern void __f_unlock_pos(struct file *); struct fd fdget(unsigned int fd); struct fd fdget_raw(unsigned int fd); struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { if (f.word & FDPUT_POS_UNLOCK) __f_unlock_pos(fd_file(f)); fdput(f); } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T)) /* * take_fd() will take care to set @fd to -EBADF ensuring that * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it * easier to rely on CLASS(get_unused_fd): * * struct file *f; * * CLASS(get_unused_fd, fd)(O_CLOEXEC); * if (fd < 0) * return fd; * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); */ #define take_fd(fd) __get_and_null(fd, -EBADF) extern void fd_install(unsigned int fd, struct file *file); int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; /* * fd_prepare: Combined fd + file allocation cleanup class. * @err: Error code to indicate if allocation succeeded. * @__fd: Allocated fd (may not be accessed directly) * @__file: Allocated struct file pointer (may not be accessed directly) * * Allocates an fd and a file together. On error paths, automatically cleans * up whichever resource was successfully allocated. Allows flexible file * allocation with different functions per usage. * * Do not use directly. */ struct fd_prepare { s32 err; s32 __fd; /* do not access directly */ struct file *__file; /* do not access directly */ }; /* Typedef for fd_prepare cleanup guards. */ typedef struct fd_prepare class_fd_prepare_t; /* * Accessors for fd_prepare class members. * _Generic() is used for zero-cost type safety. */ #define fd_prepare_fd(_fdf) \ (_Generic((_fdf), struct fd_prepare: (_fdf).__fd)) #define fd_prepare_file(_fdf) \ (_Generic((_fdf), struct fd_prepare: (_fdf).__file)) /* Do not use directly. */ static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf) { if (unlikely(fdf->__fd >= 0)) put_unused_fd(fdf->__fd); if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) fput(fdf->__file); } /* Do not use directly. */ static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf) { if (unlikely(fdf->err)) return fdf->err; if (unlikely(fdf->__fd < 0)) return fdf->__fd; if (unlikely(IS_ERR(fdf->__file))) return PTR_ERR(fdf->__file); if (unlikely(!fdf->__file)) return -ENOMEM; return 0; } /* * __FD_PREPARE_INIT - Helper to initialize fd_prepare class. * @_fd_flags: flags for get_unused_fd_flags() * @_file_owned: expression that returns struct file * * * Returns a struct fd_prepare with fd, file, and err set. * If fd allocation fails, fd will be negative and err will be set. If * fd succeeds but file_init_expr fails, file will be ERR_PTR and err * will be set. The err field is the single source of truth for error * checking. */ #define __FD_PREPARE_INIT(_fd_flags, _file_owned) \ ({ \ struct fd_prepare fdf = { \ .__fd = get_unused_fd_flags((_fd_flags)), \ }; \ if (likely(fdf.__fd >= 0)) \ fdf.__file = (_file_owned); \ fdf.err = ACQUIRE_ERR(fd_prepare, &fdf); \ fdf; \ }) /* * FD_PREPARE - Macro to declare and initialize an fd_prepare variable. * * Declares and initializes an fd_prepare variable with automatic * cleanup. No separate scope required - cleanup happens when variable * goes out of scope. * * @_fdf: name of struct fd_prepare variable to define * @_fd_flags: flags for get_unused_fd_flags() * @_file_owned: struct file to take ownership of (can be expression) */ #define FD_PREPARE(_fdf, _fd_flags, _file_owned) \ CLASS_INIT(fd_prepare, _fdf, __FD_PREPARE_INIT(_fd_flags, _file_owned)) /* * fd_publish - Publish prepared fd and file to the fd table. * @_fdf: struct fd_prepare variable */ #define fd_publish(_fdf) \ ({ \ struct fd_prepare *fdp = &(_fdf); \ VFS_WARN_ON_ONCE(fdp->err); \ VFS_WARN_ON_ONCE(fdp->__fd < 0); \ VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \ fd_install(fdp->__fd, fdp->__file); \ retain_and_null_ptr(fdp->__file); \ take_fd(fdp->__fd); \ }) /* Do not use directly. */ #define __FD_ADD(_fdf, _fd_flags, _file_owned) \ ({ \ FD_PREPARE(_fdf, _fd_flags, _file_owned); \ s32 ret = _fdf.err; \ if (likely(!ret)) \ ret = fd_publish(_fdf); \ ret; \ }) /* * FD_ADD - Allocate and install an fd and file in one step. * @_fd_flags: flags for get_unused_fd_flags() * @_file_owned: struct file to take ownership of * * Returns the allocated fd number, or negative error code on failure. */ #define FD_ADD(_fd_flags, _file_owned) \ __FD_ADD(__UNIQUE_ID(fd_prepare), _fd_flags, _file_owned) #endif /* __LINUX_FILE_H */ |
| 1 183 180 3 92 183 152 1 31 185 131 2 52 3 180 368 19 13 177 157 2 2 1 1 15 4 3 1 239 4 6 1 86 4 74 3 2 234 234 231 157 39 31 2 2 2 27 7 1 2 22 69 2 37 1 92 1 91 1 1 1 2 2 5 50 2 1 2 2 2 2 1 4 14 21 4 1 2 1 1 1 1 2 6 167 1 1 1 165 4 164 1 106 2 46 136 3 18 146 133 2 11 131 1 1 8 20 115 4 45 103 98 5 66 113 52 100 99 98 2 99 6 97 2 98 2 100 8 145 165 146 18 144 21 162 3 164 161 13 146 157 154 147 4 1 151 145 6 150 149 2 151 47 3 80 18 88 78 234 234 165 88 74 22 15 14 72 88 18 9 3 6 13 6 6 1 1 153 150 2 1 1 2 2 2 29 29 29 29 26 26 19 20 51 16 16 149 145 5 149 147 2 142 7 149 125 26 120 29 129 20 96 51 135 16 148 1 145 5 2 147 147 2 144 5 149 149 148 147 1 149 1 148 40 39 9 7 3 12 2 2 8 9 1 37 343 5 1 1 13 6 7 3 2 8 4 1 3 2 1 4 1 1 1 1 1 11 12 51 5 46 43 3 44 1 1 25 21 45 11 37 37 35 2 45 8 8 4 233 4 3 76 3 149 4 4 4 210 4 78 78 123 73 73 90 73 66 9 10 10 95 8 111 6 110 9 85 34 59 256 12 196 208 178 178 177 144 139 6 140 4 177 8 169 35 4 132 208 94 110 9 60 10 4 4 3 1 4 4 4 2 3 4 1 5 5 3 2 2 3 3 2 5 5 2 2 43 43 2 39 2 41 5 35 30 1 1 7 8 6 2 5 2 2 2 4 4 1 1 3 3 8 8 4 6 25 25 2 18 4 22 11 11 12 3 3 6 5 5 1 2 3 5 17 17 17 5 12 4 7 7 42 7 25 53 2 50 50 46 4 47 3 47 1 14 1 2 2 9 1 6 3 15 4 18 1 19 19 19 19 624 5 603 15 15 1 649 1 1 648 649 19 15 2 2 13 624 2 601 34 651 8 1 8 1 8 9 9 9 13 84 24 81 28 89 20 107 2 109 109 109 109 109 1 109 121 109 9 109 13 60 60 58 2 59 60 60 60 60 60 60 81 47 34 14 8 3 19 6 6 6 4 6 6 6 6 143 2 9 11 139 7 142 145 144 10 155 145 145 10 6 118 117 195 195 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-only /* xfrm_user.c: User interface to configure xfrm engine. * * Copyright (C) 2002 David S. Miller (davem@redhat.com) * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * */ #include <linux/compat.h> #include <linux/crypto.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/init.h> #include <linux/security.h> #include <net/sock.h> #include <net/xfrm.h> #include <net/netlink.h> #include <net/ah.h> #include <linux/uaccess.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #endif #include <linux/unaligned.h> static struct sock *xfrm_net_nlsk(const struct net *net, const struct sk_buff *skb) { /* get the source of this request, see netlink_unicast_kernel */ const struct sock *sk = NETLINK_CB(skb).sk; /* sk is refcounted, the netns stays alive and nlsk with it */ return rcu_dereference_protected(net->xfrm.nlsk, sk->sk_net_refcnt); } static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[type]; struct xfrm_algo *algp; if (!rt) return 0; algp = nla_data(rt); if (nla_len(rt) < (int)xfrm_alg_len(algp)) { NL_SET_ERR_MSG(extack, "Invalid AUTH/CRYPT/COMP attribute length"); return -EINVAL; } switch (type) { case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: break; default: NL_SET_ERR_MSG(extack, "Invalid algorithm attribute type"); return -EINVAL; } algp->alg_name[sizeof(algp->alg_name) - 1] = '\0'; return 0; } static int verify_auth_trunc(struct nlattr **attrs, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_ALG_AUTH_TRUNC]; struct xfrm_algo_auth *algp; if (!rt) return 0; algp = nla_data(rt); if (nla_len(rt) < (int)xfrm_alg_auth_len(algp)) { NL_SET_ERR_MSG(extack, "Invalid AUTH_TRUNC attribute length"); return -EINVAL; } algp->alg_name[sizeof(algp->alg_name) - 1] = '\0'; return 0; } static int verify_aead(struct nlattr **attrs, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_ALG_AEAD]; struct xfrm_algo_aead *algp; if (!rt) return 0; algp = nla_data(rt); if (nla_len(rt) < (int)aead_len(algp)) { NL_SET_ERR_MSG(extack, "Invalid AEAD attribute length"); return -EINVAL; } algp->alg_name[sizeof(algp->alg_name) - 1] = '\0'; return 0; } static void verify_one_addr(struct nlattr **attrs, enum xfrm_attr_type_t type, xfrm_address_t **addrp) { struct nlattr *rt = attrs[type]; if (rt && addrp) *addrp = nla_data(rt); } static inline int verify_sec_ctx_len(struct nlattr **attrs, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_user_sec_ctx *uctx; if (!rt) return 0; uctx = nla_data(rt); if (uctx->len > nla_len(rt) || uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len)) { NL_SET_ERR_MSG(extack, "Invalid security context length"); return -EINVAL; } return 0; } static inline int verify_replay(struct xfrm_usersa_info *p, struct nlattr **attrs, u8 sa_dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; struct xfrm_replay_state_esn *rs; if (!rt) { if (p->flags & XFRM_STATE_ESN) { NL_SET_ERR_MSG(extack, "Missing required attribute for ESN"); return -EINVAL; } return 0; } rs = nla_data(rt); if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) { NL_SET_ERR_MSG(extack, "ESN bitmap length must be <= 128"); return -EINVAL; } if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && nla_len(rt) != sizeof(*rs)) { NL_SET_ERR_MSG(extack, "ESN attribute is too short to fit the full bitmap length"); return -EINVAL; } /* As only ESP and AH support ESN feature. */ if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) { NL_SET_ERR_MSG(extack, "ESN only supported for ESP and AH"); return -EINVAL; } if (p->replay_window != 0) { NL_SET_ERR_MSG(extack, "ESN not compatible with legacy replay_window"); return -EINVAL; } if (sa_dir == XFRM_SA_DIR_OUT) { if (rs->replay_window) { NL_SET_ERR_MSG(extack, "Replay window should be 0 for output SA"); return -EINVAL; } if (rs->seq || rs->seq_hi) { NL_SET_ERR_MSG(extack, "Replay seq and seq_hi should be 0 for output SA"); return -EINVAL; } if (!(p->flags & XFRM_STATE_ESN)) { if (rs->oseq_hi) { NL_SET_ERR_MSG( extack, "Replay oseq_hi should be 0 in non-ESN mode for output SA"); return -EINVAL; } if (rs->oseq == U32_MAX) { NL_SET_ERR_MSG( extack, "Replay oseq should be less than 0xFFFFFFFF in non-ESN mode for output SA"); return -EINVAL; } } else { if (rs->oseq == U32_MAX && rs->oseq_hi == U32_MAX) { NL_SET_ERR_MSG( extack, "Replay oseq and oseq_hi should be less than 0xFFFFFFFF for output SA"); return -EINVAL; } } if (rs->bmp_len) { NL_SET_ERR_MSG(extack, "Replay bmp_len should 0 for output SA"); return -EINVAL; } } if (sa_dir == XFRM_SA_DIR_IN) { if (rs->oseq || rs->oseq_hi) { NL_SET_ERR_MSG(extack, "Replay oseq and oseq_hi should be 0 for input SA"); return -EINVAL; } if (!(p->flags & XFRM_STATE_ESN)) { if (rs->seq_hi) { NL_SET_ERR_MSG( extack, "Replay seq_hi should be 0 in non-ESN mode for input SA"); return -EINVAL; } if (rs->seq == U32_MAX) { NL_SET_ERR_MSG( extack, "Replay seq should be less than 0xFFFFFFFF in non-ESN mode for input SA"); return -EINVAL; } } else { if (rs->seq == U32_MAX && rs->seq_hi == U32_MAX) { NL_SET_ERR_MSG( extack, "Replay seq and seq_hi should be less than 0xFFFFFFFF for input SA"); return -EINVAL; } } } return 0; } static int verify_mtimer_thresh(bool has_encap, u8 dir, struct netlink_ext_ack *extack) { if (!has_encap) { NL_SET_ERR_MSG(extack, "MTIMER_THRESH requires encapsulation"); return -EINVAL; } if (dir == XFRM_SA_DIR_OUT) { NL_SET_ERR_MSG(extack, "MTIMER_THRESH should not be set on output SA"); return -EINVAL; } return 0; } static int verify_xfrm_family(u16 family, struct netlink_ext_ack *extack) { switch (family) { case AF_INET: return 0; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) return 0; #else NL_SET_ERR_MSG(extack, "IPv6 support disabled"); return -EAFNOSUPPORT; #endif default: NL_SET_ERR_MSG(extack, "Invalid address family"); return -EINVAL; } } static int verify_selector_prefixlen(u16 family, const struct xfrm_selector *sel, struct netlink_ext_ack *extack) { switch (family) { case AF_UNSPEC: return 0; case AF_INET: if (sel->prefixlen_d > 32 || sel->prefixlen_s > 32) { NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 32 for IPv4)"); return -EINVAL; } return 0; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (sel->prefixlen_d > 128 || sel->prefixlen_s > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 128 for IPv6)"); return -EINVAL; } return 0; #else NL_SET_ERR_MSG(extack, "IPv6 support disabled"); return -EAFNOSUPPORT; #endif default: NL_SET_ERR_MSG(extack, "Invalid address family in selector"); return -EINVAL; } } static int verify_newsa_info(struct xfrm_usersa_info *p, struct nlattr **attrs, struct netlink_ext_ack *extack) { int err; u8 sa_dir = nla_get_u8_default(attrs[XFRMA_SA_DIR], 0); u16 family = p->sel.family; err = verify_xfrm_family(p->family, extack); if (err) goto out; if (!family && !(p->flags & XFRM_STATE_AF_UNSPEC)) family = p->family; err = verify_selector_prefixlen(family, &p->sel, extack); if (err) goto out; err = -EINVAL; switch (p->id.proto) { case IPPROTO_AH: if (!attrs[XFRMA_ALG_AUTH] && !attrs[XFRMA_ALG_AUTH_TRUNC]) { NL_SET_ERR_MSG(extack, "Missing required attribute for AH: AUTH_TRUNC or AUTH"); goto out; } if (attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ALG_COMP] || attrs[XFRMA_TFCPAD]) { NL_SET_ERR_MSG(extack, "Invalid attributes for AH: AEAD, CRYPT, COMP, TFCPAD"); goto out; } break; case IPPROTO_ESP: if (attrs[XFRMA_ALG_COMP]) { NL_SET_ERR_MSG(extack, "Invalid attribute for ESP: COMP"); goto out; } if (!attrs[XFRMA_ALG_AUTH] && !attrs[XFRMA_ALG_AUTH_TRUNC] && !attrs[XFRMA_ALG_CRYPT] && !attrs[XFRMA_ALG_AEAD]) { NL_SET_ERR_MSG(extack, "Missing required attribute for ESP: at least one of AUTH, AUTH_TRUNC, CRYPT, AEAD"); goto out; } if ((attrs[XFRMA_ALG_AUTH] || attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_CRYPT]) && attrs[XFRMA_ALG_AEAD]) { NL_SET_ERR_MSG(extack, "Invalid attribute combination for ESP: AEAD can't be used with AUTH, AUTH_TRUNC, CRYPT"); goto out; } if (attrs[XFRMA_TFCPAD] && p->mode != XFRM_MODE_TUNNEL) { NL_SET_ERR_MSG(extack, "TFC padding can only be used in tunnel mode"); goto out; } if ((attrs[XFRMA_IPTFS_DROP_TIME] || attrs[XFRMA_IPTFS_REORDER_WINDOW] || attrs[XFRMA_IPTFS_DONT_FRAG] || attrs[XFRMA_IPTFS_INIT_DELAY] || attrs[XFRMA_IPTFS_MAX_QSIZE] || attrs[XFRMA_IPTFS_PKT_SIZE]) && p->mode != XFRM_MODE_IPTFS) { NL_SET_ERR_MSG(extack, "IP-TFS options can only be used in IP-TFS mode"); goto out; } break; case IPPROTO_COMP: if (!attrs[XFRMA_ALG_COMP]) { NL_SET_ERR_MSG(extack, "Missing required attribute for COMP: COMP"); goto out; } if (attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_AUTH] || attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_TFCPAD]) { NL_SET_ERR_MSG(extack, "Invalid attributes for COMP: AEAD, AUTH, AUTH_TRUNC, CRYPT, TFCPAD"); goto out; } if (ntohl(p->id.spi) >= 0x10000) { NL_SET_ERR_MSG(extack, "SPI is too large for COMP (must be < 0x10000)"); goto out; } break; #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_DSTOPTS: case IPPROTO_ROUTING: if (attrs[XFRMA_ALG_COMP] || attrs[XFRMA_ALG_AUTH] || attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ENCAP] || attrs[XFRMA_SEC_CTX] || attrs[XFRMA_TFCPAD]) { NL_SET_ERR_MSG(extack, "Invalid attributes for DSTOPTS/ROUTING"); goto out; } if (!attrs[XFRMA_COADDR]) { NL_SET_ERR_MSG(extack, "Missing required COADDR attribute for DSTOPTS/ROUTING"); goto out; } break; #endif default: NL_SET_ERR_MSG(extack, "Unsupported protocol"); goto out; } if ((err = verify_aead(attrs, extack))) goto out; if ((err = verify_auth_trunc(attrs, extack))) goto out; if ((err = verify_one_alg(attrs, XFRMA_ALG_AUTH, extack))) goto out; if ((err = verify_one_alg(attrs, XFRMA_ALG_CRYPT, extack))) goto out; if ((err = verify_one_alg(attrs, XFRMA_ALG_COMP, extack))) goto out; if ((err = verify_sec_ctx_len(attrs, extack))) goto out; if ((err = verify_replay(p, attrs, sa_dir, extack))) goto out; err = -EINVAL; switch (p->mode) { case XFRM_MODE_TRANSPORT: case XFRM_MODE_TUNNEL: case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_BEET: break; case XFRM_MODE_IPTFS: if (p->id.proto != IPPROTO_ESP) { NL_SET_ERR_MSG(extack, "IP-TFS mode only supported with ESP"); goto out; } if (sa_dir == 0) { NL_SET_ERR_MSG(extack, "IP-TFS mode requires in or out direction attribute"); goto out; } break; default: NL_SET_ERR_MSG(extack, "Unsupported mode"); goto out; } err = 0; if (attrs[XFRMA_MTIMER_THRESH]) { err = verify_mtimer_thresh(!!attrs[XFRMA_ENCAP], sa_dir, extack); if (err) goto out; } if (sa_dir == XFRM_SA_DIR_OUT) { if (p->flags & XFRM_STATE_DECAP_DSCP) { NL_SET_ERR_MSG(extack, "Flag DECAP_DSCP should not be set for output SA"); err = -EINVAL; goto out; } if (p->flags & XFRM_STATE_ICMP) { NL_SET_ERR_MSG(extack, "Flag ICMP should not be set for output SA"); err = -EINVAL; goto out; } if (p->flags & XFRM_STATE_WILDRECV) { NL_SET_ERR_MSG(extack, "Flag WILDRECV should not be set for output SA"); err = -EINVAL; goto out; } if (p->replay_window) { NL_SET_ERR_MSG(extack, "Replay window should be 0 for output SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_IPTFS_DROP_TIME]) { NL_SET_ERR_MSG(extack, "IP-TFS drop time should not be set for output SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_IPTFS_REORDER_WINDOW]) { NL_SET_ERR_MSG(extack, "IP-TFS reorder window should not be set for output SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_REPLAY_VAL]) { struct xfrm_replay_state *replay; replay = nla_data(attrs[XFRMA_REPLAY_VAL]); if (replay->seq || replay->bitmap) { NL_SET_ERR_MSG(extack, "Replay seq and bitmap should be 0 for output SA"); err = -EINVAL; goto out; } } } if (sa_dir == XFRM_SA_DIR_IN) { if (p->flags & XFRM_STATE_NOPMTUDISC) { NL_SET_ERR_MSG(extack, "Flag NOPMTUDISC should not be set for input SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_SA_EXTRA_FLAGS]) { u32 xflags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); if (xflags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP) { NL_SET_ERR_MSG(extack, "Flag DONT_ENCAP_DSCP should not be set for input SA"); err = -EINVAL; goto out; } if (xflags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP) { NL_SET_ERR_MSG(extack, "Flag OSEQ_MAY_WRAP should not be set for input SA"); err = -EINVAL; goto out; } } if (attrs[XFRMA_IPTFS_DONT_FRAG]) { NL_SET_ERR_MSG(extack, "IP-TFS don't fragment should not be set for input SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_IPTFS_INIT_DELAY]) { NL_SET_ERR_MSG(extack, "IP-TFS initial delay should not be set for input SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_IPTFS_MAX_QSIZE]) { NL_SET_ERR_MSG(extack, "IP-TFS max queue size should not be set for input SA"); err = -EINVAL; goto out; } if (attrs[XFRMA_IPTFS_PKT_SIZE]) { NL_SET_ERR_MSG(extack, "IP-TFS packet size should not be set for input SA"); err = -EINVAL; goto out; } } if (!sa_dir && attrs[XFRMA_SA_PCPU]) { NL_SET_ERR_MSG(extack, "SA_PCPU only supported with SA_DIR"); err = -EINVAL; goto out; } out: return err; } static int attach_one_algo(struct xfrm_algo **algpp, u8 *props, struct xfrm_algo_desc *(*get_byname)(const char *, int), struct nlattr *rta, struct netlink_ext_ack *extack) { struct xfrm_algo *p, *ualg; struct xfrm_algo_desc *algo; if (!rta) return 0; ualg = nla_data(rta); algo = get_byname(ualg->alg_name, 1); if (!algo) { NL_SET_ERR_MSG(extack, "Requested COMP algorithm not found"); return -ENOSYS; } *props = algo->desc.sadb_alg_id; p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL); if (!p) return -ENOMEM; strscpy(p->alg_name, algo->name); *algpp = p; return 0; } static int attach_crypt(struct xfrm_state *x, struct nlattr *rta, struct netlink_ext_ack *extack) { struct xfrm_algo *p, *ualg; struct xfrm_algo_desc *algo; if (!rta) return 0; ualg = nla_data(rta); algo = xfrm_ealg_get_byname(ualg->alg_name, 1); if (!algo) { NL_SET_ERR_MSG(extack, "Requested CRYPT algorithm not found"); return -ENOSYS; } x->props.ealgo = algo->desc.sadb_alg_id; p = kmemdup(ualg, xfrm_alg_len(ualg), GFP_KERNEL); if (!p) return -ENOMEM; strscpy(p->alg_name, algo->name); x->ealg = p; x->geniv = algo->uinfo.encr.geniv; return 0; } static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props, struct nlattr *rta, struct netlink_ext_ack *extack) { struct xfrm_algo *ualg; struct xfrm_algo_auth *p; struct xfrm_algo_desc *algo; if (!rta) return 0; ualg = nla_data(rta); algo = xfrm_aalg_get_byname(ualg->alg_name, 1); if (!algo) { NL_SET_ERR_MSG(extack, "Requested AUTH algorithm not found"); return -ENOSYS; } *props = algo->desc.sadb_alg_id; p = kmalloc(sizeof(*p) + (ualg->alg_key_len + 7) / 8, GFP_KERNEL); if (!p) return -ENOMEM; strscpy(p->alg_name, algo->name); p->alg_key_len = ualg->alg_key_len; p->alg_trunc_len = algo->uinfo.auth.icv_truncbits; memcpy(p->alg_key, ualg->alg_key, (ualg->alg_key_len + 7) / 8); *algpp = p; return 0; } static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props, struct nlattr *rta, struct netlink_ext_ack *extack) { struct xfrm_algo_auth *p, *ualg; struct xfrm_algo_desc *algo; if (!rta) return 0; ualg = nla_data(rta); algo = xfrm_aalg_get_byname(ualg->alg_name, 1); if (!algo) { NL_SET_ERR_MSG(extack, "Requested AUTH_TRUNC algorithm not found"); return -ENOSYS; } if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) { NL_SET_ERR_MSG(extack, "Invalid length requested for truncated ICV"); return -EINVAL; } *props = algo->desc.sadb_alg_id; p = kmemdup(ualg, xfrm_alg_auth_len(ualg), GFP_KERNEL); if (!p) return -ENOMEM; strscpy(p->alg_name, algo->name); if (!p->alg_trunc_len) p->alg_trunc_len = algo->uinfo.auth.icv_truncbits; *algpp = p; return 0; } static int attach_aead(struct xfrm_state *x, struct nlattr *rta, struct netlink_ext_ack *extack) { struct xfrm_algo_aead *p, *ualg; struct xfrm_algo_desc *algo; if (!rta) return 0; ualg = nla_data(rta); algo = xfrm_aead_get_byname(ualg->alg_name, ualg->alg_icv_len, 1); if (!algo) { NL_SET_ERR_MSG(extack, "Requested AEAD algorithm not found"); return -ENOSYS; } x->props.ealgo = algo->desc.sadb_alg_id; p = kmemdup(ualg, aead_len(ualg), GFP_KERNEL); if (!p) return -ENOMEM; strscpy(p->alg_name, algo->name); x->aead = p; x->geniv = algo->uinfo.aead.geniv; return 0; } static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_esn, struct nlattr *rp, struct netlink_ext_ack *extack) { struct xfrm_replay_state_esn *up; unsigned int ulen; if (!replay_esn || !rp) return 0; up = nla_data(rp); ulen = xfrm_replay_state_esn_len(up); /* Check the overall length and the internal bitmap length to avoid * potential overflow. */ if (nla_len(rp) < (int)ulen) { NL_SET_ERR_MSG(extack, "ESN attribute is too short"); return -EINVAL; } if (xfrm_replay_state_esn_len(replay_esn) != ulen) { NL_SET_ERR_MSG(extack, "New ESN size doesn't match the existing SA's ESN size"); return -EINVAL; } if (replay_esn->bmp_len != up->bmp_len) { NL_SET_ERR_MSG(extack, "New ESN bitmap size doesn't match the existing SA's ESN bitmap"); return -EINVAL; } if (up->replay_window > up->bmp_len * sizeof(__u32) * 8) { NL_SET_ERR_MSG(extack, "ESN replay window is longer than the bitmap"); return -EINVAL; } return 0; } static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn, struct xfrm_replay_state_esn **preplay_esn, struct nlattr *rta) { struct xfrm_replay_state_esn *p, *pp, *up; unsigned int klen, ulen; if (!rta) return 0; up = nla_data(rta); klen = xfrm_replay_state_esn_len(up); ulen = nla_len(rta) >= (int)klen ? klen : sizeof(*up); p = kzalloc(klen, GFP_KERNEL); if (!p) return -ENOMEM; pp = kzalloc(klen, GFP_KERNEL); if (!pp) { kfree(p); return -ENOMEM; } memcpy(p, up, ulen); memcpy(pp, up, ulen); *replay_esn = p; *preplay_esn = pp; return 0; } static inline unsigned int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx) { unsigned int len = 0; if (xfrm_ctx) { len += sizeof(struct xfrm_user_sec_ctx); len += xfrm_ctx->ctx_len; } return len; } static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) { memcpy(&x->id, &p->id, sizeof(x->id)); memcpy(&x->sel, &p->sel, sizeof(x->sel)); memcpy(&x->lft, &p->lft, sizeof(x->lft)); x->props.mode = p->mode; x->props.replay_window = min_t(unsigned int, p->replay_window, sizeof(x->replay.bitmap) * 8); x->props.reqid = p->reqid; x->props.family = p->family; memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); x->props.flags = p->flags; if (!x->sel.family && !(p->flags & XFRM_STATE_AF_UNSPEC)) x->sel.family = p->family; } /* * someday when pfkey also has support, we could have the code * somehow made shareable and move it to xfrm_state.c - JHS * */ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, int update_esn) { struct nlattr *rp = attrs[XFRMA_REPLAY_VAL]; struct nlattr *re = update_esn ? attrs[XFRMA_REPLAY_ESN_VAL] : NULL; struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH]; if (re && x->replay_esn && x->preplay_esn) { struct xfrm_replay_state_esn *replay_esn; replay_esn = nla_data(re); memcpy(x->replay_esn, replay_esn, xfrm_replay_state_esn_len(replay_esn)); memcpy(x->preplay_esn, replay_esn, xfrm_replay_state_esn_len(replay_esn)); } if (rp) { struct xfrm_replay_state *replay; replay = nla_data(rp); memcpy(&x->replay, replay, sizeof(*replay)); memcpy(&x->preplay, replay, sizeof(*replay)); } if (lt) { struct xfrm_lifetime_cur *ltime; ltime = nla_data(lt); x->curlft.bytes = ltime->bytes; x->curlft.packets = ltime->packets; x->curlft.add_time = ltime->add_time; x->curlft.use_time = ltime->use_time; } if (et) x->replay_maxage = nla_get_u32(et); if (rt) x->replay_maxdiff = nla_get_u32(rt); if (mt) x->mapping_maxage = nla_get_u32(mt); } static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_SET_MARK]) { m->v = nla_get_u32(attrs[XFRMA_SET_MARK]); m->m = nla_get_u32_default(attrs[XFRMA_SET_MARK_MASK], 0xffffffff); } else { m->v = m->m = 0; } } static struct xfrm_state *xfrm_state_construct(struct net *net, struct xfrm_usersa_info *p, struct nlattr **attrs, int *errp, struct netlink_ext_ack *extack) { struct xfrm_state *x = xfrm_state_alloc(net); int err = -ENOMEM; if (!x) goto error_no_put; copy_from_user_state(x, p); if (attrs[XFRMA_ENCAP]) { x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), sizeof(*x->encap), GFP_KERNEL); if (x->encap == NULL) goto error; } if (attrs[XFRMA_COADDR]) { x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), sizeof(*x->coaddr), GFP_KERNEL); if (x->coaddr == NULL) goto error; } if (attrs[XFRMA_SA_EXTRA_FLAGS]) x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); if ((err = attach_aead(x, attrs[XFRMA_ALG_AEAD], extack))) goto error; if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo, attrs[XFRMA_ALG_AUTH_TRUNC], extack))) goto error; if (!x->props.aalgo) { if ((err = attach_auth(&x->aalg, &x->props.aalgo, attrs[XFRMA_ALG_AUTH], extack))) goto error; } if ((err = attach_crypt(x, attrs[XFRMA_ALG_CRYPT], extack))) goto error; if ((err = attach_one_algo(&x->calg, &x->props.calgo, xfrm_calg_get_byname, attrs[XFRMA_ALG_COMP], extack))) goto error; if (attrs[XFRMA_TFCPAD]) { x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]); if (x->tfcpad > IP_MAX_MTU) { NL_SET_ERR_MSG(extack, "Excessive TFC padding"); err = -EINVAL; goto error; } } xfrm_mark_get(attrs, &x->mark); xfrm_smark_init(attrs, &x->props.smark); if (attrs[XFRMA_IF_ID]) x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); if (attrs[XFRMA_SA_DIR]) x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); if (attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]) x->nat_keepalive_interval = nla_get_u32(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]); if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); if (x->pcpu_num >= num_possible_cpus()) { err = -ERANGE; NL_SET_ERR_MSG(extack, "pCPU number too big"); goto error; } } err = __xfrm_init_state(x, extack); if (err) goto error; if (attrs[XFRMA_SEC_CTX]) { err = security_xfrm_state_alloc(x, nla_data(attrs[XFRMA_SEC_CTX])); if (err) goto error; } if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn, attrs[XFRMA_REPLAY_ESN_VAL]))) goto error; x->km.seq = p->seq; x->replay_maxdiff = net->xfrm.sysctl_aevent_rseqth; /* sysctl_xfrm_aevent_etime is in 100ms units */ x->replay_maxage = (net->xfrm.sysctl_aevent_etime*HZ)/XFRM_AE_ETH_M; if ((err = xfrm_init_replay(x, extack))) goto error; /* override default values from above */ xfrm_update_ae_params(x, attrs, 0); xfrm_set_type_offload(x, attrs[XFRMA_OFFLOAD_DEV]); /* configure the hardware if offload is requested */ if (attrs[XFRMA_OFFLOAD_DEV]) { err = xfrm_dev_state_add(net, x, nla_data(attrs[XFRMA_OFFLOAD_DEV]), extack); if (err) goto error; } if (x->mode_cbs && x->mode_cbs->user_init) { err = x->mode_cbs->user_init(net, x, attrs, extack); if (err) goto error; } return x; error: x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); error_no_put: *errp = err; return NULL; } static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_usersa_info *p = nlmsg_data(nlh); struct xfrm_state *x; int err; struct km_event c; err = verify_newsa_info(p, attrs, extack); if (err) return err; x = xfrm_state_construct(net, p, attrs, &err, extack); if (!x) return err; xfrm_state_hold(x); if (nlh->nlmsg_type == XFRM_MSG_NEWSA) 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_dev_state_delete(x); __xfrm_state_put(x); goto out; } if (x->km.state == XFRM_STATE_VOID) x->km.state = XFRM_STATE_VALID; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.event = nlh->nlmsg_type; km_state_notify(x, &c); out: xfrm_state_put(x); return err; } static struct xfrm_state *xfrm_user_state_lookup(struct net *net, struct xfrm_usersa_id *p, struct nlattr **attrs, int *errp) { struct xfrm_state *x = NULL; struct xfrm_mark m; int err; u32 mark = xfrm_mark_get(attrs, &m); if (xfrm_id_proto_match(p->proto, IPSEC_PROTO_ANY)) { err = -ESRCH; x = xfrm_state_lookup(net, mark, &p->daddr, p->spi, p->proto, p->family); } else { xfrm_address_t *saddr = NULL; verify_one_addr(attrs, XFRMA_SRCADDR, &saddr); if (!saddr) { err = -EINVAL; goto out; } err = -ESRCH; x = xfrm_state_lookup_byaddr(net, mark, &p->daddr, saddr, p->proto, p->family); } out: if (!x && errp) *errp = err; return x; } static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_state *x; int err = -ESRCH; struct km_event c; struct xfrm_usersa_id *p = nlmsg_data(nlh); x = xfrm_user_state_lookup(net, p, attrs, &err); if (x == NULL) return err; if ((err = security_xfrm_state_delete(x)) != 0) goto out; if (xfrm_state_kern(x)) { NL_SET_ERR_MSG(extack, "SA is in use by tunnels"); err = -EPERM; goto out; } err = xfrm_state_delete(x); if (err < 0) goto out; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.event = nlh->nlmsg_type; km_state_notify(x, &c); out: xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; } static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) { memset(p, 0, sizeof(*p)); memcpy(&p->id, &x->id, sizeof(p->id)); memcpy(&p->sel, &x->sel, sizeof(p->sel)); memcpy(&p->lft, &x->lft, sizeof(p->lft)); if (x->xso.dev) xfrm_dev_state_update_stats(x); memcpy(&p->curlft, &x->curlft, sizeof(p->curlft)); put_unaligned(x->stats.replay_window, &p->stats.replay_window); put_unaligned(x->stats.replay, &p->stats.replay); put_unaligned(x->stats.integrity_failed, &p->stats.integrity_failed); memcpy(&p->saddr, &x->props.saddr, sizeof(p->saddr)); p->mode = x->props.mode; p->replay_window = x->props.replay_window; p->reqid = x->props.reqid; p->family = x->props.family; p->flags = x->props.flags; p->seq = x->km.seq; } struct xfrm_dump_info { struct sk_buff *in_skb; struct sk_buff *out_skb; u32 nlmsg_seq; u16 nlmsg_flags; }; static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb) { struct xfrm_user_sec_ctx *uctx; struct nlattr *attr; int ctx_size = sizeof(*uctx) + s->ctx_len; attr = nla_reserve(skb, XFRMA_SEC_CTX, ctx_size); if (attr == NULL) return -EMSGSIZE; uctx = nla_data(attr); uctx->exttype = XFRMA_SEC_CTX; uctx->len = ctx_size; uctx->ctx_doi = s->ctx_doi; uctx->ctx_alg = s->ctx_alg; uctx->ctx_len = s->ctx_len; memcpy(uctx + 1, s->ctx_str, s->ctx_len); return 0; } static void xso_to_xuo(const struct xfrm_dev_offload *xso, struct xfrm_user_offload *xuo) { xuo->ifindex = xso->dev->ifindex; if (xso->dir == XFRM_DEV_OFFLOAD_IN) xuo->flags = XFRM_OFFLOAD_INBOUND; if (xso->type == XFRM_DEV_OFFLOAD_PACKET) xuo->flags |= XFRM_OFFLOAD_PACKET; } static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) { struct xfrm_user_offload *xuo; struct nlattr *attr; attr = nla_reserve(skb, XFRMA_OFFLOAD_DEV, sizeof(*xuo)); if (attr == NULL) return -EMSGSIZE; xuo = nla_data(attr); memset(xuo, 0, sizeof(*xuo)); xso_to_xuo(xso, xuo); return 0; } static bool xfrm_redact(void) { return IS_ENABLED(CONFIG_SECURITY) && security_locked_down(LOCKDOWN_XFRM_SECRET); } static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) { struct xfrm_algo *algo; struct xfrm_algo_auth *ap; struct nlattr *nla; bool redact_secret = xfrm_redact(); nla = nla_reserve(skb, XFRMA_ALG_AUTH, sizeof(*algo) + (auth->alg_key_len + 7) / 8); if (!nla) return -EMSGSIZE; algo = nla_data(nla); strscpy_pad(algo->alg_name, auth->alg_name); if (redact_secret && auth->alg_key_len) memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8); else memcpy(algo->alg_key, auth->alg_key, (auth->alg_key_len + 7) / 8); algo->alg_key_len = auth->alg_key_len; nla = nla_reserve(skb, XFRMA_ALG_AUTH_TRUNC, xfrm_alg_auth_len(auth)); if (!nla) return -EMSGSIZE; ap = nla_data(nla); strscpy_pad(ap->alg_name, auth->alg_name); ap->alg_key_len = auth->alg_key_len; ap->alg_trunc_len = auth->alg_trunc_len; if (redact_secret && auth->alg_key_len) memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8); else memcpy(ap->alg_key, auth->alg_key, (auth->alg_key_len + 7) / 8); return 0; } static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb) { struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_AEAD, aead_len(aead)); struct xfrm_algo_aead *ap; bool redact_secret = xfrm_redact(); if (!nla) return -EMSGSIZE; ap = nla_data(nla); strscpy_pad(ap->alg_name, aead->alg_name); ap->alg_key_len = aead->alg_key_len; ap->alg_icv_len = aead->alg_icv_len; if (redact_secret && aead->alg_key_len) memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8); else memcpy(ap->alg_key, aead->alg_key, (aead->alg_key_len + 7) / 8); return 0; } static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb) { struct xfrm_algo *ap; bool redact_secret = xfrm_redact(); struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(ealg)); if (!nla) return -EMSGSIZE; ap = nla_data(nla); strscpy_pad(ap->alg_name, ealg->alg_name); ap->alg_key_len = ealg->alg_key_len; if (redact_secret && ealg->alg_key_len) memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8); else memcpy(ap->alg_key, ealg->alg_key, (ealg->alg_key_len + 7) / 8); return 0; } static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb) { struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_COMP, sizeof(*calg)); struct xfrm_algo *ap; if (!nla) return -EMSGSIZE; ap = nla_data(nla); strscpy_pad(ap->alg_name, calg->alg_name); ap->alg_key_len = 0; return 0; } static int copy_to_user_encap(struct xfrm_encap_tmpl *ep, struct sk_buff *skb) { struct nlattr *nla = nla_reserve(skb, XFRMA_ENCAP, sizeof(*ep)); struct xfrm_encap_tmpl *uep; if (!nla) return -EMSGSIZE; uep = nla_data(nla); memset(uep, 0, sizeof(*uep)); uep->encap_type = ep->encap_type; uep->encap_sport = ep->encap_sport; uep->encap_dport = ep->encap_dport; uep->encap_oa = ep->encap_oa; return 0; } static int xfrm_smark_put(struct sk_buff *skb, const struct xfrm_mark *m) { int ret = 0; if (m->v | m->m) { ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v); if (!ret) ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m); } return ret; } /* Don't change this without updating xfrm_sa_len! */ static int copy_to_user_state_extra(struct xfrm_state *x, struct xfrm_usersa_info *p, struct sk_buff *skb) { int ret = 0; copy_to_user_state(x, p); if (x->props.extra_flags) { ret = nla_put_u32(skb, XFRMA_SA_EXTRA_FLAGS, x->props.extra_flags); if (ret) goto out; } if (x->coaddr) { ret = nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr); if (ret) goto out; } if (x->lastused) { ret = nla_put_u64_64bit(skb, XFRMA_LASTUSED, x->lastused, XFRMA_PAD); if (ret) goto out; } if (x->aead) { ret = copy_to_user_aead(x->aead, skb); if (ret) goto out; } if (x->aalg) { ret = copy_to_user_auth(x->aalg, skb); if (ret) goto out; } if (x->ealg) { ret = copy_to_user_ealg(x->ealg, skb); if (ret) goto out; } if (x->calg) { ret = copy_to_user_calg(x->calg, skb); if (ret) goto out; } if (x->encap) { ret = copy_to_user_encap(x->encap, skb); if (ret) goto out; } if (x->tfcpad) { ret = nla_put_u32(skb, XFRMA_TFCPAD, x->tfcpad); if (ret) goto out; } ret = xfrm_mark_put(skb, &x->mark); if (ret) goto out; ret = xfrm_smark_put(skb, &x->props.smark); if (ret) goto out; if (x->replay_esn) ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL, xfrm_replay_state_esn_len(x->replay_esn), x->replay_esn); else ret = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), &x->replay); if (ret) goto out; if(x->xso.dev) ret = copy_user_offload(&x->xso, skb); if (ret) goto out; if (x->if_id) { ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id); if (ret) goto out; } if (x->security) { ret = copy_sec_ctx(x->security, skb); if (ret) goto out; } if (x->mode_cbs && x->mode_cbs->copy_to_user) ret = x->mode_cbs->copy_to_user(x, skb); if (ret) goto out; if (x->mapping_maxage) { ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage); if (ret) goto out; } if (x->pcpu_num != UINT_MAX) { ret = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num); if (ret) goto out; } if (x->dir) ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); if (x->nat_keepalive_interval) { ret = nla_put_u32(skb, XFRMA_NAT_KEEPALIVE_INTERVAL, x->nat_keepalive_interval); if (ret) goto out; } out: return ret; } static int dump_one_state(struct xfrm_state *x, int count, void *ptr) { struct xfrm_dump_info *sp = ptr; struct sk_buff *in_skb = sp->in_skb; struct sk_buff *skb = sp->out_skb; struct xfrm_translator *xtr; struct xfrm_usersa_info *p; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq, XFRM_MSG_NEWSA, sizeof(*p), sp->nlmsg_flags); if (nlh == NULL) return -EMSGSIZE; p = nlmsg_data(nlh); err = copy_to_user_state_extra(x, p, skb); if (err) { nlmsg_cancel(skb, nlh); return err; } nlmsg_end(skb, nlh); xtr = xfrm_get_translator(); if (xtr) { err = xtr->alloc_compat(skb, nlh); xfrm_put_translator(xtr); if (err) { nlmsg_cancel(skb, nlh); return err; } } return 0; } static int xfrm_dump_sa_done(struct netlink_callback *cb) { struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1]; struct sock *sk = cb->skb->sk; struct net *net = sock_net(sk); if (cb->args[0]) xfrm_state_walk_done(walk, net); return 0; } static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1]; struct xfrm_dump_info info; BUILD_BUG_ON(sizeof(struct xfrm_state_walk) > sizeof(cb->args) - sizeof(cb->args[0])); info.in_skb = cb->skb; info.out_skb = skb; info.nlmsg_seq = cb->nlh->nlmsg_seq; info.nlmsg_flags = NLM_F_MULTI; if (!cb->args[0]) { struct nlattr *attrs[XFRMA_MAX+1]; struct xfrm_address_filter *filter = NULL; u8 proto = 0; int err; err = nlmsg_parse_deprecated(cb->nlh, 0, attrs, XFRMA_MAX, xfrma_policy, cb->extack); if (err < 0) return err; if (attrs[XFRMA_ADDRESS_FILTER]) { filter = kmemdup(nla_data(attrs[XFRMA_ADDRESS_FILTER]), sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; /* see addr_match(), (prefix length >> 5) << 2 * will be used to compare xfrm_address_t */ if (filter->splen > (sizeof(xfrm_address_t) << 3) || filter->dplen > (sizeof(xfrm_address_t) << 3)) { kfree(filter); return -EINVAL; } } if (attrs[XFRMA_PROTO]) proto = nla_get_u8(attrs[XFRMA_PROTO]); xfrm_state_walk_init(walk, proto, filter); cb->args[0] = 1; } (void) xfrm_state_walk(net, walk, dump_one_state, &info); return skb->len; } static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb, struct xfrm_state *x, u32 seq) { struct xfrm_dump_info info; struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); info.in_skb = in_skb; info.out_skb = skb; info.nlmsg_seq = seq; info.nlmsg_flags = 0; err = dump_one_state(x, 0, &info); if (err) { kfree_skb(skb); return ERR_PTR(err); } return skb; } /* A wrapper for nlmsg_multicast() checking that nlsk is still available. * Must be called with RCU read lock. */ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, u32 pid, unsigned int group) { struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); struct xfrm_translator *xtr; if (!nlsk) { kfree_skb(skb); return -EPIPE; } xtr = xfrm_get_translator(); if (xtr) { int err = xtr->alloc_compat(skb, nlmsg_hdr(skb)); xfrm_put_translator(xtr); if (err) { kfree_skb(skb); return err; } } return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); } static inline unsigned int xfrm_spdinfo_msgsize(void) { return NLMSG_ALIGN(4) + nla_total_size(sizeof(struct xfrmu_spdinfo)) + nla_total_size(sizeof(struct xfrmu_spdhinfo)) + nla_total_size(sizeof(struct xfrmu_spdhthresh)) + nla_total_size(sizeof(struct xfrmu_spdhthresh)); } static int build_spdinfo(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, u32 flags) { struct xfrmk_spdinfo si; struct xfrmu_spdinfo spc; struct xfrmu_spdhinfo sph; struct xfrmu_spdhthresh spt4, spt6; struct nlmsghdr *nlh; int err; u32 *f; unsigned lseq; nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0); if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; f = nlmsg_data(nlh); *f = flags; xfrm_spd_getinfo(net, &si); spc.incnt = si.incnt; spc.outcnt = si.outcnt; spc.fwdcnt = si.fwdcnt; spc.inscnt = si.inscnt; spc.outscnt = si.outscnt; spc.fwdscnt = si.fwdscnt; sph.spdhcnt = si.spdhcnt; sph.spdhmcnt = si.spdhmcnt; do { lseq = read_seqbegin(&net->xfrm.policy_hthresh.lock); spt4.lbits = net->xfrm.policy_hthresh.lbits4; spt4.rbits = net->xfrm.policy_hthresh.rbits4; spt6.lbits = net->xfrm.policy_hthresh.lbits6; spt6.rbits = net->xfrm.policy_hthresh.rbits6; } while (read_seqretry(&net->xfrm.policy_hthresh.lock, lseq)); err = nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc); if (!err) err = nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph); if (!err) err = nla_put(skb, XFRMA_SPD_IPV4_HTHRESH, sizeof(spt4), &spt4); if (!err) err = nla_put(skb, XFRMA_SPD_IPV6_HTHRESH, sizeof(spt6), &spt6); if (err) { nlmsg_cancel(skb, nlh); return err; } nlmsg_end(skb, nlh); return 0; } static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrmu_spdhthresh *thresh4 = NULL; struct xfrmu_spdhthresh *thresh6 = NULL; /* selector prefixlen thresholds to hash policies */ if (attrs[XFRMA_SPD_IPV4_HTHRESH]) { struct nlattr *rta = attrs[XFRMA_SPD_IPV4_HTHRESH]; if (nla_len(rta) < sizeof(*thresh4)) { NL_SET_ERR_MSG(extack, "Invalid SPD_IPV4_HTHRESH attribute length"); return -EINVAL; } thresh4 = nla_data(rta); if (thresh4->lbits > 32 || thresh4->rbits > 32) { NL_SET_ERR_MSG(extack, "Invalid hash threshold (must be <= 32 for IPv4)"); return -EINVAL; } } if (attrs[XFRMA_SPD_IPV6_HTHRESH]) { struct nlattr *rta = attrs[XFRMA_SPD_IPV6_HTHRESH]; if (nla_len(rta) < sizeof(*thresh6)) { NL_SET_ERR_MSG(extack, "Invalid SPD_IPV6_HTHRESH attribute length"); return -EINVAL; } thresh6 = nla_data(rta); if (thresh6->lbits > 128 || thresh6->rbits > 128) { NL_SET_ERR_MSG(extack, "Invalid hash threshold (must be <= 128 for IPv6)"); return -EINVAL; } } if (thresh4 || thresh6) { write_seqlock(&net->xfrm.policy_hthresh.lock); if (thresh4) { net->xfrm.policy_hthresh.lbits4 = thresh4->lbits; net->xfrm.policy_hthresh.rbits4 = thresh4->rbits; } if (thresh6) { net->xfrm.policy_hthresh.lbits6 = thresh6->lbits; net->xfrm.policy_hthresh.rbits6 = thresh6->rbits; } write_sequnlock(&net->xfrm.policy_hthresh.lock); xfrm_policy_hash_rebuild(net); } return 0; } static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct sk_buff *r_skb; u32 *flags = nlmsg_data(nlh); u32 sportid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; int err; r_skb = nlmsg_new(xfrm_spdinfo_msgsize(), GFP_ATOMIC); if (r_skb == NULL) return -ENOMEM; err = build_spdinfo(r_skb, net, sportid, seq, *flags); BUG_ON(err < 0); return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid); } static inline unsigned int xfrm_sadinfo_msgsize(void) { return NLMSG_ALIGN(4) + nla_total_size(sizeof(struct xfrmu_sadhinfo)) + nla_total_size(4); /* XFRMA_SAD_CNT */ } static int build_sadinfo(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, u32 flags) { struct xfrmk_sadinfo si; struct xfrmu_sadhinfo sh; struct nlmsghdr *nlh; int err; u32 *f; nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0); if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; f = nlmsg_data(nlh); *f = flags; xfrm_sad_getinfo(net, &si); sh.sadhmcnt = si.sadhmcnt; sh.sadhcnt = si.sadhcnt; err = nla_put_u32(skb, XFRMA_SAD_CNT, si.sadcnt); if (!err) err = nla_put(skb, XFRMA_SAD_HINFO, sizeof(sh), &sh); if (err) { nlmsg_cancel(skb, nlh); return err; } nlmsg_end(skb, nlh); return 0; } static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct sk_buff *r_skb; u32 *flags = nlmsg_data(nlh); u32 sportid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; int err; r_skb = nlmsg_new(xfrm_sadinfo_msgsize(), GFP_ATOMIC); if (r_skb == NULL) return -ENOMEM; err = build_sadinfo(r_skb, net, sportid, seq, *flags); BUG_ON(err < 0); return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid); } static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_usersa_id *p = nlmsg_data(nlh); struct xfrm_state *x; struct sk_buff *resp_skb; int err = -ESRCH; x = xfrm_user_state_lookup(net, p, attrs, &err); if (x == NULL) goto out_noput; resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq); if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); } xfrm_state_put(x); out_noput: return err; } static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct xfrm_userspi_info *p; struct xfrm_translator *xtr; struct sk_buff *resp_skb; xfrm_address_t *daddr; int family; int err; u32 mark; struct xfrm_mark m; u32 if_id = 0; u32 pcpu_num = UINT_MAX; p = nlmsg_data(nlh); err = verify_spi_info(p->info.id.proto, p->min, p->max, extack); if (err) goto out_noput; family = p->info.family; daddr = &p->info.id.daddr; x = NULL; mark = xfrm_mark_get(attrs, &m); if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); if (attrs[XFRMA_SA_PCPU]) { pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); if (pcpu_num >= num_possible_cpus()) { err = -EINVAL; NL_SET_ERR_MSG(extack, "pCPU number too big"); goto out_noput; } } if (p->info.seq) { x = xfrm_find_acq_byseq(net, mark, p->info.seq, pcpu_num); if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) { xfrm_state_put(x); x = NULL; } } if (!x) x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid, if_id, pcpu_num, p->info.id.proto, daddr, &p->info.saddr, 1, family); err = -ENOENT; if (!x) { NL_SET_ERR_MSG(extack, "Target ACQUIRE not found"); goto out_noput; } err = xfrm_alloc_spi(x, p->min, p->max, extack); if (err) goto out; if (attrs[XFRMA_SA_DIR]) x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq); if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); goto out; } xtr = xfrm_get_translator(); if (xtr) { err = xtr->alloc_compat(skb, nlmsg_hdr(skb)); xfrm_put_translator(xtr); if (err) { kfree_skb(resp_skb); goto out; } } err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); out: xfrm_state_put(x); out_noput: return err; } static int verify_policy_dir(u8 dir, struct netlink_ext_ack *extack) { switch (dir) { case XFRM_POLICY_IN: case XFRM_POLICY_OUT: case XFRM_POLICY_FWD: break; default: NL_SET_ERR_MSG(extack, "Invalid policy direction"); return -EINVAL; } return 0; } static int verify_policy_type(u8 type, struct netlink_ext_ack *extack) { switch (type) { case XFRM_POLICY_TYPE_MAIN: #ifdef CONFIG_XFRM_SUB_POLICY case XFRM_POLICY_TYPE_SUB: #endif break; default: NL_SET_ERR_MSG(extack, "Invalid policy type"); return -EINVAL; } return 0; } static int verify_newpolicy_info(struct xfrm_userpolicy_info *p, struct netlink_ext_ack *extack) { int ret; switch (p->share) { case XFRM_SHARE_ANY: case XFRM_SHARE_SESSION: case XFRM_SHARE_USER: case XFRM_SHARE_UNIQUE: break; default: NL_SET_ERR_MSG(extack, "Invalid policy share"); return -EINVAL; } switch (p->action) { case XFRM_POLICY_ALLOW: case XFRM_POLICY_BLOCK: break; default: NL_SET_ERR_MSG(extack, "Invalid policy action"); return -EINVAL; } switch (p->sel.family) { case AF_INET: if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) { NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 32 for IPv4)"); return -EINVAL; } break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length in selector (must be <= 128 for IPv6)"); return -EINVAL; } break; #else NL_SET_ERR_MSG(extack, "IPv6 support disabled"); return -EAFNOSUPPORT; #endif default: NL_SET_ERR_MSG(extack, "Invalid selector family"); return -EINVAL; } ret = verify_policy_dir(p->dir, extack); if (ret) return ret; if (p->index && (xfrm_policy_id2dir(p->index) != p->dir)) { NL_SET_ERR_MSG(extack, "Policy index doesn't match direction"); return -EINVAL; } return 0; } static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs) { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_user_sec_ctx *uctx; if (!rt) return 0; uctx = nla_data(rt); return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL); } static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, int nr) { int i; xp->xfrm_nr = nr; for (i = 0; i < nr; i++, ut++) { struct xfrm_tmpl *t = &xp->xfrm_vec[i]; memcpy(&t->id, &ut->id, sizeof(struct xfrm_id)); memcpy(&t->saddr, &ut->saddr, sizeof(xfrm_address_t)); t->reqid = ut->reqid; t->mode = ut->mode; t->share = ut->share; t->optional = ut->optional; t->aalgos = ut->aalgos; t->ealgos = ut->ealgos; t->calgos = ut->calgos; /* If all masks are ~0, then we allow all algorithms. */ t->allalgs = !~(t->aalgos & t->ealgos & t->calgos); t->encap_family = ut->family; } } static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, int dir, struct netlink_ext_ack *extack) { u16 prev_family; int i; if (nr > XFRM_MAX_DEPTH) { NL_SET_ERR_MSG(extack, "Template count must be <= XFRM_MAX_DEPTH (" __stringify(XFRM_MAX_DEPTH) ")"); return -EINVAL; } prev_family = family; for (i = 0; i < nr; i++) { /* We never validated the ut->family value, so many * applications simply leave it at zero. The check was * never made and ut->family was ignored because all * templates could be assumed to have the same family as * the policy itself. Now that we will have ipv4-in-ipv6 * and ipv6-in-ipv4 tunnels, this is no longer true. */ if (!ut[i].family) ut[i].family = family; switch (ut[i].mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: if (ut[i].optional && dir == XFRM_POLICY_OUT) { NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy"); return -EINVAL; } break; case XFRM_MODE_IPTFS: break; default: if (ut[i].family != prev_family) { NL_SET_ERR_MSG(extack, "Mode in template doesn't support a family change"); return -EINVAL; } break; } if (ut[i].mode >= XFRM_MODE_MAX) { NL_SET_ERR_MSG(extack, "Mode in template must be < XFRM_MODE_MAX (" __stringify(XFRM_MODE_MAX) ")"); return -EINVAL; } prev_family = ut[i].family; switch (ut[i].family) { case AF_INET: break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: break; #endif default: NL_SET_ERR_MSG(extack, "Invalid family in template"); return -EINVAL; } if (!xfrm_id_proto_valid(ut[i].id.proto)) { NL_SET_ERR_MSG(extack, "Invalid XFRM protocol in template"); return -EINVAL; } } return 0; } static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, int dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_TMPL]; if (!rt) { pol->xfrm_nr = 0; } else { struct xfrm_user_tmpl *utmpl = nla_data(rt); int nr = nla_len(rt) / sizeof(*utmpl); int err; err = validate_tmpl(nr, utmpl, pol->family, dir, extack); if (err) return err; copy_templates(pol, utmpl, nr); } return 0; } static int copy_from_user_policy_type(u8 *tp, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_POLICY_TYPE]; struct xfrm_userpolicy_type *upt; u8 type = XFRM_POLICY_TYPE_MAIN; int err; if (rt) { upt = nla_data(rt); type = upt->type; } err = verify_policy_type(type, extack); if (err) return err; *tp = type; return 0; } static void copy_from_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p) { xp->priority = p->priority; xp->index = p->index; memcpy(&xp->selector, &p->sel, sizeof(xp->selector)); memcpy(&xp->lft, &p->lft, sizeof(xp->lft)); xp->action = p->action; xp->flags = p->flags; xp->family = p->sel.family; /* XXX xp->share = p->share; */ } static void copy_to_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p, int dir) { memset(p, 0, sizeof(*p)); memcpy(&p->sel, &xp->selector, sizeof(p->sel)); memcpy(&p->lft, &xp->lft, sizeof(p->lft)); memcpy(&p->curlft, &xp->curlft, sizeof(p->curlft)); p->priority = xp->priority; p->index = xp->index; p->sel.family = xp->family; p->dir = dir; p->action = xp->action; p->flags = xp->flags; p->share = XFRM_SHARE_ANY; /* XXX xp->share */ } static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_userpolicy_info *p, struct nlattr **attrs, int *errp, struct netlink_ext_ack *extack) { struct xfrm_policy *xp = xfrm_policy_alloc(net, GFP_KERNEL); int err; if (!xp) { *errp = -ENOMEM; return NULL; } copy_from_user_policy(xp, p); err = copy_from_user_policy_type(&xp->type, attrs, extack); if (err) goto error; if (!(err = copy_from_user_tmpl(xp, attrs, p->dir, extack))) err = copy_from_user_sec_ctx(xp, attrs); if (err) goto error; xfrm_mark_get(attrs, &xp->mark); if (attrs[XFRMA_IF_ID]) xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); /* configure the hardware if offload is requested */ if (attrs[XFRMA_OFFLOAD_DEV]) { err = xfrm_dev_policy_add(net, xp, nla_data(attrs[XFRMA_OFFLOAD_DEV]), p->dir, extack); if (err) goto error; } return xp; error: *errp = err; xp->walk.dead = 1; xfrm_policy_destroy(xp); return NULL; } static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_info *p = nlmsg_data(nlh); struct xfrm_policy *xp; struct km_event c; int err; int excl; err = verify_newpolicy_info(p, extack); if (err) return err; err = verify_sec_ctx_len(attrs, extack); if (err) return err; xp = xfrm_policy_construct(net, p, attrs, &err, extack); if (!xp) return err; /* shouldn't excl be based on nlh flags?? * Aha! this is anti-netlink really i.e more pfkey derived * in netlink excl is a flag and you wouldn't need * a type XFRM_MSG_UPDPOLICY - JHS */ excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY; err = xfrm_policy_insert(p->dir, xp, excl); xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) { xfrm_dev_policy_delete(xp); xp->walk.dead = 1; xfrm_policy_destroy(xp); return err; } c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; km_policy_notify(xp, p->dir, &c); xfrm_pol_put(xp); return 0; } static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) { struct xfrm_user_tmpl vec[XFRM_MAX_DEPTH]; int i; if (xp->xfrm_nr == 0) return 0; if (xp->xfrm_nr > XFRM_MAX_DEPTH) return -ENOBUFS; for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; memset(up, 0, sizeof(*up)); memcpy(&up->id, &kp->id, sizeof(up->id)); up->family = kp->encap_family; memcpy(&up->saddr, &kp->saddr, sizeof(up->saddr)); up->reqid = kp->reqid; up->mode = kp->mode; up->share = kp->share; up->optional = kp->optional; up->aalgos = kp->aalgos; up->ealgos = kp->ealgos; up->calgos = kp->calgos; } return nla_put(skb, XFRMA_TMPL, sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr, vec); } static inline int copy_to_user_state_sec_ctx(struct xfrm_state *x, struct sk_buff *skb) { if (x->security) { return copy_sec_ctx(x->security, skb); } return 0; } static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *skb) { if (xp->security) return copy_sec_ctx(xp->security, skb); return 0; } static inline unsigned int userpolicy_type_attrsize(void) { #ifdef CONFIG_XFRM_SUB_POLICY return nla_total_size(sizeof(struct xfrm_userpolicy_type)); #else return 0; #endif } #ifdef CONFIG_XFRM_SUB_POLICY static int copy_to_user_policy_type(u8 type, struct sk_buff *skb) { struct xfrm_userpolicy_type upt; /* Sadly there are two holes in struct xfrm_userpolicy_type */ memset(&upt, 0, sizeof(upt)); upt.type = type; return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); } #else static inline int copy_to_user_policy_type(u8 type, struct sk_buff *skb) { return 0; } #endif static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr) { struct xfrm_dump_info *sp = ptr; struct xfrm_userpolicy_info *p; struct sk_buff *in_skb = sp->in_skb; struct sk_buff *skb = sp->out_skb; struct xfrm_translator *xtr; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq, XFRM_MSG_NEWPOLICY, sizeof(*p), sp->nlmsg_flags); if (nlh == NULL) return -EMSGSIZE; p = nlmsg_data(nlh); copy_to_user_policy(xp, p, dir); err = copy_to_user_tmpl(xp, skb); if (!err) err = copy_to_user_sec_ctx(xp, skb); if (!err) err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); if (!err && xp->xdo.dev) err = copy_user_offload(&xp->xdo, skb); if (err) { nlmsg_cancel(skb, nlh); return err; } nlmsg_end(skb, nlh); xtr = xfrm_get_translator(); if (xtr) { err = xtr->alloc_compat(skb, nlh); xfrm_put_translator(xtr); if (err) { nlmsg_cancel(skb, nlh); return err; } } return 0; } static int xfrm_dump_policy_done(struct netlink_callback *cb) { struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args; struct net *net = sock_net(cb->skb->sk); xfrm_policy_walk_done(walk, net); return 0; } static int xfrm_dump_policy_start(struct netlink_callback *cb) { struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args; BUILD_BUG_ON(sizeof(*walk) > sizeof(cb->args)); xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY); return 0; } static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *)cb->args; struct xfrm_dump_info info; info.in_skb = cb->skb; info.out_skb = skb; info.nlmsg_seq = cb->nlh->nlmsg_seq; info.nlmsg_flags = NLM_F_MULTI; (void) xfrm_policy_walk(net, walk, dump_one_policy, &info); return skb->len; } static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb, struct xfrm_policy *xp, int dir, u32 seq) { struct xfrm_dump_info info; struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); info.in_skb = in_skb; info.out_skb = skb; info.nlmsg_seq = seq; info.nlmsg_flags = 0; err = dump_one_policy(xp, dir, 0, &info); if (err) { kfree_skb(skb); return ERR_PTR(err); } return skb; } static int xfrm_notify_userpolicy(struct net *net) { struct xfrm_userpolicy_default *up; int len = NLMSG_ALIGN(sizeof(*up)); struct nlmsghdr *nlh; struct sk_buff *skb; int err; skb = nlmsg_new(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_GETDEFAULT, sizeof(*up), 0); if (nlh == NULL) { kfree_skb(skb); return -EMSGSIZE; } up = nlmsg_data(nlh); up->in = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN]); up->fwd = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD]); up->out = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]); nlmsg_end(skb, nlh); rcu_read_lock(); err = xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); rcu_read_unlock(); return err; } static bool xfrm_userpolicy_is_valid(__u8 policy) { return policy == XFRM_USERPOLICY_BLOCK || policy == XFRM_USERPOLICY_ACCEPT; } static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_default *up = nlmsg_data(nlh); if (xfrm_userpolicy_is_valid(up->in)) WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN], up->in); if (xfrm_userpolicy_is_valid(up->fwd)) WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD], up->fwd); if (xfrm_userpolicy_is_valid(up->out)) WRITE_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT], up->out); rt_genid_bump_all(net); xfrm_notify_userpolicy(net); return 0; } static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct sk_buff *r_skb; struct nlmsghdr *r_nlh; struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_default *r_up; int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default)); u32 portid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; r_skb = nlmsg_new(len, GFP_ATOMIC); if (!r_skb) return -ENOMEM; r_nlh = nlmsg_put(r_skb, portid, seq, XFRM_MSG_GETDEFAULT, sizeof(*r_up), 0); if (!r_nlh) { kfree_skb(r_skb); return -EMSGSIZE; } r_up = nlmsg_data(r_nlh); r_up->in = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_IN]); r_up->fwd = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_FWD]); r_up->out = READ_ONCE(net->xfrm.policy_default[XFRM_POLICY_OUT]); nlmsg_end(r_skb, r_nlh); return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, portid); } static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_policy *xp; struct xfrm_userpolicy_id *p; u8 type = XFRM_POLICY_TYPE_MAIN; int err; struct km_event c; int delete; struct xfrm_mark m; u32 if_id = 0; p = nlmsg_data(nlh); delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY; err = copy_from_user_policy_type(&type, attrs, extack); if (err) return err; err = verify_policy_dir(p->dir, extack); if (err) return err; if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); xfrm_mark_get(attrs, &m); if (p->index) xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; err = verify_sec_ctx_len(attrs, extack); if (err) return err; ctx = NULL; if (rt) { struct xfrm_user_sec_ctx *uctx = nla_data(rt); err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL); if (err) return err; } xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) return -ENOENT; if (!delete) { struct sk_buff *resp_skb; resp_skb = xfrm_policy_netlink(skb, xp, p->dir, nlh->nlmsg_seq); if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid); } } else { xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err != 0) goto out; c.data.byid = p->index; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; km_policy_notify(xp, p->dir, &c); } out: xfrm_pol_put(xp); return err; } static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct km_event c; struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; return err; } c.data.proto = p->proto; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.net = net; km_state_notify(NULL, &c); return 0; } static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x) { unsigned int replay_size = x->replay_esn ? xfrm_replay_state_esn_len(x->replay_esn) : sizeof(struct xfrm_replay_state); return NLMSG_ALIGN(sizeof(struct xfrm_aevent_id)) + nla_total_size(replay_size) + nla_total_size_64bit(sizeof(struct xfrm_lifetime_cur)) + nla_total_size(sizeof(struct xfrm_mark)) + nla_total_size(4) /* XFRM_AE_RTHR */ + nla_total_size(4) /* XFRM_AE_ETHR */ + nla_total_size(sizeof(x->dir)) /* XFRMA_SA_DIR */ + nla_total_size(4) /* XFRMA_SA_PCPU */ + nla_total_size(sizeof(x->if_id)); /* XFRMA_IF_ID */ } static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) { struct xfrm_aevent_id *id; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_NEWAE, sizeof(*id), 0); if (nlh == NULL) return -EMSGSIZE; id = nlmsg_data(nlh); memset(&id->sa_id, 0, sizeof(id->sa_id)); memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr)); id->sa_id.spi = x->id.spi; id->sa_id.family = x->props.family; id->sa_id.proto = x->id.proto; memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr)); id->reqid = x->props.reqid; id->flags = c->data.aevent; if (x->replay_esn) { err = nla_put(skb, XFRMA_REPLAY_ESN_VAL, xfrm_replay_state_esn_len(x->replay_esn), x->replay_esn); } else { err = nla_put(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), &x->replay); } if (err) goto out_cancel; err = nla_put_64bit(skb, XFRMA_LTIME_VAL, sizeof(x->curlft), &x->curlft, XFRMA_PAD); if (err) goto out_cancel; if (id->flags & XFRM_AE_RTHR) { err = nla_put_u32(skb, XFRMA_REPLAY_THRESH, x->replay_maxdiff); if (err) goto out_cancel; } if (id->flags & XFRM_AE_ETHR) { err = nla_put_u32(skb, XFRMA_ETIMER_THRESH, x->replay_maxage * 10 / HZ); if (err) goto out_cancel; } err = xfrm_mark_put(skb, &x->mark); if (err) goto out_cancel; err = xfrm_if_id_put(skb, x->if_id); if (err) goto out_cancel; if (x->pcpu_num != UINT_MAX) { err = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num); if (err) goto out_cancel; } if (x->dir) { err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); if (err) goto out_cancel; } nlmsg_end(skb, nlh); return 0; out_cancel: nlmsg_cancel(skb, nlh); return err; } static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct sk_buff *r_skb; int err; struct km_event c; u32 mark; struct xfrm_mark m; struct xfrm_aevent_id *p = nlmsg_data(nlh); struct xfrm_usersa_id *id = &p->sa_id; mark = xfrm_mark_get(attrs, &m); x = xfrm_state_lookup(net, mark, &id->daddr, id->spi, id->proto, id->family); if (x == NULL) return -ESRCH; r_skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC); if (r_skb == NULL) { xfrm_state_put(x); return -ENOMEM; } /* * XXX: is this lock really needed - none of the other * gets lock (the concern is things getting updated * while we are still reading) - jhs */ spin_lock_bh(&x->lock); c.data.aevent = p->flags; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; err = build_aevent(r_skb, x, &c); if (err < 0) { spin_unlock_bh(&x->lock); xfrm_state_put(x); kfree_skb(r_skb); return err; } err = nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, NETLINK_CB(skb).portid); spin_unlock_bh(&x->lock); xfrm_state_put(x); return err; } static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct km_event c; int err = -EINVAL; u32 mark = 0; struct xfrm_mark m; struct xfrm_aevent_id *p = nlmsg_data(nlh); struct nlattr *rp = attrs[XFRMA_REPLAY_VAL]; struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL]; struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; if (!lt && !rp && !re && !et && !rt) { NL_SET_ERR_MSG(extack, "Missing required attribute for AE"); return err; } /* pedantic mode - thou shalt sayeth replaceth */ if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "NLM_F_REPLACE flag is required"); return err; } mark = xfrm_mark_get(attrs, &m); x = xfrm_state_lookup(net, mark, &p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family); if (x == NULL) return -ESRCH; if (x->km.state != XFRM_STATE_VALID) { NL_SET_ERR_MSG(extack, "SA must be in VALID state"); goto out; } err = xfrm_replay_verify_len(x->replay_esn, re, extack); if (err) goto out; spin_lock_bh(&x->lock); xfrm_update_ae_params(x, attrs, 1); spin_unlock_bh(&x->lock); c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.data.aevent = XFRM_AE_CU; km_state_notify(x, &c); err = 0; out: xfrm_state_put(x); return err; } static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct km_event c; u8 type = XFRM_POLICY_TYPE_MAIN; int err; err = copy_from_user_policy_type(&type, attrs, extack); if (err) return err; err = xfrm_policy_flush(net, type, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; return err; } c.data.type = type; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; c.net = net; km_policy_notify(NULL, 0, &c); return 0; } static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_policy *xp; struct xfrm_user_polexpire *up = nlmsg_data(nlh); struct xfrm_userpolicy_info *p = &up->pol; u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; struct xfrm_mark m; u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs, extack); if (err) return err; err = verify_policy_dir(p->dir, extack); if (err) return err; if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); xfrm_mark_get(attrs, &m); if (p->index) xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; err = verify_sec_ctx_len(attrs, extack); if (err) return err; ctx = NULL; if (rt) { struct xfrm_user_sec_ctx *uctx = nla_data(rt); err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL); if (err) return err; } xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) return -ENOENT; if (unlikely(xp->walk.dead)) goto out; err = 0; if (up->hard) { xfrm_policy_delete(xp, p->dir); xfrm_audit_policy_delete(xp, 1, true); } km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid); out: xfrm_pol_put(xp); return err; } static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_state *x; int err; struct xfrm_user_expire *ue = nlmsg_data(nlh); struct xfrm_usersa_info *p = &ue->state; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); x = xfrm_state_lookup(net, mark, &p->id.daddr, p->id.spi, p->id.proto, p->family); err = -ENOENT; if (x == NULL) return err; spin_lock_bh(&x->lock); err = -EINVAL; if (x->km.state != XFRM_STATE_VALID) { NL_SET_ERR_MSG(extack, "SA must be in VALID state"); goto out; } km_state_expired(x, ue->hard, nlh->nlmsg_pid); if (ue->hard) { __xfrm_state_delete(x); xfrm_audit_state_delete(x, 1, true); } err = 0; out: spin_unlock_bh(&x->lock); xfrm_state_put(x); return err; } static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct xfrm_policy *xp; struct xfrm_user_tmpl *ut; int i; struct nlattr *rt = attrs[XFRMA_TMPL]; struct xfrm_mark mark; struct xfrm_user_acquire *ua = nlmsg_data(nlh); struct xfrm_state *x = xfrm_state_alloc(net); int err = -ENOMEM; if (!x) goto nomem; xfrm_mark_get(attrs, &mark); if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); err = -EINVAL; if (x->pcpu_num >= num_possible_cpus()) { NL_SET_ERR_MSG(extack, "pCPU number too big"); goto free_state; } } err = verify_newpolicy_info(&ua->policy, extack); if (err) goto free_state; err = verify_sec_ctx_len(attrs, extack); if (err) goto free_state; /* build an XP */ xp = xfrm_policy_construct(net, &ua->policy, attrs, &err, extack); if (!xp) goto free_state; memcpy(&x->id, &ua->id, sizeof(ua->id)); memcpy(&x->props.saddr, &ua->saddr, sizeof(ua->saddr)); memcpy(&x->sel, &ua->sel, sizeof(ua->sel)); xp->mark.m = x->mark.m = mark.m; xp->mark.v = x->mark.v = mark.v; ut = nla_data(rt); /* extract the templates and for each call km_key */ for (i = 0; i < xp->xfrm_nr; i++, ut++) { struct xfrm_tmpl *t = &xp->xfrm_vec[i]; memcpy(&x->id, &t->id, sizeof(x->id)); x->props.mode = t->mode; x->props.reqid = t->reqid; x->props.family = ut->family; t->aalgos = ua->aalgos; t->ealgos = ua->ealgos; t->calgos = ua->calgos; err = km_query(x, t, xp); } xfrm_state_free(x); xfrm_dev_policy_delete(xp); xfrm_dev_policy_free(xp); security_xfrm_policy_free(xp->security); kfree(xp); return 0; free_state: xfrm_state_free(x); nomem: return err; } #ifdef CONFIG_XFRM_MIGRATE static void copy_from_user_migrate_state(struct xfrm_migrate *ma, const struct xfrm_user_migrate_state *um) { memcpy(&ma->old_daddr, &um->id.daddr, sizeof(ma->old_daddr)); memcpy(&ma->new_daddr, &um->new_daddr, sizeof(ma->new_daddr)); memcpy(&ma->new_saddr, &um->new_saddr, sizeof(ma->new_saddr)); ma->proto = um->id.proto; ma->new_reqid = um->new_reqid; ma->old_family = um->id.family; ma->new_family = um->new_family; ma->old_mark = um->old_mark; ma->flags = um->flags; ma->new_sel = &um->new_sel; ma->msg_type = XFRM_MSG_MIGRATE_STATE; } static int copy_from_user_migrate(struct xfrm_migrate *ma, struct xfrm_kmaddress *k, struct nlattr **attrs, int *num, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_MIGRATE]; struct xfrm_user_migrate *um; int i, num_migrate; if (k != NULL) { struct xfrm_user_kmaddress *uk; uk = nla_data(attrs[XFRMA_KMADDRESS]); memcpy(&k->local, &uk->local, sizeof(k->local)); memcpy(&k->remote, &uk->remote, sizeof(k->remote)); k->family = uk->family; k->reserved = uk->reserved; } um = nla_data(rt); num_migrate = nla_len(rt) / sizeof(*um); if (num_migrate <= 0 || num_migrate > XFRM_MAX_DEPTH) { NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)"); return -EINVAL; } for (i = 0; i < num_migrate; i++, um++, ma++) { memcpy(&ma->old_daddr, &um->old_daddr, sizeof(ma->old_daddr)); memcpy(&ma->old_saddr, &um->old_saddr, sizeof(ma->old_saddr)); memcpy(&ma->new_daddr, &um->new_daddr, sizeof(ma->new_daddr)); memcpy(&ma->new_saddr, &um->new_saddr, sizeof(ma->new_saddr)); ma->proto = um->proto; ma->mode = um->mode; ma->old_reqid = um->reqid; ma->old_family = um->old_family; ma->new_family = um->new_family; ma->msg_type = XFRM_MSG_MIGRATE; } *num = i; return 0; } static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct xfrm_userpolicy_id *pi = nlmsg_data(nlh); struct xfrm_migrate m[XFRM_MAX_DEPTH] = {}; struct xfrm_kmaddress km, *kmp; u8 type; int err; int n = 0; struct net *net = sock_net(skb->sk); struct xfrm_encap_tmpl *encap = NULL; struct xfrm_user_offload *xuo = NULL; u32 if_id = 0; if (!attrs[XFRMA_MIGRATE]) { NL_SET_ERR_MSG(extack, "Missing required MIGRATE attribute"); return -EINVAL; } kmp = attrs[XFRMA_KMADDRESS] ? &km : NULL; err = copy_from_user_policy_type(&type, attrs, extack); if (err) return err; err = copy_from_user_migrate(m, kmp, attrs, &n, extack); if (err) return err; if (!n) return 0; if (attrs[XFRMA_ENCAP]) { encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), sizeof(*encap), GFP_KERNEL); if (!encap) return -ENOMEM; } if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); if (attrs[XFRMA_OFFLOAD_DEV]) { xuo = kmemdup(nla_data(attrs[XFRMA_OFFLOAD_DEV]), sizeof(*xuo), GFP_KERNEL); if (!xuo) { err = -ENOMEM; goto error; } } err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, if_id, extack, xuo); error: kfree(encap); kfree(xuo); return err; } static int build_migrate_state(struct sk_buff *skb, const struct xfrm_user_migrate_state *um, const struct xfrm_migrate *m, u8 dir, u32 portid, u32 seq) { int err; struct nlmsghdr *nlh; struct xfrm_user_migrate_state *hdr; nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_MIGRATE_STATE, sizeof(struct xfrm_user_migrate_state), 0); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); *hdr = *um; hdr->new_sel = *m->new_sel; if (m->encap) { err = nla_put(skb, XFRMA_ENCAP, sizeof(*m->encap), m->encap); if (err) goto out_cancel; } if (m->xuo) { err = nla_put(skb, XFRMA_OFFLOAD_DEV, sizeof(*m->xuo), m->xuo); if (err) goto out_cancel; } if (m->new_mark) { err = nla_put(skb, XFRMA_MARK, sizeof(*m->new_mark), m->new_mark); if (err) goto out_cancel; } err = xfrm_smark_put(skb, &m->smark); if (err) goto out_cancel; if (m->mapping_maxage) { err = nla_put_u32(skb, XFRMA_MTIMER_THRESH, m->mapping_maxage); if (err) goto out_cancel; } if (m->nat_keepalive_interval) { err = nla_put_u32(skb, XFRMA_NAT_KEEPALIVE_INTERVAL, m->nat_keepalive_interval); if (err) goto out_cancel; } if (dir) { err = nla_put_u8(skb, XFRMA_SA_DIR, dir); if (err) goto out_cancel; } nlmsg_end(skb, nlh); return 0; out_cancel: nlmsg_cancel(skb, nlh); return err; } static unsigned int xfrm_migrate_state_msgsize(const struct xfrm_migrate *m, u8 dir) { return NLMSG_ALIGN(sizeof(struct xfrm_user_migrate_state)) + (m->encap ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0) + (m->xuo ? nla_total_size(sizeof(struct xfrm_user_offload)) : 0) + (m->new_mark ? nla_total_size(sizeof(struct xfrm_mark)) : 0) + ((m->smark.v | m->smark.m) ? nla_total_size(sizeof(u32)) * 2 : 0) + (m->mapping_maxage ? nla_total_size(sizeof(u32)) : 0) + (m->nat_keepalive_interval ? nla_total_size(sizeof(u32)) : 0) + (dir ? nla_total_size(sizeof(u8)) : 0); /* XFRMA_SA_DIR */ } static int xfrm_send_migrate_state(struct net *net, const struct xfrm_user_migrate_state *um, const struct xfrm_migrate *m, u8 dir, u32 portid, u32 seq) { int err; struct sk_buff *skb; skb = nlmsg_new(xfrm_migrate_state_msgsize(m, dir), GFP_ATOMIC); if (!skb) return -ENOMEM; err = build_migrate_state(skb, um, m, dir, portid, seq); if (err < 0) { kfree_skb(skb); return err; } return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); } static int xfrm_do_migrate_state(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { struct xfrm_user_migrate_state *um = nlmsg_data(nlh); struct net *net = sock_net(skb->sk); struct xfrm_user_offload xuo = {}; struct xfrm_migrate m = {}; struct xfrm_state *xc; struct xfrm_state *x; int err; if (!um->id.spi) { NL_SET_ERR_MSG(extack, "Invalid SPI 0x0"); return -EINVAL; } if (um->reserved) { NL_SET_ERR_MSG(extack, "Reserved field must be zero"); return -EINVAL; } if (um->flags & ~XFRM_MIGRATE_STATE_KNOWN_FLAGS) { NL_SET_ERR_MSG_FMT(extack, "Unknown flags: 0x%x", um->flags & ~XFRM_MIGRATE_STATE_KNOWN_FLAGS); return -EINVAL; } err = verify_xfrm_family(um->new_family, extack); if (err) return err; if (!(um->flags & XFRM_MIGRATE_STATE_UPDATE_H2H_SEL)) { err = verify_selector_prefixlen(um->new_sel.family, &um->new_sel, extack); if (err) return err; } copy_from_user_migrate_state(&m, um); x = xfrm_state_lookup(net, m.old_mark.v & m.old_mark.m, &um->id.daddr, um->id.spi, um->id.proto, um->id.family); if (!x) { NL_SET_ERR_MSG(extack, "Can not find state"); return -ESRCH; } if (um->flags & XFRM_MIGRATE_STATE_UPDATE_H2H_SEL) { u8 prefixlen = (x->props.family == AF_INET6) ? 128 : 32; if (x->sel.prefixlen_s != x->sel.prefixlen_d || x->sel.prefixlen_d != prefixlen || !xfrm_addr_equal(&x->sel.daddr, &x->id.daddr, x->props.family) || !xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { NL_SET_ERR_MSG(extack, "SA selector is not a single-host match for SA addresses"); err = -EINVAL; goto out; } } if (attrs[XFRMA_ENCAP]) { m.encap = nla_data(attrs[XFRMA_ENCAP]); if (m.encap->encap_type == 0) { m.encap = NULL; /* sentinel: remove encap */ } else if (m.encap->encap_type != UDP_ENCAP_ESPINUDP) { NL_SET_ERR_MSG(extack, "Unsupported encapsulation type"); err = -EINVAL; goto out; } } else { m.encap = x->encap; /* omit-to-inherit */ } if (attrs[XFRMA_MTIMER_THRESH]) { err = verify_mtimer_thresh(!!m.encap, x->dir, extack); if (err) goto out; } if (nla_get_u32_default(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL], 0) && !m.encap) { NL_SET_ERR_MSG(extack, "NAT_KEEPALIVE_INTERVAL requires encapsulation"); err = -EINVAL; goto out; } if (attrs[XFRMA_OFFLOAD_DEV]) { m.xuo = nla_data(attrs[XFRMA_OFFLOAD_DEV]); } else { bool inherit_offload = !(um->flags & XFRM_MIGRATE_STATE_CLEAR_OFFLOAD); if (inherit_offload && x->xso.dev) { xso_to_xuo(&x->xso, &xuo); m.xuo = &xuo; } } if (attrs[XFRMA_MARK]) m.new_mark = nla_data(attrs[XFRMA_MARK]); if (attrs[XFRMA_SET_MARK]) xfrm_smark_init(attrs, &m.smark); else m.smark = x->props.smark; m.mapping_maxage = nla_get_u32_default(attrs[XFRMA_MTIMER_THRESH], x->mapping_maxage); m.nat_keepalive_interval = nla_get_u32_default(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL], x->nat_keepalive_interval); if (m.new_family != um->id.family || !xfrm_addr_equal(&m.new_daddr, &um->id.daddr, um->id.family)) { u32 new_mark_key = m.new_mark ? m.new_mark->v & m.new_mark->m : m.old_mark.v & m.old_mark.m; struct xfrm_state *x_new; x_new = xfrm_state_lookup(net, new_mark_key, &m.new_daddr, um->id.spi, um->id.proto, m.new_family); if (x_new) { xfrm_state_put(x_new); NL_SET_ERR_MSG(extack, "New SA tuple already occupied"); err = -EEXIST; goto out; } } xc = xfrm_state_migrate_create(x, &m, net, extack); if (!xc) { NL_SET_ERR_MSG_WEAK(extack, "State migration clone failed"); err = -EINVAL; goto out; } spin_lock_bh(&x->lock); if (x->km.state != XFRM_STATE_VALID) { spin_unlock_bh(&x->lock); NL_SET_ERR_MSG(extack, "State already deleted"); err = -ESRCH; goto out_xc; } xfrm_migrate_sync(xc, x); /* to prevent SN/IV reuse */ __xfrm_state_delete(x); spin_unlock_bh(&x->lock); err = xfrm_state_migrate_install(x, xc, &m, extack); if (err < 0) { /* * Should not occur: pre-check above ensures the new tuple is * free under xfrm_cfg_mutex. Both SAs are gone if it does; * restoring x would risk SN/IV reuse. */ goto out; } /* Restore encap cleared by sentinel (type=0) during migration. */ if (attrs[XFRMA_ENCAP]) m.encap = nla_data(attrs[XFRMA_ENCAP]); m.new_sel = &xc->sel; m.mapping_maxage = xc->mapping_maxage; m.nat_keepalive_interval = xc->nat_keepalive_interval; err = xfrm_send_migrate_state(net, um, &m, xc->dir, nlh->nlmsg_pid, nlh->nlmsg_seq); if (err < 0) { NL_SET_ERR_MSG(extack, "Failed to send migration notification"); err = 0; } out: xfrm_state_put(x); return err; out_xc: xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); xfrm_state_put(x); return err; } #else static int xfrm_do_migrate_state(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "XFRM_MSG_MIGRATE_STATE is not supported"); return -ENOPROTOOPT; } static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs, struct netlink_ext_ack *extack) { return -ENOPROTOOPT; } #endif #ifdef CONFIG_XFRM_MIGRATE static int copy_to_user_migrate(const struct xfrm_migrate *m, struct sk_buff *skb) { struct xfrm_user_migrate um; memset(&um, 0, sizeof(um)); um.proto = m->proto; um.mode = m->mode; um.reqid = m->old_reqid; um.old_family = m->old_family; memcpy(&um.old_daddr, &m->old_daddr, sizeof(um.old_daddr)); memcpy(&um.old_saddr, &m->old_saddr, sizeof(um.old_saddr)); um.new_family = m->new_family; memcpy(&um.new_daddr, &m->new_daddr, sizeof(um.new_daddr)); memcpy(&um.new_saddr, &m->new_saddr, sizeof(um.new_saddr)); return nla_put(skb, XFRMA_MIGRATE, sizeof(um), &um); } static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff *skb) { struct xfrm_user_kmaddress uk; memset(&uk, 0, sizeof(uk)); uk.family = k->family; uk.reserved = k->reserved; memcpy(&uk.local, &k->local, sizeof(uk.local)); memcpy(&uk.remote, &k->remote, sizeof(uk.remote)); return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk); } static inline unsigned int xfrm_migrate_msgsize(int num_migrate, int with_kma, int with_encp) { return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id)) + (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0) + (with_encp ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0) + nla_total_size(sizeof(struct xfrm_user_migrate) * num_migrate) + userpolicy_type_attrsize(); } static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, const struct xfrm_selector *sel, const struct xfrm_encap_tmpl *encap, u8 dir, u8 type) { const struct xfrm_migrate *mp; struct xfrm_userpolicy_id *pol_id; struct nlmsghdr *nlh; int i, err; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MIGRATE, sizeof(*pol_id), 0); if (nlh == NULL) return -EMSGSIZE; pol_id = nlmsg_data(nlh); /* copy data from selector, dir, and type to the pol_id */ memset(pol_id, 0, sizeof(*pol_id)); memcpy(&pol_id->sel, sel, sizeof(pol_id->sel)); pol_id->dir = dir; if (k != NULL) { err = copy_to_user_kmaddress(k, skb); if (err) goto out_cancel; } if (encap) { err = nla_put(skb, XFRMA_ENCAP, sizeof(*encap), encap); if (err) goto out_cancel; } err = copy_to_user_policy_type(type, skb); if (err) goto out_cancel; for (i = 0, mp = m ; i < num_migrate; i++, mp++) { err = copy_to_user_migrate(mp, skb); if (err) goto out_cancel; } nlmsg_end(skb, nlh); return 0; out_cancel: nlmsg_cancel(skb, nlh); return err; } static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { struct sk_buff *skb; int err; skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; /* build migrate */ err = build_migrate(skb, m, num_migrate, k, sel, encap, dir, type); BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); } #else static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } #endif #define XMSGSIZE(type) sizeof(struct type) const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userspi_info), [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_acquire), [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_expire), [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report), [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping), [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), [XFRM_MSG_MIGRATE_STATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_migrate_state), }; EXPORT_SYMBOL_GPL(xfrm_msg_min); #undef XMSGSIZE const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = sizeof(struct xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = sizeof(struct xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, [XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)}, [XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) }, [XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, [XFRMA_ETIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)}, [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) }, [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) }, [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) }, [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, [XFRMA_SA_PCPU] = { .type = NLA_U32 }, [XFRMA_IPTFS_DROP_TIME] = { .type = NLA_U32 }, [XFRMA_IPTFS_REORDER_WINDOW] = { .type = NLA_U16 }, [XFRMA_IPTFS_DONT_FRAG] = { .type = NLA_FLAG }, [XFRMA_IPTFS_INIT_DELAY] = { .type = NLA_U32 }, [XFRMA_IPTFS_MAX_QSIZE] = { .type = NLA_U32 }, [XFRMA_IPTFS_PKT_SIZE] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { [XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) }, [XFRMA_SPD_IPV6_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) }, }; static const struct xfrm_link { int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **, struct netlink_ext_ack *); int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff *, struct netlink_callback *); int (*done)(struct netlink_callback *); const struct nla_policy *nla_pol; int nla_max; } xfrm_dispatch[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa }, [XFRM_MSG_DELSA - XFRM_MSG_BASE] = { .doit = xfrm_del_sa }, [XFRM_MSG_GETSA - XFRM_MSG_BASE] = { .doit = xfrm_get_sa, .dump = xfrm_dump_sa, .done = xfrm_dump_sa_done }, [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy }, [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy }, [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy, .start = xfrm_dump_policy_start, .dump = xfrm_dump_policy, .done = xfrm_dump_policy_done }, [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi }, [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_acquire }, [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_sa_expire }, [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy }, [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa }, [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_pol_expire}, [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = { .doit = xfrm_flush_sa }, [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_flush_policy }, [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = { .doit = xfrm_new_ae }, [XFRM_MSG_GETAE - XFRM_MSG_BASE] = { .doit = xfrm_get_ae }, [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = { .doit = xfrm_do_migrate }, [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = { .doit = xfrm_get_sadinfo }, [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = { .doit = xfrm_set_spdinfo, .nla_pol = xfrma_spd_policy, .nla_max = XFRMA_SPD_MAX }, [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo }, [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_set_default }, [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_get_default }, [XFRM_MSG_MIGRATE_STATE - XFRM_MSG_BASE] = { .doit = xfrm_do_migrate_state }, }; static int xfrm_reject_unused_attr(int type, struct nlattr **attrs, struct netlink_ext_ack *extack) { if (attrs[XFRMA_SA_DIR]) { switch (type) { case XFRM_MSG_NEWSA: case XFRM_MSG_UPDSA: case XFRM_MSG_ALLOCSPI: break; default: NL_SET_ERR_MSG(extack, "Invalid attribute SA_DIR"); return -EINVAL; } } if (attrs[XFRMA_SA_PCPU]) { switch (type) { case XFRM_MSG_NEWSA: case XFRM_MSG_UPDSA: case XFRM_MSG_ALLOCSPI: case XFRM_MSG_ACQUIRE: break; default: NL_SET_ERR_MSG(extack, "Invalid attribute SA_PCPU"); return -EINVAL; } } if (type == XFRM_MSG_MIGRATE_STATE) { int i; for (i = 0; i <= XFRMA_MAX; i++) { if (!attrs[i]) continue; switch (i) { case XFRMA_MARK: case XFRMA_ENCAP: case XFRMA_OFFLOAD_DEV: case XFRMA_SET_MARK: case XFRMA_SET_MARK_MASK: case XFRMA_MTIMER_THRESH: case XFRMA_NAT_KEEPALIVE_INTERVAL: break; default: NL_SET_ERR_MSG_ATTR(extack, attrs[i], "Unsupported attribute in XFRM_MSG_MIGRATE_STATE"); return -EINVAL; } } } return 0; } static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *attrs[XFRMA_MAX+1]; const struct xfrm_link *link; struct nlmsghdr *nlh64 = NULL; int type, err; type = nlh->nlmsg_type; if (type > XFRM_MSG_MAX) return -EINVAL; type -= XFRM_MSG_BASE; link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (IS_ENABLED(CONFIG_COMPAT_FOR_U64_ALIGNMENT) && in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); if (!xtr) return -EOPNOTSUPP; nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max, link->nla_pol, extack); xfrm_put_translator(xtr); if (IS_ERR(nlh64)) return PTR_ERR(nlh64); if (nlh64) nlh = nlh64; } if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) && (nlh->nlmsg_flags & NLM_F_DUMP)) { struct netlink_dump_control c = { .start = link->start, .dump = link->dump, .done = link->done, }; if (link->dump == NULL) { err = -EINVAL; goto err; } err = netlink_dump_start(xfrm_net_nlsk(net, skb), skb, nlh, &c); goto err; } err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs, link->nla_max ? : XFRMA_MAX, link->nla_pol ? : xfrma_policy, extack); if (err < 0) goto err; if (!link->nla_pol || link->nla_pol == xfrma_policy) { err = xfrm_reject_unused_attr((type + XFRM_MSG_BASE), attrs, extack); if (err < 0) goto err; } if (link->doit == NULL) { err = -EINVAL; goto err; } err = link->doit(skb, nlh, attrs, extack); /* We need to free skb allocated in xfrm_alloc_compat() before * returning from this function, because consume_skb() won't take * care of frag_list since netlink destructor sets * sbk->head to NULL. (see netlink_skb_destructor()) */ if (skb_has_frag_list(skb)) { kfree_skb(skb_shinfo(skb)->frag_list); skb_shinfo(skb)->frag_list = NULL; } err: kvfree(nlh64); return err; } static void xfrm_netlink_rcv(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); mutex_lock(&net->xfrm.xfrm_cfg_mutex); netlink_rcv_skb(skb, &xfrm_user_rcv_msg); mutex_unlock(&net->xfrm.xfrm_cfg_mutex); } static inline unsigned int xfrm_expire_msgsize(void) { return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) + nla_total_size(sizeof(struct xfrm_mark)) + nla_total_size(sizeof_field(struct xfrm_state, dir)) + nla_total_size(4); /* XFRMA_SA_PCPU */ } static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) { struct xfrm_user_expire *ue; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_EXPIRE, sizeof(*ue), 0); if (nlh == NULL) return -EMSGSIZE; ue = nlmsg_data(nlh); copy_to_user_state(x, &ue->state); ue->hard = (c->data.hard != 0) ? 1 : 0; /* clear the padding bytes */ memset_after(ue, 0, hard); err = xfrm_mark_put(skb, &x->mark); if (err) return err; err = xfrm_if_id_put(skb, x->if_id); if (err) return err; if (x->pcpu_num != UINT_MAX) { err = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num); if (err) return err; } if (x->dir) { err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); if (err) return err; } nlmsg_end(skb, nlh); return 0; } static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = xs_net(x); struct sk_buff *skb; skb = nlmsg_new(xfrm_expire_msgsize(), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; if (build_expire(skb, x, c) < 0) { kfree_skb(skb); return -EMSGSIZE; } return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); } static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = xs_net(x); struct sk_buff *skb; int err; skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; err = build_aevent(skb, x, c); BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS); } static int xfrm_notify_sa_flush(const struct km_event *c) { struct net *net = c->net; struct xfrm_usersa_flush *p; struct nlmsghdr *nlh; struct sk_buff *skb; int len = NLMSG_ALIGN(sizeof(struct xfrm_usersa_flush)); skb = nlmsg_new(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHSA, sizeof(*p), 0); if (nlh == NULL) { kfree_skb(skb); return -EMSGSIZE; } p = nlmsg_data(nlh); p->proto = c->data.proto; nlmsg_end(skb, nlh); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA); } static inline unsigned int xfrm_sa_len(struct xfrm_state *x) { unsigned int l = 0; if (x->aead) l += nla_total_size(aead_len(x->aead)); if (x->aalg) { l += nla_total_size(sizeof(struct xfrm_algo) + (x->aalg->alg_key_len + 7) / 8); l += nla_total_size(xfrm_alg_auth_len(x->aalg)); } if (x->ealg) l += nla_total_size(xfrm_alg_len(x->ealg)); if (x->calg) l += nla_total_size(sizeof(*x->calg)); if (x->encap) l += nla_total_size(sizeof(*x->encap)); if (x->tfcpad) l += nla_total_size(sizeof(x->tfcpad)); if (x->replay_esn) l += nla_total_size(xfrm_replay_state_esn_len(x->replay_esn)); else l += nla_total_size(sizeof(struct xfrm_replay_state)); if (x->security) l += nla_total_size(sizeof(struct xfrm_user_sec_ctx) + x->security->ctx_len); if (x->coaddr) l += nla_total_size(sizeof(*x->coaddr)); if (x->props.extra_flags) l += nla_total_size(sizeof(x->props.extra_flags)); if (x->xso.dev) l += nla_total_size(sizeof(struct xfrm_user_offload)); if (x->props.smark.v | x->props.smark.m) { l += nla_total_size(sizeof(x->props.smark.v)); l += nla_total_size(sizeof(x->props.smark.m)); } if (x->if_id) l += nla_total_size(sizeof(x->if_id)); if (x->pcpu_num != UINT_MAX) l += nla_total_size(sizeof(x->pcpu_num)); /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); if (x->mapping_maxage) l += nla_total_size(sizeof(x->mapping_maxage)); if (x->dir) l += nla_total_size(sizeof(x->dir)); if (x->nat_keepalive_interval) l += nla_total_size(sizeof(x->nat_keepalive_interval)); if (x->mode_cbs && x->mode_cbs->sa_len) l += x->mode_cbs->sa_len(x); return l; } static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) { struct net *net = xs_net(x); struct xfrm_usersa_info *p; struct xfrm_usersa_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int len = xfrm_sa_len(x); unsigned int headlen; int err; headlen = sizeof(*p); if (c->event == XFRM_MSG_DELSA) { len += nla_total_size(headlen); headlen = sizeof(*id); len += nla_total_size(sizeof(struct xfrm_mark)); } len += NLMSG_ALIGN(headlen); skb = nlmsg_new(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0); err = -EMSGSIZE; if (nlh == NULL) goto out_free_skb; p = nlmsg_data(nlh); if (c->event == XFRM_MSG_DELSA) { struct nlattr *attr; id = nlmsg_data(nlh); memset(id, 0, sizeof(*id)); memcpy(&id->daddr, &x->id.daddr, sizeof(id->daddr)); id->spi = x->id.spi; id->family = x->props.family; id->proto = x->id.proto; attr = nla_reserve(skb, XFRMA_SA, sizeof(*p)); err = -EMSGSIZE; if (attr == NULL) goto out_free_skb; p = nla_data(attr); } err = copy_to_user_state_extra(x, p, skb); if (err) goto out_free_skb; nlmsg_end(skb, nlh); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA); out_free_skb: kfree_skb(skb); return err; } static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c) { switch (c->event) { case XFRM_MSG_EXPIRE: return xfrm_exp_state_notify(x, c); case XFRM_MSG_NEWAE: return xfrm_aevent_state_notify(x, c); case XFRM_MSG_DELSA: case XFRM_MSG_UPDSA: case XFRM_MSG_NEWSA: return xfrm_notify_sa(x, c); case XFRM_MSG_FLUSHSA: return xfrm_notify_sa_flush(c); default: printk(KERN_NOTICE "xfrm_user: Unknown SA event %d\n", c->event); break; } return 0; } static inline unsigned int xfrm_acquire_msgsize(struct xfrm_state *x, struct xfrm_policy *xp) { return NLMSG_ALIGN(sizeof(struct xfrm_user_acquire)) + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr) + nla_total_size(sizeof(struct xfrm_mark)) + nla_total_size(xfrm_user_sec_ctx_size(x->security)) + nla_total_size(4) /* XFRMA_SA_PCPU */ + userpolicy_type_attrsize(); } static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, struct xfrm_tmpl *xt, struct xfrm_policy *xp) { __u32 seq = xfrm_get_acqseq(); struct xfrm_user_acquire *ua; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_ACQUIRE, sizeof(*ua), 0); if (nlh == NULL) return -EMSGSIZE; ua = nlmsg_data(nlh); memcpy(&ua->id, &x->id, sizeof(ua->id)); memcpy(&ua->saddr, &x->props.saddr, sizeof(ua->saddr)); memcpy(&ua->sel, &x->sel, sizeof(ua->sel)); copy_to_user_policy(xp, &ua->policy, XFRM_POLICY_OUT); ua->aalgos = xt->aalgos; ua->ealgos = xt->ealgos; ua->calgos = xt->calgos; ua->seq = x->km.seq = seq; err = copy_to_user_tmpl(xp, skb); if (!err) err = copy_to_user_state_sec_ctx(x, skb); if (!err) err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); if (!err && xp->xdo.dev) err = copy_user_offload(&xp->xdo, skb); if (!err && x->pcpu_num != UINT_MAX) err = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num); if (err) { nlmsg_cancel(skb, nlh); return err; } nlmsg_end(skb, nlh); return 0; } static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, struct xfrm_policy *xp) { struct net *net = xs_net(x); struct sk_buff *skb; int err; skb = nlmsg_new(xfrm_acquire_msgsize(x, xp), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; err = build_acquire(skb, x, xt, xp); BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE); } /* User gives us xfrm_user_policy_info followed by an array of 0 * or more templates. */ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { struct net *net = sock_net(sk); struct xfrm_userpolicy_info *p = (struct xfrm_userpolicy_info *)data; struct xfrm_user_tmpl *ut = (struct xfrm_user_tmpl *) (p + 1); struct xfrm_policy *xp; int nr; switch (sk->sk_family) { case AF_INET: if (opt != IP_XFRM_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (opt != IPV6_XFRM_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #endif default: *dir = -EINVAL; return NULL; } *dir = -EINVAL; if (len < sizeof(*p) || verify_newpolicy_info(p, NULL)) return NULL; nr = ((len - sizeof(*p)) / sizeof(*ut)); if (validate_tmpl(nr, ut, p->sel.family, p->dir, NULL)) return NULL; if (p->dir > XFRM_POLICY_OUT) return NULL; xp = xfrm_policy_alloc(net, GFP_ATOMIC); if (xp == NULL) { *dir = -ENOBUFS; return NULL; } copy_from_user_policy(xp, p); xp->type = XFRM_POLICY_TYPE_MAIN; copy_templates(xp, ut, nr); *dir = p->dir; return xp; } static inline unsigned int xfrm_polexpire_msgsize(struct xfrm_policy *xp) { return NLMSG_ALIGN(sizeof(struct xfrm_user_polexpire)) + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr) + nla_total_size(xfrm_user_sec_ctx_size(xp->security)) + nla_total_size(sizeof(struct xfrm_mark)) + userpolicy_type_attrsize(); } static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_user_polexpire *upe; int hard = c->data.hard; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe), 0); if (nlh == NULL) return -EMSGSIZE; upe = nlmsg_data(nlh); copy_to_user_policy(xp, &upe->pol, dir); err = copy_to_user_tmpl(xp, skb); if (!err) err = copy_to_user_sec_ctx(xp, skb); if (!err) err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); if (!err && xp->xdo.dev) err = copy_user_offload(&xp->xdo, skb); if (err) { nlmsg_cancel(skb, nlh); return err; } upe->hard = !!hard; /* clear the padding bytes */ memset_after(upe, 0, hard); nlmsg_end(skb, nlh); return 0; } static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct net *net = xp_net(xp); struct sk_buff *skb; int err; skb = nlmsg_new(xfrm_polexpire_msgsize(xp), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; err = build_polexpire(skb, xp, dir, c); BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); } static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { unsigned int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); struct net *net = xp_net(xp); struct xfrm_userpolicy_info *p; struct xfrm_userpolicy_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int headlen; int err; headlen = sizeof(*p); if (c->event == XFRM_MSG_DELPOLICY) { len += nla_total_size(headlen); headlen = sizeof(*id); } len += userpolicy_type_attrsize(); len += nla_total_size(sizeof(struct xfrm_mark)); len += NLMSG_ALIGN(headlen); skb = nlmsg_new(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0); err = -EMSGSIZE; if (nlh == NULL) goto out_free_skb; p = nlmsg_data(nlh); if (c->event == XFRM_MSG_DELPOLICY) { struct nlattr *attr; id = nlmsg_data(nlh); memset(id, 0, sizeof(*id)); id->dir = dir; if (c->data.byid) id->index = xp->index; else memcpy(&id->sel, &xp->selector, sizeof(id->sel)); attr = nla_reserve(skb, XFRMA_POLICY, sizeof(*p)); err = -EMSGSIZE; if (attr == NULL) goto out_free_skb; p = nla_data(attr); } copy_to_user_policy(xp, p, dir); err = copy_to_user_tmpl(xp, skb); if (!err) err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); if (!err && xp->xdo.dev) err = copy_user_offload(&xp->xdo, skb); if (err) goto out_free_skb; nlmsg_end(skb, nlh); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); out_free_skb: kfree_skb(skb); return err; } static int xfrm_notify_policy_flush(const struct km_event *c) { struct net *net = c->net; struct nlmsghdr *nlh; struct sk_buff *skb; int err; skb = nlmsg_new(userpolicy_type_attrsize(), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHPOLICY, 0, 0); err = -EMSGSIZE; if (nlh == NULL) goto out_free_skb; err = copy_to_user_policy_type(c->data.type, skb); if (err) goto out_free_skb; nlmsg_end(skb, nlh); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); out_free_skb: kfree_skb(skb); return err; } static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { switch (c->event) { case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDPOLICY: case XFRM_MSG_DELPOLICY: return xfrm_notify_policy(xp, dir, c); case XFRM_MSG_FLUSHPOLICY: return xfrm_notify_policy_flush(c); case XFRM_MSG_POLEXPIRE: return xfrm_exp_policy_notify(xp, dir, c); default: printk(KERN_NOTICE "xfrm_user: Unknown Policy event %d\n", c->event); } return 0; } static inline unsigned int xfrm_report_msgsize(void) { return NLMSG_ALIGN(sizeof(struct xfrm_user_report)); } static int build_report(struct sk_buff *skb, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { struct xfrm_user_report *ur; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_REPORT, sizeof(*ur), 0); if (nlh == NULL) return -EMSGSIZE; ur = nlmsg_data(nlh); memset(ur, 0, sizeof(*ur)); ur->proto = proto; memcpy(&ur->sel, sel, sizeof(ur->sel)); if (addr) { int err = nla_put(skb, XFRMA_COADDR, sizeof(*addr), addr); if (err) { nlmsg_cancel(skb, nlh); return err; } } nlmsg_end(skb, nlh); return 0; } static int xfrm_send_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { struct sk_buff *skb; int err; skb = nlmsg_new(xfrm_report_msgsize(), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; err = build_report(skb, proto, sel, addr); BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT); } static inline unsigned int xfrm_mapping_msgsize(void) { return NLMSG_ALIGN(sizeof(struct xfrm_user_mapping)); } static int build_mapping(struct sk_buff *skb, struct xfrm_state *x, xfrm_address_t *new_saddr, __be16 new_sport) { struct xfrm_user_mapping *um; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MAPPING, sizeof(*um), 0); if (nlh == NULL) return -EMSGSIZE; um = nlmsg_data(nlh); memset(&um->id, 0, sizeof(um->id)); memcpy(&um->id.daddr, &x->id.daddr, sizeof(um->id.daddr)); um->id.spi = x->id.spi; um->id.family = x->props.family; um->id.proto = x->id.proto; memcpy(&um->new_saddr, new_saddr, sizeof(um->new_saddr)); memcpy(&um->old_saddr, &x->props.saddr, sizeof(um->old_saddr)); um->new_sport = new_sport; um->old_sport = x->encap->encap_sport; um->reqid = x->props.reqid; nlmsg_end(skb, nlh); return 0; } static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { struct net *net = xs_net(x); struct sk_buff *skb; int err; if (x->id.proto != IPPROTO_ESP) return -EINVAL; if (!x->encap) return -EINVAL; skb = nlmsg_new(xfrm_mapping_msgsize(), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; err = build_mapping(skb, x, ipaddr, sport); BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING); } static bool xfrm_is_alive(const struct km_event *c) { return (bool)xfrm_acquire_is_on(c->net); } static struct xfrm_mgr netlink_mgr = { .notify = xfrm_send_state_notify, .acquire = xfrm_send_acquire, .compile_policy = xfrm_compile_policy, .notify_policy = xfrm_send_policy_notify, .report = xfrm_send_report, .migrate = xfrm_send_migrate, .new_mapping = xfrm_send_mapping, .is_alive = xfrm_is_alive, }; static int __net_init xfrm_user_net_init(struct net *net) { struct sock *nlsk; struct netlink_kernel_cfg cfg = { .groups = XFRMNLGRP_MAX, .input = xfrm_netlink_rcv, }; nlsk = netlink_kernel_create(net, NETLINK_XFRM, &cfg); if (nlsk == NULL) return -ENOMEM; net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ rcu_assign_pointer(net->xfrm.nlsk, nlsk); return 0; } static void __net_exit xfrm_user_net_pre_exit(struct net *net) { RCU_INIT_POINTER(net->xfrm.nlsk, NULL); } static void __net_exit xfrm_user_net_exit(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) netlink_kernel_release(net->xfrm.nlsk_stash); } static struct pernet_operations xfrm_user_net_ops = { .init = xfrm_user_net_init, .pre_exit = xfrm_user_net_pre_exit, .exit_batch = xfrm_user_net_exit, }; static int __init xfrm_user_init(void) { int rv; printk(KERN_INFO "Initializing XFRM netlink socket\n"); rv = register_pernet_subsys(&xfrm_user_net_ops); if (rv < 0) return rv; xfrm_register_km(&netlink_mgr); return 0; } static void __exit xfrm_user_exit(void) { xfrm_unregister_km(&netlink_mgr); unregister_pernet_subsys(&xfrm_user_net_ops); } module_init(xfrm_user_init); module_exit(xfrm_user_exit); MODULE_DESCRIPTION("XFRM User interface"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM); |
| 21 1 21 17 13 4 10 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, Intel Corporation. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ #ifndef __NET_TC_SKBEDIT_H #define __NET_TC_SKBEDIT_H #include <net/act_api.h> #include <linux/tc_act/tc_skbedit.h> struct tcf_skbedit_params { int action; u32 flags; u32 priority; u32 mark; u32 mask; u16 queue_mapping; u16 mapping_mod; u16 ptype; struct rcu_head rcu; }; struct tcf_skbedit { struct tc_action common; struct tcf_skbedit_params __rcu *params; }; #define to_skbedit(a) ((struct tcf_skbedit *)a) /* Return true iff action is the one identified by FLAG. */ static inline bool is_tcf_skbedit_with_flag(const struct tc_action *a, u32 flag) { #ifdef CONFIG_NET_CLS_ACT u32 flags; if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { rcu_read_lock(); flags = rcu_dereference(to_skbedit(a)->params)->flags; rcu_read_unlock(); return flags == flag; } #endif return false; } /* Return true iff action is mark */ static inline bool is_tcf_skbedit_mark(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_MARK); } static inline u32 tcf_skbedit_mark(const struct tc_action *a) { u32 mark; rcu_read_lock(); mark = rcu_dereference(to_skbedit(a)->params)->mark; rcu_read_unlock(); return mark; } /* Return true iff action is ptype */ static inline bool is_tcf_skbedit_ptype(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PTYPE); } static inline u32 tcf_skbedit_ptype(const struct tc_action *a) { u16 ptype; rcu_read_lock(); ptype = rcu_dereference(to_skbedit(a)->params)->ptype; rcu_read_unlock(); return ptype; } /* Return true iff action is priority */ static inline bool is_tcf_skbedit_priority(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PRIORITY); } static inline u32 tcf_skbedit_priority(const struct tc_action *a) { u32 priority; rcu_read_lock(); priority = rcu_dereference(to_skbedit(a)->params)->priority; rcu_read_unlock(); return priority; } static inline u16 tcf_skbedit_rx_queue_mapping(const struct tc_action *a) { u16 rx_queue; rcu_read_lock(); rx_queue = rcu_dereference(to_skbedit(a)->params)->queue_mapping; rcu_read_unlock(); return rx_queue; } /* Return true iff action is queue_mapping */ static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); } /* Return true if action is on ingress traffic */ static inline bool is_tcf_skbedit_ingress(u32 flags) { return flags & TCA_ACT_FLAGS_AT_INGRESS; } static inline bool is_tcf_skbedit_tx_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_queue_mapping(a) && !is_tcf_skbedit_ingress(a->tcfa_flags); } static inline bool is_tcf_skbedit_rx_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_queue_mapping(a) && is_tcf_skbedit_ingress(a->tcfa_flags); } /* Return true iff action is inheritdsfield */ static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD); } #endif /* __NET_TC_SKBEDIT_H */ |
| 15 1 15 15 1 14 21 21 14 14 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 | /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * Copyright (c) 2005 PathScale, 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/module.h> #include <linux/init.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/file.h> #include <linux/cdev.h> #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <rdma/ib.h> #include <rdma/uverbs_std_types.h> #include <rdma/rdma_netlink.h> #include <rdma/ib_ucaps.h> #include "uverbs.h" #include "core_priv.h" #include "rdma_core.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace verbs access"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_IMPORT_NS("rdma_core"); enum { IB_UVERBS_MAJOR = 231, IB_UVERBS_BASE_MINOR = 192, IB_UVERBS_MAX_DEVICES = RDMA_MAX_PORTS, IB_UVERBS_NUM_FIXED_MINOR = 32, IB_UVERBS_NUM_DYNAMIC_MINOR = IB_UVERBS_MAX_DEVICES - IB_UVERBS_NUM_FIXED_MINOR, }; #define IB_UVERBS_BASE_DEV MKDEV(IB_UVERBS_MAJOR, IB_UVERBS_BASE_MINOR) static dev_t dynamic_uverbs_dev; static DEFINE_IDA(uverbs_ida); static int ib_uverbs_add_one(struct ib_device *device); static void ib_uverbs_remove_one(struct ib_device *device, void *client_data); static struct ib_client uverbs_client; static char *uverbs_devnode(const struct device *dev, umode_t *mode) { if (mode) *mode = 0666; return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } static const struct class uverbs_class = { .name = "infiniband_verbs", .devnode = uverbs_devnode, }; int uverbs_dealloc_mw(struct ib_mw *mw) { struct ib_pd *pd = mw->pd; int ret; ret = mw->device->ops.dealloc_mw(mw); if (ret) return ret; atomic_dec(&pd->usecnt); kfree(mw); return ret; } static void ib_uverbs_release_dev(struct device *device) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); uverbs_destroy_api(dev->uapi); cleanup_srcu_struct(&dev->disassociate_srcu); mutex_destroy(&dev->lists_mutex); mutex_destroy(&dev->xrcd_tree_mutex); kfree(dev); } void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file, struct ib_ucq_object *uobj) { struct ib_uverbs_event *evt, *tmp; if (ev_file) { spin_lock_irq(&ev_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->comp_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&ev_file->ev_queue.lock); uverbs_uobject_put(&ev_file->uobj); } ib_uverbs_release_uevent(&uobj->uevent); } void ib_uverbs_release_uevent(struct ib_uevent_object *uobj) { struct ib_uverbs_async_event_file *async_file = uobj->event_file; struct ib_uverbs_event *evt, *tmp; if (!async_file) return; spin_lock_irq(&async_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->event_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&async_file->ev_queue.lock); uverbs_uobject_put(&async_file->uobj); } void ib_uverbs_detach_umcast(struct ib_qp *qp, struct ib_uqp_object *uobj) { struct ib_uverbs_mcast_entry *mcast, *tmp; list_for_each_entry_safe(mcast, tmp, &uobj->mcast_list, list) { ib_detach_mcast(qp, &mcast->gid, mcast->lid); list_del(&mcast->list); kfree(mcast); } } static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, struct file *filp, char __user *buf, size_t count, loff_t *pos, size_t eventsz) { struct ib_uverbs_event *event; int ret = 0; spin_lock_irq(&ev_queue->lock); while (list_empty(&ev_queue->event_list)) { if (ev_queue->is_closed) { spin_unlock_irq(&ev_queue->lock); return -EIO; } spin_unlock_irq(&ev_queue->lock); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; if (wait_event_interruptible(ev_queue->poll_wait, (!list_empty(&ev_queue->event_list) || ev_queue->is_closed))) return -ERESTARTSYS; spin_lock_irq(&ev_queue->lock); } event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list); if (eventsz > count) { ret = -EINVAL; event = NULL; } else { list_del(ev_queue->event_list.next); if (event->counter) { ++(*event->counter); list_del(&event->obj_list); } } spin_unlock_irq(&ev_queue->lock); if (event) { if (copy_to_user(buf, event, eventsz)) ret = -EFAULT; else ret = eventsz; } kfree(event); return ret; } static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_read(&file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_async_event_desc)); } static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_read(&comp_ev_file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_comp_event_desc)); } static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue, struct file *filp, struct poll_table_struct *wait) { __poll_t pollflags = 0; poll_wait(filp, &ev_queue->poll_wait, wait); spin_lock_irq(&ev_queue->lock); if (!list_empty(&ev_queue->event_list)) pollflags = EPOLLIN | EPOLLRDNORM; else if (ev_queue->is_closed) pollflags = EPOLLERR; spin_unlock_irq(&ev_queue->lock); return pollflags; } static __poll_t ib_uverbs_async_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_poll(&file->ev_queue, filp, wait); } static __poll_t ib_uverbs_comp_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_poll(&comp_ev_file->ev_queue, filp, wait); } static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_async_event_file *file = filp->private_data; return fasync_helper(fd, filp, on, &file->ev_queue.async_queue); } static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return fasync_helper(fd, filp, on, &comp_ev_file->ev_queue.async_queue); } const struct file_operations uverbs_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_comp_event_read, .poll = ib_uverbs_comp_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_comp_event_fasync, }; const struct file_operations uverbs_async_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_async_event_read, .poll = ib_uverbs_async_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_async_event_fasync, }; void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) { struct ib_uverbs_event_queue *ev_queue = cq_context; struct ib_ucq_object *uobj; struct ib_uverbs_event *entry; unsigned long flags; if (!ev_queue) return; spin_lock_irqsave(&ev_queue->lock, flags); if (ev_queue->is_closed) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } entry = kmalloc_obj(*entry, GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } uobj = cq->uobject; entry->desc.comp.cq_handle = cq->uobject->uevent.uobject.user_handle; entry->counter = &uobj->comp_events_reported; list_add_tail(&entry->list, &ev_queue->event_list); list_add_tail(&entry->obj_list, &uobj->comp_list); spin_unlock_irqrestore(&ev_queue->lock, flags); wake_up_interruptible(&ev_queue->poll_wait); kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN); } void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, __u64 element, __u64 event, struct list_head *obj_list, u32 *counter) { struct ib_uverbs_event *entry; unsigned long flags; if (!async_file) return; spin_lock_irqsave(&async_file->ev_queue.lock, flags); if (async_file->ev_queue.is_closed) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry = kmalloc_obj(*entry, GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry->desc.async.element = element; entry->desc.async.event_type = event; entry->desc.async.reserved = 0; entry->counter = counter; list_add_tail(&entry->list, &async_file->ev_queue.event_list); if (obj_list) list_add_tail(&entry->obj_list, obj_list); spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); wake_up_interruptible(&async_file->ev_queue.poll_wait); kill_fasync(&async_file->ev_queue.async_queue, SIGIO, POLL_IN); } static void uverbs_uobj_event(struct ib_uevent_object *eobj, struct ib_event *event) { ib_uverbs_async_handler(eobj->event_file, eobj->uobject.user_handle, event->event, &eobj->event_list, &eobj->events_reported); } void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.cq->uobject->uevent, event); } void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr) { /* for XRC target qp's, check that qp is live */ if (!event->element.qp->uobject) return; uverbs_uobj_event(&event->element.qp->uobject->uevent, event); } void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.wq->uobject->uevent, event); } void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.srq->uobject->uevent, event); } static void ib_uverbs_event_handler(struct ib_event_handler *handler, struct ib_event *event) { ib_uverbs_async_handler( container_of(handler, struct ib_uverbs_async_event_file, event_handler), event->element.port_num, event->event, NULL, NULL); } void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue) { spin_lock_init(&ev_queue->lock); INIT_LIST_HEAD(&ev_queue->event_list); init_waitqueue_head(&ev_queue->poll_wait); ev_queue->is_closed = 0; ev_queue->async_queue = NULL; } void ib_uverbs_init_async_event_file( struct ib_uverbs_async_event_file *async_file) { struct ib_uverbs_file *uverbs_file = async_file->uobj.ufile; struct ib_device *ib_dev = async_file->uobj.context->device; ib_uverbs_init_event_queue(&async_file->ev_queue); /* The first async_event_file becomes the default one for the file. */ mutex_lock(&uverbs_file->ucontext_lock); if (!uverbs_file->default_async_file) { /* Pairs with the put in ib_uverbs_release_file */ uverbs_uobject_get(&async_file->uobj); smp_store_release(&uverbs_file->default_async_file, async_file); } mutex_unlock(&uverbs_file->ucontext_lock); INIT_IB_EVENT_HANDLER(&async_file->event_handler, ib_dev, ib_uverbs_event_handler); ib_register_event_handler(&async_file->event_handler); } static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr, struct ib_uverbs_ex_cmd_hdr *ex_hdr, size_t count, const struct uverbs_api_write_method *method_elm) { if (method_elm->is_ex) { count -= sizeof(*hdr) + sizeof(*ex_hdr); if ((hdr->in_words + ex_hdr->provider_in_words) * 8 != count) return -EINVAL; if (hdr->in_words * 8 < method_elm->req_size) return -ENOSPC; if (ex_hdr->cmd_hdr_reserved) return -EINVAL; if (ex_hdr->response) { if (!hdr->out_words && !ex_hdr->provider_out_words) return -EINVAL; if (hdr->out_words * 8 < method_elm->resp_size) return -ENOSPC; if (!access_ok(u64_to_user_ptr(ex_hdr->response), (hdr->out_words + ex_hdr->provider_out_words) * 8)) return -EFAULT; } else { if (hdr->out_words || ex_hdr->provider_out_words) return -EINVAL; } return 0; } /* not extended command */ if (hdr->in_words * 4 != count) return -EINVAL; if (count < method_elm->req_size + sizeof(*hdr)) { /* * rdma-core v18 and v19 have a bug where they send DESTROY_CQ * with a 16 byte write instead of 24. Old kernels didn't * check the size so they allowed this. Now that the size is * checked provide a compatibility work around to not break * those userspaces. */ if (hdr->command == IB_USER_VERBS_CMD_DESTROY_CQ && count == 16) { hdr->in_words = 6; return 0; } return -ENOSPC; } if (hdr->out_words * 4 < method_elm->resp_size) return -ENOSPC; return 0; } static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_file *file = filp->private_data; const struct uverbs_api_write_method *method_elm; struct uverbs_api *uapi = file->device->uapi; struct ib_uverbs_ex_cmd_hdr ex_hdr; struct ib_uverbs_cmd_hdr hdr; struct uverbs_attr_bundle bundle; int srcu_key; ssize_t ret; if (!ib_safe_file_access(filp)) { pr_err_once("uverbs_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", task_tgid_vnr(current), current->comm); return -EACCES; } if (count < sizeof(hdr)) return -EINVAL; if (copy_from_user(&hdr, buf, sizeof(hdr))) return -EFAULT; method_elm = uapi_get_method(uapi, hdr.command); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); if (method_elm->is_ex) { if (count < (sizeof(hdr) + sizeof(ex_hdr))) return -EINVAL; if (copy_from_user(&ex_hdr, buf + sizeof(hdr), sizeof(ex_hdr))) return -EFAULT; } ret = verify_hdr(&hdr, &ex_hdr, count, method_elm); if (ret) return ret; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); buf += sizeof(hdr); memset(bundle.attr_present, 0, sizeof(bundle.attr_present)); bundle.ufile = file; bundle.context = NULL; /* only valid if bundle has uobject */ bundle.uobject = NULL; if (!method_elm->is_ex) { size_t in_len = hdr.in_words * 4 - sizeof(hdr); size_t out_len = hdr.out_words * 4; u64 response = 0; if (method_elm->has_udata) { bundle.driver_udata.inlen = in_len - method_elm->req_size; in_len = method_elm->req_size; if (bundle.driver_udata.inlen) bundle.driver_udata.inbuf = buf + in_len; else bundle.driver_udata.inbuf = NULL; } else { memset(&bundle.driver_udata, 0, sizeof(bundle.driver_udata)); } if (method_elm->has_resp) { /* * The macros check that if has_resp is set * then the command request structure starts * with a '__aligned u64 response' member. */ ret = get_user(response, (const u64 __user *)buf); if (ret) goto out_unlock; if (method_elm->has_udata) { bundle.driver_udata.outlen = out_len - method_elm->resp_size; out_len = method_elm->resp_size; if (bundle.driver_udata.outlen) bundle.driver_udata.outbuf = u64_to_user_ptr(response + out_len); else bundle.driver_udata.outbuf = NULL; } } else { bundle.driver_udata.outlen = 0; bundle.driver_udata.outbuf = NULL; } ib_uverbs_init_udata_buf_or_null( &bundle.ucore, buf, u64_to_user_ptr(response), in_len, out_len); } else { buf += sizeof(ex_hdr); ib_uverbs_init_udata_buf_or_null(&bundle.ucore, buf, u64_to_user_ptr(ex_hdr.response), hdr.in_words * 8, hdr.out_words * 8); ib_uverbs_init_udata_buf_or_null( &bundle.driver_udata, buf + bundle.ucore.inlen, u64_to_user_ptr(ex_hdr.response) + bundle.ucore.outlen, ex_hdr.provider_in_words * 8, ex_hdr.provider_out_words * 8); } ret = method_elm->handler(&bundle); if (bundle.uobject) uverbs_finalize_object(bundle.uobject, UVERBS_ACCESS_NEW, true, !ret, &bundle); out_unlock: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return (ret) ? : count; } static const struct vm_operations_struct rdma_umap_ops; static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma) { struct ib_uverbs_file *file = filp->private_data; struct ib_ucontext *ucontext; int ret = 0; int srcu_key; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ucontext = ib_uverbs_get_ucontext_file(file); if (IS_ERR(ucontext)) { ret = PTR_ERR(ucontext); goto out; } mutex_lock(&file->disassociation_lock); vma->vm_ops = &rdma_umap_ops; ret = ucontext->device->ops.mmap(ucontext, vma); mutex_unlock(&file->disassociation_lock); out: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return ret; } /* * The VMA has been dup'd, initialize the vm_private_data with a new tracking * struct */ static void rdma_umap_open(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *opriv = vma->vm_private_data; struct rdma_umap_priv *priv; if (!opriv) return; /* We are racing with disassociation */ if (!down_read_trylock(&ufile->hw_destroy_rwsem)) goto out_zap; mutex_lock(&ufile->disassociation_lock); /* * Disassociation already completed, the VMA should already be zapped. */ if (!ufile->ucontext) goto out_unlock; priv = kzalloc_obj(*priv); if (!priv) goto out_unlock; rdma_umap_priv_init(priv, vma, opriv->entry); mutex_unlock(&ufile->disassociation_lock); up_read(&ufile->hw_destroy_rwsem); return; out_unlock: mutex_unlock(&ufile->disassociation_lock); up_read(&ufile->hw_destroy_rwsem); out_zap: /* * We can't allow the VMA to be created with the actual IO pages, that * would break our API contract, and it can't be stopped at this * point, so zap it. */ vma->vm_private_data = NULL; zap_special_vma_range(vma, vma->vm_start, vma->vm_end - vma->vm_start); } static void rdma_umap_close(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *priv = vma->vm_private_data; if (!priv) return; /* * The vma holds a reference on the struct file that created it, which * in turn means that the ib_uverbs_file is guaranteed to exist at * this point. */ mutex_lock(&ufile->umap_lock); if (priv->entry) rdma_user_mmap_entry_put(priv->entry); list_del(&priv->list); mutex_unlock(&ufile->umap_lock); kfree(priv); } /* * Once the zap_special_vma_range has been called touches to the VMA will come here and * we return a dummy writable zero page for all the pfns. */ static vm_fault_t rdma_umap_fault(struct vm_fault *vmf) { struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data; struct rdma_umap_priv *priv = vmf->vma->vm_private_data; vm_fault_t ret = 0; if (!priv) return VM_FAULT_SIGBUS; /* Read only pages can just use the system zero page. */ if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) { vmf->page = ZERO_PAGE(vmf->address); get_page(vmf->page); return 0; } mutex_lock(&ufile->umap_lock); if (!ufile->disassociate_page) ufile->disassociate_page = alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0); if (ufile->disassociate_page) { /* * This VMA is forced to always be shared so this doesn't have * to worry about COW. */ vmf->page = ufile->disassociate_page; get_page(vmf->page); } else { ret = VM_FAULT_SIGBUS; } mutex_unlock(&ufile->umap_lock); return ret; } static const struct vm_operations_struct rdma_umap_ops = { .open = rdma_umap_open, .close = rdma_umap_close, .fault = rdma_umap_fault, }; void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) { struct rdma_umap_priv *priv, *next_priv; mutex_lock(&ufile->disassociation_lock); while (1) { struct mm_struct *mm = NULL; /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); while (!list_empty(&ufile->umaps)) { int ret; priv = list_first_entry(&ufile->umaps, struct rdma_umap_priv, list); mm = priv->vma->vm_mm; ret = mmget_not_zero(mm); if (!ret) { list_del_init(&priv->list); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } mm = NULL; continue; } break; } mutex_unlock(&ufile->umap_lock); if (!mm) { mutex_unlock(&ufile->disassociation_lock); return; } /* * The umap_lock is nested under mmap_lock since it used within * the vma_ops callbacks, so we have to clean the list one mm * at a time to get the lock ordering right. Typically there * will only be one mm, so no big deal. */ mmap_read_lock(mm); mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { struct vm_area_struct *vma = priv->vma; if (vma->vm_mm != mm) continue; list_del_init(&priv->list); zap_special_vma_range(vma, vma->vm_start, vma->vm_end - vma->vm_start); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } } mutex_unlock(&ufile->umap_lock); mmap_read_unlock(mm); mmput(mm); } mutex_unlock(&ufile->disassociation_lock); } /** * rdma_user_mmap_disassociate() - Revoke mmaps for a device * @device: device to revoke * * This function should be called by drivers that need to disable mmaps for the * device, for instance because it is going to be reset. */ void rdma_user_mmap_disassociate(struct ib_device *device) { struct ib_uverbs_device *uverbs_dev = ib_get_client_data(device, &uverbs_client); struct ib_uverbs_file *ufile; mutex_lock(&uverbs_dev->lists_mutex); list_for_each_entry(ufile, &uverbs_dev->uverbs_file_list, list) { if (ufile->ucontext) uverbs_user_mmap_disassociate(ufile); } mutex_unlock(&uverbs_dev->lists_mutex); } EXPORT_SYMBOL(rdma_user_mmap_disassociate); /* * ib_uverbs_open() does not need the BKL: * * - the ib_uverbs_device structures are properly reference counted and * everything else is purely local to the file being created, so * races against other open calls are not a problem; * - there is no ioctl method to race against; * - the open method will either immediately run -ENXIO, or all * required initialization will be done. */ static int ib_uverbs_open(struct inode *inode, struct file *filp) { struct ib_uverbs_device *dev; struct ib_uverbs_file *file; struct ib_device *ib_dev; int ret; int module_dependent; int srcu_key; dev = container_of(inode->i_cdev, struct ib_uverbs_device, cdev); if (!refcount_inc_not_zero(&dev->refcount)) return -ENXIO; get_device(&dev->dev); srcu_key = srcu_read_lock(&dev->disassociate_srcu); mutex_lock(&dev->lists_mutex); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (!ib_dev) { ret = -EIO; goto err; } if (!rdma_dev_access_netns(ib_dev, current->nsproxy->net_ns)) { ret = -EPERM; goto err; } /* In case IB device supports disassociate ucontext, there is no hard * dependency between uverbs device and its low level device. */ module_dependent = !(ib_dev->ops.disassociate_ucontext); if (module_dependent) { if (!try_module_get(ib_dev->ops.owner)) { ret = -ENODEV; goto err; } } file = kzalloc_obj(*file); if (!file) { ret = -ENOMEM; if (module_dependent) goto err_module; goto err; } file->device = dev; kref_init(&file->ref); mutex_init(&file->ucontext_lock); spin_lock_init(&file->uobjects_lock); INIT_LIST_HEAD(&file->uobjects); init_rwsem(&file->hw_destroy_rwsem); mutex_init(&file->umap_lock); INIT_LIST_HEAD(&file->umaps); mutex_init(&file->disassociation_lock); filp->private_data = file; list_add_tail(&file->list, &dev->uverbs_file_list); mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); setup_ufile_idr_uobject(file); return stream_open(inode, filp); err_module: module_put(ib_dev->ops.owner); err: mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&dev->refcount)) ib_uverbs_comp_dev(dev); put_device(&dev->dev); return ret; } /* * Drop the ucontext off the ufile and completely disconnect it from the * ib_device */ static void ufile_destroy_ucontext(struct ib_uverbs_file *ufile, enum rdma_remove_reason reason) { struct ib_ucontext *ucontext = ufile->ucontext; struct ib_device *ib_dev = ucontext->device; /* * If we are closing the FD then the user mmap VMAs must have * already been destroyed as they hold on to the filep, otherwise * they need to be zap'd. */ if (reason == RDMA_REMOVE_DRIVER_REMOVE) { uverbs_user_mmap_disassociate(ufile); if (ib_dev->ops.disassociate_ucontext) ib_dev->ops.disassociate_ucontext(ucontext); } ib_rdmacg_uncharge(&ucontext->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE); rdma_restrack_del(&ucontext->res); ib_dev->ops.dealloc_ucontext(ucontext); WARN_ON(!xa_empty(&ucontext->mmap_xa)); kfree(ucontext); ufile->ucontext = NULL; } /* * Destroy the ucontext and every uobject associated with it. * * This is internally locked and can be called in parallel from multiple * contexts. */ void uverbs_destroy_ufile_hw(struct ib_uverbs_file *ufile, enum rdma_remove_reason reason) { down_write(&ufile->hw_destroy_rwsem); /* * If a ucontext was never created then we can't have any uobjects to * cleanup, nothing to do. */ if (!ufile->ucontext) goto done; while (!list_empty(&ufile->uobjects) && !__uverbs_cleanup_ufile(ufile, reason)) { } if (WARN_ON(!list_empty(&ufile->uobjects))) __uverbs_cleanup_ufile(ufile, RDMA_REMOVE_DRIVER_FAILURE); ufile_destroy_ucontext(ufile, reason); done: up_write(&ufile->hw_destroy_rwsem); } static int ib_uverbs_close(struct inode *inode, struct file *filp) { struct ib_uverbs_file *file = filp->private_data; uverbs_destroy_ufile_hw(file, RDMA_REMOVE_CLOSE); mutex_lock(&file->device->lists_mutex); list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); kref_put(&file->ref, ib_uverbs_release_file); return 0; } static const struct file_operations uverbs_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static const struct file_operations uverbs_mmap_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .mmap = ib_uverbs_mmap, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static int ib_uverbs_get_nl_info(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res) { struct ib_uverbs_device *uverbs_dev = client_data; int ret; if (res->port != -1) return -EINVAL; res->abi = ibdev->ops.uverbs_abi_ver; res->cdev = &uverbs_dev->dev; /* * To support DRIVER_ID binding in userspace some of the driver need * upgrading to expose their PCI dependent revision information * through get_context instead of relying on modalias matching. When * the drivers are fixed they can drop this flag. */ if (!ibdev->ops.uverbs_no_driver_id_binding) { ret = nla_put_u32(res->nl_msg, RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID, ibdev->ops.driver_id); if (ret) return ret; } return 0; } static struct ib_client uverbs_client = { .name = "uverbs", .no_kverbs_req = true, .add = ib_uverbs_add_one, .remove = ib_uverbs_remove_one, .get_nl_info = ib_uverbs_get_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("uverbs"); static ssize_t ibdev_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%s\n", dev_name(&ib_dev->dev)); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(ibdev); static ssize_t abi_version_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%u\n", ib_dev->ops.uverbs_abi_ver); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(abi_version); static struct attribute *ib_dev_attrs[] = { &dev_attr_abi_version.attr, &dev_attr_ibdev.attr, NULL, }; static const struct attribute_group dev_attr_group = { .attrs = ib_dev_attrs, }; static CLASS_ATTR_STRING(abi_version, S_IRUGO, __stringify(IB_USER_VERBS_ABI_VERSION)); static int ib_uverbs_create_uapi(struct ib_device *device, struct ib_uverbs_device *uverbs_dev) { struct uverbs_api *uapi; uapi = uverbs_alloc_api(device); if (IS_ERR(uapi)) return PTR_ERR(uapi); uverbs_dev->uapi = uapi; return 0; } static int ib_uverbs_add_one(struct ib_device *device) { int devnum; dev_t base; struct ib_uverbs_device *uverbs_dev; int ret; if (!device->ops.alloc_ucontext || device->type == RDMA_DEVICE_TYPE_SMI) return -EOPNOTSUPP; uverbs_dev = kzalloc_obj(*uverbs_dev); if (!uverbs_dev) return -ENOMEM; ret = init_srcu_struct(&uverbs_dev->disassociate_srcu); if (ret) { kfree(uverbs_dev); return -ENOMEM; } device_initialize(&uverbs_dev->dev); uverbs_dev->dev.class = &uverbs_class; uverbs_dev->dev.parent = device->dev.parent; uverbs_dev->dev.release = ib_uverbs_release_dev; uverbs_dev->groups[0] = &dev_attr_group; uverbs_dev->dev.groups = uverbs_dev->groups; refcount_set(&uverbs_dev->refcount, 1); init_completion(&uverbs_dev->comp); uverbs_dev->xrcd_tree = RB_ROOT; mutex_init(&uverbs_dev->xrcd_tree_mutex); mutex_init(&uverbs_dev->lists_mutex); INIT_LIST_HEAD(&uverbs_dev->uverbs_file_list); rcu_assign_pointer(uverbs_dev->ib_dev, device); uverbs_dev->num_comp_vectors = device->num_comp_vectors; devnum = ida_alloc_max(&uverbs_ida, IB_UVERBS_MAX_DEVICES - 1, GFP_KERNEL); if (devnum < 0) { ret = -ENOMEM; goto err; } uverbs_dev->devnum = devnum; if (devnum >= IB_UVERBS_NUM_FIXED_MINOR) base = dynamic_uverbs_dev + devnum - IB_UVERBS_NUM_FIXED_MINOR; else base = IB_UVERBS_BASE_DEV + devnum; ret = ib_uverbs_create_uapi(device, uverbs_dev); if (ret) goto err_uapi; uverbs_dev->dev.devt = base; dev_set_name(&uverbs_dev->dev, "uverbs%d", uverbs_dev->devnum); cdev_init(&uverbs_dev->cdev, device->ops.mmap ? &uverbs_mmap_fops : &uverbs_fops); uverbs_dev->cdev.owner = THIS_MODULE; ret = cdev_device_add(&uverbs_dev->cdev, &uverbs_dev->dev); if (ret) goto err_uapi; ib_set_client_data(device, &uverbs_client, uverbs_dev); return 0; err_uapi: ida_free(&uverbs_ida, devnum); err: if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); return ret; } static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, struct ib_device *ib_dev) { struct ib_uverbs_file *file; /* Pending running commands to terminate */ uverbs_disassociate_api_pre(uverbs_dev); mutex_lock(&uverbs_dev->lists_mutex); while (!list_empty(&uverbs_dev->uverbs_file_list)) { file = list_first_entry(&uverbs_dev->uverbs_file_list, struct ib_uverbs_file, list); list_del_init(&file->list); kref_get(&file->ref); /* We must release the mutex before going ahead and calling * uverbs_cleanup_ufile, as it might end up indirectly calling * uverbs_close, for example due to freeing the resources (e.g * mmput). */ mutex_unlock(&uverbs_dev->lists_mutex); uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE); kref_put(&file->ref, ib_uverbs_release_file); mutex_lock(&uverbs_dev->lists_mutex); } mutex_unlock(&uverbs_dev->lists_mutex); uverbs_disassociate_api(uverbs_dev->uapi); } static void ib_uverbs_remove_one(struct ib_device *device, void *client_data) { struct ib_uverbs_device *uverbs_dev = client_data; int wait_clients = 1; cdev_device_del(&uverbs_dev->cdev, &uverbs_dev->dev); ida_free(&uverbs_ida, uverbs_dev->devnum); if (device->ops.disassociate_ucontext) { /* We disassociate HW resources and immediately return. * Userspace will see a EIO errno for all future access. * Upon returning, ib_device may be freed internally and is not * valid any more. * uverbs_device is still available until all clients close * their files, then the uverbs device ref count will be zero * and its resources will be freed. * Note: At this point no more files can be opened since the * cdev was deleted, however active clients can still issue * commands and close their open files. */ ib_uverbs_free_hw_resources(uverbs_dev, device); wait_clients = 0; } if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); if (wait_clients) wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); } static int __init ib_uverbs_init(void) { int ret; ret = register_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR, "infiniband_verbs"); if (ret) { pr_err("user_verbs: couldn't register device number\n"); goto out; } ret = alloc_chrdev_region(&dynamic_uverbs_dev, 0, IB_UVERBS_NUM_DYNAMIC_MINOR, "infiniband_verbs"); if (ret) { pr_err("couldn't register dynamic device number\n"); goto out_alloc; } ret = class_register(&uverbs_class); if (ret) { pr_err("user_verbs: couldn't create class infiniband_verbs\n"); goto out_chrdev; } ret = class_create_file(&uverbs_class, &class_attr_abi_version.attr); if (ret) { pr_err("user_verbs: couldn't create abi_version attribute\n"); goto out_class; } ret = ib_register_client(&uverbs_client); if (ret) { pr_err("user_verbs: couldn't register client\n"); goto out_class; } return 0; out_class: class_unregister(&uverbs_class); out_chrdev: unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); out_alloc: unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); out: return ret; } static void __exit ib_uverbs_cleanup(void) { ib_unregister_client(&uverbs_client); class_unregister(&uverbs_class); unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); mmu_notifier_synchronize(); } module_init(ib_uverbs_init); module_exit(ib_uverbs_cleanup); |
| 137 144 3 59 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 | /* * Copyright (c) 1982, 1986 Regents of the University of California. * All rights reserved. * * This code is derived from software contributed to Berkeley by * Robert Elz at The University of Melbourne. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #ifndef _LINUX_QUOTA_ #define _LINUX_QUOTA_ #include <linux/list.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/spinlock.h> #include <linux/wait.h> #include <linux/percpu_counter.h> #include <linux/dqblk_xfs.h> #include <linux/dqblk_v1.h> #include <linux/dqblk_v2.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/projid.h> #include <uapi/linux/quota.h> #undef USRQUOTA #undef GRPQUOTA #undef PRJQUOTA enum quota_type { USRQUOTA = 0, /* element used for user quotas */ GRPQUOTA = 1, /* element used for group quotas */ PRJQUOTA = 2, /* element used for project quotas */ }; /* Masks for quota types when used as a bitmask */ #define QTYPE_MASK_USR (1 << USRQUOTA) #define QTYPE_MASK_GRP (1 << GRPQUOTA) #define QTYPE_MASK_PRJ (1 << PRJQUOTA) typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ typedef long long qsize_t; /* Type in which we store sizes */ struct kqid { /* Type in which we store the quota identifier */ union { kuid_t uid; kgid_t gid; kprojid_t projid; }; enum quota_type type; /* USRQUOTA (uid) or GRPQUOTA (gid) or PRJQUOTA (projid) */ }; extern bool qid_eq(struct kqid left, struct kqid right); extern bool qid_lt(struct kqid left, struct kqid right); extern qid_t from_kqid(struct user_namespace *to, struct kqid qid); extern qid_t from_kqid_munged(struct user_namespace *to, struct kqid qid); extern bool qid_valid(struct kqid qid); /** * make_kqid - Map a user-namespace, type, qid tuple into a kqid. * @from: User namespace that the qid is in * @type: The type of quota * @qid: Quota identifier * * Maps a user-namespace, type qid tuple into a kernel internal * kqid, and returns that kqid. * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to * test for and handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, enum quota_type type, qid_t qid) { struct kqid kqid; kqid.type = type; switch (type) { case USRQUOTA: kqid.uid = make_kuid(from, qid); break; case GRPQUOTA: kqid.gid = make_kgid(from, qid); break; case PRJQUOTA: kqid.projid = make_kprojid(from, qid); break; default: BUG(); } return kqid; } /** * make_kqid_invalid - Explicitly make an invalid kqid * @type: The type of quota identifier * * Returns an invalid kqid with the specified type. */ static inline struct kqid make_kqid_invalid(enum quota_type type) { struct kqid kqid; kqid.type = type; switch (type) { case USRQUOTA: kqid.uid = INVALID_UID; break; case GRPQUOTA: kqid.gid = INVALID_GID; break; case PRJQUOTA: kqid.projid = INVALID_PROJID; break; default: BUG(); } return kqid; } /** * make_kqid_uid - Make a kqid from a kuid * @uid: The kuid to make the quota identifier from */ static inline struct kqid make_kqid_uid(kuid_t uid) { struct kqid kqid; kqid.type = USRQUOTA; kqid.uid = uid; return kqid; } /** * make_kqid_gid - Make a kqid from a kgid * @gid: The kgid to make the quota identifier from */ static inline struct kqid make_kqid_gid(kgid_t gid) { struct kqid kqid; kqid.type = GRPQUOTA; kqid.gid = gid; return kqid; } /** * make_kqid_projid - Make a kqid from a projid * @projid: The kprojid to make the quota identifier from */ static inline struct kqid make_kqid_projid(kprojid_t projid) { struct kqid kqid; kqid.type = PRJQUOTA; kqid.projid = projid; return kqid; } /** * qid_has_mapping - Report if a qid maps into a user namespace. * @ns: The user namespace to see if a value maps into. * @qid: The kernel internal quota identifier to test. */ static inline bool qid_has_mapping(struct user_namespace *ns, struct kqid qid) { return from_kqid(ns, qid) != (qid_t) -1; } extern spinlock_t dq_data_lock; /* Maximal numbers of writes for quota operation (insert/delete/update) * (over VFS all formats) */ #define DQUOT_INIT_ALLOC max(V1_INIT_ALLOC, V2_INIT_ALLOC) #define DQUOT_INIT_REWRITE max(V1_INIT_REWRITE, V2_INIT_REWRITE) #define DQUOT_DEL_ALLOC max(V1_DEL_ALLOC, V2_DEL_ALLOC) #define DQUOT_DEL_REWRITE max(V1_DEL_REWRITE, V2_DEL_REWRITE) /* * Data for one user/group kept in memory */ struct mem_dqblk { qsize_t dqb_bhardlimit; /* absolute limit on disk blks alloc */ qsize_t dqb_bsoftlimit; /* preferred limit on disk blks */ qsize_t dqb_curspace; /* current used space */ qsize_t dqb_rsvspace; /* current reserved space for delalloc*/ qsize_t dqb_ihardlimit; /* absolute limit on allocated inodes */ qsize_t dqb_isoftlimit; /* preferred inode limit */ qsize_t dqb_curinodes; /* current # allocated inodes */ time64_t dqb_btime; /* time limit for excessive disk use */ time64_t dqb_itime; /* time limit for excessive inode use */ }; /* * Data for one quotafile kept in memory */ struct quota_format_type; struct mem_dqinfo { struct quota_format_type *dqi_format; int dqi_fmt_id; /* Id of the dqi_format - used when turning * quotas on after remount RW */ struct list_head dqi_dirty_list; /* List of dirty dquots [dq_list_lock] */ unsigned long dqi_flags; /* DFQ_ flags [dq_data_lock] */ unsigned int dqi_bgrace; /* Space grace time [dq_data_lock] */ unsigned int dqi_igrace; /* Inode grace time [dq_data_lock] */ qsize_t dqi_max_spc_limit; /* Maximum space limit [static] */ qsize_t dqi_max_ino_limit; /* Maximum inode limit [static] */ void *dqi_priv; }; struct super_block; /* Mask for flags passed to userspace */ #define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) /* Mask for flags modifiable from userspace */ #define DQF_SETINFO_MASK DQF_ROOT_SQUASH enum { DQF_INFO_DIRTY_B = DQF_PRIVATE, }; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); static inline int info_dirty(struct mem_dqinfo *info) { return test_bit(DQF_INFO_DIRTY_B, &info->dqi_flags); } enum { DQST_LOOKUPS, DQST_DROPS, DQST_READS, DQST_WRITES, DQST_CACHE_HITS, DQST_ALLOC_DQUOTS, DQST_FREE_DQUOTS, DQST_SYNCS, _DQST_DQSTAT_LAST }; struct dqstats { unsigned long stat[_DQST_DQSTAT_LAST]; struct percpu_counter counter[_DQST_DQSTAT_LAST]; }; extern struct dqstats dqstats; static inline void dqstats_inc(unsigned int type) { percpu_counter_inc(&dqstats.counter[type]); } static inline void dqstats_dec(unsigned int type) { percpu_counter_dec(&dqstats.counter[type]); } #define DQ_MOD_B 0 /* dquot modified since read */ #define DQ_BLKS_B 1 /* uid/gid has been warned about blk limit */ #define DQ_INODES_B 2 /* uid/gid has been warned about inode limit */ #define DQ_FAKE_B 3 /* no limits only usage */ #define DQ_READ_B 4 /* dquot was read into memory */ #define DQ_ACTIVE_B 5 /* dquot is active (dquot_release not called) */ #define DQ_RELEASING_B 6 /* dquot is in releasing_dquots list waiting * to be cleaned up */ #define DQ_LASTSET_B 7 /* Following 6 bits (see QIF_) are reserved\ * for the mask of entries set via SETQUOTA\ * quotactl. They are set under dq_data_lock\ * and the quota format handling dquot can\ * clear them when it sees fit. */ struct dquot { struct hlist_node dq_hash; /* Hash list in memory [dq_list_lock] */ struct list_head dq_inuse; /* List of all quotas [dq_list_lock] */ struct list_head dq_free; /* Free list element [dq_list_lock] */ struct list_head dq_dirty; /* List of dirty dquots [dq_list_lock] */ struct mutex dq_lock; /* dquot IO lock */ spinlock_t dq_dqb_lock; /* Lock protecting dq_dqb changes */ atomic_t dq_count; /* Use count */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ loff_t dq_off; /* Offset of dquot on disk [dq_lock, stable once set] */ unsigned long dq_flags; /* See DQ_* */ struct mem_dqblk dq_dqb; /* Diskquota usage [dq_dqb_lock] */ }; /* Operations which must be implemented by each quota format */ struct quota_format_ops { int (*check_quota_file)(struct super_block *sb, int type); /* Detect whether file is in our format */ int (*read_file_info)(struct super_block *sb, int type); /* Read main info about file - called on quotaon() */ int (*write_file_info)(struct super_block *sb, int type); /* Write main info about file */ int (*free_file_info)(struct super_block *sb, int type); /* Called on quotaoff() */ int (*read_dqblk)(struct dquot *dquot); /* Read structure for one user */ int (*commit_dqblk)(struct dquot *dquot); /* Write structure for one user */ int (*release_dqblk)(struct dquot *dquot); /* Called when last reference to dquot is being dropped */ int (*get_next_id)(struct super_block *sb, struct kqid *qid); /* Get next ID with existing structure in the quota file */ }; /* Operations working with dquots */ struct dquot_operations { int (*write_dquot) (struct dquot *); /* Ordinary dquot write */ struct dquot *(*alloc_dquot)(struct super_block *, int); /* Allocate memory for new dquot */ void (*destroy_dquot)(struct dquot *); /* Free memory for dquot */ int (*acquire_dquot) (struct dquot *); /* Quota is going to be created on disk */ int (*release_dquot) (struct dquot *); /* Quota is going to be deleted from disk */ int (*mark_dirty) (struct dquot *); /* Dquot is marked dirty */ int (*write_info) (struct super_block *, int); /* Write of quota "superblock" */ /* get reserved quota for delayed alloc, value returned is managed by * quota code only */ qsize_t *(*get_reserved_space) (struct inode *); int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */ /* Get number of inodes that were charged for a given inode */ int (*get_inode_usage) (struct inode *, qsize_t *); /* Get next ID with active quota structure */ int (*get_next_id) (struct super_block *sb, struct kqid *qid); }; struct path; /* Structure for communicating via ->get_dqblk() & ->set_dqblk() */ struct qc_dqblk { int d_fieldmask; /* mask of fields to change in ->set_dqblk() */ u64 d_spc_hardlimit; /* absolute limit on used space */ u64 d_spc_softlimit; /* preferred limit on used space */ u64 d_ino_hardlimit; /* maximum # allocated inodes */ u64 d_ino_softlimit; /* preferred inode limit */ u64 d_space; /* Space owned by the user */ u64 d_ino_count; /* # inodes owned by the user */ s64 d_ino_timer; /* zero if within inode limits */ /* if not, we refuse service */ s64 d_spc_timer; /* similar to above; for space */ int d_ino_warns; /* # warnings issued wrt num inodes */ int d_spc_warns; /* # warnings issued wrt used space */ u64 d_rt_spc_hardlimit; /* absolute limit on realtime space */ u64 d_rt_spc_softlimit; /* preferred limit on RT space */ u64 d_rt_space; /* realtime space owned */ s64 d_rt_spc_timer; /* similar to above; for RT space */ int d_rt_spc_warns; /* # warnings issued wrt RT space */ }; /* * Field specifiers for ->set_dqblk() in struct qc_dqblk and also for * ->set_info() in struct qc_info */ #define QC_INO_SOFT (1<<0) #define QC_INO_HARD (1<<1) #define QC_SPC_SOFT (1<<2) #define QC_SPC_HARD (1<<3) #define QC_RT_SPC_SOFT (1<<4) #define QC_RT_SPC_HARD (1<<5) #define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \ QC_RT_SPC_SOFT | QC_RT_SPC_HARD) #define QC_SPC_TIMER (1<<6) #define QC_INO_TIMER (1<<7) #define QC_RT_SPC_TIMER (1<<8) #define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER) #define QC_SPC_WARNS (1<<9) #define QC_INO_WARNS (1<<10) #define QC_RT_SPC_WARNS (1<<11) #define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS) #define QC_SPACE (1<<12) #define QC_INO_COUNT (1<<13) #define QC_RT_SPACE (1<<14) #define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE) #define QC_FLAGS (1<<15) #define QCI_SYSFILE (1 << 0) /* Quota file is hidden from userspace */ #define QCI_ROOT_SQUASH (1 << 1) /* Root squash turned on */ #define QCI_ACCT_ENABLED (1 << 2) /* Quota accounting enabled */ #define QCI_LIMITS_ENFORCED (1 << 3) /* Quota limits enforced */ /* Structures for communicating via ->get_state */ struct qc_type_state { unsigned int flags; /* Flags QCI_* */ unsigned int spc_timelimit; /* Time after which space softlimit is * enforced */ unsigned int ino_timelimit; /* Ditto for inode softlimit */ unsigned int rt_spc_timelimit; /* Ditto for real-time space */ unsigned int spc_warnlimit; /* Limit for number of space warnings */ unsigned int ino_warnlimit; /* Ditto for inodes */ unsigned int rt_spc_warnlimit; /* Ditto for real-time space */ unsigned long long ino; /* Inode number of quota file */ blkcnt_t blocks; /* Number of 512-byte blocks in the file */ blkcnt_t nextents; /* Number of extents in the file */ }; struct qc_state { unsigned int s_incoredqs; /* Number of dquots in core */ struct qc_type_state s_state[MAXQUOTAS]; /* Per quota type information */ }; /* Structure for communicating via ->set_info */ struct qc_info { int i_fieldmask; /* mask of fields to change in ->set_info() */ unsigned int i_flags; /* Flags QCI_* */ unsigned int i_spc_timelimit; /* Time after which space softlimit is * enforced */ unsigned int i_ino_timelimit; /* Ditto for inode softlimit */ unsigned int i_rt_spc_timelimit;/* Ditto for real-time space */ unsigned int i_spc_warnlimit; /* Limit for number of space warnings */ unsigned int i_ino_warnlimit; /* Limit for number of inode warnings */ unsigned int i_rt_spc_warnlimit; /* Ditto for real-time space */ }; /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, const struct path *); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*set_info)(struct super_block *, int, struct qc_info *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_nextdqblk)(struct super_block *, struct kqid *, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_state)(struct super_block *, struct qc_state *); int (*rm_xquota)(struct super_block *, unsigned int); }; struct quota_format_type { int qf_fmt_id; /* Quota format id */ const struct quota_format_ops *qf_ops; /* Operations of format */ struct module *qf_owner; /* Module implementing quota format */ struct quota_format_type *qf_next; }; /** * Quota state flags - they come in three flavors - for users, groups and projects. * * Actual typed flags layout: * USRQUOTA GRPQUOTA PRJQUOTA * DQUOT_USAGE_ENABLED 0x0001 0x0002 0x0004 * DQUOT_LIMITS_ENABLED 0x0008 0x0010 0x0020 * DQUOT_SUSPENDED 0x0040 0x0080 0x0100 * * Following bits are used for non-typed flags: * DQUOT_QUOTA_SYS_FILE 0x0200 * DQUOT_NEGATIVE_USAGE 0x0400 * DQUOT_NOLIST_DIRTY 0x0800 */ enum { _DQUOT_USAGE_ENABLED = 0, /* Track disk usage for users */ _DQUOT_LIMITS_ENABLED, /* Enforce quota limits for users */ _DQUOT_SUSPENDED, /* User diskquotas are off, but * we have necessary info in * memory to turn them on */ _DQUOT_STATE_FLAGS }; #define DQUOT_USAGE_ENABLED (1 << _DQUOT_USAGE_ENABLED * MAXQUOTAS) #define DQUOT_LIMITS_ENABLED (1 << _DQUOT_LIMITS_ENABLED * MAXQUOTAS) #define DQUOT_SUSPENDED (1 << _DQUOT_SUSPENDED * MAXQUOTAS) #define DQUOT_STATE_FLAGS (DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED | \ DQUOT_SUSPENDED) /* Other quota flags */ #define DQUOT_STATE_LAST (_DQUOT_STATE_FLAGS * MAXQUOTAS) #define DQUOT_QUOTA_SYS_FILE (1 << DQUOT_STATE_LAST) /* Quota file is a special * system file and user cannot * touch it. Filesystem is * responsible for setting * S_NOQUOTA, S_NOATIME flags */ #define DQUOT_NEGATIVE_USAGE (1 << (DQUOT_STATE_LAST + 1)) /* Allow negative quota usage */ /* Do not track dirty dquots in a list */ #define DQUOT_NOLIST_DIRTY (1 << (DQUOT_STATE_LAST + 2)) static inline unsigned int dquot_state_flag(unsigned int flags, int type) { return flags << type; } static inline unsigned int dquot_generic_flag(unsigned int flags, int type) { return (flags >> type) & DQUOT_STATE_FLAGS; } /* Bitmap of quota types where flag is set in flags */ static __always_inline unsigned dquot_state_types(unsigned flags, unsigned flag) { BUILD_BUG_ON_NOT_POWER_OF_2(flag); return (flags / flag) & ((1 << MAXQUOTAS) - 1); } #ifdef CONFIG_QUOTA_NETLINK_INTERFACE extern void quota_send_warning(struct kqid qid, dev_t dev, const char warntype); #else static inline void quota_send_warning(struct kqid qid, dev_t dev, const char warntype) { return; } #endif /* CONFIG_QUOTA_NETLINK_INTERFACE */ struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ struct rw_semaphore dqio_sem; /* Lock quota file while I/O in progress */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; void register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); struct quota_module_name { int qm_fmt_id; char *qm_mod_name; }; #define INIT_QUOTA_MODULE_NAMES {\ {QFMT_VFS_OLD, "quota_v1"},\ {QFMT_VFS_V0, "quota_v2"},\ {QFMT_VFS_V1, "quota_v2"},\ {0, NULL}} #endif /* _QUOTA_ */ |
| 2315 318 318 2311 935 551 364 397 1305 628 1327 1412 21 21 26 26 362 1324 7 31 89 184 21 184 184 184 184 369 1143 184 1120 979 10 860 229 305 91 935 551 44 331 142 144 225 3 87 7 19 288 209 25 606 602 26 7 185 185 21 21 2 434 349 15 286 139 229 315 34 25 9 34 2 27 27 16 7 27 19 10 7 5 1434 27 481 1323 1412 1141 184 1326 1327 1327 19 1327 1327 1283 1299 39 450 47 356 449 448 3 31 38 450 9 360 89 450 450 30 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <linux/bitmap.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) /* for any branch, call, exit record the history of jmps in the given state */ int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, int insn_flags, int spi, int frame, u64 linked_regs) { u32 cnt = cur->jmp_history_cnt; struct bpf_jmp_history_entry *p; size_t alloc_size; /* combine instruction flags if we already recorded this instruction */ if (env->cur_hist_ent) { /* atomic instructions push insn_flags twice, for READ and * WRITE sides, but they should agree on stack slot */ verifier_bug_if((env->cur_hist_ent->flags & insn_flags) && (env->cur_hist_ent->flags & insn_flags) != insn_flags, env, "insn history: insn_idx %d cur flags %x new flags %x", env->insn_idx, env->cur_hist_ent->flags, insn_flags); env->cur_hist_ent->flags |= insn_flags; env->cur_hist_ent->spi = spi; env->cur_hist_ent->frame = frame; verifier_bug_if(env->cur_hist_ent->linked_regs != 0, env, "insn history: insn_idx %d linked_regs: %#llx", env->insn_idx, env->cur_hist_ent->linked_regs); env->cur_hist_ent->linked_regs = linked_regs; return 0; } cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_KERNEL_ACCOUNT); if (!p) return -ENOMEM; cur->jmp_history = p; p = &cur->jmp_history[cnt - 1]; p->idx = env->insn_idx; p->prev_idx = env->prev_insn_idx; p->flags = insn_flags; p->spi = spi; p->frame = frame; p->linked_regs = linked_regs; cur->jmp_history_cnt = cnt; env->cur_hist_ent = p; return 0; } static bool is_atomic_load_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_LOAD_ACQ; } static bool is_atomic_fetch_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && (insn->imm & BPF_FETCH); } /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. * Return -ENOENT if we exhausted all instructions within given state. * * It's legal to have a bit of a looping with the same starting and ending * insn index within the same state, e.g.: 3->4->5->3, so just because current * instruction index is the same as state's first_idx doesn't mean we are * done. If there is still some jump history left, we should keep going. We * need to take into account that we might have a jump history between given * state's parent and itself, due to checkpointing. In this case, we'll have * history entry recording a jump from last instruction of parent state and * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; if (i == st->first_insn_idx) { if (cnt == 0) return -ENOENT; if (cnt == 1 && st->jmp_history[0].idx == i) return -ENOENT; } if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; } else { i--; } return i; } static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st, u32 hist_end, int insn_idx) { if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx) return &st->jmp_history[hist_end - 1]; return NULL; } static inline void bt_init(struct backtrack_state *bt, u32 frame) { bt->frame = frame; } static inline void bt_reset(struct backtrack_state *bt) { struct bpf_verifier_env *env = bt->env; memset(bt, 0, sizeof(*bt)); bt->env = env; } static inline u32 bt_empty(struct backtrack_state *bt) { u64 mask = 0; int i; for (i = 0; i <= bt->frame; i++) mask |= bt->reg_masks[i] | bt->stack_masks[i] | bt->stack_arg_masks[i]; return mask == 0; } static inline void bt_clear_frame_stack_arg_slot(struct backtrack_state *bt, u32 frame, u32 slot) { bt->stack_arg_masks[frame] &= ~(1 << slot); } static inline bool bt_is_frame_stack_arg_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) { return bt->stack_arg_masks[frame] & (1 << slot); } static inline int bt_subprog_enter(struct backtrack_state *bt) { if (bt->frame == MAX_CALL_FRAMES - 1) { verifier_bug(bt->env, "subprog enter from frame %d", bt->frame); return -EFAULT; } bt->frame++; return 0; } static inline int bt_subprog_exit(struct backtrack_state *bt) { if (bt->frame == 0) { verifier_bug(bt->env, "subprog exit from frame 0"); return -EFAULT; } bt->frame--; return 0; } static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) { bt->reg_masks[frame] &= ~(1 << reg); } static inline void bt_set_reg(struct backtrack_state *bt, u32 reg) { bpf_bt_set_frame_reg(bt, bt->frame, reg); } static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg) { bt_clear_frame_reg(bt, bt->frame, reg); } static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) { bt->stack_masks[frame] &= ~(1ull << slot); } static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) { return bt->reg_masks[frame]; } static inline u32 bt_reg_mask(struct backtrack_state *bt) { return bt->reg_masks[bt->frame]; } static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame) { return bt->stack_masks[frame]; } static inline u64 bt_stack_mask(struct backtrack_state *bt) { return bt->stack_masks[bt->frame]; } static inline u8 bt_stack_arg_mask(struct backtrack_state *bt) { return bt->stack_arg_masks[bt->frame]; } static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) { return bt->reg_masks[bt->frame] & (1 << reg); } /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask) { DECLARE_BITMAP(mask, 64); bool first = true; int i, n; buf[0] = '\0'; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i); first = false; buf += n; buf_sz -= n; if (buf_sz < 0) break; } } /* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */ void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) { DECLARE_BITMAP(mask, 64); bool first = true; int i, n; buf[0] = '\0'; bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8); first = false; buf += n; buf_sz -= n; if (buf_sz < 0) break; } } /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. * * @idx is an index of the instruction we are currently processing; * @subseq_idx is an index of the subsequent instruction that: * - *would be* executed next, if jump history is viewed in forward order; * - *was* processed previously during backtracking. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, struct bpf_jmp_history_entry *hist, struct backtrack_state *bt) { struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u32 dreg = insn->dst_reg; u32 sreg = insn->src_reg; u32 spi, i, fr; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt)); verbose(env, "mark_precise: frame%d: regs=%s ", bt->frame, env->tmp_str_buf); bpf_fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); bpf_verbose_insn(env, insn); } /* If there is a history record that some registers gained range at this insn, * propagate precision marks to those registers, so that bt_is_reg_set() * accounts for these registers. */ bpf_bt_sync_linked_regs(bt, hist); if (class == BPF_ALU || class == BPF_ALU64) { if (!bt_is_reg_set(bt, dreg)) return 0; if (opcode == BPF_END || opcode == BPF_NEG) { /* sreg is reserved and unused * dreg still need precision before this insn */ return 0; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { /* dreg = sreg or dreg = (s8, s16, s32)sreg * dreg needs precision after this insn * sreg needs precision before this insn */ bt_clear_reg(bt, dreg); if (sreg != BPF_REG_FP) bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. * Corresponding register is already marked * as precise=true in this verifier state. * No further markings in parent are necessary */ bt_clear_reg(bt, dreg); } } else { if (BPF_SRC(insn->code) == BPF_X) { /* dreg += sreg * both dreg and sreg need precision * before this insn */ if (sreg != BPF_REG_FP) bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX || is_atomic_load_insn(insn) || is_atomic_fetch_insn(insn)) { u32 load_reg = dreg; /* * Atomic fetch operation writes the old value into * a register (sreg or r0) and if it was tracked for * precision, propagate to the stack slot like we do * in regular ldx. */ if (is_atomic_fetch_insn(insn)) load_reg = insn->imm == BPF_CMPXCHG ? BPF_REG_0 : sreg; if (!bt_is_reg_set(bt, load_reg)) return 0; bt_clear_reg(bt, load_reg); if (hist && hist->flags & INSN_F_STACK_ARG_ACCESS) { spi = hist->spi; /* * Stack arg read: callee reads from r11+off, but * the data lives in the caller's stack_arg_regs. * Set the mask in the caller frame so precision * is marked in the caller's slot at the callee * entry checkpoint. */ bt_set_frame_stack_arg_slot(bt, bt->frame - 1, spi); return 0; } /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. * The desire to keep that precision is already indicated * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ spi = hist->spi; fr = hist->frame; bpf_bt_set_frame_slot(bt, fr, spi); } else if (class == BPF_STX || class == BPF_ST) { if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ return -ENOTSUPP; if (hist && hist->flags & INSN_F_STACK_ARG_ACCESS) { spi = hist->spi; if (!bt_is_frame_stack_arg_slot_set(bt, bt->frame, spi)) return 0; bt_clear_frame_stack_arg_slot(bt, bt->frame, spi); if (class == BPF_STX) bt_set_reg(bt, sreg); return 0; } /* scalars can only be spilled into stack */ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; spi = hist->spi; fr = hist->frame; if (!bt_is_frame_slot_set(bt, fr, spi)) return 0; bt_clear_frame_slot(bt, fr, spi); if (class == BPF_STX) bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { if (bpf_pseudo_call(insn)) { int subprog_insn_idx, subprog; subprog_insn_idx = idx + insn->imm + 1; subprog = bpf_find_subprog(env, subprog_insn_idx); if (subprog < 0) return -EFAULT; if (bpf_subprog_is_global(env, subprog)) { /* check that jump history doesn't have any * extra instructions from subprog; the next * instruction after call to global subprog * should be literally next instruction in * caller program */ verifier_bug_if(idx + 1 != subseq_idx, env, "extra insn from subprog"); /* r1-r5 are invalidated after subprog call, * so for global func call it shouldn't be set * anymore */ if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { verifier_bug(env, "global subprog unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } /* global subprog always sets R0 */ bt_clear_reg(bt, BPF_REG_0); return 0; } else { /* static subprog call instruction, which * means that we are exiting current subprog, * so only r1-r5 could be still requested as * precise, r0 and r6-r10 or any stack slot in * the current frame should be zero by now */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verifier_bug(env, "static subprog unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } /* we are now tracking register spills correctly, * so any instance of leftover slots is a bug */ if (bt_stack_mask(bt) != 0) { verifier_bug(env, "static subprog leftover stack slots %llx", bt_stack_mask(bt)); return -EFAULT; } /* propagate r1-r5 to the caller */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (bt_is_reg_set(bt, i)) { bt_clear_reg(bt, i); bpf_bt_set_frame_reg(bt, bt->frame - 1, i); } } if (bt_stack_arg_mask(bt)) { verifier_bug(env, "static subprog leftover stack arg slots %x", bt_stack_arg_mask(bt)); return -EFAULT; } if (bt_subprog_exit(bt)) return -EFAULT; return 0; } } else if (bpf_is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) { /* exit from callback subprog to callback-calling helper or * kfunc call. Use idx/subseq_idx check to discern it from * straight line code backtracking. * Unlike the subprog call handling above, we shouldn't * propagate precision of r1-r5 (if any requested), as they are * not actually arguments passed directly to callback subprogs */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verifier_bug(env, "callback unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } if (bt_stack_mask(bt) != 0) { verifier_bug(env, "callback leftover stack slots %llx", bt_stack_mask(bt)); return -EFAULT; } /* clear r1-r5 in callback subprog's mask */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); if (bt_subprog_exit(bt)) return -EFAULT; return 0; } else if (opcode == BPF_CALL) { /* kfunc with imm==0 is invalid and fixup_kfunc_call will * catch this error later. Make backtracking conservative * with ENOTSUPP. */ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* regular helper call sets R0 */ bt_clear_reg(bt, BPF_REG_0); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { /* if backtracking was looking for registers R1-R5 * they should have been found already. */ verifier_bug(env, "backtracking call unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } if (insn->src_reg == BPF_REG_0 && insn->imm == BPF_FUNC_tail_call && subseq_idx - idx != 1) { if (bt_subprog_enter(bt)) return -EFAULT; } } else if (opcode == BPF_EXIT) { bool r0_precise; /* Backtracking to a nested function call, 'idx' is a part of * the inner frame 'subseq_idx' is a part of the outer frame. * In case of a regular function call, instructions giving * precision to registers R1-R5 should have been found already. * In case of a callback, it is ok to have R1-R5 marked for * backtracking, as these registers are set by the function * invoking callback. */ if (subseq_idx >= 0 && bpf_calls_callback(env, subseq_idx)) for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { verifier_bug(env, "backtracking exit unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } /* BPF_EXIT in subprog or callback always returns * right after the call instruction, so by checking * whether the instruction at subseq_idx-1 is subprog * call or not we can distinguish actual exit from * *subprog* from exit from *callback*. In the former * case, we need to propagate r0 precision, if * necessary. In the former we never do that. */ r0_precise = subseq_idx - 1 >= 0 && bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && bt_is_reg_set(bt, BPF_REG_0); bt_clear_reg(bt, BPF_REG_0); if (bt_subprog_enter(bt)) return -EFAULT; if (r0_precise) bt_set_reg(bt, BPF_REG_0); /* r6-r9 and stack slots will stay set in caller frame * bitmasks until we return back from callee(s) */ return 0; } else if (BPF_SRC(insn->code) == BPF_X) { if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg)) return 0; /* dreg <cond> sreg * Both dreg and sreg need precision before * this insn. If only sreg was marked precise * before it would be equally necessary to * propagate it to dreg. */ if (!hist || !(hist->flags & INSN_F_SRC_REG_STACK)) bt_set_reg(bt, sreg); if (!hist || !(hist->flags & INSN_F_DST_REG_STACK)) bt_set_reg(bt, dreg); } else if (BPF_SRC(insn->code) == BPF_K) { /* dreg <cond> K * Only dreg still needs precision before * this insn, so for the K-based conditional * there is nothing new to be marked. */ } } else if (class == BPF_LD) { if (!bt_is_reg_set(bt, dreg)) return 0; bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; } /* Propagate precision marks to linked registers, to account for * registers marked as precise in this function. */ bpf_bt_sync_linked_regs(bt, hist); return 0; } /* the scalar precision tracking algorithm: * . at the start all registers have precise=false. * . scalar ranges are tracked as normal through alu and jmp insns. * . once precise value of the scalar register is used in: * . ptr + scalar alu * . if (scalar cond K|scalar) * . helper_call(.., scalar, ...) where ARG_CONST is expected * backtrack through the verifier states and mark all registers and * stack slots with spilled constants that these scalar registers * should be precise. * . during state pruning two registers (or spilled stack slots) * are equivalent if both are not precise. * * Note the verifier cannot simply walk register parentage chain, * since many different registers and stack slots could have been * used to compute single precise scalar. * * The approach of starting with precise=true for all registers and then * backtrack to mark a register as not precise when the verifier detects * that program doesn't care about specific value (e.g., when helper * takes register as ARG_ANYTHING parameter) is not safe. * * It's ok to walk single parentage chain of the verifier states. * It's possible that this backtracking will go all the way till 1st insn. * All other branches will be explored for needing precision later. * * The backtracking needs to deal with cases like: * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0) * r9 -= r8 * r5 = r9 * if r5 > 0x79f goto pc+7 * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff)) * r5 += 1 * ... * call bpf_perf_event_output#25 * where .arg5_type = ARG_CONST_SIZE_OR_ZERO * * and this case: * r6 = 1 * call foo // uses callee's r6 inside to compute r0 * r0 += r6 * if r0 == 0 goto * * to track above reg_mask/stack_mask needs to be independent for each frame. * * Also if parent's curframe > frame where backtracking started, * the verifier need to mark registers in both frames, otherwise callees * may incorrectly prune callers. This is similar to * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") * * For now backtracking falls back into conservative marking. */ void bpf_mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n", st->curframe); } /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, * because precision markings in current non-checkpointed state are * not needed. See why in the comment in __mark_chain_precision below. */ for (st = st->parent; st; st = st->parent) { for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "force_precise: frame%d: forcing r%d to be precise\n", i, j); } } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!bpf_is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n", i, -(j + 1) * 8); } } } } } /* * bpf_mark_chain_precision() backtracks BPF program instruction sequence and * chain of verifier states making sure that register *regno* (if regno >= 0) * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked * SCALARS, as well as any other registers and slots that contribute to * a tracked state of given registers/stack slots, depending on specific BPF * assembly instructions (see backtrack_insns() for exact instruction handling * logic). This backtracking relies on recorded jmp_history and is able to * traverse entire chain of parent states. This process ends only when all the * necessary registers/slots and their transitive dependencies are marked as * precise. * * One important and subtle aspect is that precise marks *do not matter* in * the currently verified state (current state). It is important to understand * why this is the case. * * First, note that current state is the state that is not yet "checkpointed", * i.e., it is not yet put into env->explored_states, and it has no children * states as well. It's ephemeral, and can end up either a) being discarded if * compatible explored state is found at some point or BPF_EXIT instruction is * reached or b) checkpointed and put into env->explored_states, branching out * into one or more children states. * * In the former case, precise markings in current state are completely * ignored by state comparison code (see regsafe() for details). Only * checkpointed ("old") state precise markings are important, and if old * state's register/slot is precise, regsafe() assumes current state's * register/slot as precise and checks value ranges exactly and precisely. If * states turn out to be compatible, current state's necessary precise * markings and any required parent states' precise markings are enforced * after the fact with propagate_precision() logic, after the fact. But it's * important to realize that in this case, even after marking current state * registers/slots as precise, we immediately discard current state. So what * actually matters is any of the precise markings propagated into current * state's parent states, which are always checkpointed (due to b) case above). * As such, for scenario a) it doesn't matter if current state has precise * markings set or not. * * Now, for the scenario b), checkpointing and forking into child(ren) * state(s). Note that before current state gets to checkpointing step, any * processed instruction always assumes precise SCALAR register/slot * knowledge: if precise value or range is useful to prune jump branch, BPF * verifier takes this opportunity enthusiastically. Similarly, when * register's value is used to calculate offset or memory address, exact * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to * what we mentioned above about state comparison ignoring precise markings * during state comparison, BPF verifier ignores and also assumes precise * markings *at will* during instruction verification process. But as verifier * assumes precision, it also propagates any precision dependencies across * parent states, which are not yet finalized, so can be further restricted * based on new knowledge gained from restrictions enforced by their children * states. This is so that once those parent states are finalized, i.e., when * they have no more active children state, state comparison logic in * is_state_visited() would enforce strict and precise SCALAR ranges, if * required for correctness. * * To build a bit more intuition, note also that once a state is checkpointed, * the path we took to get to that state is not important. This is crucial * property for state pruning. When state is checkpointed and finalized at * some instruction index, it can be correctly and safely used to "short * circuit" any *compatible* state that reaches exactly the same instruction * index. I.e., if we jumped to that instruction from a completely different * code path than original finalized state was derived from, it doesn't * matter, current state can be discarded because from that instruction * forward having a compatible state will ensure we will safely reach the * exit. States describe preconditions for further exploration, but completely * forget the history of how we got here. * * This also means that even if we needed precise SCALAR range to get to * finalized state, but from that point forward *that same* SCALAR register is * never used in a precise context (i.e., it's precise value is not needed for * correctness), it's correct and safe to mark such register as "imprecise" * (i.e., precise marking set to false). This is what we rely on when we do * not set precise marking in current state. If no child state requires * precision for any given SCALAR register, it's safe to dictate that it can * be imprecise. If any child state does require this register to be precise, * we'll mark it precise later retroactively during precise markings * propagation from child state to parent states. * * Skipping precise marking setting in current state is a mild version of * relying on the above observation. But we can utilize this property even * more aggressively by proactively forgetting any precise marking in the * current state (which we inherited from the parent state), right before we * checkpoint it and branch off into new child state. This is done by * mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ int bpf_mark_chain_precision(struct bpf_verifier_env *env, struct bpf_verifier_state *starting_state, int regno, bool *changed) { struct bpf_verifier_state *st = starting_state; struct backtrack_state *bt = &env->bt; int first_idx = st->first_insn_idx; int last_idx = starting_state->insn_idx; int subseq_idx = -1; struct bpf_func_state *func; bool tmp, skip_first = true; struct bpf_reg_state *reg; int i, fr, err; if (!env->bpf_capable) return 0; changed = changed ?: &tmp; /* set frame number from which we are starting to backtrack */ bt_init(bt, starting_state->curframe); /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ func = st->frame[bt->frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { verifier_bug(env, "backtracking misuse"); return -EFAULT; } bt_set_reg(bt, regno); } if (bt_empty(bt)) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; struct bpf_jmp_history_entry *hist; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", bt->frame, last_idx, first_idx, subseq_idx); } if (last_idx < 0) { /* we are at the entry into subprog, which * is expected for global funcs, but only if * requested precise registers are R1-R5 * (which are global func's input arguments) */ if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && bt_stack_mask(bt) == 0 && (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) { bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; bt_clear_reg(bt, i); if (reg->type == SCALAR_VALUE) { reg->precise = true; *changed = true; } } return 0; } verifier_bug(env, "backtracking func entry subprog %d reg_mask %x stack_mask %llx", st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); return -EFAULT; } for (i = last_idx;;) { if (skip_first) { err = 0; skip_first = false; } else { hist = get_jmp_hist_entry(st, history, i); err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { bpf_mark_all_scalars_precise(env, starting_state); bt_reset(bt); return 0; } else if (err) { return err; } if (bt_empty(bt)) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. */ return 0; subseq_idx = i; i = get_prev_insn_idx(st, i, &history); if (i == -ENOENT) break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask * to backtrack. * It means the backtracking missed the spot where * particular register was initialized with a constant. */ verifier_bug(env, "backtracking idx %d", i); return -EFAULT; } } st = st->parent; if (!st) break; for (fr = bt->frame; fr >= 0; fr--) { func = st->frame[fr]; bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr)); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (reg->type != SCALAR_VALUE) { bt_clear_frame_reg(bt, fr, i); continue; } if (reg->precise) { bt_clear_frame_reg(bt, fr, i); } else { reg->precise = true; *changed = true; } } bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); for_each_set_bit(i, mask, 64) { if (verifier_bug_if(i >= func->allocated_stack / BPF_REG_SIZE, env, "stack slot %d, total slots %d", i, func->allocated_stack / BPF_REG_SIZE)) return -EFAULT; if (!bpf_is_spilled_scalar_reg(&func->stack[i])) { bt_clear_frame_slot(bt, fr, i); continue; } reg = &func->stack[i].spilled_ptr; if (reg->precise) { bt_clear_frame_slot(bt, fr, i); } else { reg->precise = true; *changed = true; } } for (i = 0; i < func->out_stack_arg_cnt; i++) { if (!bt_is_frame_stack_arg_slot_set(bt, fr, i)) continue; reg = &func->stack_arg_regs[i]; if (reg->type != SCALAR_VALUE || reg->precise) { bt_clear_frame_stack_arg_slot(bt, fr, i); } else { reg->precise = true; *changed = true; } } if (env->log.level & BPF_LOG_LEVEL2) { fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_reg_mask(bt, fr)); verbose(env, "mark_precise: frame%d: parent state regs=%s ", fr, env->tmp_str_buf); bpf_fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_stack_mask(bt, fr)); verbose(env, "stack=%s: ", env->tmp_str_buf); print_verifier_state(env, st, fr, true); } } if (bt_empty(bt)) return 0; subseq_idx = first_idx; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } /* if we still have requested precise regs or slots, we missed * something (e.g., stack access through non-r10 register), so * fallback to marking all precise */ if (!bt_empty(bt)) { bpf_mark_all_scalars_precise(env, starting_state); bt_reset(bt); } return 0; } |
| 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash algorithms. * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_HASH_H #define _CRYPTO_INTERNAL_HASH_H #include <crypto/algapi.h> #include <crypto/hash.h> /* Set this bit to handle partial blocks in the API. */ #define CRYPTO_AHASH_ALG_BLOCK_ONLY 0x01000000 /* Set this bit if final requires at least one byte. */ #define CRYPTO_AHASH_ALG_FINAL_NONZERO 0x02000000 /* Set this bit if finup can deal with multiple blocks. */ #define CRYPTO_AHASH_ALG_FINUP_MAX 0x04000000 /* This bit is set by the Crypto API if export_core is not supported. */ #define CRYPTO_AHASH_ALG_NO_EXPORT_CORE 0x08000000 #define HASH_FBREQ_ON_STACK(name, req) \ char __##name##_req[sizeof(struct ahash_request) + \ MAX_SYNC_HASH_REQSIZE] CRYPTO_MINALIGN_ATTR; \ struct ahash_request *name = ahash_fbreq_on_stack_init( \ __##name##_req, (req)) struct ahash_request; struct scatterlist; struct crypto_hash_walk { const char *data; unsigned int offset; unsigned int flags; struct page *pg; unsigned int entrylen; unsigned int total; struct scatterlist *sg; }; struct ahash_instance { void (*free)(struct ahash_instance *inst); union { struct { char head[offsetof(struct ahash_alg, halg.base)]; struct crypto_instance base; } s; struct ahash_alg alg; }; }; struct shash_instance { void (*free)(struct shash_instance *inst); union { struct { char head[offsetof(struct shash_alg, base)]; struct crypto_instance base; } s; struct shash_alg alg; }; }; struct crypto_ahash_spawn { struct crypto_spawn base; }; struct crypto_shash_spawn { struct crypto_spawn base; }; int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err); int crypto_hash_walk_first(struct ahash_request *req, struct crypto_hash_walk *walk); static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) { return !(walk->entrylen | walk->total); } int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); void crypto_unregister_ahashes(struct ahash_alg *algs, int count); int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst); void ahash_free_singlespawn_instance(struct ahash_instance *inst); int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); static inline bool crypto_shash_alg_has_setkey(struct shash_alg *alg) { return alg->setkey != shash_no_setkey; } bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg); static inline bool crypto_shash_alg_needs_key(struct shash_alg *alg) { return crypto_shash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } static inline bool crypto_hash_alg_needs_key(struct hash_alg_common *alg) { return crypto_hash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } static inline bool crypto_hash_no_export_core(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->base.cra_flags & CRYPTO_AHASH_ALG_NO_EXPORT_CORE; } int crypto_grab_ahash(struct crypto_ahash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_ahash(struct crypto_ahash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct hash_alg_common *crypto_spawn_ahash_alg( struct crypto_ahash_spawn *spawn) { return __crypto_hash_alg_common(spawn->base.alg); } int crypto_register_shash(struct shash_alg *alg); void crypto_unregister_shash(struct shash_alg *alg); int crypto_register_shashes(struct shash_alg *algs, int count); void crypto_unregister_shashes(struct shash_alg *algs, int count); int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst); void shash_free_singlespawn_instance(struct shash_instance *inst); int crypto_grab_shash(struct crypto_shash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_shash(struct crypto_shash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct shash_alg *crypto_spawn_shash_alg( struct crypto_shash_spawn *spawn) { return __crypto_shash_alg(spawn->base.alg); } int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc); static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm) { return crypto_tfm_ctx(crypto_ahash_tfm(tfm)); } static inline void *crypto_ahash_ctx_dma(struct crypto_ahash *tfm) { return crypto_tfm_ctx_dma(crypto_ahash_tfm(tfm)); } static inline struct ahash_alg *__crypto_ahash_alg(struct crypto_alg *alg) { return container_of(__crypto_hash_alg_common(alg), struct ahash_alg, halg); } static inline struct ahash_alg *crypto_ahash_alg(struct crypto_ahash *hash) { return container_of(crypto_hash_alg_common(hash), struct ahash_alg, halg); } static inline void crypto_ahash_set_statesize(struct crypto_ahash *tfm, unsigned int size) { tfm->statesize = size; } static inline void crypto_ahash_set_reqsize(struct crypto_ahash *tfm, unsigned int reqsize) { tfm->reqsize = reqsize; } static inline bool crypto_ahash_tested(struct crypto_ahash *tfm) { struct crypto_tfm *tfm_base = crypto_ahash_tfm(tfm); return tfm_base->__crt_alg->cra_flags & CRYPTO_ALG_TESTED; } static inline void crypto_ahash_set_reqsize_dma(struct crypto_ahash *ahash, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); ahash->reqsize = reqsize; } static inline struct crypto_instance *ahash_crypto_instance( struct ahash_instance *inst) { return &inst->s.base; } static inline struct ahash_instance *ahash_instance( struct crypto_instance *inst) { return container_of(inst, struct ahash_instance, s.base); } static inline struct ahash_instance *ahash_alg_instance( struct crypto_ahash *ahash) { return ahash_instance(crypto_tfm_alg_instance(&ahash->base)); } static inline void *ahash_instance_ctx(struct ahash_instance *inst) { return crypto_instance_ctx(ahash_crypto_instance(inst)); } static inline void *ahash_request_ctx_dma(struct ahash_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(ahash_request_ctx(req), align); } static inline void ahash_request_complete(struct ahash_request *req, int err) { crypto_request_complete(&req->base, err); } static inline u32 ahash_request_flags(struct ahash_request *req) { return crypto_request_flags(&req->base) & ~CRYPTO_AHASH_REQ_PRIVATE; } static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline int ahash_enqueue_request(struct crypto_queue *queue, struct ahash_request *request) { return crypto_enqueue_request(queue, &request->base); } static inline struct ahash_request *ahash_dequeue_request( struct crypto_queue *queue) { return ahash_request_cast(crypto_dequeue_request(queue)); } static inline void *crypto_shash_ctx(struct crypto_shash *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline struct crypto_instance *shash_crypto_instance( struct shash_instance *inst) { return &inst->s.base; } static inline struct shash_instance *shash_instance( struct crypto_instance *inst) { return container_of(inst, struct shash_instance, s.base); } static inline struct shash_instance *shash_alg_instance( struct crypto_shash *shash) { return shash_instance(crypto_tfm_alg_instance(&shash->base)); } static inline void *shash_instance_ctx(struct shash_instance *inst) { return crypto_instance_ctx(shash_crypto_instance(inst)); } static inline struct crypto_shash *crypto_spawn_shash( struct crypto_shash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_shash, base); } static inline bool ahash_request_isvirt(struct ahash_request *req) { return req->base.flags & CRYPTO_AHASH_REQ_VIRT; } static inline bool crypto_ahash_req_virt(struct crypto_ahash *tfm) { return crypto_tfm_req_virt(&tfm->base); } static inline struct crypto_ahash *crypto_ahash_fb(struct crypto_ahash *tfm) { return __crypto_ahash_cast(crypto_ahash_tfm(tfm)->fb); } static inline struct ahash_request *ahash_fbreq_on_stack_init( char *buf, struct ahash_request *old) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(old); struct ahash_request *req = (void *)buf; crypto_stack_request_init(&req->base, crypto_ahash_tfm(crypto_ahash_fb(tfm))); ahash_request_set_callback(req, ahash_request_flags(old), NULL, NULL); req->base.flags &= ~CRYPTO_AHASH_REQ_PRIVATE; req->base.flags |= old->base.flags & CRYPTO_AHASH_REQ_PRIVATE; req->src = old->src; req->result = old->result; req->nbytes = old->nbytes; return req; } /* Return the state size without partial block for block-only algorithms. */ static inline unsigned int crypto_shash_coresize(struct crypto_shash *tfm) { return crypto_shash_statesize(tfm) - crypto_shash_blocksize(tfm) - 1; } /* This can only be used if the request was never cloned. */ #define HASH_REQUEST_ZERO(name) \ memzero_explicit(__##name##_req, sizeof(__##name##_req)) /** * crypto_ahash_export_core() - extract core state for message digest * @req: reference to the ahash_request handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * Export the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_ahash_export_core(struct ahash_request *req, void *out); /** * crypto_ahash_import_core() - import core state * @req: reference to ahash_request handle the state is imported into * @in: buffer holding the state * * Import the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_ahash_import_core(struct ahash_request *req, const void *in); /** * crypto_shash_export_core() - extract core state for message digest * @desc: reference to the operational state handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * Export the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_shash_export_core(struct shash_desc *desc, void *out); /** * crypto_shash_import_core() - import core state * @desc: reference to the operational state handle the state imported into * @in: buffer holding the state * * Import the hash state without the partial block buffer. * * Context: Softirq or process context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_shash_import_core(struct shash_desc *desc, const void *in); #endif /* _CRYPTO_INTERNAL_HASH_H */ |
| 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tlb #if !defined(_TRACE_TLB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TLB_H #include <linux/mm_types.h> #include <linux/tracepoint.h> #define TLB_FLUSH_REASON \ EM( TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" ) \ EM( TLB_REMOTE_SHOOTDOWN, "remote shootdown" ) \ EM( TLB_LOCAL_SHOOTDOWN, "local shootdown" ) \ EM( TLB_LOCAL_MM_SHOOTDOWN, "local MM shootdown" ) \ EM( TLB_REMOTE_SEND_IPI, "remote IPI send" ) \ EMe( TLB_REMOTE_WRONG_CPU, "remote wrong CPU" ) /* * First define the enums in TLB_FLUSH_REASON to be exported 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); TLB_FLUSH_REASON /* * 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 } TRACE_EVENT(tlb_flush, TP_PROTO(int reason, unsigned long pages), TP_ARGS(reason, pages), TP_STRUCT__entry( __field( int, reason) __field(unsigned long, pages) ), TP_fast_assign( __entry->reason = reason; __entry->pages = pages; ), TP_printk("pages:%ld reason:%s (%d)", __entry->pages, __print_symbolic(__entry->reason, TLB_FLUSH_REASON), __entry->reason) ); #endif /* _TRACE_TLB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 4 4 2 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007-2008 BalaBit IT Ltd. * Author: Krisztian Kovacs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> #include <net/sock.h> #include <net/inet_sock.h> #include <net/netfilter/nf_socket.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif static int extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol, __be32 *raddr, __be32 *laddr, __be16 *rport, __be16 *lport) { unsigned int outside_hdrlen = ip_hdrlen(skb); struct iphdr *inside_iph, _inside_iph; struct icmphdr *icmph, _icmph; __be16 *ports, _ports[2]; icmph = skb_header_pointer(skb, outside_hdrlen, sizeof(_icmph), &_icmph); if (icmph == NULL) return 1; if (!icmp_is_err(icmph->type)) return 1; inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(struct icmphdr), sizeof(_inside_iph), &_inside_iph); if (inside_iph == NULL) return 1; if (inside_iph->protocol != IPPROTO_TCP && inside_iph->protocol != IPPROTO_UDP) return 1; ports = skb_header_pointer(skb, outside_hdrlen + sizeof(struct icmphdr) + (inside_iph->ihl << 2), sizeof(_ports), &_ports); if (ports == NULL) return 1; /* the inside IP packet is the one quoted from our side, thus * its saddr is the local address */ *protocol = inside_iph->protocol; *laddr = inside_iph->saddr; *lport = ports[0]; *raddr = inside_iph->daddr; *rport = ports[1]; return 0; } static struct sock * nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, const struct net_device *in) { switch (protocol) { case IPPROTO_TCP: return inet_lookup(net, skb, doff, saddr, sport, daddr, dport, in->ifindex); case IPPROTO_UDP: return udp4_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); } return NULL; } struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, const struct net_device *indev) { __be32 daddr, saddr; __be16 dport, sport; const struct iphdr *iph = ip_hdr(skb); struct sk_buff *data_skb = NULL; u8 protocol; #if IS_ENABLED(CONFIG_NF_CONNTRACK) enum ip_conntrack_info ctinfo; struct nf_conn const *ct; #endif int doff = 0; if (ntohs(iph->frag_off) & IP_OFFSET) return NULL; if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { struct tcphdr _hdr; struct udphdr *hp; hp = skb_header_pointer(skb, ip_hdrlen(skb), iph->protocol == IPPROTO_UDP ? sizeof(*hp) : sizeof(_hdr), &_hdr); if (hp == NULL) return NULL; protocol = iph->protocol; saddr = iph->saddr; sport = hp->source; daddr = iph->daddr; dport = hp->dest; data_skb = (struct sk_buff *)skb; doff = iph->protocol == IPPROTO_TCP ? ip_hdrlen(skb) + __tcp_hdrlen((struct tcphdr *)hp) : ip_hdrlen(skb) + sizeof(*hp); } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, &sport, &dport)) return NULL; } else { return NULL; } #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Do the lookup with the original socket address in * case this is a reply packet of an established * SNAT-ted connection. */ ct = nf_ct_get(skb, &ctinfo); if (ct && ((iph->protocol != IPPROTO_ICMP && ctinfo == IP_CT_ESTABLISHED_REPLY) || (iph->protocol == IPPROTO_ICMP && ctinfo == IP_CT_RELATED_REPLY)) && (ct->status & IPS_SRC_NAT_DONE)) { daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; dport = (iph->protocol == IPPROTO_TCP) ? ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port : ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; } #endif return nf_socket_get_sock_v4(net, data_skb, doff, protocol, saddr, daddr, sport, dport, indev); } EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v4); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler"); MODULE_DESCRIPTION("Netfilter IPv4 socket lookup infrastructure"); |
| 35 35 35 1 1 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/mrp_bridge.h> #include "br_private_mrp.h" static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 }; static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 }; static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); static struct br_frame_type mrp_frame_type __read_mostly = { .type = cpu_to_be16(ETH_P_MRP), .frame_handler = br_mrp_process, }; static bool br_mrp_is_ring_port(struct net_bridge_port *p_port, struct net_bridge_port *s_port, struct net_bridge_port *port) { if (port == p_port || port == s_port) return true; return false; } static bool br_mrp_is_in_port(struct net_bridge_port *i_port, struct net_bridge_port *port) { if (port == i_port) return true; return false; } static struct net_bridge_port *br_mrp_get_port(struct net_bridge *br, u32 ifindex) { struct net_bridge_port *res = NULL; struct net_bridge_port *port; list_for_each_entry(port, &br->port_list, list) { if (port->dev->ifindex == ifindex) { res = port; break; } } return res; } static struct br_mrp *br_mrp_find_id(struct net_bridge *br, u32 ring_id) { struct br_mrp *res = NULL; struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { if (mrp->ring_id == ring_id) { res = mrp; break; } } return res; } static struct br_mrp *br_mrp_find_in_id(struct net_bridge *br, u32 in_id) { struct br_mrp *res = NULL; struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { if (mrp->in_id == in_id) { res = mrp; break; } } return res; } static bool br_mrp_unique_ifindex(struct net_bridge *br, u32 ifindex) { struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { struct net_bridge_port *p; p = rtnl_dereference(mrp->p_port); if (p && p->dev->ifindex == ifindex) return false; p = rtnl_dereference(mrp->s_port); if (p && p->dev->ifindex == ifindex) return false; p = rtnl_dereference(mrp->i_port); if (p && p->dev->ifindex == ifindex) return false; } return true; } static struct br_mrp *br_mrp_find_port(struct net_bridge *br, struct net_bridge_port *p) { struct br_mrp *res = NULL; struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { if (rcu_access_pointer(mrp->p_port) == p || rcu_access_pointer(mrp->s_port) == p || rcu_access_pointer(mrp->i_port) == p) { res = mrp; break; } } return res; } static int br_mrp_next_seq(struct br_mrp *mrp) { mrp->seq_id++; return mrp->seq_id; } static struct sk_buff *br_mrp_skb_alloc(struct net_bridge_port *p, const u8 *src, const u8 *dst) { struct ethhdr *eth_hdr; struct sk_buff *skb; __be16 *version; skb = dev_alloc_skb(MRP_MAX_FRAME_LENGTH); if (!skb) return NULL; skb->dev = p->dev; skb->protocol = htons(ETH_P_MRP); skb->priority = MRP_FRAME_PRIO; skb_reserve(skb, sizeof(*eth_hdr)); eth_hdr = skb_push(skb, sizeof(*eth_hdr)); ether_addr_copy(eth_hdr->h_dest, dst); ether_addr_copy(eth_hdr->h_source, src); eth_hdr->h_proto = htons(ETH_P_MRP); version = skb_put(skb, sizeof(*version)); *version = cpu_to_be16(MRP_VERSION); return skb; } static void br_mrp_skb_tlv(struct sk_buff *skb, enum br_mrp_tlv_header_type type, u8 length) { struct br_mrp_tlv_hdr *hdr; hdr = skb_put(skb, sizeof(*hdr)); hdr->type = type; hdr->length = length; } static void br_mrp_skb_common(struct sk_buff *skb, struct br_mrp *mrp) { struct br_mrp_common_hdr *hdr; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_COMMON, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); hdr->seq_id = cpu_to_be16(br_mrp_next_seq(mrp)); memset(hdr->domain, 0xff, MRP_DOMAIN_UUID_LENGTH); } static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, struct net_bridge_port *p, enum br_mrp_port_role_type port_role) { struct br_mrp_ring_test_hdr *hdr = NULL; struct sk_buff *skb = NULL; if (!p) return NULL; skb = br_mrp_skb_alloc(p, p->dev->dev_addr, mrp_test_dmac); if (!skb) return NULL; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_RING_TEST, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); hdr->prio = cpu_to_be16(mrp->prio); ether_addr_copy(hdr->sa, p->br->dev->dev_addr); hdr->port_role = cpu_to_be16(port_role); hdr->state = cpu_to_be16(mrp->ring_state); hdr->transitions = cpu_to_be16(mrp->ring_transitions); hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies)); br_mrp_skb_common(skb, mrp); /* In case the node behaves as MRA then the Test frame needs to have * an Option TLV which includes eventually a sub-option TLV that has * the type AUTO_MGR */ if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { struct br_mrp_sub_option1_hdr *sub_opt = NULL; struct br_mrp_tlv_hdr *sub_tlv = NULL; struct br_mrp_oui_hdr *oui = NULL; u8 length; length = sizeof(*sub_opt) + sizeof(*sub_tlv) + sizeof(oui) + MRP_OPT_PADDING; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_OPTION, length); oui = skb_put(skb, sizeof(*oui)); memset(oui, 0x0, sizeof(*oui)); sub_opt = skb_put(skb, sizeof(*sub_opt)); memset(sub_opt, 0x0, sizeof(*sub_opt)); sub_tlv = skb_put(skb, sizeof(*sub_tlv)); sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; /* 32 bit alligment shall be ensured therefore add 2 bytes */ skb_put(skb, MRP_OPT_PADDING); } br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); return skb; } static struct sk_buff *br_mrp_alloc_in_test_skb(struct br_mrp *mrp, struct net_bridge_port *p, enum br_mrp_port_role_type port_role) { struct br_mrp_in_test_hdr *hdr = NULL; struct sk_buff *skb = NULL; if (!p) return NULL; skb = br_mrp_skb_alloc(p, p->dev->dev_addr, mrp_in_test_dmac); if (!skb) return NULL; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_IN_TEST, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); hdr->id = cpu_to_be16(mrp->in_id); ether_addr_copy(hdr->sa, p->br->dev->dev_addr); hdr->port_role = cpu_to_be16(port_role); hdr->state = cpu_to_be16(mrp->in_state); hdr->transitions = cpu_to_be16(mrp->in_transitions); hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies)); br_mrp_skb_common(skb, mrp); br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); return skb; } /* This function is continuously called in the following cases: * - when node role is MRM, in this case test_monitor is always set to false * because it needs to notify the userspace that the ring is open and needs to * send MRP_Test frames * - when node role is MRA, there are 2 subcases: * - when MRA behaves as MRM, in this case is similar with MRM role * - when MRA behaves as MRC, in this case test_monitor is set to true, * because it needs to detect when it stops seeing MRP_Test frames * from MRM node but it doesn't need to send MRP_Test frames. */ static void br_mrp_test_work_expired(struct work_struct *work) { struct delayed_work *del_work = to_delayed_work(work); struct br_mrp *mrp = container_of(del_work, struct br_mrp, test_work); struct net_bridge_port *p; bool notify_open = false; struct sk_buff *skb; if (time_before_eq(mrp->test_end, jiffies)) return; if (mrp->test_count_miss < mrp->test_max_miss) { mrp->test_count_miss++; } else { /* Notify that the ring is open only if the ring state is * closed, otherwise it would continue to notify at every * interval. * Also notify that the ring is open when the node has the * role MRA and behaves as MRC. The reason is that the * userspace needs to know when the MRM stopped sending * MRP_Test frames so that the current node to try to take * the role of a MRM. */ if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED || mrp->test_monitor) notify_open = true; } rcu_read_lock(); p = rcu_dereference(mrp->p_port); if (p) { if (!mrp->test_monitor) { skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_PRIMARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); } if (notify_open && !mrp->ring_role_offloaded) br_mrp_ring_port_open(p->dev, true); } p = rcu_dereference(mrp->s_port); if (p) { if (!mrp->test_monitor) { skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_SECONDARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); } if (notify_open && !mrp->ring_role_offloaded) br_mrp_ring_port_open(p->dev, true); } out: rcu_read_unlock(); queue_delayed_work(system_percpu_wq, &mrp->test_work, usecs_to_jiffies(mrp->test_interval)); } /* This function is continuously called when the node has the interconnect role * MIM. It would generate interconnect test frames and will send them on all 3 * ports. But will also check if it stop receiving interconnect test frames. */ static void br_mrp_in_test_work_expired(struct work_struct *work) { struct delayed_work *del_work = to_delayed_work(work); struct br_mrp *mrp = container_of(del_work, struct br_mrp, in_test_work); struct net_bridge_port *p; bool notify_open = false; struct sk_buff *skb; if (time_before_eq(mrp->in_test_end, jiffies)) return; if (mrp->in_test_count_miss < mrp->in_test_max_miss) { mrp->in_test_count_miss++; } else { /* Notify that the interconnect ring is open only if the * interconnect ring state is closed, otherwise it would * continue to notify at every interval. */ if (mrp->in_state == BR_MRP_IN_STATE_CLOSED) notify_open = true; } rcu_read_lock(); p = rcu_dereference(mrp->p_port); if (p) { skb = br_mrp_alloc_in_test_skb(mrp, p, BR_MRP_PORT_ROLE_PRIMARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); if (notify_open && !mrp->in_role_offloaded) br_mrp_in_port_open(p->dev, true); } p = rcu_dereference(mrp->s_port); if (p) { skb = br_mrp_alloc_in_test_skb(mrp, p, BR_MRP_PORT_ROLE_SECONDARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); if (notify_open && !mrp->in_role_offloaded) br_mrp_in_port_open(p->dev, true); } p = rcu_dereference(mrp->i_port); if (p) { skb = br_mrp_alloc_in_test_skb(mrp, p, BR_MRP_PORT_ROLE_INTER); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); if (notify_open && !mrp->in_role_offloaded) br_mrp_in_port_open(p->dev, true); } out: rcu_read_unlock(); queue_delayed_work(system_percpu_wq, &mrp->in_test_work, usecs_to_jiffies(mrp->in_test_interval)); } /* Deletes the MRP instance. * note: called under rtnl_lock */ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) { struct net_bridge_port *p; u8 state; /* Stop sending MRP_Test frames */ cancel_delayed_work_sync(&mrp->test_work); br_mrp_switchdev_send_ring_test(br, mrp, 0, 0, 0, 0); /* Stop sending MRP_InTest frames if has an interconnect role */ cancel_delayed_work_sync(&mrp->in_test_work); br_mrp_switchdev_send_in_test(br, mrp, 0, 0, 0); /* Disable the roles */ br_mrp_switchdev_set_ring_role(br, mrp, BR_MRP_RING_ROLE_DISABLED); p = rtnl_dereference(mrp->i_port); if (p) br_mrp_switchdev_set_in_role(br, mrp, mrp->in_id, mrp->ring_id, BR_MRP_IN_ROLE_DISABLED); br_mrp_switchdev_del(br, mrp); /* Reset the ports */ p = rtnl_dereference(mrp->p_port); if (p) { spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; clear_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->p_port, NULL); } p = rtnl_dereference(mrp->s_port); if (p) { spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; clear_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->s_port, NULL); } p = rtnl_dereference(mrp->i_port); if (p) { spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; clear_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->i_port, NULL); } hlist_del_rcu(&mrp->list); kfree_rcu(mrp, rcu); if (hlist_empty(&br->mrp_list)) br_del_frame(br, &mrp_frame_type); } /* Adds a new MRP instance. * note: called under rtnl_lock */ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance) { struct net_bridge_port *p; struct br_mrp *mrp; int err; /* If the ring exists, it is not possible to create another one with the * same ring_id */ mrp = br_mrp_find_id(br, instance->ring_id); if (mrp) return -EINVAL; if (!br_mrp_get_port(br, instance->p_ifindex) || !br_mrp_get_port(br, instance->s_ifindex)) return -EINVAL; /* It is not possible to have the same port part of multiple rings */ if (!br_mrp_unique_ifindex(br, instance->p_ifindex) || !br_mrp_unique_ifindex(br, instance->s_ifindex)) return -EINVAL; mrp = kzalloc_obj(*mrp); if (!mrp) return -ENOMEM; mrp->ring_id = instance->ring_id; mrp->prio = instance->prio; p = br_mrp_get_port(br, instance->p_ifindex); spin_lock_bh(&br->lock); p->state = BR_STATE_FORWARDING; set_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->p_port, p); p = br_mrp_get_port(br, instance->s_ifindex); spin_lock_bh(&br->lock); p->state = BR_STATE_FORWARDING; set_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->s_port, p); if (hlist_empty(&br->mrp_list)) br_add_frame(br, &mrp_frame_type); INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired); INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired); hlist_add_tail_rcu(&mrp->list, &br->mrp_list); err = br_mrp_switchdev_add(br, mrp); if (err) goto delete_mrp; return 0; delete_mrp: br_mrp_del_impl(br, mrp); return err; } /* Deletes the MRP instance from which the port is part of * note: called under rtnl_lock */ void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p) { struct br_mrp *mrp = br_mrp_find_port(br, p); /* If the port is not part of a MRP instance just bail out */ if (!mrp) return; br_mrp_del_impl(br, mrp); } /* Deletes existing MRP instance based on ring_id * note: called under rtnl_lock */ int br_mrp_del(struct net_bridge *br, struct br_mrp_instance *instance) { struct br_mrp *mrp = br_mrp_find_id(br, instance->ring_id); if (!mrp) return -EINVAL; br_mrp_del_impl(br, mrp); return 0; } /* Set port state, port state can be forwarding, blocked or disabled * note: already called with rtnl_lock */ int br_mrp_set_port_state(struct net_bridge_port *p, enum br_mrp_port_state_type state) { u32 port_state; if (!p || !test_bit(BR_MRP_AWARE_BIT, &p->flags)) return -EINVAL; spin_lock_bh(&p->br->lock); if (state == BR_MRP_PORT_STATE_FORWARDING) port_state = BR_STATE_FORWARDING; else port_state = BR_STATE_BLOCKING; p->state = port_state; spin_unlock_bh(&p->br->lock); br_mrp_port_switchdev_set_state(p, port_state); return 0; } /* Set port role, port role can be primary or secondary * note: already called with rtnl_lock */ int br_mrp_set_port_role(struct net_bridge_port *p, enum br_mrp_port_role_type role) { struct br_mrp *mrp; if (!p || !test_bit(BR_MRP_AWARE_BIT, &p->flags)) return -EINVAL; mrp = br_mrp_find_port(p->br, p); if (!mrp) return -EINVAL; switch (role) { case BR_MRP_PORT_ROLE_PRIMARY: rcu_assign_pointer(mrp->p_port, p); break; case BR_MRP_PORT_ROLE_SECONDARY: rcu_assign_pointer(mrp->s_port, p); break; default: return -EINVAL; } br_mrp_port_switchdev_set_role(p, role); return 0; } /* Set ring state, ring state can be only Open or Closed * note: already called with rtnl_lock */ int br_mrp_set_ring_state(struct net_bridge *br, struct br_mrp_ring_state *state) { struct br_mrp *mrp = br_mrp_find_id(br, state->ring_id); if (!mrp) return -EINVAL; if (mrp->ring_state != state->ring_state) mrp->ring_transitions++; mrp->ring_state = state->ring_state; br_mrp_switchdev_set_ring_state(br, mrp, state->ring_state); return 0; } /* Set ring role, ring role can be only MRM(Media Redundancy Manager) or * MRC(Media Redundancy Client). * note: already called with rtnl_lock */ int br_mrp_set_ring_role(struct net_bridge *br, struct br_mrp_ring_role *role) { struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id); enum br_mrp_hw_support support; if (!mrp) return -EINVAL; mrp->ring_role = role->ring_role; /* If there is an error just bailed out */ support = br_mrp_switchdev_set_ring_role(br, mrp, role->ring_role); if (support == BR_MRP_NONE) return -EOPNOTSUPP; /* Now detect if the HW actually applied the role or not. If the HW * applied the role it means that the SW will not to do those operations * anymore. For example if the role ir MRM then the HW will notify the * SW when ring is open, but if the is not pushed to the HW the SW will * need to detect when the ring is open */ mrp->ring_role_offloaded = support == BR_MRP_SW ? 0 : 1; return 0; } /* Start to generate or monitor MRP test frames, the frames are generated by * HW and if it fails, they are generated by the SW. * note: already called with rtnl_lock */ int br_mrp_start_test(struct net_bridge *br, struct br_mrp_start_test *test) { struct br_mrp *mrp = br_mrp_find_id(br, test->ring_id); enum br_mrp_hw_support support; if (!mrp) return -EINVAL; /* Try to push it to the HW and if it fails then continue with SW * implementation and if that also fails then return error. */ support = br_mrp_switchdev_send_ring_test(br, mrp, test->interval, test->max_miss, test->period, test->monitor); if (support == BR_MRP_NONE) return -EOPNOTSUPP; if (support == BR_MRP_HW) return 0; mrp->test_interval = test->interval; mrp->test_end = jiffies + usecs_to_jiffies(test->period); mrp->test_max_miss = test->max_miss; mrp->test_monitor = test->monitor; mrp->test_count_miss = 0; queue_delayed_work(system_percpu_wq, &mrp->test_work, usecs_to_jiffies(test->interval)); return 0; } /* Set in state, int state can be only Open or Closed * note: already called with rtnl_lock */ int br_mrp_set_in_state(struct net_bridge *br, struct br_mrp_in_state *state) { struct br_mrp *mrp = br_mrp_find_in_id(br, state->in_id); if (!mrp) return -EINVAL; if (mrp->in_state != state->in_state) mrp->in_transitions++; mrp->in_state = state->in_state; br_mrp_switchdev_set_in_state(br, mrp, state->in_state); return 0; } /* Set in role, in role can be only MIM(Media Interconnection Manager) or * MIC(Media Interconnection Client). * note: already called with rtnl_lock */ int br_mrp_set_in_role(struct net_bridge *br, struct br_mrp_in_role *role) { struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id); enum br_mrp_hw_support support; struct net_bridge_port *p; if (!mrp) return -EINVAL; if (!br_mrp_get_port(br, role->i_ifindex)) return -EINVAL; if (role->in_role == BR_MRP_IN_ROLE_DISABLED) { u8 state; /* It is not allowed to disable a port that doesn't exist */ p = rtnl_dereference(mrp->i_port); if (!p) return -EINVAL; /* Stop the generating MRP_InTest frames */ cancel_delayed_work_sync(&mrp->in_test_work); br_mrp_switchdev_send_in_test(br, mrp, 0, 0, 0); /* Remove the port */ spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; clear_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->i_port, NULL); mrp->in_role = role->in_role; mrp->in_id = 0; return 0; } /* It is not possible to have the same port part of multiple rings */ if (!br_mrp_unique_ifindex(br, role->i_ifindex)) return -EINVAL; /* It is not allowed to set a different interconnect port if the mrp * instance has already one. First it needs to be disabled and after * that set the new port */ if (rcu_access_pointer(mrp->i_port)) return -EINVAL; p = br_mrp_get_port(br, role->i_ifindex); spin_lock_bh(&br->lock); p->state = BR_STATE_FORWARDING; set_bit(BR_MRP_AWARE_BIT, &p->flags); spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->i_port, p); mrp->in_role = role->in_role; mrp->in_id = role->in_id; /* If there is an error just bailed out */ support = br_mrp_switchdev_set_in_role(br, mrp, role->in_id, role->ring_id, role->in_role); if (support == BR_MRP_NONE) return -EOPNOTSUPP; /* Now detect if the HW actually applied the role or not. If the HW * applied the role it means that the SW will not to do those operations * anymore. For example if the role is MIM then the HW will notify the * SW when interconnect ring is open, but if the is not pushed to the HW * the SW will need to detect when the interconnect ring is open. */ mrp->in_role_offloaded = support == BR_MRP_SW ? 0 : 1; return 0; } /* Start to generate MRP_InTest frames, the frames are generated by * HW and if it fails, they are generated by the SW. * note: already called with rtnl_lock */ int br_mrp_start_in_test(struct net_bridge *br, struct br_mrp_start_in_test *in_test) { struct br_mrp *mrp = br_mrp_find_in_id(br, in_test->in_id); enum br_mrp_hw_support support; if (!mrp) return -EINVAL; if (mrp->in_role != BR_MRP_IN_ROLE_MIM) return -EINVAL; /* Try to push it to the HW and if it fails then continue with SW * implementation and if that also fails then return error. */ support = br_mrp_switchdev_send_in_test(br, mrp, in_test->interval, in_test->max_miss, in_test->period); if (support == BR_MRP_NONE) return -EOPNOTSUPP; if (support == BR_MRP_HW) return 0; mrp->in_test_interval = in_test->interval; mrp->in_test_end = jiffies + usecs_to_jiffies(in_test->period); mrp->in_test_max_miss = in_test->max_miss; mrp->in_test_count_miss = 0; queue_delayed_work(system_percpu_wq, &mrp->in_test_work, usecs_to_jiffies(in_test->interval)); return 0; } /* Determine if the frame type is a ring frame */ static bool br_mrp_ring_frame(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return false; if (hdr->type == BR_MRP_TLV_HEADER_RING_TEST || hdr->type == BR_MRP_TLV_HEADER_RING_TOPO || hdr->type == BR_MRP_TLV_HEADER_RING_LINK_DOWN || hdr->type == BR_MRP_TLV_HEADER_RING_LINK_UP || hdr->type == BR_MRP_TLV_HEADER_OPTION) return true; return false; } /* Determine if the frame type is an interconnect frame */ static bool br_mrp_in_frame(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return false; if (hdr->type == BR_MRP_TLV_HEADER_IN_TEST || hdr->type == BR_MRP_TLV_HEADER_IN_TOPO || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_DOWN || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) return true; return false; } /* Process only MRP Test frame. All the other MRP frames are processed by * userspace application * note: already called with rcu_read_lock */ static void br_mrp_mrm_process(struct br_mrp *mrp, struct net_bridge_port *port, struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return; if (hdr->type != BR_MRP_TLV_HEADER_RING_TEST) return; mrp->test_count_miss = 0; /* Notify the userspace that the ring is closed only when the ring is * not closed */ if (mrp->ring_state != BR_MRP_RING_STATE_CLOSED) br_mrp_ring_port_open(port->dev, false); } /* Determine if the test hdr has a better priority than the node */ static bool br_mrp_test_better_than_own(struct br_mrp *mrp, struct net_bridge *br, const struct br_mrp_ring_test_hdr *hdr) { u16 prio = be16_to_cpu(hdr->prio); if (prio < mrp->prio || (prio == mrp->prio && ether_addr_to_u64(hdr->sa) < ether_addr_to_u64(br->dev->dev_addr))) return true; return false; } /* Process only MRP Test frame. All the other MRP frames are processed by * userspace application * note: already called with rcu_read_lock */ static void br_mrp_mra_process(struct br_mrp *mrp, struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb) { const struct br_mrp_ring_test_hdr *test_hdr; struct br_mrp_ring_test_hdr _test_hdr; const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return; if (hdr->type != BR_MRP_TLV_HEADER_RING_TEST) return; test_hdr = skb_header_pointer(skb, sizeof(uint16_t) + sizeof(_hdr), sizeof(_test_hdr), &_test_hdr); if (!test_hdr) return; /* Only frames that have a better priority than the node will * clear the miss counter because otherwise the node will need to behave * as MRM. */ if (br_mrp_test_better_than_own(mrp, br, test_hdr)) mrp->test_count_miss = 0; } /* Process only MRP InTest frame. All the other MRP frames are processed by * userspace application * note: already called with rcu_read_lock */ static bool br_mrp_mim_process(struct br_mrp *mrp, struct net_bridge_port *port, struct sk_buff *skb) { const struct br_mrp_in_test_hdr *in_hdr; struct br_mrp_in_test_hdr _in_hdr; const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return false; /* The check for InTest frame type was already done */ in_hdr = skb_header_pointer(skb, sizeof(uint16_t) + sizeof(_hdr), sizeof(_in_hdr), &_in_hdr); if (!in_hdr) return false; /* It needs to process only it's own InTest frames. */ if (mrp->in_id != ntohs(in_hdr->id)) return false; mrp->in_test_count_miss = 0; /* Notify the userspace that the ring is closed only when the ring is * not closed */ if (mrp->in_state != BR_MRP_IN_STATE_CLOSED) br_mrp_in_port_open(port->dev, false); return true; } /* Get the MRP frame type * note: already called with rcu_read_lock */ static u8 br_mrp_get_frame_type(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return 0xff; return hdr->type; } static bool br_mrp_mrm_behaviour(struct br_mrp *mrp) { if (mrp->ring_role == BR_MRP_RING_ROLE_MRM || (mrp->ring_role == BR_MRP_RING_ROLE_MRA && !mrp->test_monitor)) return true; return false; } static bool br_mrp_mrc_behaviour(struct br_mrp *mrp) { if (mrp->ring_role == BR_MRP_RING_ROLE_MRC || (mrp->ring_role == BR_MRP_RING_ROLE_MRA && mrp->test_monitor)) return true; return false; } /* This will just forward the frame to the other mrp ring ports, depending on * the frame type, ring role and interconnect role * note: already called with rcu_read_lock */ static int br_mrp_rcv(struct net_bridge_port *p, struct sk_buff *skb, struct net_device *dev) { struct net_bridge_port *p_port, *s_port, *i_port = NULL; struct net_bridge_port *p_dst, *s_dst, *i_dst = NULL; struct net_bridge *br; struct br_mrp *mrp; /* If port is disabled don't accept any frames */ if (p->state == BR_STATE_DISABLED) return 0; br = p->br; mrp = br_mrp_find_port(br, p); if (unlikely(!mrp)) return 0; p_port = rcu_dereference(mrp->p_port); if (!p_port) return 0; p_dst = p_port; s_port = rcu_dereference(mrp->s_port); if (!s_port) return 0; s_dst = s_port; /* If the frame is a ring frame then it is not required to check the * interconnect role and ports to process or forward the frame */ if (br_mrp_ring_frame(skb)) { /* If the role is MRM then don't forward the frames */ if (mrp->ring_role == BR_MRP_RING_ROLE_MRM) { br_mrp_mrm_process(mrp, p, skb); goto no_forward; } /* If the role is MRA then don't forward the frames if it * behaves as MRM node */ if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { if (!mrp->test_monitor) { br_mrp_mrm_process(mrp, p, skb); goto no_forward; } br_mrp_mra_process(mrp, br, p, skb); } goto forward; } if (br_mrp_in_frame(skb)) { u8 in_type = br_mrp_get_frame_type(skb); i_port = rcu_dereference(mrp->i_port); i_dst = i_port; /* If the ring port is in block state it should not forward * In_Test frames */ if (br_mrp_is_ring_port(p_port, s_port, p) && p->state == BR_STATE_BLOCKING && in_type == BR_MRP_TLV_HEADER_IN_TEST) goto no_forward; /* Nodes that behaves as MRM needs to stop forwarding the * frames in case the ring is closed, otherwise will be a loop. * In this case the frame is no forward between the ring ports. */ if (br_mrp_mrm_behaviour(mrp) && br_mrp_is_ring_port(p_port, s_port, p) && (s_port->state != BR_STATE_FORWARDING || p_port->state != BR_STATE_FORWARDING)) { p_dst = NULL; s_dst = NULL; } /* A node that behaves as MRC and doesn't have a interconnect * role then it should forward all frames between the ring ports * because it doesn't have an interconnect port */ if (br_mrp_mrc_behaviour(mrp) && mrp->in_role == BR_MRP_IN_ROLE_DISABLED) goto forward; if (mrp->in_role == BR_MRP_IN_ROLE_MIM) { if (in_type == BR_MRP_TLV_HEADER_IN_TEST) { /* MIM should not forward it's own InTest * frames */ if (br_mrp_mim_process(mrp, p, skb)) { goto no_forward; } else { if (br_mrp_is_ring_port(p_port, s_port, p)) i_dst = NULL; if (br_mrp_is_in_port(i_port, p)) goto no_forward; } } else { /* MIM should forward IntLinkChange/Status and * IntTopoChange between ring ports but MIM * should not forward IntLinkChange/Status and * IntTopoChange if the frame was received at * the interconnect port */ if (br_mrp_is_ring_port(p_port, s_port, p)) i_dst = NULL; if (br_mrp_is_in_port(i_port, p)) goto no_forward; } } if (mrp->in_role == BR_MRP_IN_ROLE_MIC) { /* MIC should forward InTest frames on all ports * regardless of the received port */ if (in_type == BR_MRP_TLV_HEADER_IN_TEST) goto forward; /* MIC should forward IntLinkChange frames only if they * are received on ring ports to all the ports */ if (br_mrp_is_ring_port(p_port, s_port, p) && (in_type == BR_MRP_TLV_HEADER_IN_LINK_UP || in_type == BR_MRP_TLV_HEADER_IN_LINK_DOWN)) goto forward; /* MIC should forward IntLinkStatus frames only to * interconnect port if it was received on a ring port. * If it is received on interconnect port then, it * should be forward on both ring ports */ if (br_mrp_is_ring_port(p_port, s_port, p) && in_type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) { p_dst = NULL; s_dst = NULL; } /* Should forward the InTopo frames only between the * ring ports */ if (in_type == BR_MRP_TLV_HEADER_IN_TOPO) { i_dst = NULL; goto forward; } /* In all the other cases don't forward the frames */ goto no_forward; } } forward: if (p_dst) br_forward(p_dst, skb, true, false); if (s_dst) br_forward(s_dst, skb, true, false); if (i_dst) br_forward(i_dst, skb, true, false); no_forward: return 1; } /* Check if the frame was received on a port that is part of MRP ring * and if the frame has MRP eth. In that case process the frame otherwise do * normal forwarding. * note: already called with rcu_read_lock */ static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) { /* If there is no MRP instance do normal forwarding */ if (likely(!test_bit(BR_MRP_AWARE_BIT, &p->flags))) goto out; return br_mrp_rcv(p, skb, p->dev); out: return 0; } bool br_mrp_enabled(struct net_bridge *br) { return !hlist_empty(&br->mrp_list); } |
| 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * usb hub driver head file * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 1999 Johannes Erdfelt * Copyright (C) 1999 Gregory P. Smith * Copyright (C) 2001 Brad Hards (bhards@bigpond.net.au) * Copyright (C) 2012 Intel Corp (tianyu.lan@intel.com) * * move struct usb_hub to this file. */ #include <linux/usb.h> #include <linux/usb/ch11.h> #include <linux/usb/hcd.h> #include <linux/usb/typec.h> #include "usb.h" struct usb_hub { struct device *intfdev; /* the "interface" device */ struct usb_device *hdev; struct kref kref; struct urb *urb; /* for interrupt polling pipe */ /* buffer for urb ... with extra space in case of babble */ u8 (*buffer)[8]; union { struct usb_hub_status hub; struct usb_port_status port; } *status; /* buffer for status reports */ struct mutex status_mutex; /* for the status buffer */ int error; /* last reported error */ int nerrors; /* track consecutive errors */ unsigned long event_bits[1]; /* status change bitmask */ unsigned long change_bits[1]; /* ports with logical connect status change */ unsigned long removed_bits[1]; /* ports with a "removed" device present */ unsigned long wakeup_bits[1]; /* ports that have signaled remote wakeup */ unsigned long power_bits[1]; /* ports that are powered */ unsigned long child_usage_bits[1]; /* ports powered on for children */ unsigned long warm_reset_bits[1]; /* ports requesting warm reset recovery */ #if USB_MAXCHILDREN > 31 /* 8*sizeof(unsigned long) - 1 */ #error event_bits[] is too short! #endif struct usb_hub_descriptor *descriptor; /* class descriptor */ struct usb_tt tt; /* Transaction Translator */ unsigned mA_per_port; /* current for each child */ #ifdef CONFIG_PM unsigned wakeup_enabled_descendants; #endif unsigned limited_power:1; unsigned quiescing:1; unsigned disconnected:1; unsigned in_reset:1; unsigned quirk_disable_autosuspend:1; unsigned quirk_check_port_auto_suspend:1; unsigned has_indicators:1; u8 indicator[USB_MAXCHILDREN]; struct delayed_work leds; struct delayed_work init_work; struct delayed_work post_resume_work; struct work_struct events; spinlock_t irq_urb_lock; struct timer_list irq_urb_retry; struct usb_port **ports; struct list_head onboard_devs; }; /** * struct usb port - kernel's representation of a usb port * @child: usb device attached to the port * @dev: generic device interface * @port_owner: port's owner * @peer: related usb2 and usb3 ports (share the same connector) * @connector: USB Type-C connector * @req: default pm qos request for hubs without port power control * @connect_type: port's connect type * @state: device state of the usb device attached to the port * @state_kn: kernfs_node of the sysfs attribute that accesses @state * @location: opaque representation of platform connector location * @status_lock: synchronize port_event() vs usb_port_{suspend|resume} * @portnum: port index num based one * @is_superspeed cache super-speed status * @usb3_lpm_u1_permit: whether USB3 U1 LPM is permitted. * @usb3_lpm_u2_permit: whether USB3 U2 LPM is permitted. * @early_stop: whether port initialization will be stopped earlier. * @ignore_event: whether events of the port are ignored. */ struct usb_port { struct usb_device *child; struct device dev; struct usb_dev_state *port_owner; struct usb_port *peer; struct typec_connector *connector; struct dev_pm_qos_request *req; enum usb_port_connect_type connect_type; enum usb_device_state state; struct kernfs_node *state_kn; usb_port_location_t location; struct mutex status_lock; u32 over_current_count; u8 portnum; u32 quirks; unsigned int early_stop:1; unsigned int ignore_event:1; unsigned int is_superspeed:1; unsigned int usb3_lpm_u1_permit:1; unsigned int usb3_lpm_u2_permit:1; }; #define to_usb_port(_dev) \ container_of(_dev, struct usb_port, dev) extern int usb_hub_create_port_device(struct usb_hub *hub, int port1); extern void usb_hub_remove_port_device(struct usb_hub *hub, int port1); extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set); extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev); extern void hub_get(struct usb_hub *hub); extern void hub_put(struct usb_hub *hub); extern int hub_port_debounce(struct usb_hub *hub, int port1, bool must_be_connected); extern int usb_clear_port_feature(struct usb_device *hdev, int port1, int feature); extern int usb_hub_port_status(struct usb_hub *hub, int port1, u16 *status, u16 *change); extern int usb_port_is_power_on(struct usb_hub *hub, unsigned int portstatus); static inline bool hub_is_port_power_switchable(struct usb_hub *hub) { __le16 hcs; if (!hub) return false; hcs = hub->descriptor->wHubCharacteristics; return (le16_to_cpu(hcs) & HUB_CHAR_LPSM) < HUB_CHAR_NO_LPSM; } static inline int hub_is_superspeed(struct usb_device *hdev) { return hdev->descriptor.bDeviceProtocol == USB_HUB_PR_SS; } static inline int hub_is_superspeedplus(struct usb_device *hdev) { return (hdev->descriptor.bDeviceProtocol == USB_HUB_PR_SS && le16_to_cpu(hdev->descriptor.bcdUSB) >= 0x0310 && hdev->bos && hdev->bos->ssp_cap); } static inline unsigned hub_power_on_good_delay(struct usb_hub *hub) { unsigned delay = hub->descriptor->bPwrOn2PwrGood * 2; if (!hub->hdev->parent) /* root hub */ return delay; else /* Wait at least 100 msec for power to become stable */ return max(delay, 100U); } static inline int hub_port_debounce_be_connected(struct usb_hub *hub, int port1) { return hub_port_debounce(hub, port1, true); } static inline int hub_port_debounce_be_stable(struct usb_hub *hub, int port1) { return hub_port_debounce(hub, port1, false); } |
| 167 15 1 14 41 1 51 8 9 16 40 40 1 39 13 11 3 13 16 16 5 13 16 16 42 19 19 19 19 19 19 2 117 117 3 3 11 11 10 1 1 1 3 1 2 2 1 1 37 1 36 36 24 1 1 1 1 42 45 3 19 1 18 24 12 32 32 2 48 9 7 5 6 5 2 4 20 9 15 2 2 3 5 5 5 13 9 7 6 3 2 5 5 3 6 26 10 25 18 7 3 7 2 11 2 6 1 54 3 5 9 9 7 68 67 43 1 43 12 1 41 2 36 8 36 4 36 6 41 44 22 36 18 18 12 12 11 1 5 2 18 18 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/shm.c * Copyright (C) 1992, 1993 Krishna Balasubramanian * Many improvements/fixes by Bruno Haible. * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994. * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli. * * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * BIGMEM support, Andrea Arcangeli <andrea@suse.de> * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr> * HIGHMEM support, Ingo Molnar <mingo@redhat.com> * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com> * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com> * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * Better ipc lock (kern_ipc_perm.lock) handling * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013. */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/shm.h> #include <uapi/linux/shm.h> #include <linux/init.h> #include <linux/file.h> #include <linux/mman.h> #include <linux/shmem_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/ptrace.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/mount.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/nstree.h> #include <linux/uaccess.h> #include "util.h" struct shmid_kernel /* private to the kernel */ { struct kern_ipc_perm shm_perm; struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; time64_t shm_atim; time64_t shm_dtim; time64_t shm_ctim; struct pid *shm_cprid; struct pid *shm_lprid; struct ucounts *mlock_ucounts; /* * The task created the shm object, for * task_lock(shp->shm_creator) */ struct task_struct *shm_creator; /* * List by creator. task_lock(->shm_creator) required for read/write. * If list_empty(), then the creator is dead already. */ struct list_head shm_clist; struct ipc_namespace *ns; } __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ struct shm_file_data { int id; struct ipc_namespace *ns; struct file *file; const struct vm_operations_struct *vm_ops; }; #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) #define shm_unlock(shp) \ ipc_unlock(&(shp)->shm_perm) static int newseg(struct ipc_namespace *, struct ipc_params *); static void shm_open(struct vm_area_struct *vma); static void shm_close(struct vm_area_struct *vma); static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp); #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it); #endif void shm_init_ns(struct ipc_namespace *ns) { ns->shm_ctlmax = SHMMAX; ns->shm_ctlall = SHMALL; ns->shm_ctlmni = SHMMNI; ns->shm_rmid_forced = 0; ns->shm_tot = 0; ipc_init_ids(&shm_ids(ns)); } /* * Called with shm_ids.rwsem (writer) and the shp structure locked. * Only shm_ids.rwsem remains locked on exit. */ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; /* Do not find it any more */ ipc_set_key_private(&shm_ids(ns), &shp->shm_perm); shm_unlock(shp); } else shm_destroy(ns, shp); } #ifdef CONFIG_IPC_NS void shm_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &shm_ids(ns), do_shm_rmid); idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht); } #endif static int __init ipc_ns_init(void) { shm_init_ns(&init_ipc_ns); ns_tree_add(&init_ipc_ns); return 0; } pure_initcall(ipc_ns_init); void __init shm_init(void) { ipc_init_proc_interface("sysvipc/shm", #if BITS_PER_LONG <= 32 " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #else " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #endif IPC_SHM_IDS, sysvipc_shm_proc_show); } static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } /* * shm_lock_(check_) routines are called in the paths where the rwsem * is not necessarily held. */ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp; rcu_read_lock(); ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) goto err; ipc_lock_object(ipcp); /* * ipc_rmid() may have already freed the ID while ipc_lock_object() * was spinning: here verify that the structure is still valid. * Upon races with RMID, return -EIDRM, thus indicating that * the ID points to a removed identifier. */ if (ipc_valid_object(ipcp)) { /* return a locked ipc object upon success */ return container_of(ipcp, struct shmid_kernel, shm_perm); } ipc_unlock_object(ipcp); ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* * Callers of shm_lock() must validate the status of the returned ipc * object pointer and error out as appropriate. */ return ERR_CAST(ipcp); } static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) { rcu_read_lock(); ipc_lock_object(&ipcp->shm_perm); } static void shm_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, rcu); struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(&shp->shm_perm); kfree(shp); } /* * It has to be called with shp locked. * It must be called before ipc_rmid() */ static inline void shm_clist_rm(struct shmid_kernel *shp) { struct task_struct *creator; /* ensure that shm_creator does not disappear */ rcu_read_lock(); /* * A concurrent exit_shm may do a list_del_init() as well. * Just do nothing if exit_shm already did the work */ if (!list_empty(&shp->shm_clist)) { /* * shp->shm_creator is guaranteed to be valid *only* * if shp->shm_clist is not empty. */ creator = shp->shm_creator; task_lock(creator); /* * list_del_init() is a nop if the entry was already removed * from the list. */ list_del_init(&shp->shm_clist); task_unlock(creator); } rcu_read_unlock(); } static inline void shm_rmid(struct shmid_kernel *s) { shm_clist_rm(s); ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } static int __shm_open(struct shm_file_data *sfd) { struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); if (IS_ERR(shp)) return PTR_ERR(shp); if (shp->shm_file != sfd->file) { /* ID was reused */ shm_unlock(shp); return -EINVAL; } shp->shm_atim = ktime_get_real_seconds(); ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_nattch++; shm_unlock(shp); return 0; } /* This is called by fork, once for every shm attach. */ static void shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); int err; /* Always call underlying open if present */ if (sfd->vm_ops->open) sfd->vm_ops->open(vma); err = __shm_open(sfd); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ WARN_ON_ONCE(err); } /* * shm_destroy - free the struct shmid_kernel * * @ns: namespace * @shp: struct to free * * It has to be called with shp and shm_ids.rwsem (writer) locked, * but returns with shp unlocked and freed. */ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) { struct file *shm_file; shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_ucounts); fput(shm_file); ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); } /* * shm_may_destroy - identifies whether shm segment should be destroyed now * * Returns true if and only if there are no active users of the segment and * one of the following is true: * * 1) shmctl(id, IPC_RMID, NULL) was called for this shp * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } /* * remove the attach descriptor vma. * free memory for segment if it is marked destroyed. * The descriptor has already been removed from the current->mm->mmap list * and will later be kfree()d. */ static void __shm_close(struct shm_file_data *sfd) { struct shmid_kernel *shp; struct ipc_namespace *ns = sfd->ns; down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ if (WARN_ON_ONCE(IS_ERR(shp))) goto done; /* no-op */ ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_dtim = ktime_get_real_seconds(); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); done: up_write(&shm_ids(ns).rwsem); } static void shm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); /* Always call underlying close if present */ if (sfd->vm_ops->close) sfd->vm_ops->close(vma); __shm_close(sfd); } /* Called with ns->shm_ids(ns).rwsem locked */ static int shm_try_destroy_orphaned(int id, void *p, void *data) { struct ipc_namespace *ns = data; struct kern_ipc_perm *ipcp = p; struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm); /* * We want to destroy segments without users and with already * exit'ed originating process. * * shm_nattch can be changed under shm_perm.lock without holding the * rwsem, so take the object lock before checking shm_may_destroy(). */ if (!list_empty(&shp->shm_clist)) return 0; shm_lock_by_ptr(shp); if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); return 0; } void shm_destroy_orphaned(struct ipc_namespace *ns) { down_write(&shm_ids(ns).rwsem); if (shm_ids(ns).in_use) { rcu_read_lock(); idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns); rcu_read_unlock(); } up_write(&shm_ids(ns).rwsem); } /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { for (;;) { struct shmid_kernel *shp; struct ipc_namespace *ns; task_lock(task); if (list_empty(&task->sysvshm.shm_clist)) { task_unlock(task); break; } shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, shm_clist); /* * 1) Get pointer to the ipc namespace. It is worth to say * that this pointer is guaranteed to be valid because * shp lifetime is always shorter than namespace lifetime * in which shp lives. * We taken task_lock it means that shp won't be freed. */ ns = shp->ns; /* * 2) If kernel.shm_rmid_forced is not set then only keep track of * which shmids are orphaned, so that a later set of the sysctl * can clean them up. */ if (!ns->shm_rmid_forced) goto unlink_continue; /* * 3) get a reference to the namespace. * The refcount could be already 0. If it is 0, then * the shm objects will be free by free_ipc_work(). */ ns = get_ipc_ns_not_zero(ns); if (!ns) { unlink_continue: list_del_init(&shp->shm_clist); task_unlock(task); continue; } /* * 4) get a reference to shp. * This cannot fail: shm_clist_rm() is called before * ipc_rmid(), thus the refcount cannot be 0. */ WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); /* * 5) unlink the shm segment from the list of segments * created by current. * This must be done last. After unlinking, * only the refcounts obtained above prevent IPC_RMID * from destroying the segment or the namespace. */ list_del_init(&shp->shm_clist); task_unlock(task); /* * 6) we have all references * Thus lock & if needed destroy shp. */ down_write(&shm_ids(ns).rwsem); shm_lock_by_ptr(shp); /* * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's * safe to call ipc_rcu_putref here */ ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); if (ipc_valid_object(&shp->shm_perm)) { if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); } else { /* * Someone else deleted the shp from namespace * idr/kht while we have waited. * Just unlock and continue. */ shm_unlock(shp); } up_write(&shm_ids(ns).rwsem); put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ } } static vm_fault_t shm_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); return sfd->vm_ops->fault(vmf); } static int shm_may_split(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->may_split) return sfd->vm_ops->may_split(vma, addr); return 0; } static unsigned long shm_pagesize(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->pagesize) return sfd->vm_ops->pagesize(vma); return PAGE_SIZE; } #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { struct shm_file_data *sfd = shm_file_data(vma->vm_file); int err = 0; if (sfd->vm_ops->set_policy) err = sfd->vm_ops->set_policy(vma, mpol); return err; } static struct mempolicy *shm_get_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { struct shm_file_data *sfd = shm_file_data(vma->vm_file); struct mempolicy *mpol = vma->vm_policy; if (sfd->vm_ops->get_policy) mpol = sfd->vm_ops->get_policy(vma, addr, ilx); return mpol; } #endif static int shm_mmap(struct file *file, struct vm_area_struct *vma) { struct shm_file_data *sfd = shm_file_data(file); int ret; /* * In case of remap_file_pages() emulation, the file can represent an * IPC ID that was removed, and possibly even reused by another shm * segment already. Propagate this case as an error to caller. */ ret = __shm_open(sfd); if (ret) return ret; ret = vfs_mmap(sfd->file, vma); if (ret) { __shm_close(sfd); return ret; } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; return 0; } static int shm_release(struct inode *ino, struct file *file) { struct shm_file_data *sfd = shm_file_data(file); put_ipc_ns(sfd->ns); fput(sfd->file); shm_file_data(file) = NULL; kfree(sfd); return 0; } static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fsync) return -EINVAL; return sfd->file->f_op->fsync(sfd->file, start, end, datasync); } static long shm_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fallocate) return -EOPNOTSUPP; return sfd->file->f_op->fallocate(file, mode, offset, len); } static unsigned long shm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct shm_file_data *sfd = shm_file_data(file); return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len, pgoff, flags); } static const struct file_operations shm_file_operations = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, }; /* * shm_file_operations_huge is now identical to shm_file_operations * except for fop_flags */ static const struct file_operations shm_file_operations_huge = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, .fop_flags = FOP_HUGE_PAGES, }; static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .may_split = shm_may_split, .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, #endif }; /** * newseg - Create a new shared memory segment * @ns: namespace * @params: ptr to the structure that contains key, size and shmflg * * Called with shm_ids.rwsem held as a writer. */ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) { key_t key = params->key; int shmflg = params->flg; size_t size = params->u.size; int error; struct shmid_kernel *shp; size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; const bool has_no_reserve = shmflg & SHM_NORESERVE; vma_flags_t acctflag = EMPTY_VMA_FLAGS; struct file *file; char name[13]; if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; if (numpages << PAGE_SHIFT < size) return -ENOSPC; if (ns->shm_tot + numpages < ns->shm_tot || ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; shp = kmalloc_obj(*shp, GFP_KERNEL_ACCOUNT); if (unlikely(!shp)) return -ENOMEM; shp->shm_perm.key = key; shp->shm_perm.mode = (shmflg & S_IRWXUGO); shp->mlock_ucounts = NULL; shp->shm_perm.security = NULL; error = security_shm_alloc(&shp->shm_perm); if (error) { kfree(shp); return error; } sprintf(name, "SYSV%08x", key); if (shmflg & SHM_HUGETLB) { struct hstate *hs; size_t hugesize; hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); if (!hs) { error = -EINVAL; goto no_file; } hugesize = ALIGN(size, huge_page_size(hs)); /* hugetlb_file_setup applies strict accounting */ if (has_no_reserve) vma_flags_set(&acctflag, VMA_NORESERVE_BIT); file = hugetlb_file_setup(name, hugesize, acctflag, HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. */ if (has_no_reserve && sysctl_overcommit_memory != OVERCOMMIT_NEVER) vma_flags_set(&acctflag, VMA_NORESERVE_BIT); file = shmem_kernel_file_setup(name, size, acctflag); } error = PTR_ERR(file); if (IS_ERR(file)) goto no_file; shp->shm_cprid = get_pid(task_tgid(current)); shp->shm_lprid = NULL; shp->shm_atim = shp->shm_dtim = 0; shp->shm_ctim = ktime_get_real_seconds(); shp->shm_segsz = size; shp->shm_nattch = 0; shp->shm_file = file; shp->shm_creator = current; /* ipc_addid() locks shp upon success. */ error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); if (error < 0) goto no_id; shp->ns = ns; task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. * proc-ps tools use this. Changing this will break them. */ file_inode(file)->i_ino = shp->shm_perm.id; ns->shm_tot += numpages; error = shp->shm_perm.id; ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); return error; no_id: ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); fput(file); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; no_file: call_rcu(&shp->shm_perm.rcu, shm_rcu_free); return error; } /* * Called with shm_ids.rwsem and ipcp locked. */ static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); if (shp->shm_segsz < params->u.size) return -EINVAL; return 0; } long ksys_shmget(key_t key, size_t size, int shmflg) { struct ipc_namespace *ns; static const struct ipc_ops shm_ops = { .getnew = newseg, .associate = security_shm_associate, .more_checks = shm_more_checks, }; struct ipc_params shm_params; ns = current->nsproxy->ipc_ns; shm_params.key = key; shm_params.flg = shmflg; shm_params.u.size = size; return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params); } SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) { return ksys_shmget(key, size, shmflg); } static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shmid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm); out.shm_segsz = in->shm_segsz; out.shm_atime = in->shm_atime; out.shm_dtime = in->shm_dtime; out.shm_ctime = in->shm_ctime; out.shm_cpid = in->shm_cpid; out.shm_lpid = in->shm_lpid; out.shm_nattch = in->shm_nattch; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static inline unsigned long copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct shmid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->shm_perm.uid = tbuf_old.shm_perm.uid; out->shm_perm.gid = tbuf_old.shm_perm.gid; out->shm_perm.mode = tbuf_old.shm_perm.mode; return 0; } default: return -EINVAL; } } static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shminfo out; if (in->shmmax > INT_MAX) out.shmmax = INT_MAX; else out.shmmax = (int)in->shmmax; out.shmmin = in->shmmin; out.shmmni = in->shmmni; out.shmseg = in->shmseg; out.shmall = in->shmall; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } /* * Calculate and add used RSS and swap pages of a shm. * Called with shm_ids.rwsem held as a reader */ static void shm_add_rss_swap(struct shmid_kernel *shp, unsigned long *rss_add, unsigned long *swp_add) { struct inode *inode; inode = file_inode(shp->shm_file); if (is_file_hugepages(shp->shm_file)) { struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_file(shp->shm_file); *rss_add += pages_per_huge_page(h) * mapping->nrpages; } else { #ifdef CONFIG_SHMEM struct shmem_inode_info *info = SHMEM_I(inode); spin_lock_irq(&info->lock); *rss_add += inode->i_mapping->nrpages; *swp_add += info->swapped; spin_unlock_irq(&info->lock); #else *rss_add += inode->i_mapping->nrpages; #endif } } /* * Called with shm_ids.rwsem held as a reader */ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, unsigned long *swp) { int next_id; int total, in_use; *rss = 0; *swp = 0; in_use = shm_ids(ns).in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { struct kern_ipc_perm *ipc; struct shmid_kernel *shp; ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id); if (ipc == NULL) continue; shp = container_of(ipc, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, rss, swp); total++; } } /* * This function handles some shmctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *shmid64) { struct kern_ipc_perm *ipcp; struct shmid_kernel *shp; int err; down_write(&shm_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &shm_ids(ns), shmid, cmd, &shmid64->shm_perm, 0); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } shp = container_of(ipcp, struct shmid_kernel, shm_perm); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&shp->shm_perm); /* do_shm_rmid unlocks the ipc object and rcu */ do_shm_rmid(ns, ipcp); goto out_up; case IPC_SET: ipc_lock_object(&shp->shm_perm); err = ipc_update_perm(&shmid64->shm_perm, ipcp); if (err) goto out_unlock0; shp->shm_ctim = ktime_get_real_seconds(); break; default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&shm_ids(ns).rwsem); return err; } static int shmctl_ipc_info(struct ipc_namespace *ns, struct shminfo64 *shminfo) { int err = security_shm_shmctl(NULL, IPC_INFO); if (!err) { memset(shminfo, 0, sizeof(*shminfo)); shminfo->shmmni = shminfo->shmseg = ns->shm_ctlmni; shminfo->shmmax = ns->shm_ctlmax; shminfo->shmall = ns->shm_ctlall; shminfo->shmmin = SHMMIN; down_read(&shm_ids(ns).rwsem); err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_shm_info(struct ipc_namespace *ns, struct shm_info *shm_info) { int err = security_shm_shmctl(NULL, SHM_INFO); if (!err) { memset(shm_info, 0, sizeof(*shm_info)); down_read(&shm_ids(ns).rwsem); shm_info->used_ids = shm_ids(ns).in_use; shm_get_stat(ns, &shm_info->shm_rss, &shm_info->shm_swp); shm_info->shm_tot = ns->shm_tot; shm_info->swap_attempts = 0; shm_info->swap_successes = 0; err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_stat(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *tbuf) { struct shmid_kernel *shp; int err; memset(tbuf, 0, sizeof(*tbuf)); rcu_read_lock(); if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) { shp = shm_obtain_object(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } else { /* IPC_STAT */ shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } /* * Semantically SHM_STAT_ANY ought to be identical to * that functionality provided by the /proc/sysvipc/ * interface. As such, only audit these calls and * do not do traditional S_IRUGO permission checks on * the ipc object. */ if (cmd == SHM_STAT_ANY) audit_ipc_obj(&shp->shm_perm); else { err = -EACCES; if (ipcperms(ns, &shp->shm_perm, S_IRUGO)) goto out_unlock; } err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm); tbuf->shm_segsz = shp->shm_segsz; tbuf->shm_atime = shp->shm_atim; tbuf->shm_dtime = shp->shm_dtim; tbuf->shm_ctime = shp->shm_ctim; #ifndef CONFIG_64BIT tbuf->shm_atime_high = shp->shm_atim >> 32; tbuf->shm_dtime_high = shp->shm_dtim >> 32; tbuf->shm_ctime_high = shp->shm_ctim >> 32; #endif tbuf->shm_cpid = pid_vnr(shp->shm_cprid); tbuf->shm_lpid = pid_vnr(shp->shm_lprid); tbuf->shm_nattch = shp->shm_nattch; if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * SHM_STAT and SHM_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = shp->shm_perm.id; } ipc_unlock_object(&shp->shm_perm); out_unlock: rcu_read_unlock(); return err; } static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) { struct shmid_kernel *shp; struct file *shm_file; int err; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock1; } audit_ipc_obj(&(shp->shm_perm)); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { err = -EIDRM; goto out_unlock0; } if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) { kuid_t euid = current_euid(); if (!uid_eq(euid, shp->shm_perm.uid) && !uid_eq(euid, shp->shm_perm.cuid)) { err = -EPERM; goto out_unlock0; } if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) { err = -EPERM; goto out_unlock0; } } shm_file = shp->shm_file; if (is_file_hugepages(shm_file)) goto out_unlock0; if (cmd == SHM_LOCK) { struct ucounts *ucounts = current_ucounts(); err = shmem_lock(shm_file, 1, ucounts); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { shp->shm_perm.mode |= SHM_LOCKED; shp->mlock_ucounts = ucounts; } goto out_unlock0; } /* SHM_UNLOCK */ if (!(shp->shm_perm.mode & SHM_LOCKED)) goto out_unlock0; shmem_lock(shm_file, 0, shp->mlock_ucounts); shp->shm_perm.mode &= ~SHM_LOCKED; shp->mlock_ucounts = NULL; get_file(shm_file); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); shmem_unlock_mapping(shm_file->f_mapping); fput(shm_file); return err; out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); return err; } static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version) { int err; struct ipc_namespace *ns; struct shmid64_ds sem64; if (cmd < 0 || shmid < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_shminfo_to_user(buf, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (copy_to_user(buf, &shm_info, sizeof(shm_info))) err = -EFAULT; return err; } case SHM_STAT: case SHM_STAT_ANY: case IPC_STAT: { err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_shmid_to_user(buf, &sem64, version)) err = -EFAULT; return err; } case IPC_SET: if (copy_shmid_from_user(&sem64, buf, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } } SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_shmctl(shmid, cmd, buf, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) { int version = ipc_parse_version(&cmd); return ksys_shmctl(shmid, cmd, buf, version); } SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_old_shmctl(shmid, cmd, buf); } #endif #ifdef CONFIG_COMPAT struct compat_shmid_ds { struct compat_ipc_perm shm_perm; int shm_segsz; old_time32_t shm_atime; old_time32_t shm_dtime; old_time32_t shm_ctime; compat_ipc_pid_t shm_cpid; compat_ipc_pid_t shm_lpid; unsigned short shm_nattch; unsigned short shm_unused; compat_uptr_t shm_unused2; compat_uptr_t shm_unused3; }; struct compat_shminfo64 { compat_ulong_t shmmax; compat_ulong_t shmmin; compat_ulong_t shmmni; compat_ulong_t shmseg; compat_ulong_t shmall; compat_ulong_t __unused1; compat_ulong_t __unused2; compat_ulong_t __unused3; compat_ulong_t __unused4; }; struct compat_shm_info { compat_int_t used_ids; compat_ulong_t shm_tot, shm_rss, shm_swp; compat_ulong_t swap_attempts, swap_successes; }; static int copy_compat_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { if (in->shmmax > INT_MAX) in->shmmax = INT_MAX; if (version == IPC_64) { struct compat_shminfo64 info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } else { struct shminfo info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } } static int put_compat_shm_info(struct shm_info *ip, struct compat_shm_info __user *uip) { struct compat_shm_info info; memset(&info, 0, sizeof(info)); info.used_ids = ip->used_ids; info.shm_tot = ip->shm_tot; info.shm_rss = ip->shm_rss; info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { if (version == IPC_64) { struct compat_shmid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm); v.shm_atime = lower_32_bits(in->shm_atime); v.shm_atime_high = upper_32_bits(in->shm_atime); v.shm_dtime = lower_32_bits(in->shm_dtime); v.shm_dtime_high = upper_32_bits(in->shm_dtime); v.shm_ctime = lower_32_bits(in->shm_ctime); v.shm_ctime_high = upper_32_bits(in->shm_ctime); v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_shmid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.shm_perm, &in->shm_perm); v.shm_perm.key = in->shm_perm.key; v.shm_atime = in->shm_atime; v.shm_dtime = in->shm_dtime; v.shm_ctime = in->shm_ctime; v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } } static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_shmid64_ds __user *p = buf; return get_compat_ipc64_perm(&out->shm_perm, &p->shm_perm); } else { struct compat_shmid_ds __user *p = buf; return get_compat_ipc_perm(&out->shm_perm, &p->shm_perm); } } static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; struct shmid64_ds sem64; int err; ns = current->nsproxy->ipc_ns; if (cmd < 0 || shmid < 0) return -EINVAL; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_compat_shminfo_to_user(uptr, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (put_compat_shm_info(&shm_info, uptr)) err = -EFAULT; return err; } case IPC_STAT: case SHM_STAT_ANY: case SHM_STAT: err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_compat_shmid_to_user(uptr, &sem64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_compat_shmid_from_user(&sem64, uptr, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } return err; } COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_shmctl(shmid, cmd, uptr, version); } COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_old_shmctl(shmid, cmd, uptr); } #endif #endif /* * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists. * * NOTE! Despite the name, this is NOT a direct system call entrypoint. The * "raddr" thing points to kernel space, and there has to be a wrapper around * this. */ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, unsigned long shmlba) { struct shmid_kernel *shp; unsigned long addr = (unsigned long)shmaddr; unsigned long size; struct file *file, *base; int err; unsigned long flags = MAP_SHARED; unsigned long prot; int acc_mode; struct ipc_namespace *ns; struct shm_file_data *sfd; int f_flags; unsigned long populate = 0; err = -EINVAL; if (shmid < 0) goto out; if (addr) { if (addr & (shmlba - 1)) { if (shmflg & SHM_RND) { addr &= ~(shmlba - 1); /* round down */ /* * Ensure that the round-down is non-nil * when remapping. This can happen for * cases when addr < shmlba. */ if (!addr && (shmflg & SHM_REMAP)) goto out; } else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) #endif goto out; } flags |= MAP_FIXED; } else if ((shmflg & SHM_REMAP)) goto out; if (shmflg & SHM_RDONLY) { prot = PROT_READ; acc_mode = S_IRUGO; f_flags = O_RDONLY; } else { prot = PROT_READ | PROT_WRITE; acc_mode = S_IRUGO | S_IWUGO; f_flags = O_RDWR; } if (shmflg & SHM_EXEC) { prot |= PROT_EXEC; acc_mode |= S_IXUGO; } /* * We cannot rely on the fs check since SYSV IPC does have an * additional creator id... */ ns = current->nsproxy->ipc_ns; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } err = -EACCES; if (ipcperms(ns, &shp->shm_perm, acc_mode)) goto out_unlock; err = security_shm_shmat(&shp->shm_perm, shmaddr, shmflg); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } /* * We need to take a reference to the real shm file to prevent the * pointer from becoming stale in cases where the lifetime of the outer * file extends beyond that of the shm segment. It's not usually * possible, but it can happen during remap_file_pages() emulation as * that unmaps the memory, then does ->mmap() via file reference only. * We'll deny the ->mmap() if the shm segment was since removed, but to * detect shm ID reuse we need to compare the file pointers. */ base = get_file(shp->shm_file); shp->shm_nattch++; size = i_size_read(file_inode(base)); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); err = -ENOMEM; sfd = kzalloc_obj(*sfd); if (!sfd) { fput(base); goto out_nattch; } file = alloc_file_clone(base, f_flags, is_file_hugepages(base) ? &shm_file_operations_huge : &shm_file_operations); err = PTR_ERR(file); if (IS_ERR(file)) { kfree(sfd); fput(base); goto out_nattch; } sfd->id = shp->shm_perm.id; sfd->ns = get_ipc_ns(ns); sfd->file = base; sfd->vm_ops = NULL; file->private_data = sfd; err = security_mmap_file(file, prot, flags); if (err) goto out_fput; if (mmap_write_lock_killable(current->mm)) { err = -EINTR; goto out_fput; } if (addr && !(shmflg & SHM_REMAP)) { err = -EINVAL; if (addr + size < addr) goto invalid; if (find_vma_intersection(current->mm, addr, addr + size)) goto invalid; } addr = do_mmap(file, addr, size, prot, flags, 0, 0, &populate, NULL); *raddr = addr; err = 0; if (IS_ERR_VALUE(addr)) err = (long)addr; invalid: mmap_write_unlock(current->mm); if (populate) mm_populate(addr, populate); out_fput: fput(file); out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); up_write(&shm_ids(ns).rwsem); return err; out_unlock: rcu_read_unlock(); out: return err; } SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #ifdef CONFIG_COMPAT #ifndef COMPAT_SHMLBA #define COMPAT_SHMLBA SHMLBA #endif COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #endif /* * detach and kill segment if marked destroyed. * The work is done in shm_close. */ long ksys_shmdt(char __user *shmaddr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long addr = (unsigned long)shmaddr; int retval = -EINVAL; #ifdef CONFIG_MMU loff_t size = 0; struct file *file; VMA_ITERATOR(vmi, mm, addr); #endif if (addr & ~PAGE_MASK) return retval; if (mmap_write_lock_killable(mm)) return -EINTR; /* * This function tries to be smart and unmap shm segments that * were modified by partial mlock or munmap calls: * - It first determines the size of the shm segment that should be * unmapped: It searches for a vma that is backed by shm and that * started at address shmaddr. It records it's size and then unmaps * it. * - Then it unmaps all shm vmas that started at shmaddr and that * are within the initially determined size and that are from the * same shm segment from which we determined the size. * Errors from do_munmap are ignored: the function only fails if * it's called with invalid parameters or if it's called to unmap * a part of a vma. Both calls in this function are for full vmas, * the parameters are directly copied from the vma itself and always * valid - therefore do_munmap cannot fail. (famous last words?) */ /* * If it had been mremap()'d, the starting address would not * match the usual checks anyway. So assume all vma's are * above the starting address given. */ #ifdef CONFIG_MMU for_each_vma(vmi, vma) { /* * Check if the starting address would match, i.e. it's * a fragment created by mprotect() and/or munmap(), or it * otherwise it starts at this address with no hassles. */ if ((vma->vm_ops == &shm_vm_ops) && (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { /* * Record the file of the shm segment being * unmapped. With mremap(), someone could place * page from another segment but with equal offsets * in the range we are unmapping. */ file = vma->vm_file; size = i_size_read(file_inode(vma->vm_file)); do_vmi_align_munmap(&vmi, vma, mm, vma->vm_start, vma->vm_end, NULL, false); /* * We discovered the size of the shm segment, so * break out of here and fall through to the next * loop that uses the size information to stop * searching for matching vma's. */ retval = 0; vma = vma_next(&vmi); break; } } /* * We need look no further than the maximum address a fragment * could possibly have landed at. Also cast things to loff_t to * prevent overflows and make comparisons vs. equal-width types. */ size = PAGE_ALIGN(size); while (vma && (loff_t)(vma->vm_end - addr) <= size) { /* finding a matching vma now does not alter retval */ if ((vma->vm_ops == &shm_vm_ops) && ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && (vma->vm_file == file)) { do_vmi_align_munmap(&vmi, vma, mm, vma->vm_start, vma->vm_end, NULL, false); } vma = vma_next(&vmi); } #else /* CONFIG_MMU */ vma = vma_lookup(mm, addr); /* under NOMMU conditions, the exact address to be destroyed must be * given */ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); retval = 0; } #endif mmap_write_unlock(mm); return retval; } SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) { return ksys_shmdt(shmaddr); } #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it) { struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct shmid_kernel *shp; unsigned long rss = 0, swp = 0; shp = container_of(ipcp, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, &rss, &swp); #if BITS_PER_LONG <= 32 #define SIZE_SPEC "%10lu" #else #define SIZE_SPEC "%21lu" #endif seq_printf(s, "%10d %10d %4o " SIZE_SPEC " %5u %5u " "%5lu %5u %5u %5u %5u %10llu %10llu %10llu " SIZE_SPEC " " SIZE_SPEC "\n", shp->shm_perm.key, shp->shm_perm.id, shp->shm_perm.mode, shp->shm_segsz, pid_nr_ns(shp->shm_cprid, pid_ns), pid_nr_ns(shp->shm_lprid, pid_ns), shp->shm_nattch, from_kuid_munged(user_ns, shp->shm_perm.uid), from_kgid_munged(user_ns, shp->shm_perm.gid), from_kuid_munged(user_ns, shp->shm_perm.cuid), from_kgid_munged(user_ns, shp->shm_perm.cgid), shp->shm_atim, shp->shm_dtim, shp->shm_ctim, rss * PAGE_SIZE, swp * PAGE_SIZE); return 0; } #endif |
| 34 34 34 34 8 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Public Key Signature Algorithm * * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/sig.h> #include <linux/cryptouser.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/string.h> #include <net/netlink.h> #include "internal.h" static void crypto_sig_exit_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); struct sig_alg *alg = crypto_sig_alg(sig); alg->exit(sig); } static int crypto_sig_init_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); struct sig_alg *alg = crypto_sig_alg(sig); if (alg->exit) sig->base.exit = crypto_sig_exit_tfm; if (alg->init) return alg->init(sig); return 0; } static void crypto_sig_free_instance(struct crypto_instance *inst) { struct sig_instance *sig = sig_instance(inst); sig->free(sig); } static void __maybe_unused crypto_sig_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : sig\n"); } static int __maybe_unused crypto_sig_report(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_sig rsig = { .type = "sig", }; return nla_put(skb, CRYPTOCFGA_REPORT_SIG, sizeof(rsig), &rsig); } static const struct crypto_type crypto_sig_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_sig_init_tfm, .free = crypto_sig_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_sig_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_sig_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SIG, .tfmsize = offsetof(struct crypto_sig, base), .algsize = offsetof(struct sig_alg, base), }; struct crypto_sig *crypto_alloc_sig(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_sig_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_sig); static int sig_default_sign(struct crypto_sig *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { return -ENOSYS; } static int sig_default_verify(struct crypto_sig *tfm, const void *src, unsigned int slen, const void *dst, unsigned int dlen) { return -ENOSYS; } static int sig_default_set_key(struct crypto_sig *tfm, const void *key, unsigned int keylen) { return -ENOSYS; } static unsigned int sig_default_size(struct crypto_sig *tfm) { return DIV_ROUND_UP_POW2(crypto_sig_keysize(tfm), BITS_PER_BYTE); } static int sig_prepare_alg(struct sig_alg *alg) { struct crypto_alg *base = &alg->base; if (!alg->sign) alg->sign = sig_default_sign; if (!alg->verify) alg->verify = sig_default_verify; if (!alg->set_priv_key) alg->set_priv_key = sig_default_set_key; if (!alg->set_pub_key) return -EINVAL; if (!alg->key_size) return -EINVAL; if (!alg->max_size) alg->max_size = sig_default_size; if (!alg->digest_size) alg->digest_size = sig_default_size; base->cra_type = &crypto_sig_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_SIG; return 0; } int crypto_register_sig(struct sig_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = sig_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_sig); void crypto_unregister_sig(struct sig_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_sig); int sig_register_instance(struct crypto_template *tmpl, struct sig_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = sig_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, sig_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(sig_register_instance); int crypto_grab_sig(struct crypto_sig_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_sig_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_sig); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Public Key Signature Algorithms"); |
| 9 9 9 43 22 362 361 355 352 58 187 189 183 9 229 201 230 220 220 220 194 219 196 3 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include <net/genetlink.h> #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> #include "devl_internal.h" EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); static struct devlink *devlinks_xa_get(unsigned long index) { struct devlink *devlink; rcu_read_lock(); devlink = xa_find(&devlinks, &index, index, DEVLINK_REGISTERED); if (!devlink || !devlink_try_get(devlink)) devlink = NULL; rcu_read_unlock(); return devlink; } /* devlink_rels xarray contains 1:1 relationships between * devlink object and related nested devlink instance. * The xarray index is used to get the nested object from * the nested-in object code. */ static DEFINE_XARRAY_FLAGS(devlink_rels, XA_FLAGS_ALLOC1); #define DEVLINK_REL_IN_USE XA_MARK_0 struct devlink_rel { u32 index; refcount_t refcount; u32 devlink_index; struct { u32 devlink_index; u32 obj_index; devlink_rel_notify_cb_t *notify_cb; devlink_rel_cleanup_cb_t *cleanup_cb; struct delayed_work notify_work; } nested_in; }; static void devlink_rel_free(struct devlink_rel *rel) { xa_erase(&devlink_rels, rel->index); kfree(rel); } static void __devlink_rel_get(struct devlink_rel *rel) { refcount_inc(&rel->refcount); } static void __devlink_rel_put(struct devlink_rel *rel) { if (refcount_dec_and_test(&rel->refcount)) devlink_rel_free(rel); } static void devlink_rel_nested_in_notify_work(struct work_struct *work) { struct devlink_rel *rel = container_of(work, struct devlink_rel, nested_in.notify_work.work); struct devlink *devlink; devlink = devlinks_xa_get(rel->nested_in.devlink_index); if (!devlink) goto rel_put; if (!devl_trylock(devlink)) { devlink_put(devlink); goto reschedule_work; } if (!devl_is_registered(devlink)) { devl_unlock(devlink); devlink_put(devlink); goto rel_put; } if (!xa_get_mark(&devlink_rels, rel->index, DEVLINK_REL_IN_USE)) rel->nested_in.cleanup_cb(devlink, rel->nested_in.obj_index, rel->index); rel->nested_in.notify_cb(devlink, rel->nested_in.obj_index); devl_unlock(devlink); devlink_put(devlink); rel_put: __devlink_rel_put(rel); return; reschedule_work: schedule_delayed_work(&rel->nested_in.notify_work, 1); } static void devlink_rel_nested_in_notify_work_schedule(struct devlink_rel *rel) { __devlink_rel_get(rel); schedule_delayed_work(&rel->nested_in.notify_work, 0); } static struct devlink_rel *devlink_rel_alloc(void) { struct devlink_rel *rel; static u32 next; int err; rel = kzalloc_obj(*rel); if (!rel) return ERR_PTR(-ENOMEM); err = xa_alloc_cyclic(&devlink_rels, &rel->index, rel, xa_limit_32b, &next, GFP_KERNEL); if (err < 0) { kfree(rel); return ERR_PTR(err); } refcount_set(&rel->refcount, 1); INIT_DELAYED_WORK(&rel->nested_in.notify_work, &devlink_rel_nested_in_notify_work); return rel; } static void devlink_rel_put(struct devlink *devlink) { struct devlink_rel *rel = devlink->rel; if (!rel) return; xa_clear_mark(&devlink_rels, rel->index, DEVLINK_REL_IN_USE); devlink_rel_nested_in_notify_work_schedule(rel); __devlink_rel_put(rel); devlink->rel = NULL; } void devlink_rel_nested_in_clear(u32 rel_index) { xa_clear_mark(&devlink_rels, rel_index, DEVLINK_REL_IN_USE); } int devlink_rel_nested_in_add(u32 *rel_index, u32 devlink_index, u32 obj_index, devlink_rel_notify_cb_t *notify_cb, devlink_rel_cleanup_cb_t *cleanup_cb, struct devlink *devlink) { struct devlink_rel *rel = devlink_rel_alloc(); ASSERT_DEVLINK_NOT_REGISTERED(devlink); if (IS_ERR(rel)) return PTR_ERR(rel); rel->devlink_index = devlink->index; rel->nested_in.devlink_index = devlink_index; rel->nested_in.obj_index = obj_index; rel->nested_in.notify_cb = notify_cb; rel->nested_in.cleanup_cb = cleanup_cb; *rel_index = rel->index; xa_set_mark(&devlink_rels, rel->index, DEVLINK_REL_IN_USE); devlink->rel = rel; return 0; } /** * devlink_rel_nested_in_notify - Notify the object this devlink * instance is nested in. * @devlink: devlink * * This is called upon network namespace change of devlink instance. * In case this devlink instance is nested in another devlink object, * a notification of a change of this object should be sent * over netlink. The parent devlink instance lock needs to be * taken during the notification preparation. * Since the parent may or may not be locked, 'work' is utilized. */ void devlink_rel_nested_in_notify(struct devlink *devlink) { struct devlink_rel *rel = devlink->rel; if (!rel) return; devlink_rel_nested_in_notify_work_schedule(rel); } static struct devlink_rel *devlink_rel_find(unsigned long rel_index) { return xa_find(&devlink_rels, &rel_index, rel_index, DEVLINK_REL_IN_USE); } static struct devlink *devlink_rel_devlink_get(u32 rel_index) { struct devlink_rel *rel; u32 devlink_index; if (!rel_index) return NULL; xa_lock(&devlink_rels); rel = devlink_rel_find(rel_index); if (rel) devlink_index = rel->devlink_index; xa_unlock(&devlink_rels); if (!rel) return NULL; return devlinks_xa_get(devlink_index); } int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink, u32 rel_index, int attrtype, bool *msg_updated) { struct net *net = devlink_net(devlink); struct devlink *rel_devlink; int err; rel_devlink = devlink_rel_devlink_get(rel_index); if (!rel_devlink) return 0; err = devlink_nl_put_nested_handle(msg, net, rel_devlink, attrtype); devlink_put(rel_devlink); if (!err && msg_updated) *msg_updated = true; return err; } void *devlink_priv(struct devlink *devlink) { return &devlink->priv; } EXPORT_SYMBOL_GPL(devlink_priv); struct devlink *priv_to_devlink(void *priv) { return container_of(priv, struct devlink, priv); } EXPORT_SYMBOL_GPL(priv_to_devlink); struct device *devlink_to_dev(const struct devlink *devlink) { return devlink->dev; } EXPORT_SYMBOL_GPL(devlink_to_dev); const char *devlink_bus_name(const struct devlink *devlink) { return devlink->dev ? devlink->dev->bus->name : DEVLINK_INDEX_BUS_NAME; } EXPORT_SYMBOL_GPL(devlink_bus_name); const char *devlink_dev_name(const struct devlink *devlink) { return devlink->dev ? dev_name(devlink->dev) : devlink->dev_name_index; } EXPORT_SYMBOL_GPL(devlink_dev_name); const char *devlink_dev_driver_name(const struct devlink *devlink) { return devlink->dev_driver->name; } EXPORT_SYMBOL_GPL(devlink_dev_driver_name); struct net *devlink_net(const struct devlink *devlink) { return read_pnet(&devlink->_net); } EXPORT_SYMBOL_GPL(devlink_net); void devl_assert_locked(struct devlink *devlink) { lockdep_assert_held(&devlink->lock); } EXPORT_SYMBOL_GPL(devl_assert_locked); #ifdef CONFIG_LOCKDEP /* For use in conjunction with LOCKDEP only e.g. rcu_dereference_protected() */ bool devl_lock_is_held(struct devlink *devlink) { return lockdep_is_held(&devlink->lock); } EXPORT_SYMBOL_GPL(devl_lock_is_held); #endif void devl_lock(struct devlink *devlink) { mutex_lock(&devlink->lock); } EXPORT_SYMBOL_GPL(devl_lock); int devl_trylock(struct devlink *devlink) { return mutex_trylock(&devlink->lock); } EXPORT_SYMBOL_GPL(devl_trylock); void devl_unlock(struct devlink *devlink) { mutex_unlock(&devlink->lock); } EXPORT_SYMBOL_GPL(devl_unlock); /** * devlink_try_get() - try to obtain a reference on a devlink instance * @devlink: instance to reference * * Obtain a reference on a devlink instance. A reference on a devlink instance * only implies that it's safe to take the instance lock. It does not imply * that the instance is registered, use devl_is_registered() after taking * the instance lock to check registration status. */ struct devlink *__must_check devlink_try_get(struct devlink *devlink) { if (refcount_inc_not_zero(&devlink->refcount)) return devlink; return NULL; } static void devlink_release(struct work_struct *work) { struct devlink *devlink; devlink = container_of(to_rcu_work(work), struct devlink, rwork); mutex_destroy(&devlink->lock); lockdep_unregister_key(&devlink->lock_key); if (devlink->dev) put_device(devlink->dev); else kfree(devlink->dev_name_index); kvfree(devlink); } void devlink_put(struct devlink *devlink) { if (refcount_dec_and_test(&devlink->refcount)) queue_rcu_work(system_percpu_wq, &devlink->rwork); } static struct devlink *__devlinks_xa_find_get(struct net *net, unsigned long *indexp, unsigned long end) { struct devlink *devlink = NULL; rcu_read_lock(); retry: devlink = xa_find(&devlinks, indexp, end, DEVLINK_REGISTERED); if (!devlink) goto unlock; if (!devlink_try_get(devlink)) goto next; if (!net_eq(devlink_net(devlink), net)) { devlink_put(devlink); goto next; } unlock: rcu_read_unlock(); return devlink; next: (*indexp)++; goto retry; } struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp) { return __devlinks_xa_find_get(net, indexp, ULONG_MAX); } struct devlink *devlinks_xa_lookup_get(struct net *net, unsigned long index) { return __devlinks_xa_find_get(net, &index, index); } /** * devl_register - Register devlink instance * @devlink: devlink */ int devl_register(struct devlink *devlink) { ASSERT_DEVLINK_NOT_REGISTERED(devlink); devl_assert_locked(devlink); xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); devlink_notify_register(devlink); devlink_rel_nested_in_notify(devlink); return 0; } EXPORT_SYMBOL_GPL(devl_register); void devlink_register(struct devlink *devlink) { devl_lock(devlink); devl_register(devlink); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_register); /** * devl_unregister - Unregister devlink instance * @devlink: devlink */ void devl_unregister(struct devlink *devlink) { ASSERT_DEVLINK_REGISTERED(devlink); devl_assert_locked(devlink); devlink_notify_unregister(devlink); xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); devlink_rel_put(devlink); } EXPORT_SYMBOL_GPL(devl_unregister); void devlink_unregister(struct devlink *devlink) { devl_lock(devlink); devl_unregister(devlink); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_unregister); struct devlink *__devlink_alloc(const struct devlink_ops *ops, size_t priv_size, struct net *net, struct device *dev, const struct device_driver *dev_driver) { struct devlink *devlink; static u32 last_id; int ret; WARN_ON(!ops || !dev_driver); if (!devlink_reload_actions_valid(ops)) return NULL; devlink = kvzalloc_flex(*devlink, priv, priv_size); if (!devlink) return NULL; ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, &last_id, GFP_KERNEL); if (ret < 0) goto err_xa_alloc; if (dev) { devlink->dev = get_device(dev); } else { devlink->dev_name_index = kasprintf(GFP_KERNEL, "%u", devlink->index); if (!devlink->dev_name_index) goto err_kasprintf; } devlink->ops = ops; devlink->dev_driver = dev_driver; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); xa_init_flags(&devlink->params, XA_FLAGS_ALLOC); xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); xa_init_flags(&devlink->nested_rels, XA_FLAGS_ALLOC); write_pnet(&devlink->_net, net); INIT_LIST_HEAD(&devlink->rate_list); INIT_LIST_HEAD(&devlink->linecard_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->region_list); INIT_LIST_HEAD(&devlink->reporter_list); INIT_LIST_HEAD(&devlink->trap_list); INIT_LIST_HEAD(&devlink->trap_group_list); INIT_LIST_HEAD(&devlink->trap_policer_list); INIT_RCU_WORK(&devlink->rwork, devlink_release); lockdep_register_key(&devlink->lock_key); mutex_init(&devlink->lock); lockdep_set_class(&devlink->lock, &devlink->lock_key); refcount_set(&devlink->refcount, 1); return devlink; err_kasprintf: xa_erase(&devlinks, devlink->index); err_xa_alloc: kvfree(devlink); return NULL; } /** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace * * @ops: ops * @priv_size: size of user private data * @net: net namespace * @dev: parent device * * Allocate new devlink instance resources, including devlink index * and name. */ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, size_t priv_size, struct net *net, struct device *dev) { WARN_ON(!dev); return __devlink_alloc(ops, priv_size, net, dev, dev->driver); } EXPORT_SYMBOL_GPL(devlink_alloc_ns); /** * devlink_free - Free devlink instance resources * * @devlink: devlink */ void devlink_free(struct devlink *devlink) { ASSERT_DEVLINK_NOT_REGISTERED(devlink); devlink_rel_put(devlink); WARN_ON(!list_empty(&devlink->trap_policer_list)); WARN_ON(!list_empty(&devlink->trap_group_list)); WARN_ON(!list_empty(&devlink->trap_list)); WARN_ON(!list_empty(&devlink->reporter_list)); WARN_ON(!list_empty(&devlink->region_list)); WARN_ON(!list_empty(&devlink->resource_list)); WARN_ON(!list_empty(&devlink->dpipe_table_list)); WARN_ON(!list_empty(&devlink->sb_list)); WARN_ON(devlink_rates_check(devlink, NULL, NULL)); WARN_ON(!list_empty(&devlink->linecard_list)); WARN_ON(!xa_empty(&devlink->ports)); xa_destroy(&devlink->nested_rels); xa_destroy(&devlink->snapshot_ids); xa_destroy(&devlink->params); xa_destroy(&devlink->ports); xa_erase(&devlinks, devlink->index); devlink_put(devlink); } EXPORT_SYMBOL_GPL(devlink_free); static void __net_exit devlink_pernet_pre_exit(struct net *net) { struct devlink *devlink; u32 actions_performed; unsigned long index; int err; /* In case network namespace is getting destroyed, reload * all devlink instances from this namespace into init_net. */ devlinks_xa_for_each_registered_get(net, index, devlink) { devl_dev_lock(devlink, true); err = 0; if (devl_is_registered(devlink)) err = devlink_reload(devlink, &init_net, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_LIMIT_UNSPEC, &actions_performed, NULL); devl_dev_unlock(devlink, true); devlink_put(devlink); if (err && err != -EOPNOTSUPP) pr_warn("Failed to reload devlink instance into init_net\n"); } } static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; static struct notifier_block devlink_port_netdevice_nb = { .notifier_call = devlink_port_netdevice_event, }; static int __init devlink_init(void) { int err; err = register_pernet_subsys(&devlink_pernet_ops); if (err) goto out; err = genl_register_family(&devlink_nl_family); if (err) goto out_unreg_pernet_subsys; err = register_netdevice_notifier(&devlink_port_netdevice_nb); if (!err) return 0; genl_unregister_family(&devlink_nl_family); out_unreg_pernet_subsys: unregister_pernet_subsys(&devlink_pernet_ops); out: WARN_ON(err); return err; } subsys_initcall(devlink_init); |
| 52 53 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Do sleep inside a spin-lock * Copyright (c) 1999 by Takashi Iwai <tiwai@suse.de> */ #include <linux/export.h> #include <sound/core.h> #include "seq_lock.h" /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { int warn_count = 5 * HZ; if (atomic_read(lockp) < 0) { pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line); return; } while (atomic_read(lockp) > 0) { if (warn_count-- == 0) pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line); schedule_timeout_uninterruptible(1); } } EXPORT_SYMBOL(snd_use_lock_sync_helper); |
| 586 1902 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 */ #ifndef LINUX_RESUME_USER_MODE_H #define LINUX_RESUME_USER_MODE_H #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/rseq.h> #include <linux/blk-cgroup.h> /** * set_notify_resume - cause resume_user_mode_work() to be called * @task: task that will call resume_user_mode_work() * * Calling this arranges that @task will call resume_user_mode_work() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call resume_user_mode_work() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); } /** * resume_user_mode_work - Perform work before returning to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void resume_user_mode_work(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(task_work_pending(current))) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_slowpath(regs); } #endif /* LINUX_RESUME_USER_MODE_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM oom #if !defined(_TRACE_OOM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_OOM_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> #define PG_COUNT_TO_KB(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(oom_score_adj_update, TP_PROTO(struct task_struct *task), TP_ARGS(task), TP_STRUCT__entry( __field( pid_t, pid) __array( char, comm, TASK_COMM_LEN ) __field( short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d comm=%s oom_score_adj=%hd", __entry->pid, __entry->comm, __entry->oom_score_adj) ); TRACE_EVENT(reclaim_retry_zone, TP_PROTO(struct zoneref *zoneref, int order, unsigned long reclaimable, unsigned long available, unsigned long min_wmark, int no_progress_loops, bool wmark_check), TP_ARGS(zoneref, order, reclaimable, available, min_wmark, no_progress_loops, wmark_check), TP_STRUCT__entry( __field( int, node) __field( int, zone_idx) __field( int, order) __field( unsigned long, reclaimable) __field( unsigned long, available) __field( unsigned long, min_wmark) __field( int, no_progress_loops) __field( bool, wmark_check) ), TP_fast_assign( __entry->node = zonelist_node_idx(zoneref); __entry->zone_idx = zonelist_zone_idx(zoneref); __entry->order = order; __entry->reclaimable = reclaimable; __entry->available = available; __entry->min_wmark = min_wmark; __entry->no_progress_loops = no_progress_loops; __entry->wmark_check = wmark_check; ), TP_printk("node=%d zone=%-8s order=%d reclaimable=%lu available=%lu min_wmark=%lu no_progress_loops=%d wmark_check=%d", __entry->node, __print_symbolic(__entry->zone_idx, ZONE_TYPE), __entry->order, __entry->reclaimable, __entry->available, __entry->min_wmark, __entry->no_progress_loops, __entry->wmark_check) ); TRACE_EVENT(mark_victim, TP_PROTO(struct task_struct *task, uid_t uid), TP_ARGS(task, uid), TP_STRUCT__entry( __field(int, pid) __string(comm, task->comm) __field(unsigned long, total_vm) __field(unsigned long, anon_rss) __field(unsigned long, file_rss) __field(unsigned long, shmem_rss) __field(uid_t, uid) __field(unsigned long, pgtables) __field(short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; __assign_str(comm); __entry->total_vm = PG_COUNT_TO_KB(task->mm->total_vm); __entry->anon_rss = PG_COUNT_TO_KB(get_mm_counter(task->mm, MM_ANONPAGES)); __entry->file_rss = PG_COUNT_TO_KB(get_mm_counter(task->mm, MM_FILEPAGES)); __entry->shmem_rss = PG_COUNT_TO_KB(get_mm_counter(task->mm, MM_SHMEMPAGES)); __entry->uid = uid; __entry->pgtables = mm_pgtables_bytes(task->mm) >> 10; __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d comm=%s total-vm=%lukB anon-rss=%lukB file-rss:%lukB shmem-rss:%lukB uid=%u pgtables=%lukB oom_score_adj=%hd", __entry->pid, __get_str(comm), __entry->total_vm, __entry->anon_rss, __entry->file_rss, __entry->shmem_rss, __entry->uid, __entry->pgtables, __entry->oom_score_adj ) ); TRACE_EVENT(wake_reaper, TP_PROTO(int pid), TP_ARGS(pid), TP_STRUCT__entry( __field(int, pid) ), TP_fast_assign( __entry->pid = pid; ), TP_printk("pid=%d", __entry->pid) ); TRACE_EVENT(start_task_reaping, TP_PROTO(int pid), TP_ARGS(pid), TP_STRUCT__entry( __field(int, pid) ), TP_fast_assign( __entry->pid = pid; ), TP_printk("pid=%d", __entry->pid) ); TRACE_EVENT(finish_task_reaping, TP_PROTO(int pid), TP_ARGS(pid), TP_STRUCT__entry( __field(int, pid) ), TP_fast_assign( __entry->pid = pid; ), TP_printk("pid=%d", __entry->pid) ); TRACE_EVENT(skip_task_reaping, TP_PROTO(int pid), TP_ARGS(pid), TP_STRUCT__entry( __field(int, pid) ), TP_fast_assign( __entry->pid = pid; ), TP_printk("pid=%d", __entry->pid) ); #ifdef CONFIG_COMPACTION TRACE_EVENT(compact_retry, TP_PROTO(int order, enum compact_priority priority, enum compact_result result, int retries, int max_retries, bool ret), TP_ARGS(order, priority, result, retries, max_retries, ret), TP_STRUCT__entry( __field( int, order) __field( int, priority) __field( int, result) __field( int, retries) __field( int, max_retries) __field( bool, ret) ), TP_fast_assign( __entry->order = order; __entry->priority = priority; __entry->result = compact_result_to_feedback(result); __entry->retries = retries; __entry->max_retries = max_retries; __entry->ret = ret; ), TP_printk("order=%d priority=%s compaction_result=%s retries=%d max_retries=%d should_retry=%d", __entry->order, __print_symbolic(__entry->priority, COMPACTION_PRIORITY), __print_symbolic(__entry->result, COMPACTION_FEEDBACK), __entry->retries, __entry->max_retries, __entry->ret) ); #endif /* CONFIG_COMPACTION */ #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 18 16 16 2 3 8 28 1 2 26 24 2 2 10 20 20 16 6 9 9 15 3 3 21 3 43 3 28 3 10 22 22 62 26 21 29 43 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Cong Wang <cong.wang@bytedance.com> */ #include <linux/bpf.h> #include <linux/skmsg.h> #include <net/af_unix.h> #include "af_unix.h" #define unix_sk_has_data(__sk, __psock) \ ({ !skb_queue_empty(&__sk->sk_receive_queue) || \ !skb_queue_empty(&__psock->ingress_skb) || \ !list_empty(&__psock->ingress_msg); \ }) static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct unix_sock *u = unix_sk(sk); int ret = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) return 1; if (!timeo) return ret; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); if (!unix_sk_has_data(sk, psock)) { mutex_unlock(&u->iolock); wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); mutex_lock(&u->iolock); ret = unix_sk_has_data(sk, psock); } sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; } static int __unix_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { if (sk->sk_type == SOCK_DGRAM) return __unix_dgram_recvmsg(sk, msg, len, flags); else return __unix_stream_recvmsg(sk, msg, len, flags); } static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct unix_sock *u = unix_sk(sk); struct sk_psock *psock; int copied; if (flags & MSG_OOB) return -EOPNOTSUPP; if (!len) return 0; psock = sk_psock_get(sk); if (unlikely(!psock)) return __unix_recvmsg(sk, msg, len, flags); mutex_lock(&u->iolock); if (!skb_queue_empty(&sk->sk_receive_queue) && sk_psock_queue_empty(psock)) { mutex_unlock(&u->iolock); sk_psock_put(sk, psock); return __unix_recvmsg(sk, msg, len, flags); } msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { long timeo; int data; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = unix_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; mutex_unlock(&u->iolock); sk_psock_put(sk, psock); return __unix_recvmsg(sk, msg, len, flags); } copied = -EAGAIN; } mutex_unlock(&u->iolock); sk_psock_put(sk, psock); return copied; } static struct proto *unix_dgram_prot_saved __read_mostly; static DEFINE_SPINLOCK(unix_dgram_prot_lock); static struct proto unix_dgram_bpf_prot; static struct proto *unix_stream_prot_saved __read_mostly; static DEFINE_SPINLOCK(unix_stream_prot_lock); static struct proto unix_stream_bpf_prot; static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; prot->sock_is_readable = sk_msg_is_readable; } static void unix_stream_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; prot->sock_is_readable = sk_msg_is_readable; prot->unhash = sock_map_unhash; } static void unix_dgram_bpf_check_needs_rebuild(struct proto *ops) { if (unlikely(ops != smp_load_acquire(&unix_dgram_prot_saved))) { spin_lock_bh(&unix_dgram_prot_lock); if (likely(ops != unix_dgram_prot_saved)) { unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, ops); smp_store_release(&unix_dgram_prot_saved, ops); } spin_unlock_bh(&unix_dgram_prot_lock); } } static void unix_stream_bpf_check_needs_rebuild(struct proto *ops) { if (unlikely(ops != smp_load_acquire(&unix_stream_prot_saved))) { spin_lock_bh(&unix_stream_prot_lock); if (likely(ops != unix_stream_prot_saved)) { unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, ops); smp_store_release(&unix_stream_prot_saved, ops); } spin_unlock_bh(&unix_stream_prot_lock); } } int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { if (sk->sk_type != SOCK_DGRAM) return -EOPNOTSUPP; if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } unix_dgram_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_dgram_bpf_prot); return 0; } int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { struct sock *sk_pair; /* Restore does not decrement the sk_pair reference yet because we must * keep the a reference to the socket until after an RCU grace period * and any pending sends have completed. */ if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } /* psock_update_sk_prot can be called multiple times if psock is * added to multiple maps and/or slots in the same map. There is * also an edge case where replacing a psock with itself can trigger * an extra psock_update_sk_prot during the insert process. So it * must be safe to do multiple calls. Here we need to ensure we don't * increment the refcnt through sock_hold many times. There will only * be a single matching destroy operation. */ if (!psock->sk_pair) { sk_pair = unix_peer(sk); if (unlikely(!sk_pair)) return -EINVAL; sock_hold(sk_pair); psock->sk_pair = sk_pair; } unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; } void __init unix_bpf_build_proto(void) { unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, &unix_dgram_proto); unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, &unix_stream_proto); } |
| 1336 2346 2345 2292 11089 347 1 1 2048 10 2300 13455 12844 1317 691 689 3791 2492 13458 12844 699 5 5 12778 2330 7 12777 699 690 7 1 699 7 1335 10 1292 1336 2049 2046 2046 2 1 2 2 2 1 1 1 1 2 2465 1332 3088 1336 2488 1333 1336 3770 1336 3767 41 2314 5268 2132 2015 1854 694 12688 4032 1743 1821 1586 921 692 4 693 174 174 1147 1826 2347 2331 79 2333 2295 2252 2329 5 5 2329 1 4 469 4 5 7 4 4 3002 77 1501 2329 2200 475 697 10 696 10 699 697 2296 1 2296 2306 10 699 699 699 896 2330 3641 3478 2020 2615 225 3641 25 25 3 3 3 3 699 699 698 698 698 698 698 699 699 699 11 698 697 697 699 699 7 699 699 697 699 699 699 699 699 697 698 698 691 564 698 135 699 670 698 699 698 201 699 660 690 699 697 690 698 699 4795 12917 12880 11586 10824 12918 12695 12869 699 699 6 696 241 518 506 243 11 170 430 430 416 40 32 175 175 175 25 25 175 8 3 699 699 697 2 2 697 696 699 422 83 688 643 699 699 422 692 643 94 688 699 83 697 699 528 698 699 698 696 33 128 152 1 695 697 698 698 10 691 690 690 699 698 692 14 698 1 3 175 173 174 174 25 22 9 25 25 378 378 166 212 378 378 1854 1721 179 1674 77 1719 175 3646 3652 3647 2908 2776 2885 266 266 4 175 2 142 1 28 2 56 94 4710 12791 10866 636 620 636 630 10 10 10 10 174 173 175 174 174 33 142 175 175 175 175 2376 2303 156 2378 2375 495 2216 1691 2070 25 2379 1012 895 1884 2380 2306 156 2375 48 217 260 49 214 8 1159 71 83 4 546 934 3646 16 842 843 6 845 845 567 416 64 566 1 562 561 568 472 568 568 567 565 568 568 25 25 25 25 25 25 3758 1377 490 845 261 2381 175 568 25 10 2011 2159 77 3537 1105 3781 3778 2545 175 571 25 2394 10 378 1854 3776 2008 3651 3645 1235 3643 3026 148 571 844 2370 2569 2542 1248 858 859 35 836 858 858 857 859 856 858 859 1127 1131 1125 49 1133 1127 3162 3164 1730 2290 2295 3166 1132 3159 3133 161 1459 1562 1564 10 1565 1563 1560 1566 1568 1561 6000 6002 5642 220 3391 3130 1380 6005 2439 5313 1564 5996 5994 1145 1913 1081 1081 1080 1081 1080 1081 178 1076 1080 1078 1080 91 920 1 147 122 1078 1080 1081 122 835 836 835 834 835 5 836 836 5 4712 4705 4721 4702 1732 121 836 5 858 857 836 836 836 834 834 1080 1080 1081 1081 1079 121 48 1078 1081 169 168 169 510 347 169 169 169 169 508 7 510 679 679 680 679 680 1927 1931 1928 1930 1931 2488 131 33 2369 2487 2490 2510 2516 1076 2447 785 3784 19 1413 1412 9 1412 1412 3163 60 3154 223 223 3154 60 3142 1991 1988 66 3152 57 25 19 19 1748 1732 2133 2279 1733 3383 3391 21 1 12 10 3 21 16 6 112 110 112 112 111 112 2564 631 634 629 636 631 72 72 72 72 858 859 112 112 678 679 679 679 679 679 680 679 679 680 680 679 679 679 679 680 2113 1773 500 45 44 10814 10822 10868 10822 3315 174 3266 174 8354 3312 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <liam@infradead.org> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> #define TP_FCT tracepoint_string(__func__) /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. * * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is * permissible to bypass this. Otherwise remain cautious and retain the hashing. * * Userland doesn't know about %px so also use %p there. */ #if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) #define PTR_FMT "%px" #else #define PTR_FMT "%p" #endif #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_PREALLOC 1 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, [maple_copy] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, [maple_copy] = 3, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, [maple_copy] = 3, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, [maple_copy] = 1, /* Should never be used */ }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_return_sheaf(struct slab_sheaf *sheaf) { kmem_cache_return_sheaf(maple_node_cache, GFP_NOWAIT, sheaf); } static struct slab_sheaf *mt_get_sheaf(gfp_t gfp, int count) { return kmem_cache_prefill_sheaf(maple_node_cache, gfp, count); } static int mt_refill_sheaf(gfp_t gfp, struct slab_sheaf **sheaf, unsigned int size) { return kmem_cache_refill_sheaf(maple_node_cache, gfp, sheaf, size); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); kfree_rcu(node, rcu); } static void mt_set_height(struct maple_tree *mt, unsigned char height) { unsigned int new_flags = mt->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MT_BUG_ON(mt, height > MAPLE_HEIGHT_MAX); new_flags |= height << MT_FLAGS_HEIGHT_OFFSET; mt->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void ma_init_slot(void __rcu **slot, const struct maple_node *mn, const enum maple_type mt) { /* WARNING: this is unsafe if the slot is exposed to readers. */ RCU_INIT_POINTER(*slot, (void *)mt_mk_node(mn, mt)); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Node types: * 0b??1 = Root * 0b?00 = 16 bit nodes * 0b010 = 32 bit nodes * 0b110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x02 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @enode: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *node; node = mte_to_node(enode); return ma_dead_node(node); } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node: the maple node * @type: the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_copy: return node->cp.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node: the maple node * @type: the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_copy: return node->cp.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_copy: case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_copy: return mn->cp.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat: the ma_topiary, a linked list of dead nodes. * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas: the maple state * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min for the parent node of mas->node. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; /* * !mas->offset implies that parent node min == mas->min. * mas->offset > 0 implies that we need to walk up to find the * implied pivot min. */ if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static __always_inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_node *ret; if (mas->alloc) { ret = mas->alloc; mas->alloc = NULL; goto out; } if (WARN_ON_ONCE(!mas->sheaf)) return NULL; ret = kmem_cache_alloc_from_sheaf(maple_node_cache, GFP_NOWAIT, mas->sheaf); out: memset(ret, 0, sizeof(*ret)); return ret; } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { if (!mas->node_request) return; if (mas->node_request == 1) { if (mas->sheaf) goto use_sheaf; if (mas->alloc) return; mas->alloc = mt_alloc_one(gfp); if (!mas->alloc) goto error; mas->node_request = 0; return; } use_sheaf: if (unlikely(mas->alloc)) { kfree(mas->alloc); mas->alloc = NULL; } if (mas->sheaf) { unsigned long refill; refill = mas->node_request; if (kmem_cache_sheaf_size(mas->sheaf) >= refill) { mas->node_request = 0; return; } if (mt_refill_sheaf(gfp, &mas->sheaf, refill)) goto error; mas->node_request = 0; return; } mas->sheaf = mt_get_sheaf(gfp, mas->node_request); if (likely(mas->sheaf)) { mas->node_request = 0; return; } error: mas_set_err(mas, -ENOMEM); } static inline void mas_empty_nodes(struct ma_state *mas) { mas->node_request = 0; if (mas->sheaf) { mt_return_sheaf(mas->sheaf); mas->sheaf = NULL; } if (mas->alloc) { kfree(mas->alloc); mas->alloc = NULL; } } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { ma_free_rcu(mte_to_node(used)); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == ma_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == ma_root * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 0; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } mas->node = NULL; /* empty tree */ if (unlikely(!root)) { mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } static inline void wr_mas_setup(struct ma_wr_state *wr_mas, struct ma_state *mas) { wr_mas->node = mas_mn(mas); wr_mas->type = mte_node_type(mas->node); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = mas_safe_pivot(mas, wr_mas->pivots, mas->offset, wr_mas->type); } static inline void wr_mas_ascend(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; mas_ascend(mas); wr_mas_setup(wr_mas, mas); mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); /* Careful, this may be wrong.. */ wr_mas->end_piv = wr_mas->r_max; wr_mas->offset_end = mas->offset; } static inline unsigned long ma_leaf_max_gap(struct maple_node *mn, enum maple_type mt, unsigned long min, unsigned long max, unsigned long *pivots, void __rcu **slots) { unsigned long pstart, gap, max_gap; unsigned char i; unsigned char max_piv; max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ if (likely(!slots[0])) { max_gap = pivots[0] - min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas: the maple state * * Return: The maximum gap in the leaf. */ static inline unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; mn = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(mn, mt); pivots = ma_pivots(mn, mt); return ma_leaf_max_gap(mn, mt, mas->min, mas->max, pivots, slots); } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas: the maple state (for the tree) * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas: the maple state with the new node * @old_enode: The old maple encoded node to replace. * @new_height: if we are inserting a root node, update the height of the tree */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode, char new_height) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mt_set_height(mas->tree, new_height); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas: the ma_state with @mas->node pointing to the new node. * @old_enode: The old maple encoded node. * @new_height: The new height of the tree as a result of the operation */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode, unsigned char new_height) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode, new_height); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * If @mas->index cannot be found within the containing * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } static inline void rebalance_sib(struct ma_state *parent, struct ma_state *sib) { *sib = *parent; /* Prioritize move right to pull data left */ if (sib->offset < sib->end) sib->offset++; else sib->offset--; mas_descend(sib); sib->end = mas_data_end(sib); } static inline void spanning_sib(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *nneighbour) { struct ma_state l_tmp = *l_wr_mas->mas; struct ma_state r_tmp = *r_wr_mas->mas; unsigned char depth = 0; do { mas_ascend(&r_tmp); mas_ascend(&l_tmp); depth++; if (r_tmp.offset < mas_data_end(&r_tmp)) { r_tmp.offset++; mas_descend(&r_tmp); r_tmp.offset = 0; while (--depth) mas_descend(&r_tmp); r_tmp.end = mas_data_end(&r_tmp); *nneighbour = r_tmp; return; } else if (l_tmp.offset) { l_tmp.offset--; do { mas_descend(&l_tmp); l_tmp.offset = mas_data_end(&l_tmp); } while (--depth); l_tmp.end = l_tmp.offset; *nneighbour = l_tmp; return; } } while (!mte_is_root(r_tmp.node)); WARN_ON_ONCE(1); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); ma_free_rcu(tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * @new_height: The new height of the tree as a result of the operation * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode, unsigned char new_height) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode, new_height); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * node_copy() - Copy from one node to another. * * @mas: The maple state * @src: The source node * @start: The offset into the src to start copying * @size: The size to copy (non-zero) * @s_max: The source node max * @s_mt: The source maple node type * @dst: The destination * @d_start: The start location in the destination node * @d_mt: The destination maple node type */ static inline unsigned long node_copy(struct ma_state *mas, struct maple_node *src, unsigned char start, unsigned char size, unsigned long s_max, enum maple_type s_mt, struct maple_node *dst, unsigned char d_start, enum maple_type d_mt) { unsigned long *s_pivots, *d_pivots; void __rcu **s_slots, **d_slots; unsigned long *s_gaps, *d_gaps; unsigned long d_max; d_slots = ma_slots(dst, d_mt) + d_start; d_pivots = ma_pivots(dst, d_mt) + d_start; s_slots = ma_slots(src, s_mt) + start; s_pivots = ma_pivots(src, s_mt) + start; memcpy(d_slots, s_slots, size * sizeof(void __rcu *)); if (!ma_is_leaf(d_mt) && s_mt == maple_copy) { struct maple_enode *edst = mt_mk_node(dst, d_mt); for (int i = 0; i < size; i++) mas_set_parent(mas, mt_slot_locked(mas->tree, d_slots, i), edst, d_start + i); } d_gaps = ma_gaps(dst, d_mt); if (d_gaps) { s_gaps = ma_gaps(src, s_mt) + start; d_gaps += d_start; memcpy(d_gaps, s_gaps, size * sizeof(unsigned long)); } if (start + size - 1 < mt_pivots[s_mt]) d_max = s_pivots[size - 1]; else d_max = s_max; if (d_start + size <= mt_pivots[d_mt]) d_pivots[size - 1] = d_max; size--; if (size) memcpy(d_pivots, s_pivots, size * sizeof(unsigned long)); return d_max; } /* * node_finalise() - Zero out unused area and populate metadata * @node: The maple node * @mt: The maple node type * @end: The end of the used area */ static inline void node_finalise(struct maple_node *node, enum maple_type mt, unsigned char end) { unsigned char max_end = mt_slots[mt]; unsigned char size; unsigned long *gaps; unsigned char gap_slot; gaps = ma_gaps(node, mt); if (end < max_end - 1) { size = max_end - end; memset(ma_slots(node, mt) + end, 0, size * sizeof(void *)); if (gaps) memset(gaps + end, 0, size * sizeof(unsigned long)); if (--size) memset(ma_pivots(node, mt) + end, 0, size * sizeof(unsigned long)); } gap_slot = 0; if (gaps && !ma_is_leaf(mt)) { unsigned long max_gap; max_gap = 0; for (int i = 0; i <= end; i++) if (gaps[i] > max_gap) { gap_slot = i; max_gap = gaps[i]; } } if (mt == maple_arange_64) ma_set_meta(node, mt, gap_slot, end - 1); else if (end <= max_end - 1) ma_set_meta(node, mt, gap_slot, end - 1); } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @cp: The maple copy node * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_copy *cp) { struct maple_enode *old_enode; old_enode = mas->node; mas->node = mt_slot_locked(mas->tree, cp->slot, 0); /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode, cp->height); if (!mte_is_leaf(mas->node)) mas_update_gap(mas); mtree_range_walk(mas); } /* * cp_leaf_init() - Initialize a maple_copy node for the leaf level of a * spanning store * @cp: The maple copy node * @mas: The maple state * @l_wr_mas: The left write state of the spanning store * @r_wr_mas: The right write state of the spanning store */ static inline void cp_leaf_init(struct maple_copy *cp, struct ma_state *mas, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { unsigned char end = 0; /* * WARNING: The use of RCU_INIT_POINTER() makes it extremely important * to not expose the maple_copy node to any readers. Exposure may * result in buggy code when a compiler reorders the instructions. */ cp->height = 1; /* Create entries to insert including split entries to left and right */ if (l_wr_mas->r_min < mas->index) { end++; RCU_INIT_POINTER(cp->slot[0], l_wr_mas->content); cp->pivot[0] = mas->index - 1; } RCU_INIT_POINTER(cp->slot[end], l_wr_mas->entry); cp->pivot[end] = mas->last; if (r_wr_mas->end_piv > mas->last) { end++; RCU_INIT_POINTER(cp->slot[end], r_wr_mas->slots[r_wr_mas->offset_end]); cp->pivot[end] = r_wr_mas->end_piv; } cp->min = l_wr_mas->r_min; cp->max = cp->pivot[end]; cp->end = end; } /* * cp_data_calc() - Calculate the size of the data (1 indexed). * @cp: The maple copy struct with the new data populated. * @l_wr_mas: The maple write state containing the data to the left of the write * @r_wr_mas: The maple write state containing the data to the right of the * write * * cp->data is a size (not indexed by 0). */ static inline void cp_data_calc(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { /* Add 1 every time for the 0th element */ cp->data = l_wr_mas->mas->offset; /* Add the new data and any partial overwrites */ cp->data += cp->end + 1; /* Data from right (offset + 1 to end), +1 for zero */ cp->data += r_wr_mas->mas->end - r_wr_mas->offset_end; } static bool data_fits(struct ma_state *sib, struct ma_state *mas, struct maple_copy *cp) { unsigned char new_data; enum maple_type type; unsigned char space; unsigned char end; type = mte_node_type(mas->node); space = 2 * mt_slots[type]; end = sib->end; new_data = end + 1 + cp->data; if (new_data > space) return false; /* * This is off by one by design. The extra space is left to reduce * jitter in operations that add then remove two entries. * * end is an index while new space and data are both sizes. Adding one * to end to convert the index to a size means that the below * calculation should be <=, but we want to keep an extra space in nodes * to reduce jitter. * * Note that it is still possible to get a full node on the left by the * NULL landing exactly on the split. The NULL ending of a node happens * in the dst_setup() function, where we will either increase the split * by one or decrease it by one, if possible. In the case of split * (this case), it is always possible to shift the spilt by one - again * because there is at least one slot free by the below checking. */ if (new_data < space) return true; return false; } static inline void push_data_sib(struct maple_copy *cp, struct ma_state *mas, struct ma_state *sib, struct ma_state *parent) { if (mte_is_root(mas->node)) goto no_push; *sib = *parent; if (sib->offset) { sib->offset--; mas_descend(sib); sib->end = mas_data_end(sib); if (data_fits(sib, mas, cp)) /* Push left */ return; *sib = *parent; } if (sib->offset >= sib->end) goto no_push; sib->offset++; mas_descend(sib); sib->end = mas_data_end(sib); if (data_fits(sib, mas, cp)) /* Push right*/ return; no_push: sib->end = 0; } /* * rebalance_data() - Calculate the @cp data, populate @sib if insufficient or * if the data can be pushed into a sibling. * @cp: The maple copy node * @wr_mas: The left write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. * */ static inline void rebalance_data(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { cp_data_calc(cp, wr_mas, wr_mas); sib->end = 0; if (cp->data > mt_slots[wr_mas->type]) { push_data_sib(cp, wr_mas->mas, sib, parent); if (sib->end) goto use_sib; } else if (cp->data <= mt_min_slots[wr_mas->type]) { if ((wr_mas->mas->min != 0) || (wr_mas->mas->max != ULONG_MAX)) { rebalance_sib(parent, sib); goto use_sib; } } return; use_sib: cp->data += sib->end + 1; } /* * spanning_data() - Calculate the @cp data and populate @sib if insufficient * @cp: The maple copy node * @l_wr_mas: The left write maple state * @r_wr_mas: The right write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. */ static inline void spanning_data(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { cp_data_calc(cp, l_wr_mas, r_wr_mas); if (((l_wr_mas->mas->min != 0) || (r_wr_mas->mas->max != ULONG_MAX)) && (cp->data <= mt_min_slots[l_wr_mas->type])) { spanning_sib(l_wr_mas, r_wr_mas, sib); cp->data += sib->end + 1; } else { sib->end = 0; } } /* * dst_setup() - Set up one or more destinations for the new data. * @cp: The maple copy node * @mas: The maple state * @mt: The source node type */ static inline void dst_setup(struct maple_copy *cp, struct ma_state *mas, enum maple_type mt) { /* Data is 1 indexed, every src has +1 added. */ if (cp->data <= mt_slots[mt]) { cp->split = cp->data - 1; cp->d_count = 1; goto node_setup; } cp->split = (cp->data - 1) / 2; cp->d_count = 2; if (cp->data < mt_slots[mt] * 2) goto node_setup; if (cp->data == mt_slots[mt] * 2) { unsigned char off; unsigned char s; if (!ma_is_leaf(mt)) goto node_setup; /* * Leaf nodes are a bit tricky because we cannot assume the data * can fit due to the NULL limitation on node ends. */ off = cp->split; for (s = 0; s < cp->s_count; s++) { unsigned char s_off; s_off = cp->src[s].end - cp->src[s].start; if (s_off >= off) break; s_off++; off -= s_off; } off += cp->src[s].start; if (ma_slots(cp->src[s].node, cp->src[s].mt)[off]) goto node_setup; cp->split++; if (cp->split < mt_slots[mt]) goto node_setup; cp->split -= 2; if (cp->data - 2 - cp->split < mt_slots[mt]) goto node_setup; } /* No other choice but to 3-way split the data */ cp->split = (cp->data + 2) / 3; cp->d_count = 3; node_setup: for (int i = 0; i < cp->d_count; i++) { cp->dst[i].mt = mt; cp->dst[i].node = ma_mnode_ptr(mas_pop_node(mas)); } } static inline void append_mas_cp(struct maple_copy *cp, struct ma_state *mas, unsigned char start, unsigned char end) { struct maple_node *node; enum maple_type mt; unsigned char count; count = cp->s_count; node = mas_mn(mas); mt = mte_node_type(mas->node); cp->src[count].node = node; cp->src[count].mt = mt; if (mas->end <= end) cp->src[count].max = mas->max; else cp->src[count].max = ma_pivots(node, mt)[end]; cp->src[count].start = start; cp->src[count].end = end; cp->s_count++; } static inline void append_wr_mas_cp(struct maple_copy *cp, struct ma_wr_state *wr_mas, unsigned char start, unsigned char end) { unsigned char count; count = cp->s_count; cp->src[count].node = wr_mas->node; cp->src[count].mt = wr_mas->type; if (wr_mas->mas->end <= end) cp->src[count].max = wr_mas->mas->max; else cp->src[count].max = wr_mas->pivots[end]; cp->src[count].start = start; cp->src[count].end = end; cp->s_count++; } static inline void init_cp_src(struct maple_copy *cp) { cp->src[cp->s_count].node = ma_mnode_ptr(cp); cp->src[cp->s_count].mt = maple_copy; cp->src[cp->s_count].max = cp->max; cp->src[cp->s_count].start = 0; cp->src[cp->s_count].end = cp->end; cp->s_count++; } /* * multi_src_setup() - Set the @cp node up with multiple sources to copy from. * @cp: The maple copy node * @l_wr_mas: The left write maple state * @r_wr_mas: The right write maple state * @sib: The sibling maple state * * Note: @sib->end == 0 indicates no sibling will be used. */ static inline void multi_src_setup(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { cp->s_count = 0; if (sib->end && sib->max < l_wr_mas->mas->min) append_mas_cp(cp, sib, 0, sib->end); /* Copy left 0 - offset */ if (l_wr_mas->mas->offset) { unsigned char off = l_wr_mas->mas->offset - 1; append_wr_mas_cp(cp, l_wr_mas, 0, off); cp->src[cp->s_count - 1].max = cp->min - 1; } init_cp_src(cp); /* Copy right either from offset or offset + 1 pending on r_max */ if (r_wr_mas->mas->end != r_wr_mas->offset_end) append_wr_mas_cp(cp, r_wr_mas, r_wr_mas->offset_end + 1, r_wr_mas->mas->end); if (sib->end && sib->min > r_wr_mas->mas->max) append_mas_cp(cp, sib, 0, sib->end); } static inline void cp_data_write(struct maple_copy *cp, struct ma_state *mas) { struct maple_node *dst, *src; unsigned char s, d; unsigned char dst_offset; unsigned char data_offset; unsigned char src_end, s_offset; unsigned char split; unsigned long s_max, d_max; unsigned char dst_size; enum maple_type s_mt, d_mt; data_offset = 0; s = d = 0; /* Readability help */ src = cp->src[s].node; dst = cp->dst[d].node; s_offset = cp->src[s].start; src_end = cp->src[s].end; split = cp->split; s_max = cp->src[s].max; s_mt = cp->src[s].mt; d_mt = cp->dst[d].mt; do { dst_offset = 0; d_max = 0; dst = cp->dst[d].node; d_mt = cp->dst[d].mt; dst_size = split + 1; while (dst_size) { unsigned char size; if (src_end - s_offset + 1 < dst_size) size = src_end - s_offset + 1; else size = dst_size; d_max = node_copy(mas, src, s_offset, size, s_max, s_mt, dst, dst_offset, d_mt); dst_offset += size; s_offset += size; if (s_offset > src_end) { /* This source is exhausted */ s++; if (s >= cp->s_count) { cp->dst[d].max = d_max; node_finalise(dst, d_mt, dst_offset); return; } /* Reset local src */ src = cp->src[s].node; s_offset = cp->src[s].start; src_end = cp->src[s].end; s_max = cp->src[s].max; s_mt = cp->src[s].mt; } dst_size -= size; data_offset += size; } split = cp->split; cp->dst[d].max = d_max; /* Handle null entries */ if (cp->dst[d].max != ULONG_MAX && !ma_slots(dst, d_mt)[dst_offset - 1]) { if (s_offset == cp->src[s].start) { s--; src = cp->src[s].node; src_end = cp->src[s].end; s_max = cp->src[s].max; s_mt = cp->src[s].mt; s_offset = src_end; } else { s_offset--; } /* Set dst max and clear pivot */ split++; data_offset--; dst_offset--; cp->dst[d].max = ma_pivots(dst, d_mt)[dst_offset - 1]; } node_finalise(dst, d_mt, dst_offset); ++d; /* Next destination */ if (d == cp->d_count - 1) split = cp->data - data_offset; if (d >= cp->d_count) { WARN_ON(data_offset < cp->data); return; } } while (data_offset <= cp->data); } /* * cp_dst_to_slots() - Migrate the maple copy destination to the maple copy * slots * @cp: The maple copy node * @min: The minimal value represented * @max: The maximum value represented * @mas: The maple state */ static inline void cp_dst_to_slots(struct maple_copy *cp, unsigned long min, unsigned long max, struct ma_state *mas) { unsigned char d; unsigned long slot_min = min; for (d = 0; d < cp->d_count; d++) { struct maple_node *mn = cp->dst[d].node; enum maple_type mt = cp->dst[d].mt; unsigned long slot_max = cp->dst[d].max; /* * Warning, see cp_leaf_init() comment and rcu_assign_pointer() * documentation. Since these are new nodes, there are no * read-side operations that can view them until they are * inserted into the tree after an rcu_assign_pointer() call. */ ma_init_slot(&cp->slot[d], mn, mt); cp->pivot[d] = slot_max; if (mt_is_alloc(mas->tree)) { if (ma_is_leaf(mt)) { cp->gap[d] = ma_leaf_max_gap(mn, mt, slot_min, slot_max, ma_pivots(mn, mt), ma_slots(mn, mt)); } else { unsigned long *gaps = ma_gaps(mn, mt); if (gaps) { unsigned char gap_slot; gap_slot = ma_meta_gap(mn); cp->gap[d] = gaps[gap_slot]; } } } slot_min = slot_max + 1; } cp->end = cp->d_count - 1; cp->min = min; cp->max = max; } static inline bool cp_is_new_root(struct maple_copy *cp, struct ma_state *mas) { if (cp->min || cp->max != ULONG_MAX) return false; if (cp->d_count != 1) { enum maple_type mt = maple_arange_64; if (!mt_is_alloc(mas->tree)) mt = maple_range_64; cp->data = cp->d_count; cp->s_count = 0; dst_setup(cp, mas, mt); init_cp_src(cp); node_copy(mas, cp->src[0].node, 0, cp->data, cp->max, maple_copy, cp->dst[0].node, 0, mt); node_finalise(cp->dst[0].node, mt, cp->end + 1); /* * Warning, see cp_leaf_init() comment and rcu_assign_pointer() * documentation. Since this is a new root, there are no * read-side operations that can view it until it is insert into * the tree after an rcu_assign_pointer() call. */ ma_init_slot(&cp->slot[0], cp->dst[0].node, mt); cp->height++; } WARN_ON_ONCE(cp->dst[0].node != mte_to_node( mt_slot_locked(mas->tree, cp->slot, 0))); cp->dst[0].node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->min = 0; mas->max = ULONG_MAX; mas->depth = 0; mas->node = mas_root_locked(mas); return true; } static inline bool cp_converged(struct maple_copy *cp, struct ma_state *mas, struct ma_state *sib) { if (cp->d_count != 1 || sib->end) return false; cp->dst[0].node->parent = ma_parent_ptr(mas_mn(mas)->parent); return true; } /* * spanning_ascend() - See if a spanning store operation has to keep walking up * the tree * @cp: The maple_copy node * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state * @sib: the maple state of the sibling * * Returns: True if another iteration is necessary. */ static bool spanning_ascend(struct maple_copy *cp, struct ma_state *mas, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { if (sib->end) { if (sib->max < l_wr_mas->mas->min) *l_wr_mas->mas = *sib; else *r_wr_mas->mas = *sib; } cp_dst_to_slots(cp, l_wr_mas->mas->min, r_wr_mas->mas->max, mas); if (cp_is_new_root(cp, mas)) return false; /* Converged and has a single destination */ if ((cp->d_count == 1) && (l_wr_mas->mas->node == r_wr_mas->mas->node)) { cp->dst[0].node->parent = ma_parent_ptr(mas_mn(mas)->parent); return false; } cp->height++; wr_mas_ascend(l_wr_mas); wr_mas_ascend(r_wr_mas); return true; } static inline void copy_tree_location(const struct ma_state *src, struct ma_state *dst) { dst->node = src->node; dst->offset = src->offset; dst->min = src->min; dst->max = src->max; dst->end = src->end; dst->depth = src->depth; } /* * rebalance_ascend() - Ascend the tree and set up for the next loop - if * necessary * * Return: True if there another rebalancing operation on the next level is * needed, false otherwise. */ static inline bool rebalance_ascend(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { struct ma_state *mas; unsigned long min, max; mas = wr_mas->mas; if (!sib->end) { min = mas->min; max = mas->max; } else if (sib->min > mas->max) { /* Move right succeeded */ min = mas->min; max = sib->max; wr_mas->offset_end = parent->offset + 1; } else { min = sib->min; max = mas->max; wr_mas->offset_end = parent->offset; parent->offset--; } cp_dst_to_slots(cp, min, max, mas); if (cp_is_new_root(cp, mas)) return false; if (cp_converged(cp, mas, sib)) return false; cp->height++; copy_tree_location(parent, mas); wr_mas_setup(wr_mas, mas); return true; } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mt_set_height(mas->tree, 1); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); } /* * mas_store_root() - Storing value into root. * @mas: The maple state * @entry: The entry to store. * * There is no root node now and we are storing a value into the root - this * function either assigns the pointer or expands into a node. */ static inline void mas_store_root(struct ma_state *mas, void *entry) { if (!entry) { if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL); } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; if (mas->end < mt_slots[wr_mas->type] - 1) wr_mas->vacant_height = mas->depth + 1; if (ma_is_root(mas_mn(mas))) { /* root needs more than 2 entries to be sufficient + 1 */ if (mas->end > 2) wr_mas->sufficient_height = 1; } else if (mas->end > mt_min_slots[wr_mas->type] + 1) wr_mas->sufficient_height = mas->depth + 1; mas_wr_walk_traverse(wr_mas); } return true; } static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return; mas_wr_walk_traverse(wr_mas); } } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; l_wr_mas->r_min = l_mas->index; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; r_wr_mas->r_max = r_mas->last; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX */ static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); if (!entry) { mt_set_height(mas->tree, 0); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mt_set_height(mas->tree, 1); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state */ static void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_copy cp; struct ma_state *mas; struct ma_state sib; /* Left and Right side of spanning store */ MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; r_wr_mas.end_piv = r_wr_mas.r_max; /* Set up left side. */ mas_wr_walk_index(wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(wr_mas, &r_wr_mas); mas->last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!mas->index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } cp_leaf_init(&cp, mas, wr_mas, &r_wr_mas); do { spanning_data(&cp, wr_mas, &r_wr_mas, &sib); multi_src_setup(&cp, wr_mas, &r_wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (spanning_ascend(&cp, mas, wr_mas, &r_wr_mas, &sib)); mas_wmb_replace(mas, &cp); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. */ static inline void mas_wr_node_store(struct ma_wr_state *wr_mas) { unsigned char dst_offset, offset_end; unsigned char copy_size, node_pivots; struct maple_node reuse, *newnode; unsigned long *dst_pivots; void __rcu **dst_slots; unsigned char new_end; struct ma_state *mas; bool in_rcu; mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); in_rcu = mt_in_rcu(mas->tree); offset_end = wr_mas->offset_end; node_pivots = mt_pivots[wr_mas->type]; /* Assume last adds an entry */ new_end = mas->end + 1 - offset_end + mas->offset; if (mas->last == wr_mas->end_piv) { offset_end++; /* don't copy this offset */ new_end--; } /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ if (mas->offset) { memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void __rcu *) * mas->offset); } /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; new_end++; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void __rcu *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode, mas_mt_height(mas)); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state */ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else { WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. */ static inline void mas_wr_append(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; void __rcu **slots; unsigned char end = mas->end; unsigned char new_end = mas_wr_new_end(wr_mas); if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry); } /* * split_ascend() - See if a split operation has to keep walking up the tree * @cp: The maple_copy node * @wr_mas: The maple write state * @sib: the maple state of the sibling * * Return: true if another split operation on the next level is needed, false * otherwise */ static inline bool split_ascend(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { struct ma_state *mas; unsigned long min, max; mas = wr_mas->mas; min = mas->min; /* push right, or normal split */ max = mas->max; wr_mas->offset_end = parent->offset; if (sib->end) { if (sib->max < mas->min) { min = sib->min; /* push left */ parent->offset--; } else { max = sib->max; /* push right */ wr_mas->offset_end++; } } cp_dst_to_slots(cp, min, max, mas); if (cp_is_new_root(cp, mas)) return false; if (cp_converged(cp, mas, sib)) return false; cp->height++; copy_tree_location(parent, mas); wr_mas_setup(wr_mas, mas); return true; } /* * split_data() - Calculate the @cp data, populate @sib if the data can be * pushed into a sibling. * @cp: The maple copy node * @wr_mas: The left write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. * */ static inline void split_data(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { cp_data_calc(cp, wr_mas, wr_mas); if (cp->data <= mt_slots[wr_mas->type]) { sib->end = 0; return; } push_data_sib(cp, wr_mas->mas, sib, parent); if (sib->end) cp->data += sib->end + 1; } /* * mas_wr_split() - Expand one node into two * @wr_mas: The write maple state */ static void mas_wr_split(struct ma_wr_state *wr_mas) { struct ma_state parent; struct ma_state *mas; struct maple_copy cp; struct ma_state sib; mas = wr_mas->mas; trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry); parent = *mas; cp_leaf_init(&cp, mas, wr_mas, wr_mas); do { if (!mte_is_root(parent.node)) { mas_ascend(&parent); parent.end = mas_data_end(&parent); } split_data(&cp, wr_mas, &sib, &parent); multi_src_setup(&cp, wr_mas, wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (split_ascend(&cp, wr_mas, &sib, &parent)); mas_wmb_replace(mas, &cp); } /* * mas_wr_rebalance() - Insufficient data in one node needs to either get data * from a sibling or absorb a sibling all together. * @wr_mas: The write maple state * * Rebalance is different than a spanning store in that the write state is * already at the leaf node that's being altered. */ static void mas_wr_rebalance(struct ma_wr_state *wr_mas) { struct ma_state parent; struct ma_state *mas; struct maple_copy cp; struct ma_state sib; /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); parent = *mas; cp_leaf_init(&cp, mas, wr_mas, wr_mas); do { if (!mte_is_root(parent.node)) { mas_ascend(&parent); parent.end = mas_data_end(&parent); } rebalance_data(&cp, wr_mas, &sib, &parent); multi_src_setup(&cp, wr_mas, wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (rebalance_ascend(&cp, wr_mas, &sib, &parent)); mas_wmb_replace(mas, &cp); } /* * mas_wr_store_entry() - Internal call to store a value * @wr_mas: The maple write state */ static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; switch (mas->store_type) { case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); break; case wr_append: mas_wr_append(wr_mas); break; case wr_slot_store: mas_wr_slot_store(wr_mas); break; case wr_node_store: mas_wr_node_store(wr_mas); break; case wr_spanning_store: mas_wr_spanning_store(wr_mas); break; case wr_split_store: mas_wr_split(wr_mas); break; case wr_rebalance: mas_wr_rebalance(wr_mas); break; case wr_new_root: mas_new_root(mas, wr_mas->entry); break; case wr_store_root: mas_store_root(mas, wr_mas->entry); break; case wr_invalid: MT_BUG_ON(mas->tree, 1); } } static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!mas_is_active(mas)) { if (mas_is_start(mas)) goto set_content; if (unlikely(mas_is_paused(mas))) goto reset; if (unlikely(mas_is_none(mas))) goto reset; if (unlikely(mas_is_overflow(mas))) goto reset; if (unlikely(mas_is_underflow(mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (mas->last > mas->max) goto reset; if (wr_mas->entry) goto set_content; if (mte_is_leaf(mas->node) && mas->last == mas->max) goto reset; goto set_content; reset: mas_reset(mas); set_content: wr_mas->content = mas_start(mas); } /** * mas_prealloc_calc() - Calculate number of nodes needed for a * given store oepration * @wr_mas: The maple write state * @entry: The entry to store into the tree * * Return: Number of nodes required for preallocation. */ static inline void mas_prealloc_calc(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; unsigned char height = mas_mt_height(mas); int ret = height * 3 + 1; unsigned char delta = height - wr_mas->vacant_height; switch (mas->store_type) { case wr_exact_fit: case wr_append: case wr_slot_store: ret = 0; break; case wr_spanning_store: if (wr_mas->sufficient_height < wr_mas->vacant_height) ret = (height - wr_mas->sufficient_height) * 3 + 1; else ret = delta * 3 + 1; break; case wr_split_store: ret = delta * 2 + 1; break; case wr_rebalance: if (wr_mas->sufficient_height < wr_mas->vacant_height) ret = (height - wr_mas->sufficient_height) * 2 + 1; else ret = delta * 2 + 1; break; case wr_node_store: ret = mt_in_rcu(mas->tree) ? 1 : 0; break; case wr_new_root: ret = 1; break; case wr_store_root: if (likely((mas->last != 0) || (mas->index != 0))) ret = 1; else if (((unsigned long) (entry) & 3) == 2) ret = 1; else ret = 0; break; case wr_invalid: WARN_ON_ONCE(1); } mas->node_request = ret; } /* * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state * * Return: the type of store needed for the operation */ static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return wr_store_root; if (unlikely(!mas_wr_walk(wr_mas))) return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) return wr_exact_fit; if (unlikely(!mas->index && mas->last == ULONG_MAX)) return wr_new_root; new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { if (!mte_is_root(mas->node)) return wr_rebalance; return wr_node_store; } if (new_end >= mt_slots[wr_mas->type]) return wr_split_store; if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || (wr_mas->offset_end - mas->offset == 1))) return wr_slot_store; return wr_node_store; } /** * mas_wr_preallocate() - Preallocate enough nodes for a store operation * @wr_mas: The maple write state * @entry: The entry that will be stored * */ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; mas_wr_prealloc_setup(wr_mas); mas->store_type = mas_wr_store_type(wr_mas); mas_prealloc_calc(wr_mas, entry); if (!mas->node_request) return; mas_alloc_nodes(mas, GFP_NOWAIT); } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; mas_wr_preallocate(&wr_mas, entry); if (mas_is_err(mas)) return NULL; /* spanning writes always overwrite something */ if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; } mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } /** * mas_alloc_cyclic() - Internal call to find somewhere to store an entry * @mas: The maple state. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, or -EBUSY if there are no * free entries. */ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { unsigned long min = range_lo; int ret = 0; range_lo = max(min, *next); ret = mas_empty_area(mas, range_lo, range_hi, 1); if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && range_lo > min) { mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; } if (ret < 0) return ret; do { mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas)) return xa_err(mas->node); *startp = mas->index; *next = *startp + 1; if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @min: The minimum starting range * @empty: Can be empty * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) goto underflow; goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; break; } mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) && !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, error == -EBUSY) * found the gap. (return) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); else if (mas->offset >= 2) mas->offset -= 2; else mas->offset = mas_data_end(mas); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @enode: the encoded node * @mt: the maple tree * @slots: Pointer to the slot array * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: kfree(node); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { mte_set_node_dead(enode); node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) kfree(node); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(TP_FCT, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); return wr_mas.content; } mas_prealloc_calc(&wr_mas, entry); if (!mas->node_request) goto store; mas_alloc_nodes(mas, GFP_NOWAIT); if (mas_is_err(mas)) return NULL; store: mas_wr_store_entry(&wr_mas); mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { unsigned long index = mas->index; unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); int ret = 0; retry: mas_wr_preallocate(&wr_mas, entry); if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last); goto retry; } if (mas_is_err(mas)) { ret = xa_err(mas->node); goto out; } mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); if (mas->store_type == wr_store_root) { mas_wr_prealloc_setup(&wr_mas); goto store; } mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) { /* set wr_mas->content to current slot */ wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas); } store: trace_ma_write(TP_FCT, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); mas_prealloc_calc(&wr_mas, entry); if (!mas->node_request) goto set_flag; mas->mas_flags &= ~MA_STATE_PREALLOC; mas_alloc_nodes(mas, gfp); if (mas_is_err(mas)) { int ret = xa_err(mas->node); mas->node_request = 0; mas_destroy(mas); mas_reset(mas); return ret; } set_flag: mas->mas_flags |= MA_STATE_PREALLOC; return 0; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { mas->mas_flags &= ~MA_STATE_PREALLOC; mas_empty_nodes(mas); } EXPORT_SYMBOL_GPL(mas_destroy); static void mas_may_activate(struct ma_state *mas) { if (!mas->node) { mas->status = ma_start; } else if (mas->index > mas->max || mas->index < mas->min) { mas->status = ma_start; } else { mas->status = ma_active; } } static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas_may_activate(mas); break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas_may_activate(mas); break; case ma_overflow: /* User expects mas to be one after where it is */ mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_preallocate(&wr_mas, NULL); if (mas_nomem(mas, GFP_KERNEL)) { /* in case the range of entry changed when unlocked */ mas->index = mas->last = index; goto write_retry; } if (mas_is_err(mas)) goto out; mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas->sheaf && !mas->alloc) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { struct kmem_cache_args args = { .align = sizeof(struct maple_node), .sheaf_capacity = 32, }; maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), &args, SLAB_PANIC); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(TP_FCT, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); int ret = 0; trace_ma_write(TP_FCT, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry from [first, last] at a given range * if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range (inclusive) * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Note that @last is inclusive. That is, @last = @first + length - 1; * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) ret = xa_err(ms.node); mas_destroy(&ms); return ret; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); /** * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. * @mt: The maple tree. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Finds an empty entry in @mt after @next, stores the new index into * the @id pointer, stores the entry at that index, then updates @next. * * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. * * Context: Any context. Takes and releases the mt.lock. May sleep if * the @gfp flags permit. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no * free entries. */ int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { int ret; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, next, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_cyclic); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(TP_FCT, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); kfree(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); count = mas->node_request = mas_data_end(mas) + 1; mas_alloc_nodes(mas, gfp); if (unlikely(mas_is_err(mas))) return; slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; /* * Warning, see rcu_assign_pointer() documentation. Since this * is a duplication of a tree, there are no readers walking the * tree until after the rcu_assign_pointer() call in * mas_dup_build(). */ RCU_INIT_POINTER(new_slots[i], ma_mnode_ptr((unsigned long)mas_pop_node(mas) | val)); } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) goto empty_mas; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); empty_mas: mas_empty_nodes(mas); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(TP_FCT, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_slot(&mas, max, false); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *)); void mt_set_callback(void (*callback)(void *)) { kmem_cache_set_callback(maple_node_cache, callback); } extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); void mt_set_private(void *private) { kmem_cache_set_private(maple_node_cache, private); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); else if (entry) mt_dump_entry(entry, 0, 0, 0, format); else pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (!mas_is_active(&mas)) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (!mte_is_root(mas.node)))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("Store Type: "); switch (mas->store_type) { case wr_invalid: pr_err("invalid store type\n"); break; case wr_new_root: pr_err("new_root\n"); break; case wr_store_root: pr_err("store_root\n"); break; case wr_exact_fit: pr_err("exact_fit\n"); break; case wr_split_store: pr_err("split_store\n"); break; case wr_slot_store: pr_err("slot_store\n"); break; case wr_append: pr_err("append\n"); break; case wr_node_store: pr_err("node_store\n"); break; case wr_spanning_store: pr_err("spanning_store\n"); break; case wr_rebalance: pr_err("rebalance\n"); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx sheaf=" PTR_FMT ", request %lu depth=%u, flags=%x\n", mas->min, mas->max, mas->sheaf, mas->node_request, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 285 210 13 1139 1540 1 1 1294 1136 1531 308 81 285 131 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_H #define BLK_MQ_H #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> #include <linux/srcu.h> #include <linux/rw_hint.h> #include <linux/rwsem.h> struct blk_mq_tags; struct blk_flush_queue; struct io_comp_batch; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 enum rq_end_io_ret { RQ_END_IO_NONE, RQ_END_IO_FREE, }; typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t, const struct io_comp_batch *); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* Keep rqf_name[] in sync with the definitions below */ enum rqf_flags { /* drive already may have started this one */ __RQF_STARTED, /* request for flush sequence */ __RQF_FLUSH_SEQ, /* merge of different types, fail separately */ __RQF_MIXED_MERGE, /* don't call prep for this one */ __RQF_DONTPREP, /* use hctx->sched_tags */ __RQF_SCHED_TAGS, /* use an I/O scheduler for this request */ __RQF_USE_SCHED, /* vaguely specified driver internal error. Ignored by block layer */ __RQF_FAILED, /* don't warn about errors */ __RQF_QUIET, /* account into disk and partition IO statistics */ __RQF_IO_STAT, /* runtime pm request */ __RQF_PM, /* on IO scheduler merge hash */ __RQF_HASHED, /* track IO completion time */ __RQF_STATS, /* Look at ->special_vec for the actual data payload instead of the bio chain. */ __RQF_SPECIAL_PAYLOAD, /* request completion needs to be signaled to zone write plugging. */ __RQF_ZONE_WRITE_PLUGGING, /* ->timeout has been called, don't expire again */ __RQF_TIMED_OUT, __RQF_RESV, __RQF_BITS }; #define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) #define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) #define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) #define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) #define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) #define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) #define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) #define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) #define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) #define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) #define RQF_SPECIAL_PAYLOAD \ ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) #define RQF_ZONE_WRITE_PLUGGING \ ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) #define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) #define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; blk_opf_t cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; unsigned int timeout; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; union { struct list_head queuelist; struct request *rq_next; }; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; unsigned short nr_integrity_segments; /* * The lowest set bit for address gaps between physical segments. This * provides information necessary for dma optimization opprotunities, * like for testing if the segments can be coalesced against the * device's iommu granule. */ unsigned char phys_gap_bit; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_crypto_keyslot *crypt_keyslot; #endif enum mq_rq_state state; atomic_t ref; unsigned long deadline; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct llist_node ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. special_vec must * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be * insert into an IO scheduler. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; rq_end_io_fn *saved_end_io; } flush; u64 fifo_time; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; }; /* * Returns a mask with all bits starting at req->phys_gap_bit set to 1. */ static inline unsigned long req_phys_gap_mask(const struct request *req) { return ~(((1 << req->phys_gap_bit) >> 1) - 1); } static inline enum req_op req_op(const struct request *req) { return req->cmd_flags & REQ_OP_MASK; } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) { if (req->bio) return req->bio->bi_ioprio; return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) static inline int rq_list_empty(const struct rq_list *rl) { return rl->head == NULL; } static inline void rq_list_init(struct rq_list *rl) { rl->head = NULL; rl->tail = NULL; } static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) { rq->rq_next = NULL; if (rl->tail) rl->tail->rq_next = rq; else rl->head = rq; rl->tail = rq; } static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) { rq->rq_next = rl->head; rl->head = rq; if (!rl->tail) rl->tail = rq; } static inline struct request *rq_list_pop(struct rq_list *rl) { struct request *rq = rl->head; if (rq) { rl->head = rl->head->rq_next; if (!rl->head) rl->tail = NULL; rq->rq_next = NULL; } return rq; } static inline struct request *rq_list_peek(struct rq_list *rl) { return rl->head; } #define rq_list_for_each(rl, pos) \ for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) #define rq_list_for_each_safe(rl, pos, nxt) \ for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) /** * enum blk_eh_timer_return - How the timeout handler should proceed * @BLK_EH_DONE: The block driver completed the command or will complete it at * a later time. * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the * request to complete. */ enum blk_eh_timer_return { BLK_EH_DONE, BLK_EH_RESET_TIMER, }; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device */ struct blk_mq_hw_ctx { struct { /** @lock: Protects the dispatch list. */ spinlock_t lock; /** * @dispatch: Used for requests that are ready to be * dispatched to the hardware but for some reason (e.g. lack of * resources) could not be sent to the hardware. As soon as the * driver can send new requests, requests at this list will * be sent first for a fairer dispatch. */ struct list_head dispatch; /** * @state: BLK_MQ_S_* flags. Defines the state of the hw * queue (active, scheduled to restart, stopped). */ unsigned long state; } ____cacheline_aligned_in_smp; /** * @run_work: Used for scheduling a hardware queue run at a later time. */ struct delayed_work run_work; /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; /** * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU * selection from @cpumask. */ int next_cpu; /** * @next_cpu_batch: Counter of how many works left in the batch before * changing to the next CPU. */ int next_cpu_batch; /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ unsigned long flags; /** * @sched_data: Pointer owned by the IO scheduler attached to a request * queue. It's up to the IO scheduler how to use this pointer. */ void *sched_data; /** * @queue: Pointer to the request queue that owns this hardware context. */ struct request_queue *queue; /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; /** * @driver_data: Pointer to data owned by the block driver that created * this hctx */ void *driver_data; /** * @ctx_map: Bitmap for each software queue. If bit is on, there is a * pending request in that software queue. */ struct sbitmap ctx_map; /** * @dispatch_from: Software queue to be used when no scheduler was * selected. */ struct blk_mq_ctx *dispatch_from; /** * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to * decide if the hw_queue is busy using Exponential Weighted Moving * Average algorithm. */ unsigned int dispatch_busy; /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; /** * @dispatch_wait: Waitqueue to put requests when there is no tag * available at the moment, to wait for another try in the future. */ wait_queue_entry_t dispatch_wait; /** * @wait_index: Index of next available dispatch_wait queue to insert * requests. */ atomic_t wait_index; /** * @tags: Tags owned by the block driver. A tag at this set is only * assigned when a request is dispatched from a hardware queue. */ struct blk_mq_tags *tags; /** * @sched_tags: Tags owned by I/O scheduler. If there is an I/O * scheduler associated with a request queue, a tag is assigned when * that request is allocated. Else, this member is not used. */ struct blk_mq_tags *sched_tags; /** @numa_node: NUMA node the storage adapter has been connected to. */ int numa_node; /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; /** * @nr_active: Number of active requests. Only used when a tag set is * shared across request queues. */ atomic_t nr_active; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named * as cpu<cpu_number>. */ struct dentry *debugfs_dir; /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif /** * @hctx_list: if this hctx is not in use, this is an entry in * q->unused_hctx_list. */ struct list_head hctx_list; }; /** * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). * @nr_queues: Number of hardware queues to map CPU IDs onto. * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe * driver to map each hardware queue type (enum hctx_type) onto a distinct * set of hardware queues. */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; /** * enum hctx_ty |